You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hbase.apache.org by gi...@apache.org on 2026/07/08 23:59:33 UTC
(hbase-site) branch asf-site updated: Published site at e3da929fc0a197e7a8a7a50bdbe574f4124003eb.
This is an automated email from the ASF dual-hosted git repository.
asf-gitbox-commits pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/hbase-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new dd8a2e663c5 Published site at e3da929fc0a197e7a8a7a50bdbe574f4124003eb.
dd8a2e663c5 is described below
commit dd8a2e663c5304ee5b900f226a4a427533f4f648
Author: HBase <de...@hbase.apache.org>
AuthorDate: Wed Jul 8 23:53:18 2026 +0000
Published site at e3da929fc0a197e7a8a7a50bdbe574f4124003eb.
---
__spa-fallback.html | 4 +-
acid-semantics/index.html | 4 +-
apidocs/index-all.html | 4 +
apidocs/member-search-index.js | 2 +-
.../hadoop/hbase/client/class-use/RegionInfo.html | 10 +-
.../master/ServerManager.ServerLiveState.html | 565 +-
.../apache/hadoop/hbase/master/ServerManager.html | 565 +-
.../util/ModifyRegionUtils.RegionEditTask.html | 432 +-
.../util/ModifyRegionUtils.RegionFillTask.html | 432 +-
.../hadoop/hbase/util/ModifyRegionUtils.html | 432 +-
assets/docs-Dp5xyhQm.js | 4 +
assets/index-feH7IxLp.js | 48983 +++++++++++++++++++
assets/manifest-0a09de0e.js | 1 +
books/apache-hbase-reference-guide-dark-mode.pdf | Bin 38943790 -> 38943794 bytes
books/apache-hbase-reference-guide.pdf | Bin 38833623 -> 38833626 bytes
checkstyle-aggregate.html | 10 +-
code-of-conduct/index.html | 4 +-
dependency-convergence.html | 2 +-
dependency-info.html | 2 +-
dependency-management.html | 2 +-
devapidocs/index-all.html | 8 +
devapidocs/member-search-index.js | 2 +-
.../apache/hadoop/hbase/class-use/TableName.html | 149 +-
.../hadoop/hbase/client/class-use/RegionInfo.html | 129 +-
.../ServerManager.FlushedSequenceIdFlusher.html | 6 +-
.../apache/hadoop/hbase/master/ServerManager.html | 39 +-
.../assignment/RegionStates.RegionFailedOpen.html | 22 +-
.../hbase/master/assignment/RegionStates.html | 292 +-
...plitTableRegionProcedure.StoreFileSplitter.html | 14 +-
.../assignment/SplitTableRegionProcedure.html | 104 +-
.../master/assignment/class-use/RegionStates.html | 19 +
.../hbase/master/assignment/package-use.html | 17 +
.../CreateTableProcedure.CreateHdfsRegions.html | 4 +-
.../master/procedure/CreateTableProcedure.html | 20 +-
.../util/ModifyRegionUtils.RegionEditTask.html | 4 +-
.../util/ModifyRegionUtils.RegionFillTask.html | 4 +-
.../hadoop/hbase/util/ModifyRegionUtils.html | 82 +-
.../ServerManager.FlushedSequenceIdFlusher.html | 565 +-
.../master/ServerManager.ServerLiveState.html | 565 +-
.../apache/hadoop/hbase/master/ServerManager.html | 565 +-
.../assignment/RegionStates.RegionFailedOpen.html | 781 +-
.../hbase/master/assignment/RegionStates.html | 781 +-
...plitTableRegionProcedure.StoreFileSplitter.html | 1837 +-
.../assignment/SplitTableRegionProcedure.html | 1837 +-
.../CreateTableProcedure.CreateHdfsRegions.html | 294 +-
.../master/procedure/CreateTableProcedure.html | 294 +-
.../util/ModifyRegionUtils.RegionEditTask.html | 432 +-
.../util/ModifyRegionUtils.RegionFillTask.html | 432 +-
.../hadoop/hbase/util/ModifyRegionUtils.html | 432 +-
docs/acl-matrix/index.html | 6 +-
docs/amv2/index.html | 6 +-
docs/architecture/bulk-loading/index.html | 6 +-
docs/architecture/catalog-tables/index.html | 6 +-
.../architecture/client-request-filters/index.html | 6 +-
docs/architecture/client/index.html | 6 +-
docs/architecture/hbase-mob/index.html | 6 +-
docs/architecture/hdfs/index.html | 6 +-
docs/architecture/index.html | 6 +-
docs/architecture/master/index.html | 6 +-
docs/architecture/overview/index.html | 6 +-
docs/architecture/regions/index.html | 6 +-
docs/architecture/regionserver/index.html | 6 +-
docs/architecture/snapshot-scanner/index.html | 6 +-
.../timeline-consistent-reads/index.html | 6 +-
docs/asf/index.html | 6 +-
docs/backup-restore/additional-topics/index.html | 6 +-
docs/backup-restore/administration/index.html | 6 +-
docs/backup-restore/commands/index.html | 6 +-
docs/backup-restore/index.html | 6 +-
docs/backup-restore/overview/index.html | 6 +-
docs/building-and-developing/announcing/index.html | 6 +-
docs/building-and-developing/building/index.html | 6 +-
.../developer-guidelines/index.html | 6 +-
.../generating-documentation/index.html | 6 +-
.../getting-involved/index.html | 6 +-
docs/building-and-developing/ides/index.html | 6 +-
docs/building-and-developing/index.html | 6 +-
docs/building-and-developing/releasing/index.html | 6 +-
.../repositories/index.html | 6 +-
docs/building-and-developing/tests/index.html | 6 +-
.../updating-landing/index.html | 6 +-
docs/building-and-developing/voting/index.html | 6 +-
docs/bulk-data-generator-tool/index.html | 6 +-
docs/case-studies/index.html | 6 +-
docs/community/index.html | 6 +-
docs/compression/index.html | 6 +-
docs/configuration/basic-prerequisites/index.html | 6 +-
docs/configuration/confirm/index.html | 6 +-
docs/configuration/default/index.html | 6 +-
docs/configuration/dynamic/index.html | 6 +-
docs/configuration/example/index.html | 6 +-
docs/configuration/hbase-run-models/index.html | 6 +-
docs/configuration/important/index.html | 6 +-
docs/configuration/index.html | 6 +-
docs/contributing-to-documentation/index.html | 6 +-
docs/cp/index.html | 6 +-
docs/datamodel/index.html | 6 +-
docs/external-apis/index.html | 6 +-
docs/faq/index.html | 6 +-
docs/getting-started/index.html | 6 +-
docs/hbase-apis/index.html | 6 +-
docs/hbase-history/index.html | 6 +-
docs/hbase-incompatibilities/index.html | 6 +-
docs/hbtop/index.html | 6 +-
docs/hfile-format/index.html | 6 +-
docs/index.html | 6 +-
docs/inmemory-compaction/index.html | 6 +-
docs/mapreduce/index.html | 6 +-
docs/offheap-read-write/index.html | 6 +-
.../backup-and-snapshots/index.html | 6 +-
.../cluster-replication/index.html | 6 +-
docs/operational-management/index.html | 6 +-
.../metrics-and-monitoring/index.html | 6 +-
docs/operational-management/node/index.html | 6 +-
.../region-and-capacity/index.html | 6 +-
.../index.html | 6 +-
.../operational-management/table-rename/index.html | 6 +-
docs/operational-management/tools/index.html | 6 +-
docs/orca/index.html | 6 +-
docs/other-info/index.html | 6 +-
docs/performance/index.html | 6 +-
docs/profiler/index.html | 6 +-
docs/protobuf/index.html | 6 +-
docs/pv2/index.html | 6 +-
docs/regionserver-sizing/index.html | 6 +-
docs/rpc/index.html | 6 +-
docs/schema-design/index.html | 6 +-
docs/security/client-access/index.html | 6 +-
docs/security/data-access/index.html | 6 +-
docs/security/example/index.html | 6 +-
docs/security/hdfs-and-zookeeper-access/index.html | 6 +-
docs/security/index.html | 6 +-
docs/security/tls/index.html | 6 +-
docs/security/user-access/index.html | 6 +-
docs/security/web-ui/index.html | 6 +-
docs/shell/index.html | 6 +-
docs/single-page/index.html | 6 +-
docs/spark/index.html | 6 +-
docs/sql/index.html | 6 +-
docs/store-file-tracking/index.html | 6 +-
docs/sync-replication/index.html | 6 +-
docs/thrift-filter-language/index.html | 6 +-
docs/tracing/index.html | 6 +-
docs/troubleshooting/index.html | 6 +-
docs/unit-testing/index.html | 6 +-
docs/upgrading/index.html | 6 +-
docs/upgrading/paths/index.html | 6 +-
docs/upgrading/rollback/index.html | 6 +-
docs/upgrading/rolling/index.html | 6 +-
docs/upgrading/version-number/index.html | 6 +-
docs/ycsb/index.html | 6 +-
docs/zookeeper/index.html | 6 +-
downloads/index.html | 4 +-
export-control/index.html | 4 +-
hbase-website/dependency-convergence.html | 2 +-
hbase-website/dependency-info.html | 2 +-
hbase-website/dependency-management.html | 2 +-
hbase-website/index.html | 2 +-
hbase-website/issue-management.html | 2 +-
hbase-website/licenses.html | 2 +-
hbase-website/mailing-lists.html | 2 +-
hbase-website/plugin-management.html | 2 +-
hbase-website/plugins.html | 2 +-
hbase-website/project-info.html | 2 +-
hbase-website/scm.html | 2 +-
hbase-website/summary.html | 2 +-
hbase-website/team.html | 2 +-
index.html | 4 +-
issue-management.html | 2 +-
licenses.html | 2 +-
mailing-lists.html | 2 +-
mailing-lists/index.html | 4 +-
news/index.html | 4 +-
other-resources/index.html | 4 +-
plugin-management.html | 2 +-
plugins.html | 2 +-
powered-by-hbase/index.html | 4 +-
project-info.html | 2 +-
project-reports.html | 2 +-
scm.html | 2 +-
security-model/index.html | 4 +-
source-repository/index.html | 4 +-
sponsors/index.html | 4 +-
summary.html | 2 +-
team.html | 2 +-
team/index.html | 4 +-
testapidocs/allclasses-index.html | 2184 +-
testapidocs/index-all.html | 20 +-
testapidocs/member-search-index.js | 2 +-
.../TestRecoverUnknownWithNullRegionLocation.html | 62 +
.../hadoop/hbase/master/package-summary.html | 94 +-
.../apache/hadoop/hbase/master/package-tree.html | 1 +
testapidocs/overview-tree.html | 1 +
.../TestRecoverUnknownWithNullRegionLocation.html | 188 +
testapidocs/type-search-index.js | 2 +-
testdevapidocs/allclasses-index.html | 3254 +-
testdevapidocs/index-all.html | 317 +-
testdevapidocs/member-search-index.js | 2 +-
.../hadoop/hbase/class-use/HBaseTestingUtil.html | 29 +-
.../bucket/TestRecoveryPersistentBucketCache.html | 22 +-
.../TestRecoverUnknownWithNullRegionLocation.html | 264 +
.../TestRecoverUnknownWithNullRegionLocation.html | 62 +
.../hadoop/hbase/master/package-summary.html | 106 +-
.../apache/hadoop/hbase/master/package-tree.html | 1 +
.../TestEncodedNameCollisionDetection.html | 165 +-
.../TestEncodedNameCollisionDetection.html | 62 +
.../hbase/master/procedure/package-summary.html | 302 +-
.../hbase/master/procedure/package-tree.html | 1 +
testdevapidocs/overview-tree.html | 2 +
.../bucket/TestRecoveryPersistentBucketCache.html | 518 +-
.../TestRecoverUnknownWithNullRegionLocation.html | 188 +
.../TestEncodedNameCollisionDetection.html | 203 +
testdevapidocs/type-search-index.js | 2 +-
213 files changed, 60177 insertions(+), 9773 deletions(-)
diff --git a/__spa-fallback.html b/__spa-fallback.html
index 33d99dfe6bb..5ad9e80dc0e 100644
--- a/__spa-fallback.html
+++ b/__spa-fallback.html
@@ -1,4 +1,4 @@
-<!DOCTYPE html><html lang="en"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="font" href="/fonts/inter-latin-wght-normal.woff2" type="font/woff2" crossorigin="anonymous"/><link rel="prefetch" as="font" href="/fonts/inter-latin-wght-italic.woff2" type="font/woff2" crossorigin="anonymous"/><link rel="modulepreload" href="/assets/manifest-5a115ba0.js"/><link rel="modulepreload" href="/assets/entry.client-Bi9_frb9.js" [...]
+<!DOCTYPE html><html lang="en"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="font" href="/fonts/inter-latin-wght-normal.woff2" type="font/woff2" crossorigin="anonymous"/><link rel="prefetch" as="font" href="/fonts/inter-latin-wght-italic.woff2" type="font/woff2" crossorigin="anonymous"/><link rel="modulepreload" href="/assets/manifest-0a09de0e.js"/><link rel="modulepreload" href="/assets/entry.client-Bi9_frb9.js" [...]
(function() {
const theme = localStorage.getItem('theme');
const root = document.documentElement;
@@ -19,7 +19,7 @@
"functions. Check out https://reactrouter.com/start/framework/route-module#hydratefallback " +
"for more information."
);
- </script><script>window.__reactRouterContext = {"basename":"/","future":{"unstable_optimizeDeps":false,"v8_passThroughRequests":false,"v8_trailingSlashAwareDataRequests":false,"unstable_previewServerPrerendering":false,"v8_middleware":false,"v8_splitRouteModules":false,"v8_viteEnvironmentApi":false},"routeDiscovery":{"mode":"initial"},"ssr":false,"isSpaMode":true};window.__reactRouterContext.stream = new ReadableStream({start(controller){window.__reactRouterContext.streamCont [...]
+ </script><script>window.__reactRouterContext = {"basename":"/","future":{"unstable_optimizeDeps":false,"v8_passThroughRequests":false,"v8_trailingSlashAwareDataRequests":false,"unstable_previewServerPrerendering":false,"v8_middleware":false,"v8_splitRouteModules":false,"v8_viteEnvironmentApi":false},"routeDiscovery":{"mode":"initial"},"ssr":false,"isSpaMode":true};window.__reactRouterContext.stream = new ReadableStream({start(controller){window.__reactRouterContext.streamCont [...]
import * as route0 from "/assets/root-COkOICkm.js";
window.__reactRouterRouteModules = {"root":route0};
diff --git a/acid-semantics/index.html b/acid-semantics/index.html
index d3733d1640c..fed4e3c31aa 100644
--- a/acid-semantics/index.html
+++ b/acid-semantics/index.html
@@ -1,4 +1,4 @@
-<!DOCTYPE html><html lang="en"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="image" href="/images/logo.svg"/><title>ACID Semantics - Apache HBase</title><meta name="description" content="Apache HBase ACID properties and guarantees specification."/><link rel="preload" as="font" href="/fonts/inter-latin-wght-normal.woff2" type="font/woff2" crossorigin="anonymous"/><link rel="prefetch" as="font" href="/fonts/inter-l [...]
+<!DOCTYPE html><html lang="en"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="image" href="/images/logo.svg"/><title>ACID Semantics - Apache HBase</title><meta name="description" content="Apache HBase ACID properties and guarantees specification."/><link rel="preload" as="font" href="/fonts/inter-latin-wght-normal.woff2" type="font/woff2" crossorigin="anonymous"/><link rel="prefetch" as="font" href="/fonts/inter-l [...]
(function() {
const theme = localStorage.getItem('theme');
const root = document.documentElement;
@@ -133,7 +133,7 @@ an update is considered visible if any subsequent read will see the update as ha
console.error(error);
sessionStorage.removeItem(storageKey2);
}
- })("react-router-scroll-positions", null)</script><script>window.__reactRouterContext = {"basename":"/","future":{"unstable_optimizeDeps":false,"v8_passThroughRequests":false,"v8_trailingSlashAwareDataRequests":false,"unstable_previewServerPrerendering":false,"v8_middleware":false,"v8_splitRouteModules":false,"v8_viteEnvironmentApi":false},"routeDiscovery":{"mode":"initial"},"ssr":false,"isSpaMode":false};window.__reactRouterContext.stream = new ReadableStream({start(controller){window [...]
+ })("react-router-scroll-positions", null)</script><script>window.__reactRouterContext = {"basename":"/","future":{"unstable_optimizeDeps":false,"v8_passThroughRequests":false,"v8_trailingSlashAwareDataRequests":false,"unstable_previewServerPrerendering":false,"v8_middleware":false,"v8_splitRouteModules":false,"v8_viteEnvironmentApi":false},"routeDiscovery":{"mode":"initial"},"ssr":false,"isSpaMode":false};window.__reactRouterContext.stream = new ReadableStream({start(controller){window [...]
import * as route0 from "/assets/root-COkOICkm.js";
import * as route1 from "/assets/landing-layout-Dqj0MjmT.js";
import * as route2 from "/assets/acid-semantics-Dx21iP6k.js";
diff --git a/apidocs/index-all.html b/apidocs/index-all.html
index 5a0f5e8d8b6..58caef783db 100644
--- a/apidocs/index-all.html
+++ b/apidocs/index-all.html
@@ -6321,6 +6321,10 @@ loadScripts(document, 'script');</script>
<dd>
<div class="block">Pre check when creating a new table.</div>
</dd>
+<dt>checkForEncodedNameCollisions(Collection<RegionInfo>, RegionStates) - Static method in class org.apache.hadoop.hbase.util.ModifyRegionUtils</dt>
+<dd>
+<div class="block">Checks candidate regions for encoded\-name collisions.</div>
+</dd>
<dt>checkFormatVersion(int) - Static method in class org.apache.hadoop.hbase.io.hfile.HFile</dt>
<dd>
<div class="block">Checks the given <code>HFile</code> format version, and throws an exception if invalid.</div>
diff --git a/apidocs/member-search-index.js b/apidocs/member-search-index.js
index 44cadcc3ba6..a54fd2252c4 100644
--- a/apidocs/member-search-index.js
+++ b/apidocs/member-search-index.js
@@ -1 +1 @@
-memberSearchIndex = [{"p":"org.apache.hadoop.hbase.filter","c":"ParseConstants","l":"A"},{"p":"org.apache.hadoop.hbase.master","c":"RegionState.State","l":"ABNORMALLY_CLOSED"},{"p":"org.apache.hadoop.hbase.coprocessor","c":"CoprocessorHost","l":"ABORT_ON_ERROR_KEY"},{"p":"org.apache.hadoop.hdfs","c":"DummyDFSOutputStream","l":"abort()"},{"p":"org.apache.hadoop.hbase","c":"Abortable","l":"abort(String)","u":"abort(java.lang.String)"},{"p":"org.apache.hadoop.hbase","c":"Abortable","l":"abo [...]
\ No newline at end of file
+memberSearchIndex = [{"p":"org.apache.hadoop.hbase.filter","c":"ParseConstants","l":"A"},{"p":"org.apache.hadoop.hbase.master","c":"RegionState.State","l":"ABNORMALLY_CLOSED"},{"p":"org.apache.hadoop.hbase.coprocessor","c":"CoprocessorHost","l":"ABORT_ON_ERROR_KEY"},{"p":"org.apache.hadoop.hdfs","c":"DummyDFSOutputStream","l":"abort()"},{"p":"org.apache.hadoop.hbase","c":"Abortable","l":"abort(String)","u":"abort(java.lang.String)"},{"p":"org.apache.hadoop.hbase","c":"Abortable","l":"abo [...]
\ No newline at end of file
diff --git a/apidocs/org/apache/hadoop/hbase/client/class-use/RegionInfo.html b/apidocs/org/apache/hadoop/hbase/client/class-use/RegionInfo.html
index c224b35bf08..c8c92927d05 100644
--- a/apidocs/org/apache/hadoop/hbase/client/class-use/RegionInfo.html
+++ b/apidocs/org/apache/hadoop/hbase/client/class-use/RegionInfo.html
@@ -3203,10 +3203,16 @@ Input/OutputFormats, a table indexing MapReduce job, and utility methods.</div>
<div class="table-header col-second">Method</div>
<div class="table-header col-last">Description</div>
<div class="col-first even-row-color"><code>static void</code></div>
-<div class="col-second even-row-color"><span class="type-name-label">ModifyRegionUtils.</span><code>editRegions<wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/util/concurrent/ThreadPoolExecutor.html" title="class or interface in java.util.concurrent" class="external-link">ThreadPoolExecutor</a> exec,
+<div class="col-second even-row-color"><span class="type-name-label">ModifyRegionUtils.</span><code>checkForEncodedNameCollisions<wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/util/Collection.html" title="class or interface in java.util" class="external-link">Collection</a><org.apache.hadoop.hbase.client.RegionInfo> candidates,
+ org.apache.hadoop.hbase.master.assignment.RegionStates regionStates)</code></div>
+<div class="col-last even-row-color">
+<div class="block">Checks candidate regions for encoded\-name collisions.</div>
+</div>
+<div class="col-first odd-row-color"><code>static void</code></div>
+<div class="col-second odd-row-color"><span class="type-name-label">ModifyRegionUtils.</span><code>editRegions<wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/util/concurrent/ThreadPoolExecutor.html" title="class or interface in java.util.concurrent" class="external-link">ThreadPoolExecutor</a> exec,
<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/util/Collection.html" title="class or interface in java.util" class="external-link">Collection</a><org.apache.hadoop.hbase.client.RegionInfo> regions,
org.apache.hadoop.hbase.util.ModifyRegionUtils.RegionEditTask task)</code></div>
-<div class="col-last even-row-color">
+<div class="col-last odd-row-color">
<div class="block">Execute the task on the specified set of regions.</div>
</div>
</div>
diff --git a/apidocs/src-html/org/apache/hadoop/hbase/master/ServerManager.ServerLiveState.html b/apidocs/src-html/org/apache/hadoop/hbase/master/ServerManager.ServerLiveState.html
index 483cebf36de..5d37c40abcc 100644
--- a/apidocs/src-html/org/apache/hadoop/hbase/master/ServerManager.ServerLiveState.html
+++ b/apidocs/src-html/org/apache/hadoop/hbase/master/ServerManager.ServerLiveState.html
@@ -993,288 +993,291 @@
<span class="source-line-no">980</span><span id="line-980"> /**</span>
<span class="source-line-no">981</span><span id="line-981"> * Check if a server is unknown. A server can be online, or known to be dead, or unknown to this</span>
<span class="source-line-no">982</span><span id="line-982"> * manager (i.e, not online, not known to be dead either; it is simply not tracked by the master</span>
-<span class="source-line-no">983</span><span id="line-983"> * any more, for example, a very old previous instance).</span>
-<span class="source-line-no">984</span><span id="line-984"> */</span>
-<span class="source-line-no">985</span><span id="line-985"> public boolean isServerUnknown(ServerName serverName) {</span>
-<span class="source-line-no">986</span><span id="line-986"> return serverName == null</span>
-<span class="source-line-no">987</span><span id="line-987"> || (!onlineServers.containsKey(serverName) && !deadservers.isDeadServer(serverName));</span>
-<span class="source-line-no">988</span><span id="line-988"> }</span>
-<span class="source-line-no">989</span><span id="line-989"></span>
-<span class="source-line-no">990</span><span id="line-990"> public void shutdownCluster() {</span>
-<span class="source-line-no">991</span><span id="line-991"> String statusStr = "Cluster shutdown requested of master=" + this.master.getServerName();</span>
-<span class="source-line-no">992</span><span id="line-992"> LOG.info(statusStr);</span>
-<span class="source-line-no">993</span><span id="line-993"> this.clusterShutdown.set(true);</span>
-<span class="source-line-no">994</span><span id="line-994"> if (onlineServers.isEmpty()) {</span>
-<span class="source-line-no">995</span><span id="line-995"> // we do not synchronize here so this may cause a double stop, but not a big deal</span>
-<span class="source-line-no">996</span><span id="line-996"> master.stop("OnlineServer=0 right after cluster shutdown set");</span>
-<span class="source-line-no">997</span><span id="line-997"> }</span>
-<span class="source-line-no">998</span><span id="line-998"> }</span>
-<span class="source-line-no">999</span><span id="line-999"></span>
-<span class="source-line-no">1000</span><span id="line-1000"> public boolean isClusterShutdown() {</span>
-<span class="source-line-no">1001</span><span id="line-1001"> return this.clusterShutdown.get();</span>
-<span class="source-line-no">1002</span><span id="line-1002"> }</span>
-<span class="source-line-no">1003</span><span id="line-1003"></span>
-<span class="source-line-no">1004</span><span id="line-1004"> /**</span>
-<span class="source-line-no">1005</span><span id="line-1005"> * start chore in ServerManager</span>
-<span class="source-line-no">1006</span><span id="line-1006"> */</span>
-<span class="source-line-no">1007</span><span id="line-1007"> public void startChore() {</span>
-<span class="source-line-no">1008</span><span id="line-1008"> Configuration c = master.getConfiguration();</span>
-<span class="source-line-no">1009</span><span id="line-1009"> if (persistFlushedSequenceId) {</span>
-<span class="source-line-no">1010</span><span id="line-1010"> new Thread(() -> {</span>
-<span class="source-line-no">1011</span><span id="line-1011"> // after AM#loadMeta, RegionStates should be loaded, and some regions are</span>
-<span class="source-line-no">1012</span><span id="line-1012"> // deleted by drop/split/merge during removeDeletedRegionFromLoadedFlushedSequenceIds,</span>
-<span class="source-line-no">1013</span><span id="line-1013"> // but these deleted regions are not added back to RegionStates,</span>
-<span class="source-line-no">1014</span><span id="line-1014"> // so we can safely remove deleted regions.</span>
-<span class="source-line-no">1015</span><span id="line-1015"> removeDeletedRegionFromLoadedFlushedSequenceIds();</span>
-<span class="source-line-no">1016</span><span id="line-1016"> }, "RemoveDeletedRegionSyncThread").start();</span>
-<span class="source-line-no">1017</span><span id="line-1017"> int flushPeriod =</span>
-<span class="source-line-no">1018</span><span id="line-1018"> c.getInt(FLUSHEDSEQUENCEID_FLUSHER_INTERVAL, FLUSHEDSEQUENCEID_FLUSHER_INTERVAL_DEFAULT);</span>
-<span class="source-line-no">1019</span><span id="line-1019"> flushedSeqIdFlusher = new FlushedSequenceIdFlusher("FlushedSequenceIdFlusher", flushPeriod);</span>
-<span class="source-line-no">1020</span><span id="line-1020"> master.getChoreService().scheduleChore(flushedSeqIdFlusher);</span>
-<span class="source-line-no">1021</span><span id="line-1021"> }</span>
-<span class="source-line-no">1022</span><span id="line-1022"> }</span>
-<span class="source-line-no">1023</span><span id="line-1023"></span>
-<span class="source-line-no">1024</span><span id="line-1024"> /**</span>
-<span class="source-line-no">1025</span><span id="line-1025"> * Stop the ServerManager.</span>
-<span class="source-line-no">1026</span><span id="line-1026"> */</span>
-<span class="source-line-no">1027</span><span id="line-1027"> public void stop() {</span>
-<span class="source-line-no">1028</span><span id="line-1028"> if (flushedSeqIdFlusher != null) {</span>
-<span class="source-line-no">1029</span><span id="line-1029"> flushedSeqIdFlusher.shutdown();</span>
-<span class="source-line-no">1030</span><span id="line-1030"> }</span>
-<span class="source-line-no">1031</span><span id="line-1031"> if (persistFlushedSequenceId) {</span>
-<span class="source-line-no">1032</span><span id="line-1032"> try {</span>
-<span class="source-line-no">1033</span><span id="line-1033"> persistRegionLastFlushedSequenceIds();</span>
-<span class="source-line-no">1034</span><span id="line-1034"> } catch (IOException e) {</span>
-<span class="source-line-no">1035</span><span id="line-1035"> LOG.warn("Failed to persist last flushed sequence id of regions" + " to file system", e);</span>
-<span class="source-line-no">1036</span><span id="line-1036"> }</span>
-<span class="source-line-no">1037</span><span id="line-1037"> }</span>
-<span class="source-line-no">1038</span><span id="line-1038"> }</span>
-<span class="source-line-no">1039</span><span id="line-1039"></span>
-<span class="source-line-no">1040</span><span id="line-1040"> /**</span>
-<span class="source-line-no">1041</span><span id="line-1041"> * Creates a list of possible destinations for a region. It contains the online servers, but not</span>
-<span class="source-line-no">1042</span><span id="line-1042"> * the draining or dying servers.</span>
-<span class="source-line-no">1043</span><span id="line-1043"> * @param serversToExclude can be null if there is no server to exclude</span>
-<span class="source-line-no">1044</span><span id="line-1044"> */</span>
-<span class="source-line-no">1045</span><span id="line-1045"> public List<ServerName> createDestinationServersList(final List<ServerName> serversToExclude) {</span>
-<span class="source-line-no">1046</span><span id="line-1046"> Set<ServerName> destServers = new HashSet<>();</span>
-<span class="source-line-no">1047</span><span id="line-1047"> onlineServers.forEach((sn, sm) -> {</span>
-<span class="source-line-no">1048</span><span id="line-1048"> if (sm.getLastReportTimestamp() > 0) {</span>
-<span class="source-line-no">1049</span><span id="line-1049"> // This means we have already called regionServerReport at leaset once, then let's include</span>
-<span class="source-line-no">1050</span><span id="line-1050"> // this server for region assignment. This is an optimization to avoid assigning regions to</span>
-<span class="source-line-no">1051</span><span id="line-1051"> // an uninitialized server. See HBASE-25032 for more details.</span>
-<span class="source-line-no">1052</span><span id="line-1052"> destServers.add(sn);</span>
-<span class="source-line-no">1053</span><span id="line-1053"> }</span>
-<span class="source-line-no">1054</span><span id="line-1054"> });</span>
-<span class="source-line-no">1055</span><span id="line-1055"></span>
-<span class="source-line-no">1056</span><span id="line-1056"> if (serversToExclude != null) {</span>
-<span class="source-line-no">1057</span><span id="line-1057"> destServers.removeAll(serversToExclude);</span>
-<span class="source-line-no">1058</span><span id="line-1058"> }</span>
-<span class="source-line-no">1059</span><span id="line-1059"></span>
-<span class="source-line-no">1060</span><span id="line-1060"> // Loop through the draining server list and remove them from the server list</span>
-<span class="source-line-no">1061</span><span id="line-1061"> final List<ServerName> drainingServersCopy = getDrainingServersList();</span>
-<span class="source-line-no">1062</span><span id="line-1062"> destServers.removeAll(drainingServersCopy);</span>
-<span class="source-line-no">1063</span><span id="line-1063"></span>
-<span class="source-line-no">1064</span><span id="line-1064"> return new ArrayList<>(destServers);</span>
-<span class="source-line-no">1065</span><span id="line-1065"> }</span>
+<span class="source-line-no">983</span><span id="line-983"> * anymore, for example, a very old previous instance). A serverName with value null should not be</span>
+<span class="source-line-no">984</span><span id="line-984"> * considered unknown. We set value of regionLocation to null just before finding the assign</span>
+<span class="source-line-no">985</span><span id="line-985"> * candidate (in-between region transition) or while marking it OFFLINE/FAILED_OPEN. Refer</span>
+<span class="source-line-no">986</span><span id="line-986"> * HBASE-30142.</span>
+<span class="source-line-no">987</span><span id="line-987"> */</span>
+<span class="source-line-no">988</span><span id="line-988"> public boolean isServerUnknown(ServerName serverName) {</span>
+<span class="source-line-no">989</span><span id="line-989"> return serverName != null</span>
+<span class="source-line-no">990</span><span id="line-990"> && (!onlineServers.containsKey(serverName) && !deadservers.isDeadServer(serverName));</span>
+<span class="source-line-no">991</span><span id="line-991"> }</span>
+<span class="source-line-no">992</span><span id="line-992"></span>
+<span class="source-line-no">993</span><span id="line-993"> public void shutdownCluster() {</span>
+<span class="source-line-no">994</span><span id="line-994"> String statusStr = "Cluster shutdown requested of master=" + this.master.getServerName();</span>
+<span class="source-line-no">995</span><span id="line-995"> LOG.info(statusStr);</span>
+<span class="source-line-no">996</span><span id="line-996"> this.clusterShutdown.set(true);</span>
+<span class="source-line-no">997</span><span id="line-997"> if (onlineServers.isEmpty()) {</span>
+<span class="source-line-no">998</span><span id="line-998"> // we do not synchronize here so this may cause a double stop, but not a big deal</span>
+<span class="source-line-no">999</span><span id="line-999"> master.stop("OnlineServer=0 right after cluster shutdown set");</span>
+<span class="source-line-no">1000</span><span id="line-1000"> }</span>
+<span class="source-line-no">1001</span><span id="line-1001"> }</span>
+<span class="source-line-no">1002</span><span id="line-1002"></span>
+<span class="source-line-no">1003</span><span id="line-1003"> public boolean isClusterShutdown() {</span>
+<span class="source-line-no">1004</span><span id="line-1004"> return this.clusterShutdown.get();</span>
+<span class="source-line-no">1005</span><span id="line-1005"> }</span>
+<span class="source-line-no">1006</span><span id="line-1006"></span>
+<span class="source-line-no">1007</span><span id="line-1007"> /**</span>
+<span class="source-line-no">1008</span><span id="line-1008"> * start chore in ServerManager</span>
+<span class="source-line-no">1009</span><span id="line-1009"> */</span>
+<span class="source-line-no">1010</span><span id="line-1010"> public void startChore() {</span>
+<span class="source-line-no">1011</span><span id="line-1011"> Configuration c = master.getConfiguration();</span>
+<span class="source-line-no">1012</span><span id="line-1012"> if (persistFlushedSequenceId) {</span>
+<span class="source-line-no">1013</span><span id="line-1013"> new Thread(() -> {</span>
+<span class="source-line-no">1014</span><span id="line-1014"> // after AM#loadMeta, RegionStates should be loaded, and some regions are</span>
+<span class="source-line-no">1015</span><span id="line-1015"> // deleted by drop/split/merge during removeDeletedRegionFromLoadedFlushedSequenceIds,</span>
+<span class="source-line-no">1016</span><span id="line-1016"> // but these deleted regions are not added back to RegionStates,</span>
+<span class="source-line-no">1017</span><span id="line-1017"> // so we can safely remove deleted regions.</span>
+<span class="source-line-no">1018</span><span id="line-1018"> removeDeletedRegionFromLoadedFlushedSequenceIds();</span>
+<span class="source-line-no">1019</span><span id="line-1019"> }, "RemoveDeletedRegionSyncThread").start();</span>
+<span class="source-line-no">1020</span><span id="line-1020"> int flushPeriod =</span>
+<span class="source-line-no">1021</span><span id="line-1021"> c.getInt(FLUSHEDSEQUENCEID_FLUSHER_INTERVAL, FLUSHEDSEQUENCEID_FLUSHER_INTERVAL_DEFAULT);</span>
+<span class="source-line-no">1022</span><span id="line-1022"> flushedSeqIdFlusher = new FlushedSequenceIdFlusher("FlushedSequenceIdFlusher", flushPeriod);</span>
+<span class="source-line-no">1023</span><span id="line-1023"> master.getChoreService().scheduleChore(flushedSeqIdFlusher);</span>
+<span class="source-line-no">1024</span><span id="line-1024"> }</span>
+<span class="source-line-no">1025</span><span id="line-1025"> }</span>
+<span class="source-line-no">1026</span><span id="line-1026"></span>
+<span class="source-line-no">1027</span><span id="line-1027"> /**</span>
+<span class="source-line-no">1028</span><span id="line-1028"> * Stop the ServerManager.</span>
+<span class="source-line-no">1029</span><span id="line-1029"> */</span>
+<span class="source-line-no">1030</span><span id="line-1030"> public void stop() {</span>
+<span class="source-line-no">1031</span><span id="line-1031"> if (flushedSeqIdFlusher != null) {</span>
+<span class="source-line-no">1032</span><span id="line-1032"> flushedSeqIdFlusher.shutdown();</span>
+<span class="source-line-no">1033</span><span id="line-1033"> }</span>
+<span class="source-line-no">1034</span><span id="line-1034"> if (persistFlushedSequenceId) {</span>
+<span class="source-line-no">1035</span><span id="line-1035"> try {</span>
+<span class="source-line-no">1036</span><span id="line-1036"> persistRegionLastFlushedSequenceIds();</span>
+<span class="source-line-no">1037</span><span id="line-1037"> } catch (IOException e) {</span>
+<span class="source-line-no">1038</span><span id="line-1038"> LOG.warn("Failed to persist last flushed sequence id of regions" + " to file system", e);</span>
+<span class="source-line-no">1039</span><span id="line-1039"> }</span>
+<span class="source-line-no">1040</span><span id="line-1040"> }</span>
+<span class="source-line-no">1041</span><span id="line-1041"> }</span>
+<span class="source-line-no">1042</span><span id="line-1042"></span>
+<span class="source-line-no">1043</span><span id="line-1043"> /**</span>
+<span class="source-line-no">1044</span><span id="line-1044"> * Creates a list of possible destinations for a region. It contains the online servers, but not</span>
+<span class="source-line-no">1045</span><span id="line-1045"> * the draining or dying servers.</span>
+<span class="source-line-no">1046</span><span id="line-1046"> * @param serversToExclude can be null if there is no server to exclude</span>
+<span class="source-line-no">1047</span><span id="line-1047"> */</span>
+<span class="source-line-no">1048</span><span id="line-1048"> public List<ServerName> createDestinationServersList(final List<ServerName> serversToExclude) {</span>
+<span class="source-line-no">1049</span><span id="line-1049"> Set<ServerName> destServers = new HashSet<>();</span>
+<span class="source-line-no">1050</span><span id="line-1050"> onlineServers.forEach((sn, sm) -> {</span>
+<span class="source-line-no">1051</span><span id="line-1051"> if (sm.getLastReportTimestamp() > 0) {</span>
+<span class="source-line-no">1052</span><span id="line-1052"> // This means we have already called regionServerReport at leaset once, then let's include</span>
+<span class="source-line-no">1053</span><span id="line-1053"> // this server for region assignment. This is an optimization to avoid assigning regions to</span>
+<span class="source-line-no">1054</span><span id="line-1054"> // an uninitialized server. See HBASE-25032 for more details.</span>
+<span class="source-line-no">1055</span><span id="line-1055"> destServers.add(sn);</span>
+<span class="source-line-no">1056</span><span id="line-1056"> }</span>
+<span class="source-line-no">1057</span><span id="line-1057"> });</span>
+<span class="source-line-no">1058</span><span id="line-1058"></span>
+<span class="source-line-no">1059</span><span id="line-1059"> if (serversToExclude != null) {</span>
+<span class="source-line-no">1060</span><span id="line-1060"> destServers.removeAll(serversToExclude);</span>
+<span class="source-line-no">1061</span><span id="line-1061"> }</span>
+<span class="source-line-no">1062</span><span id="line-1062"></span>
+<span class="source-line-no">1063</span><span id="line-1063"> // Loop through the draining server list and remove them from the server list</span>
+<span class="source-line-no">1064</span><span id="line-1064"> final List<ServerName> drainingServersCopy = getDrainingServersList();</span>
+<span class="source-line-no">1065</span><span id="line-1065"> destServers.removeAll(drainingServersCopy);</span>
<span class="source-line-no">1066</span><span id="line-1066"></span>
-<span class="source-line-no">1067</span><span id="line-1067"> /**</span>
-<span class="source-line-no">1068</span><span id="line-1068"> * Calls {@link #createDestinationServersList} without server to exclude.</span>
-<span class="source-line-no">1069</span><span id="line-1069"> */</span>
-<span class="source-line-no">1070</span><span id="line-1070"> public List<ServerName> createDestinationServersList() {</span>
-<span class="source-line-no">1071</span><span id="line-1071"> return createDestinationServersList(null);</span>
-<span class="source-line-no">1072</span><span id="line-1072"> }</span>
-<span class="source-line-no">1073</span><span id="line-1073"></span>
-<span class="source-line-no">1074</span><span id="line-1074"> /**</span>
-<span class="source-line-no">1075</span><span id="line-1075"> * To clear any dead server with same host name and port of any online server</span>
-<span class="source-line-no">1076</span><span id="line-1076"> */</span>
-<span class="source-line-no">1077</span><span id="line-1077"> void clearDeadServersWithSameHostNameAndPortOfOnlineServer() {</span>
-<span class="source-line-no">1078</span><span id="line-1078"> for (ServerName serverName : getOnlineServersList()) {</span>
-<span class="source-line-no">1079</span><span id="line-1079"> deadservers.cleanAllPreviousInstances(serverName);</span>
-<span class="source-line-no">1080</span><span id="line-1080"> }</span>
-<span class="source-line-no">1081</span><span id="line-1081"> }</span>
-<span class="source-line-no">1082</span><span id="line-1082"></span>
-<span class="source-line-no">1083</span><span id="line-1083"> /**</span>
-<span class="source-line-no">1084</span><span id="line-1084"> * Called by delete table and similar to notify the ServerManager that a region was removed.</span>
-<span class="source-line-no">1085</span><span id="line-1085"> */</span>
-<span class="source-line-no">1086</span><span id="line-1086"> public void removeRegion(final RegionInfo regionInfo) {</span>
-<span class="source-line-no">1087</span><span id="line-1087"> final byte[] encodedName = regionInfo.getEncodedNameAsBytes();</span>
-<span class="source-line-no">1088</span><span id="line-1088"> storeFlushedSequenceIdsByRegion.remove(encodedName);</span>
-<span class="source-line-no">1089</span><span id="line-1089"> flushedSequenceIdByRegion.remove(encodedName);</span>
-<span class="source-line-no">1090</span><span id="line-1090"> }</span>
-<span class="source-line-no">1091</span><span id="line-1091"></span>
-<span class="source-line-no">1092</span><span id="line-1092"> public boolean isRegionInServerManagerStates(final RegionInfo hri) {</span>
-<span class="source-line-no">1093</span><span id="line-1093"> final byte[] encodedName = hri.getEncodedNameAsBytes();</span>
-<span class="source-line-no">1094</span><span id="line-1094"> return (storeFlushedSequenceIdsByRegion.containsKey(encodedName)</span>
-<span class="source-line-no">1095</span><span id="line-1095"> || flushedSequenceIdByRegion.containsKey(encodedName));</span>
-<span class="source-line-no">1096</span><span id="line-1096"> }</span>
-<span class="source-line-no">1097</span><span id="line-1097"></span>
-<span class="source-line-no">1098</span><span id="line-1098"> /**</span>
-<span class="source-line-no">1099</span><span id="line-1099"> * Called by delete table and similar to notify the ServerManager that a region was removed.</span>
-<span class="source-line-no">1100</span><span id="line-1100"> */</span>
-<span class="source-line-no">1101</span><span id="line-1101"> public void removeRegions(final List<RegionInfo> regions) {</span>
-<span class="source-line-no">1102</span><span id="line-1102"> for (RegionInfo hri : regions) {</span>
-<span class="source-line-no">1103</span><span id="line-1103"> removeRegion(hri);</span>
-<span class="source-line-no">1104</span><span id="line-1104"> }</span>
-<span class="source-line-no">1105</span><span id="line-1105"> }</span>
-<span class="source-line-no">1106</span><span id="line-1106"></span>
-<span class="source-line-no">1107</span><span id="line-1107"> /**</span>
-<span class="source-line-no">1108</span><span id="line-1108"> * May return 0 when server is not online.</span>
-<span class="source-line-no">1109</span><span id="line-1109"> */</span>
-<span class="source-line-no">1110</span><span id="line-1110"> public int getVersionNumber(ServerName serverName) {</span>
-<span class="source-line-no">1111</span><span id="line-1111"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
-<span class="source-line-no">1112</span><span id="line-1112"> return serverMetrics != null ? serverMetrics.getVersionNumber() : 0;</span>
-<span class="source-line-no">1113</span><span id="line-1113"> }</span>
-<span class="source-line-no">1114</span><span id="line-1114"></span>
-<span class="source-line-no">1115</span><span id="line-1115"> /**</span>
-<span class="source-line-no">1116</span><span id="line-1116"> * May return "0.0.0" when server is not online</span>
-<span class="source-line-no">1117</span><span id="line-1117"> */</span>
-<span class="source-line-no">1118</span><span id="line-1118"> public String getVersion(ServerName serverName) {</span>
-<span class="source-line-no">1119</span><span id="line-1119"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
-<span class="source-line-no">1120</span><span id="line-1120"> return serverMetrics != null ? serverMetrics.getVersion() : "0.0.0";</span>
-<span class="source-line-no">1121</span><span id="line-1121"> }</span>
-<span class="source-line-no">1122</span><span id="line-1122"></span>
-<span class="source-line-no">1123</span><span id="line-1123"> public int getInfoPort(ServerName serverName) {</span>
-<span class="source-line-no">1124</span><span id="line-1124"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
-<span class="source-line-no">1125</span><span id="line-1125"> return serverMetrics != null ? serverMetrics.getInfoServerPort() : 0;</span>
-<span class="source-line-no">1126</span><span id="line-1126"> }</span>
-<span class="source-line-no">1127</span><span id="line-1127"></span>
-<span class="source-line-no">1128</span><span id="line-1128"> /**</span>
-<span class="source-line-no">1129</span><span id="line-1129"> * Persist last flushed sequence id of each region to HDFS</span>
-<span class="source-line-no">1130</span><span id="line-1130"> * @throws IOException if persit to HDFS fails</span>
-<span class="source-line-no">1131</span><span id="line-1131"> */</span>
-<span class="source-line-no">1132</span><span id="line-1132"> private void persistRegionLastFlushedSequenceIds() throws IOException {</span>
-<span class="source-line-no">1133</span><span id="line-1133"> if (isFlushSeqIdPersistInProgress) {</span>
-<span class="source-line-no">1134</span><span id="line-1134"> return;</span>
-<span class="source-line-no">1135</span><span id="line-1135"> }</span>
-<span class="source-line-no">1136</span><span id="line-1136"> isFlushSeqIdPersistInProgress = true;</span>
-<span class="source-line-no">1137</span><span id="line-1137"> try {</span>
-<span class="source-line-no">1138</span><span id="line-1138"> Configuration conf = master.getConfiguration();</span>
-<span class="source-line-no">1139</span><span id="line-1139"> Path rootDir = CommonFSUtils.getRootDir(conf);</span>
-<span class="source-line-no">1140</span><span id="line-1140"> Path lastFlushedSeqIdPath = new Path(rootDir, LAST_FLUSHED_SEQ_ID_FILE);</span>
-<span class="source-line-no">1141</span><span id="line-1141"> FileSystem fs = FileSystem.get(conf);</span>
-<span class="source-line-no">1142</span><span id="line-1142"> if (fs.exists(lastFlushedSeqIdPath)) {</span>
-<span class="source-line-no">1143</span><span id="line-1143"> LOG.info("Rewriting .lastflushedseqids file at: " + lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1144</span><span id="line-1144"> if (!fs.delete(lastFlushedSeqIdPath, false)) {</span>
-<span class="source-line-no">1145</span><span id="line-1145"> throw new IOException("Unable to remove existing " + lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1146</span><span id="line-1146"> }</span>
-<span class="source-line-no">1147</span><span id="line-1147"> } else {</span>
-<span class="source-line-no">1148</span><span id="line-1148"> LOG.info("Writing .lastflushedseqids file at: " + lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1149</span><span id="line-1149"> }</span>
-<span class="source-line-no">1150</span><span id="line-1150"> FSDataOutputStream out = fs.create(lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1151</span><span id="line-1151"> FlushedSequenceId.Builder flushedSequenceIdBuilder = FlushedSequenceId.newBuilder();</span>
-<span class="source-line-no">1152</span><span id="line-1152"> try {</span>
-<span class="source-line-no">1153</span><span id="line-1153"> for (Entry<byte[], Long> entry : flushedSequenceIdByRegion.entrySet()) {</span>
-<span class="source-line-no">1154</span><span id="line-1154"> FlushedRegionSequenceId.Builder flushedRegionSequenceIdBuilder =</span>
-<span class="source-line-no">1155</span><span id="line-1155"> FlushedRegionSequenceId.newBuilder();</span>
-<span class="source-line-no">1156</span><span id="line-1156"> flushedRegionSequenceIdBuilder.setRegionEncodedName(ByteString.copyFrom(entry.getKey()));</span>
-<span class="source-line-no">1157</span><span id="line-1157"> flushedRegionSequenceIdBuilder.setSeqId(entry.getValue());</span>
-<span class="source-line-no">1158</span><span id="line-1158"> ConcurrentNavigableMap<byte[], Long> storeSeqIds =</span>
-<span class="source-line-no">1159</span><span id="line-1159"> storeFlushedSequenceIdsByRegion.get(entry.getKey());</span>
-<span class="source-line-no">1160</span><span id="line-1160"> if (storeSeqIds != null) {</span>
-<span class="source-line-no">1161</span><span id="line-1161"> for (Entry<byte[], Long> store : storeSeqIds.entrySet()) {</span>
-<span class="source-line-no">1162</span><span id="line-1162"> FlushedStoreSequenceId.Builder flushedStoreSequenceIdBuilder =</span>
-<span class="source-line-no">1163</span><span id="line-1163"> FlushedStoreSequenceId.newBuilder();</span>
-<span class="source-line-no">1164</span><span id="line-1164"> flushedStoreSequenceIdBuilder.setFamily(ByteString.copyFrom(store.getKey()));</span>
-<span class="source-line-no">1165</span><span id="line-1165"> flushedStoreSequenceIdBuilder.setSeqId(store.getValue());</span>
-<span class="source-line-no">1166</span><span id="line-1166"> flushedRegionSequenceIdBuilder.addStores(flushedStoreSequenceIdBuilder);</span>
-<span class="source-line-no">1167</span><span id="line-1167"> }</span>
-<span class="source-line-no">1168</span><span id="line-1168"> }</span>
-<span class="source-line-no">1169</span><span id="line-1169"> flushedSequenceIdBuilder.addRegionSequenceId(flushedRegionSequenceIdBuilder);</span>
-<span class="source-line-no">1170</span><span id="line-1170"> }</span>
-<span class="source-line-no">1171</span><span id="line-1171"> flushedSequenceIdBuilder.build().writeDelimitedTo(out);</span>
-<span class="source-line-no">1172</span><span id="line-1172"> } finally {</span>
-<span class="source-line-no">1173</span><span id="line-1173"> if (out != null) {</span>
-<span class="source-line-no">1174</span><span id="line-1174"> out.close();</span>
-<span class="source-line-no">1175</span><span id="line-1175"> }</span>
-<span class="source-line-no">1176</span><span id="line-1176"> }</span>
-<span class="source-line-no">1177</span><span id="line-1177"> } finally {</span>
-<span class="source-line-no">1178</span><span id="line-1178"> isFlushSeqIdPersistInProgress = false;</span>
-<span class="source-line-no">1179</span><span id="line-1179"> }</span>
-<span class="source-line-no">1180</span><span id="line-1180"> }</span>
-<span class="source-line-no">1181</span><span id="line-1181"></span>
-<span class="source-line-no">1182</span><span id="line-1182"> /**</span>
-<span class="source-line-no">1183</span><span id="line-1183"> * Load last flushed sequence id of each region from HDFS, if persisted</span>
-<span class="source-line-no">1184</span><span id="line-1184"> */</span>
-<span class="source-line-no">1185</span><span id="line-1185"> public void loadLastFlushedSequenceIds() throws IOException {</span>
-<span class="source-line-no">1186</span><span id="line-1186"> if (!persistFlushedSequenceId) {</span>
-<span class="source-line-no">1187</span><span id="line-1187"> return;</span>
-<span class="source-line-no">1188</span><span id="line-1188"> }</span>
-<span class="source-line-no">1189</span><span id="line-1189"> Configuration conf = master.getConfiguration();</span>
-<span class="source-line-no">1190</span><span id="line-1190"> Path rootDir = CommonFSUtils.getRootDir(conf);</span>
-<span class="source-line-no">1191</span><span id="line-1191"> Path lastFlushedSeqIdPath = new Path(rootDir, LAST_FLUSHED_SEQ_ID_FILE);</span>
-<span class="source-line-no">1192</span><span id="line-1192"> FileSystem fs = FileSystem.get(conf);</span>
-<span class="source-line-no">1193</span><span id="line-1193"> if (!fs.exists(lastFlushedSeqIdPath)) {</span>
-<span class="source-line-no">1194</span><span id="line-1194"> LOG.info("No .lastflushedseqids found at " + lastFlushedSeqIdPath</span>
-<span class="source-line-no">1195</span><span id="line-1195"> + " will record last flushed sequence id"</span>
-<span class="source-line-no">1196</span><span id="line-1196"> + " for regions by regionserver report all over again");</span>
-<span class="source-line-no">1197</span><span id="line-1197"> return;</span>
-<span class="source-line-no">1198</span><span id="line-1198"> } else {</span>
-<span class="source-line-no">1199</span><span id="line-1199"> LOG.info("begin to load .lastflushedseqids at " + lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1200</span><span id="line-1200"> }</span>
-<span class="source-line-no">1201</span><span id="line-1201"> FSDataInputStream in = fs.open(lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1202</span><span id="line-1202"> try {</span>
-<span class="source-line-no">1203</span><span id="line-1203"> FlushedSequenceId flushedSequenceId = FlushedSequenceId.parseDelimitedFrom(in);</span>
-<span class="source-line-no">1204</span><span id="line-1204"> if (flushedSequenceId == null) {</span>
-<span class="source-line-no">1205</span><span id="line-1205"> LOG.info(".lastflushedseqids found at {} is empty", lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1206</span><span id="line-1206"> return;</span>
-<span class="source-line-no">1207</span><span id="line-1207"> }</span>
-<span class="source-line-no">1208</span><span id="line-1208"> for (FlushedRegionSequenceId flushedRegionSequenceId : flushedSequenceId</span>
-<span class="source-line-no">1209</span><span id="line-1209"> .getRegionSequenceIdList()) {</span>
-<span class="source-line-no">1210</span><span id="line-1210"> byte[] encodedRegionName = flushedRegionSequenceId.getRegionEncodedName().toByteArray();</span>
-<span class="source-line-no">1211</span><span id="line-1211"> flushedSequenceIdByRegion.putIfAbsent(encodedRegionName,</span>
-<span class="source-line-no">1212</span><span id="line-1212"> flushedRegionSequenceId.getSeqId());</span>
-<span class="source-line-no">1213</span><span id="line-1213"> if (</span>
-<span class="source-line-no">1214</span><span id="line-1214"> flushedRegionSequenceId.getStoresList() != null</span>
-<span class="source-line-no">1215</span><span id="line-1215"> && flushedRegionSequenceId.getStoresList().size() != 0</span>
-<span class="source-line-no">1216</span><span id="line-1216"> ) {</span>
-<span class="source-line-no">1217</span><span id="line-1217"> ConcurrentNavigableMap<byte[], Long> storeFlushedSequenceId =</span>
-<span class="source-line-no">1218</span><span id="line-1218"> computeIfAbsent(storeFlushedSequenceIdsByRegion, encodedRegionName,</span>
-<span class="source-line-no">1219</span><span id="line-1219"> () -> new ConcurrentSkipListMap<>(Bytes.BYTES_COMPARATOR));</span>
-<span class="source-line-no">1220</span><span id="line-1220"> for (FlushedStoreSequenceId flushedStoreSequenceId : flushedRegionSequenceId</span>
-<span class="source-line-no">1221</span><span id="line-1221"> .getStoresList()) {</span>
-<span class="source-line-no">1222</span><span id="line-1222"> storeFlushedSequenceId.put(flushedStoreSequenceId.getFamily().toByteArray(),</span>
-<span class="source-line-no">1223</span><span id="line-1223"> flushedStoreSequenceId.getSeqId());</span>
-<span class="source-line-no">1224</span><span id="line-1224"> }</span>
-<span class="source-line-no">1225</span><span id="line-1225"> }</span>
-<span class="source-line-no">1226</span><span id="line-1226"> }</span>
-<span class="source-line-no">1227</span><span id="line-1227"> } finally {</span>
-<span class="source-line-no">1228</span><span id="line-1228"> in.close();</span>
-<span class="source-line-no">1229</span><span id="line-1229"> }</span>
-<span class="source-line-no">1230</span><span id="line-1230"> }</span>
-<span class="source-line-no">1231</span><span id="line-1231"></span>
-<span class="source-line-no">1232</span><span id="line-1232"> /**</span>
-<span class="source-line-no">1233</span><span id="line-1233"> * Regions may have been removed between latest persist of FlushedSequenceIds and master abort. So</span>
-<span class="source-line-no">1234</span><span id="line-1234"> * after loading FlushedSequenceIds from file, and after meta loaded, we need to remove the</span>
-<span class="source-line-no">1235</span><span id="line-1235"> * deleted region according to RegionStates.</span>
-<span class="source-line-no">1236</span><span id="line-1236"> */</span>
-<span class="source-line-no">1237</span><span id="line-1237"> public void removeDeletedRegionFromLoadedFlushedSequenceIds() {</span>
-<span class="source-line-no">1238</span><span id="line-1238"> RegionStates regionStates = master.getAssignmentManager().getRegionStates();</span>
-<span class="source-line-no">1239</span><span id="line-1239"> Iterator<byte[]> it = flushedSequenceIdByRegion.keySet().iterator();</span>
-<span class="source-line-no">1240</span><span id="line-1240"> while (it.hasNext()) {</span>
-<span class="source-line-no">1241</span><span id="line-1241"> byte[] regionEncodedName = it.next();</span>
-<span class="source-line-no">1242</span><span id="line-1242"> if (regionStates.getRegionState(Bytes.toStringBinary(regionEncodedName)) == null) {</span>
-<span class="source-line-no">1243</span><span id="line-1243"> it.remove();</span>
-<span class="source-line-no">1244</span><span id="line-1244"> storeFlushedSequenceIdsByRegion.remove(regionEncodedName);</span>
-<span class="source-line-no">1245</span><span id="line-1245"> }</span>
-<span class="source-line-no">1246</span><span id="line-1246"> }</span>
-<span class="source-line-no">1247</span><span id="line-1247"> }</span>
-<span class="source-line-no">1248</span><span id="line-1248"></span>
-<span class="source-line-no">1249</span><span id="line-1249"> private class FlushedSequenceIdFlusher extends ScheduledChore {</span>
-<span class="source-line-no">1250</span><span id="line-1250"></span>
-<span class="source-line-no">1251</span><span id="line-1251"> public FlushedSequenceIdFlusher(String name, int p) {</span>
-<span class="source-line-no">1252</span><span id="line-1252"> super(name, master, p, 60 * 1000); // delay one minute before first execute</span>
-<span class="source-line-no">1253</span><span id="line-1253"> }</span>
-<span class="source-line-no">1254</span><span id="line-1254"></span>
-<span class="source-line-no">1255</span><span id="line-1255"> @Override</span>
-<span class="source-line-no">1256</span><span id="line-1256"> protected void chore() {</span>
-<span class="source-line-no">1257</span><span id="line-1257"> try {</span>
-<span class="source-line-no">1258</span><span id="line-1258"> persistRegionLastFlushedSequenceIds();</span>
-<span class="source-line-no">1259</span><span id="line-1259"> } catch (IOException e) {</span>
-<span class="source-line-no">1260</span><span id="line-1260"> LOG.debug("Failed to persist last flushed sequence id of regions" + " to file system", e);</span>
-<span class="source-line-no">1261</span><span id="line-1261"> }</span>
-<span class="source-line-no">1262</span><span id="line-1262"> }</span>
-<span class="source-line-no">1263</span><span id="line-1263"> }</span>
-<span class="source-line-no">1264</span><span id="line-1264">}</span>
+<span class="source-line-no">1067</span><span id="line-1067"> return new ArrayList<>(destServers);</span>
+<span class="source-line-no">1068</span><span id="line-1068"> }</span>
+<span class="source-line-no">1069</span><span id="line-1069"></span>
+<span class="source-line-no">1070</span><span id="line-1070"> /**</span>
+<span class="source-line-no">1071</span><span id="line-1071"> * Calls {@link #createDestinationServersList} without server to exclude.</span>
+<span class="source-line-no">1072</span><span id="line-1072"> */</span>
+<span class="source-line-no">1073</span><span id="line-1073"> public List<ServerName> createDestinationServersList() {</span>
+<span class="source-line-no">1074</span><span id="line-1074"> return createDestinationServersList(null);</span>
+<span class="source-line-no">1075</span><span id="line-1075"> }</span>
+<span class="source-line-no">1076</span><span id="line-1076"></span>
+<span class="source-line-no">1077</span><span id="line-1077"> /**</span>
+<span class="source-line-no">1078</span><span id="line-1078"> * To clear any dead server with same host name and port of any online server</span>
+<span class="source-line-no">1079</span><span id="line-1079"> */</span>
+<span class="source-line-no">1080</span><span id="line-1080"> void clearDeadServersWithSameHostNameAndPortOfOnlineServer() {</span>
+<span class="source-line-no">1081</span><span id="line-1081"> for (ServerName serverName : getOnlineServersList()) {</span>
+<span class="source-line-no">1082</span><span id="line-1082"> deadservers.cleanAllPreviousInstances(serverName);</span>
+<span class="source-line-no">1083</span><span id="line-1083"> }</span>
+<span class="source-line-no">1084</span><span id="line-1084"> }</span>
+<span class="source-line-no">1085</span><span id="line-1085"></span>
+<span class="source-line-no">1086</span><span id="line-1086"> /**</span>
+<span class="source-line-no">1087</span><span id="line-1087"> * Called by delete table and similar to notify the ServerManager that a region was removed.</span>
+<span class="source-line-no">1088</span><span id="line-1088"> */</span>
+<span class="source-line-no">1089</span><span id="line-1089"> public void removeRegion(final RegionInfo regionInfo) {</span>
+<span class="source-line-no">1090</span><span id="line-1090"> final byte[] encodedName = regionInfo.getEncodedNameAsBytes();</span>
+<span class="source-line-no">1091</span><span id="line-1091"> storeFlushedSequenceIdsByRegion.remove(encodedName);</span>
+<span class="source-line-no">1092</span><span id="line-1092"> flushedSequenceIdByRegion.remove(encodedName);</span>
+<span class="source-line-no">1093</span><span id="line-1093"> }</span>
+<span class="source-line-no">1094</span><span id="line-1094"></span>
+<span class="source-line-no">1095</span><span id="line-1095"> public boolean isRegionInServerManagerStates(final RegionInfo hri) {</span>
+<span class="source-line-no">1096</span><span id="line-1096"> final byte[] encodedName = hri.getEncodedNameAsBytes();</span>
+<span class="source-line-no">1097</span><span id="line-1097"> return (storeFlushedSequenceIdsByRegion.containsKey(encodedName)</span>
+<span class="source-line-no">1098</span><span id="line-1098"> || flushedSequenceIdByRegion.containsKey(encodedName));</span>
+<span class="source-line-no">1099</span><span id="line-1099"> }</span>
+<span class="source-line-no">1100</span><span id="line-1100"></span>
+<span class="source-line-no">1101</span><span id="line-1101"> /**</span>
+<span class="source-line-no">1102</span><span id="line-1102"> * Called by delete table and similar to notify the ServerManager that a region was removed.</span>
+<span class="source-line-no">1103</span><span id="line-1103"> */</span>
+<span class="source-line-no">1104</span><span id="line-1104"> public void removeRegions(final List<RegionInfo> regions) {</span>
+<span class="source-line-no">1105</span><span id="line-1105"> for (RegionInfo hri : regions) {</span>
+<span class="source-line-no">1106</span><span id="line-1106"> removeRegion(hri);</span>
+<span class="source-line-no">1107</span><span id="line-1107"> }</span>
+<span class="source-line-no">1108</span><span id="line-1108"> }</span>
+<span class="source-line-no">1109</span><span id="line-1109"></span>
+<span class="source-line-no">1110</span><span id="line-1110"> /**</span>
+<span class="source-line-no">1111</span><span id="line-1111"> * May return 0 when server is not online.</span>
+<span class="source-line-no">1112</span><span id="line-1112"> */</span>
+<span class="source-line-no">1113</span><span id="line-1113"> public int getVersionNumber(ServerName serverName) {</span>
+<span class="source-line-no">1114</span><span id="line-1114"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
+<span class="source-line-no">1115</span><span id="line-1115"> return serverMetrics != null ? serverMetrics.getVersionNumber() : 0;</span>
+<span class="source-line-no">1116</span><span id="line-1116"> }</span>
+<span class="source-line-no">1117</span><span id="line-1117"></span>
+<span class="source-line-no">1118</span><span id="line-1118"> /**</span>
+<span class="source-line-no">1119</span><span id="line-1119"> * May return "0.0.0" when server is not online</span>
+<span class="source-line-no">1120</span><span id="line-1120"> */</span>
+<span class="source-line-no">1121</span><span id="line-1121"> public String getVersion(ServerName serverName) {</span>
+<span class="source-line-no">1122</span><span id="line-1122"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
+<span class="source-line-no">1123</span><span id="line-1123"> return serverMetrics != null ? serverMetrics.getVersion() : "0.0.0";</span>
+<span class="source-line-no">1124</span><span id="line-1124"> }</span>
+<span class="source-line-no">1125</span><span id="line-1125"></span>
+<span class="source-line-no">1126</span><span id="line-1126"> public int getInfoPort(ServerName serverName) {</span>
+<span class="source-line-no">1127</span><span id="line-1127"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
+<span class="source-line-no">1128</span><span id="line-1128"> return serverMetrics != null ? serverMetrics.getInfoServerPort() : 0;</span>
+<span class="source-line-no">1129</span><span id="line-1129"> }</span>
+<span class="source-line-no">1130</span><span id="line-1130"></span>
+<span class="source-line-no">1131</span><span id="line-1131"> /**</span>
+<span class="source-line-no">1132</span><span id="line-1132"> * Persist last flushed sequence id of each region to HDFS</span>
+<span class="source-line-no">1133</span><span id="line-1133"> * @throws IOException if persit to HDFS fails</span>
+<span class="source-line-no">1134</span><span id="line-1134"> */</span>
+<span class="source-line-no">1135</span><span id="line-1135"> private void persistRegionLastFlushedSequenceIds() throws IOException {</span>
+<span class="source-line-no">1136</span><span id="line-1136"> if (isFlushSeqIdPersistInProgress) {</span>
+<span class="source-line-no">1137</span><span id="line-1137"> return;</span>
+<span class="source-line-no">1138</span><span id="line-1138"> }</span>
+<span class="source-line-no">1139</span><span id="line-1139"> isFlushSeqIdPersistInProgress = true;</span>
+<span class="source-line-no">1140</span><span id="line-1140"> try {</span>
+<span class="source-line-no">1141</span><span id="line-1141"> Configuration conf = master.getConfiguration();</span>
+<span class="source-line-no">1142</span><span id="line-1142"> Path rootDir = CommonFSUtils.getRootDir(conf);</span>
+<span class="source-line-no">1143</span><span id="line-1143"> Path lastFlushedSeqIdPath = new Path(rootDir, LAST_FLUSHED_SEQ_ID_FILE);</span>
+<span class="source-line-no">1144</span><span id="line-1144"> FileSystem fs = FileSystem.get(conf);</span>
+<span class="source-line-no">1145</span><span id="line-1145"> if (fs.exists(lastFlushedSeqIdPath)) {</span>
+<span class="source-line-no">1146</span><span id="line-1146"> LOG.info("Rewriting .lastflushedseqids file at: " + lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1147</span><span id="line-1147"> if (!fs.delete(lastFlushedSeqIdPath, false)) {</span>
+<span class="source-line-no">1148</span><span id="line-1148"> throw new IOException("Unable to remove existing " + lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1149</span><span id="line-1149"> }</span>
+<span class="source-line-no">1150</span><span id="line-1150"> } else {</span>
+<span class="source-line-no">1151</span><span id="line-1151"> LOG.info("Writing .lastflushedseqids file at: " + lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1152</span><span id="line-1152"> }</span>
+<span class="source-line-no">1153</span><span id="line-1153"> FSDataOutputStream out = fs.create(lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1154</span><span id="line-1154"> FlushedSequenceId.Builder flushedSequenceIdBuilder = FlushedSequenceId.newBuilder();</span>
+<span class="source-line-no">1155</span><span id="line-1155"> try {</span>
+<span class="source-line-no">1156</span><span id="line-1156"> for (Entry<byte[], Long> entry : flushedSequenceIdByRegion.entrySet()) {</span>
+<span class="source-line-no">1157</span><span id="line-1157"> FlushedRegionSequenceId.Builder flushedRegionSequenceIdBuilder =</span>
+<span class="source-line-no">1158</span><span id="line-1158"> FlushedRegionSequenceId.newBuilder();</span>
+<span class="source-line-no">1159</span><span id="line-1159"> flushedRegionSequenceIdBuilder.setRegionEncodedName(ByteString.copyFrom(entry.getKey()));</span>
+<span class="source-line-no">1160</span><span id="line-1160"> flushedRegionSequenceIdBuilder.setSeqId(entry.getValue());</span>
+<span class="source-line-no">1161</span><span id="line-1161"> ConcurrentNavigableMap<byte[], Long> storeSeqIds =</span>
+<span class="source-line-no">1162</span><span id="line-1162"> storeFlushedSequenceIdsByRegion.get(entry.getKey());</span>
+<span class="source-line-no">1163</span><span id="line-1163"> if (storeSeqIds != null) {</span>
+<span class="source-line-no">1164</span><span id="line-1164"> for (Entry<byte[], Long> store : storeSeqIds.entrySet()) {</span>
+<span class="source-line-no">1165</span><span id="line-1165"> FlushedStoreSequenceId.Builder flushedStoreSequenceIdBuilder =</span>
+<span class="source-line-no">1166</span><span id="line-1166"> FlushedStoreSequenceId.newBuilder();</span>
+<span class="source-line-no">1167</span><span id="line-1167"> flushedStoreSequenceIdBuilder.setFamily(ByteString.copyFrom(store.getKey()));</span>
+<span class="source-line-no">1168</span><span id="line-1168"> flushedStoreSequenceIdBuilder.setSeqId(store.getValue());</span>
+<span class="source-line-no">1169</span><span id="line-1169"> flushedRegionSequenceIdBuilder.addStores(flushedStoreSequenceIdBuilder);</span>
+<span class="source-line-no">1170</span><span id="line-1170"> }</span>
+<span class="source-line-no">1171</span><span id="line-1171"> }</span>
+<span class="source-line-no">1172</span><span id="line-1172"> flushedSequenceIdBuilder.addRegionSequenceId(flushedRegionSequenceIdBuilder);</span>
+<span class="source-line-no">1173</span><span id="line-1173"> }</span>
+<span class="source-line-no">1174</span><span id="line-1174"> flushedSequenceIdBuilder.build().writeDelimitedTo(out);</span>
+<span class="source-line-no">1175</span><span id="line-1175"> } finally {</span>
+<span class="source-line-no">1176</span><span id="line-1176"> if (out != null) {</span>
+<span class="source-line-no">1177</span><span id="line-1177"> out.close();</span>
+<span class="source-line-no">1178</span><span id="line-1178"> }</span>
+<span class="source-line-no">1179</span><span id="line-1179"> }</span>
+<span class="source-line-no">1180</span><span id="line-1180"> } finally {</span>
+<span class="source-line-no">1181</span><span id="line-1181"> isFlushSeqIdPersistInProgress = false;</span>
+<span class="source-line-no">1182</span><span id="line-1182"> }</span>
+<span class="source-line-no">1183</span><span id="line-1183"> }</span>
+<span class="source-line-no">1184</span><span id="line-1184"></span>
+<span class="source-line-no">1185</span><span id="line-1185"> /**</span>
+<span class="source-line-no">1186</span><span id="line-1186"> * Load last flushed sequence id of each region from HDFS, if persisted</span>
+<span class="source-line-no">1187</span><span id="line-1187"> */</span>
+<span class="source-line-no">1188</span><span id="line-1188"> public void loadLastFlushedSequenceIds() throws IOException {</span>
+<span class="source-line-no">1189</span><span id="line-1189"> if (!persistFlushedSequenceId) {</span>
+<span class="source-line-no">1190</span><span id="line-1190"> return;</span>
+<span class="source-line-no">1191</span><span id="line-1191"> }</span>
+<span class="source-line-no">1192</span><span id="line-1192"> Configuration conf = master.getConfiguration();</span>
+<span class="source-line-no">1193</span><span id="line-1193"> Path rootDir = CommonFSUtils.getRootDir(conf);</span>
+<span class="source-line-no">1194</span><span id="line-1194"> Path lastFlushedSeqIdPath = new Path(rootDir, LAST_FLUSHED_SEQ_ID_FILE);</span>
+<span class="source-line-no">1195</span><span id="line-1195"> FileSystem fs = FileSystem.get(conf);</span>
+<span class="source-line-no">1196</span><span id="line-1196"> if (!fs.exists(lastFlushedSeqIdPath)) {</span>
+<span class="source-line-no">1197</span><span id="line-1197"> LOG.info("No .lastflushedseqids found at " + lastFlushedSeqIdPath</span>
+<span class="source-line-no">1198</span><span id="line-1198"> + " will record last flushed sequence id"</span>
+<span class="source-line-no">1199</span><span id="line-1199"> + " for regions by regionserver report all over again");</span>
+<span class="source-line-no">1200</span><span id="line-1200"> return;</span>
+<span class="source-line-no">1201</span><span id="line-1201"> } else {</span>
+<span class="source-line-no">1202</span><span id="line-1202"> LOG.info("begin to load .lastflushedseqids at " + lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1203</span><span id="line-1203"> }</span>
+<span class="source-line-no">1204</span><span id="line-1204"> FSDataInputStream in = fs.open(lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1205</span><span id="line-1205"> try {</span>
+<span class="source-line-no">1206</span><span id="line-1206"> FlushedSequenceId flushedSequenceId = FlushedSequenceId.parseDelimitedFrom(in);</span>
+<span class="source-line-no">1207</span><span id="line-1207"> if (flushedSequenceId == null) {</span>
+<span class="source-line-no">1208</span><span id="line-1208"> LOG.info(".lastflushedseqids found at {} is empty", lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1209</span><span id="line-1209"> return;</span>
+<span class="source-line-no">1210</span><span id="line-1210"> }</span>
+<span class="source-line-no">1211</span><span id="line-1211"> for (FlushedRegionSequenceId flushedRegionSequenceId : flushedSequenceId</span>
+<span class="source-line-no">1212</span><span id="line-1212"> .getRegionSequenceIdList()) {</span>
+<span class="source-line-no">1213</span><span id="line-1213"> byte[] encodedRegionName = flushedRegionSequenceId.getRegionEncodedName().toByteArray();</span>
+<span class="source-line-no">1214</span><span id="line-1214"> flushedSequenceIdByRegion.putIfAbsent(encodedRegionName,</span>
+<span class="source-line-no">1215</span><span id="line-1215"> flushedRegionSequenceId.getSeqId());</span>
+<span class="source-line-no">1216</span><span id="line-1216"> if (</span>
+<span class="source-line-no">1217</span><span id="line-1217"> flushedRegionSequenceId.getStoresList() != null</span>
+<span class="source-line-no">1218</span><span id="line-1218"> && flushedRegionSequenceId.getStoresList().size() != 0</span>
+<span class="source-line-no">1219</span><span id="line-1219"> ) {</span>
+<span class="source-line-no">1220</span><span id="line-1220"> ConcurrentNavigableMap<byte[], Long> storeFlushedSequenceId =</span>
+<span class="source-line-no">1221</span><span id="line-1221"> computeIfAbsent(storeFlushedSequenceIdsByRegion, encodedRegionName,</span>
+<span class="source-line-no">1222</span><span id="line-1222"> () -> new ConcurrentSkipListMap<>(Bytes.BYTES_COMPARATOR));</span>
+<span class="source-line-no">1223</span><span id="line-1223"> for (FlushedStoreSequenceId flushedStoreSequenceId : flushedRegionSequenceId</span>
+<span class="source-line-no">1224</span><span id="line-1224"> .getStoresList()) {</span>
+<span class="source-line-no">1225</span><span id="line-1225"> storeFlushedSequenceId.put(flushedStoreSequenceId.getFamily().toByteArray(),</span>
+<span class="source-line-no">1226</span><span id="line-1226"> flushedStoreSequenceId.getSeqId());</span>
+<span class="source-line-no">1227</span><span id="line-1227"> }</span>
+<span class="source-line-no">1228</span><span id="line-1228"> }</span>
+<span class="source-line-no">1229</span><span id="line-1229"> }</span>
+<span class="source-line-no">1230</span><span id="line-1230"> } finally {</span>
+<span class="source-line-no">1231</span><span id="line-1231"> in.close();</span>
+<span class="source-line-no">1232</span><span id="line-1232"> }</span>
+<span class="source-line-no">1233</span><span id="line-1233"> }</span>
+<span class="source-line-no">1234</span><span id="line-1234"></span>
+<span class="source-line-no">1235</span><span id="line-1235"> /**</span>
+<span class="source-line-no">1236</span><span id="line-1236"> * Regions may have been removed between latest persist of FlushedSequenceIds and master abort. So</span>
+<span class="source-line-no">1237</span><span id="line-1237"> * after loading FlushedSequenceIds from file, and after meta loaded, we need to remove the</span>
+<span class="source-line-no">1238</span><span id="line-1238"> * deleted region according to RegionStates.</span>
+<span class="source-line-no">1239</span><span id="line-1239"> */</span>
+<span class="source-line-no">1240</span><span id="line-1240"> public void removeDeletedRegionFromLoadedFlushedSequenceIds() {</span>
+<span class="source-line-no">1241</span><span id="line-1241"> RegionStates regionStates = master.getAssignmentManager().getRegionStates();</span>
+<span class="source-line-no">1242</span><span id="line-1242"> Iterator<byte[]> it = flushedSequenceIdByRegion.keySet().iterator();</span>
+<span class="source-line-no">1243</span><span id="line-1243"> while (it.hasNext()) {</span>
+<span class="source-line-no">1244</span><span id="line-1244"> byte[] regionEncodedName = it.next();</span>
+<span class="source-line-no">1245</span><span id="line-1245"> if (regionStates.getRegionState(Bytes.toStringBinary(regionEncodedName)) == null) {</span>
+<span class="source-line-no">1246</span><span id="line-1246"> it.remove();</span>
+<span class="source-line-no">1247</span><span id="line-1247"> storeFlushedSequenceIdsByRegion.remove(regionEncodedName);</span>
+<span class="source-line-no">1248</span><span id="line-1248"> }</span>
+<span class="source-line-no">1249</span><span id="line-1249"> }</span>
+<span class="source-line-no">1250</span><span id="line-1250"> }</span>
+<span class="source-line-no">1251</span><span id="line-1251"></span>
+<span class="source-line-no">1252</span><span id="line-1252"> private class FlushedSequenceIdFlusher extends ScheduledChore {</span>
+<span class="source-line-no">1253</span><span id="line-1253"></span>
+<span class="source-line-no">1254</span><span id="line-1254"> public FlushedSequenceIdFlusher(String name, int p) {</span>
+<span class="source-line-no">1255</span><span id="line-1255"> super(name, master, p, 60 * 1000); // delay one minute before first execute</span>
+<span class="source-line-no">1256</span><span id="line-1256"> }</span>
+<span class="source-line-no">1257</span><span id="line-1257"></span>
+<span class="source-line-no">1258</span><span id="line-1258"> @Override</span>
+<span class="source-line-no">1259</span><span id="line-1259"> protected void chore() {</span>
+<span class="source-line-no">1260</span><span id="line-1260"> try {</span>
+<span class="source-line-no">1261</span><span id="line-1261"> persistRegionLastFlushedSequenceIds();</span>
+<span class="source-line-no">1262</span><span id="line-1262"> } catch (IOException e) {</span>
+<span class="source-line-no">1263</span><span id="line-1263"> LOG.debug("Failed to persist last flushed sequence id of regions" + " to file system", e);</span>
+<span class="source-line-no">1264</span><span id="line-1264"> }</span>
+<span class="source-line-no">1265</span><span id="line-1265"> }</span>
+<span class="source-line-no">1266</span><span id="line-1266"> }</span>
+<span class="source-line-no">1267</span><span id="line-1267">}</span>
diff --git a/apidocs/src-html/org/apache/hadoop/hbase/master/ServerManager.html b/apidocs/src-html/org/apache/hadoop/hbase/master/ServerManager.html
index 1b48584e9a9..7bc7b9cb40d 100644
--- a/apidocs/src-html/org/apache/hadoop/hbase/master/ServerManager.html
+++ b/apidocs/src-html/org/apache/hadoop/hbase/master/ServerManager.html
@@ -993,288 +993,291 @@
<span class="source-line-no">980</span><span id="line-980"> /**</span>
<span class="source-line-no">981</span><span id="line-981"> * Check if a server is unknown. A server can be online, or known to be dead, or unknown to this</span>
<span class="source-line-no">982</span><span id="line-982"> * manager (i.e, not online, not known to be dead either; it is simply not tracked by the master</span>
-<span class="source-line-no">983</span><span id="line-983"> * any more, for example, a very old previous instance).</span>
-<span class="source-line-no">984</span><span id="line-984"> */</span>
-<span class="source-line-no">985</span><span id="line-985"> public boolean isServerUnknown(ServerName serverName) {</span>
-<span class="source-line-no">986</span><span id="line-986"> return serverName == null</span>
-<span class="source-line-no">987</span><span id="line-987"> || (!onlineServers.containsKey(serverName) && !deadservers.isDeadServer(serverName));</span>
-<span class="source-line-no">988</span><span id="line-988"> }</span>
-<span class="source-line-no">989</span><span id="line-989"></span>
-<span class="source-line-no">990</span><span id="line-990"> public void shutdownCluster() {</span>
-<span class="source-line-no">991</span><span id="line-991"> String statusStr = "Cluster shutdown requested of master=" + this.master.getServerName();</span>
-<span class="source-line-no">992</span><span id="line-992"> LOG.info(statusStr);</span>
-<span class="source-line-no">993</span><span id="line-993"> this.clusterShutdown.set(true);</span>
-<span class="source-line-no">994</span><span id="line-994"> if (onlineServers.isEmpty()) {</span>
-<span class="source-line-no">995</span><span id="line-995"> // we do not synchronize here so this may cause a double stop, but not a big deal</span>
-<span class="source-line-no">996</span><span id="line-996"> master.stop("OnlineServer=0 right after cluster shutdown set");</span>
-<span class="source-line-no">997</span><span id="line-997"> }</span>
-<span class="source-line-no">998</span><span id="line-998"> }</span>
-<span class="source-line-no">999</span><span id="line-999"></span>
-<span class="source-line-no">1000</span><span id="line-1000"> public boolean isClusterShutdown() {</span>
-<span class="source-line-no">1001</span><span id="line-1001"> return this.clusterShutdown.get();</span>
-<span class="source-line-no">1002</span><span id="line-1002"> }</span>
-<span class="source-line-no">1003</span><span id="line-1003"></span>
-<span class="source-line-no">1004</span><span id="line-1004"> /**</span>
-<span class="source-line-no">1005</span><span id="line-1005"> * start chore in ServerManager</span>
-<span class="source-line-no">1006</span><span id="line-1006"> */</span>
-<span class="source-line-no">1007</span><span id="line-1007"> public void startChore() {</span>
-<span class="source-line-no">1008</span><span id="line-1008"> Configuration c = master.getConfiguration();</span>
-<span class="source-line-no">1009</span><span id="line-1009"> if (persistFlushedSequenceId) {</span>
-<span class="source-line-no">1010</span><span id="line-1010"> new Thread(() -> {</span>
-<span class="source-line-no">1011</span><span id="line-1011"> // after AM#loadMeta, RegionStates should be loaded, and some regions are</span>
-<span class="source-line-no">1012</span><span id="line-1012"> // deleted by drop/split/merge during removeDeletedRegionFromLoadedFlushedSequenceIds,</span>
-<span class="source-line-no">1013</span><span id="line-1013"> // but these deleted regions are not added back to RegionStates,</span>
-<span class="source-line-no">1014</span><span id="line-1014"> // so we can safely remove deleted regions.</span>
-<span class="source-line-no">1015</span><span id="line-1015"> removeDeletedRegionFromLoadedFlushedSequenceIds();</span>
-<span class="source-line-no">1016</span><span id="line-1016"> }, "RemoveDeletedRegionSyncThread").start();</span>
-<span class="source-line-no">1017</span><span id="line-1017"> int flushPeriod =</span>
-<span class="source-line-no">1018</span><span id="line-1018"> c.getInt(FLUSHEDSEQUENCEID_FLUSHER_INTERVAL, FLUSHEDSEQUENCEID_FLUSHER_INTERVAL_DEFAULT);</span>
-<span class="source-line-no">1019</span><span id="line-1019"> flushedSeqIdFlusher = new FlushedSequenceIdFlusher("FlushedSequenceIdFlusher", flushPeriod);</span>
-<span class="source-line-no">1020</span><span id="line-1020"> master.getChoreService().scheduleChore(flushedSeqIdFlusher);</span>
-<span class="source-line-no">1021</span><span id="line-1021"> }</span>
-<span class="source-line-no">1022</span><span id="line-1022"> }</span>
-<span class="source-line-no">1023</span><span id="line-1023"></span>
-<span class="source-line-no">1024</span><span id="line-1024"> /**</span>
-<span class="source-line-no">1025</span><span id="line-1025"> * Stop the ServerManager.</span>
-<span class="source-line-no">1026</span><span id="line-1026"> */</span>
-<span class="source-line-no">1027</span><span id="line-1027"> public void stop() {</span>
-<span class="source-line-no">1028</span><span id="line-1028"> if (flushedSeqIdFlusher != null) {</span>
-<span class="source-line-no">1029</span><span id="line-1029"> flushedSeqIdFlusher.shutdown();</span>
-<span class="source-line-no">1030</span><span id="line-1030"> }</span>
-<span class="source-line-no">1031</span><span id="line-1031"> if (persistFlushedSequenceId) {</span>
-<span class="source-line-no">1032</span><span id="line-1032"> try {</span>
-<span class="source-line-no">1033</span><span id="line-1033"> persistRegionLastFlushedSequenceIds();</span>
-<span class="source-line-no">1034</span><span id="line-1034"> } catch (IOException e) {</span>
-<span class="source-line-no">1035</span><span id="line-1035"> LOG.warn("Failed to persist last flushed sequence id of regions" + " to file system", e);</span>
-<span class="source-line-no">1036</span><span id="line-1036"> }</span>
-<span class="source-line-no">1037</span><span id="line-1037"> }</span>
-<span class="source-line-no">1038</span><span id="line-1038"> }</span>
-<span class="source-line-no">1039</span><span id="line-1039"></span>
-<span class="source-line-no">1040</span><span id="line-1040"> /**</span>
-<span class="source-line-no">1041</span><span id="line-1041"> * Creates a list of possible destinations for a region. It contains the online servers, but not</span>
-<span class="source-line-no">1042</span><span id="line-1042"> * the draining or dying servers.</span>
-<span class="source-line-no">1043</span><span id="line-1043"> * @param serversToExclude can be null if there is no server to exclude</span>
-<span class="source-line-no">1044</span><span id="line-1044"> */</span>
-<span class="source-line-no">1045</span><span id="line-1045"> public List<ServerName> createDestinationServersList(final List<ServerName> serversToExclude) {</span>
-<span class="source-line-no">1046</span><span id="line-1046"> Set<ServerName> destServers = new HashSet<>();</span>
-<span class="source-line-no">1047</span><span id="line-1047"> onlineServers.forEach((sn, sm) -> {</span>
-<span class="source-line-no">1048</span><span id="line-1048"> if (sm.getLastReportTimestamp() > 0) {</span>
-<span class="source-line-no">1049</span><span id="line-1049"> // This means we have already called regionServerReport at leaset once, then let's include</span>
-<span class="source-line-no">1050</span><span id="line-1050"> // this server for region assignment. This is an optimization to avoid assigning regions to</span>
-<span class="source-line-no">1051</span><span id="line-1051"> // an uninitialized server. See HBASE-25032 for more details.</span>
-<span class="source-line-no">1052</span><span id="line-1052"> destServers.add(sn);</span>
-<span class="source-line-no">1053</span><span id="line-1053"> }</span>
-<span class="source-line-no">1054</span><span id="line-1054"> });</span>
-<span class="source-line-no">1055</span><span id="line-1055"></span>
-<span class="source-line-no">1056</span><span id="line-1056"> if (serversToExclude != null) {</span>
-<span class="source-line-no">1057</span><span id="line-1057"> destServers.removeAll(serversToExclude);</span>
-<span class="source-line-no">1058</span><span id="line-1058"> }</span>
-<span class="source-line-no">1059</span><span id="line-1059"></span>
-<span class="source-line-no">1060</span><span id="line-1060"> // Loop through the draining server list and remove them from the server list</span>
-<span class="source-line-no">1061</span><span id="line-1061"> final List<ServerName> drainingServersCopy = getDrainingServersList();</span>
-<span class="source-line-no">1062</span><span id="line-1062"> destServers.removeAll(drainingServersCopy);</span>
-<span class="source-line-no">1063</span><span id="line-1063"></span>
-<span class="source-line-no">1064</span><span id="line-1064"> return new ArrayList<>(destServers);</span>
-<span class="source-line-no">1065</span><span id="line-1065"> }</span>
+<span class="source-line-no">983</span><span id="line-983"> * anymore, for example, a very old previous instance). A serverName with value null should not be</span>
+<span class="source-line-no">984</span><span id="line-984"> * considered unknown. We set value of regionLocation to null just before finding the assign</span>
+<span class="source-line-no">985</span><span id="line-985"> * candidate (in-between region transition) or while marking it OFFLINE/FAILED_OPEN. Refer</span>
+<span class="source-line-no">986</span><span id="line-986"> * HBASE-30142.</span>
+<span class="source-line-no">987</span><span id="line-987"> */</span>
+<span class="source-line-no">988</span><span id="line-988"> public boolean isServerUnknown(ServerName serverName) {</span>
+<span class="source-line-no">989</span><span id="line-989"> return serverName != null</span>
+<span class="source-line-no">990</span><span id="line-990"> && (!onlineServers.containsKey(serverName) && !deadservers.isDeadServer(serverName));</span>
+<span class="source-line-no">991</span><span id="line-991"> }</span>
+<span class="source-line-no">992</span><span id="line-992"></span>
+<span class="source-line-no">993</span><span id="line-993"> public void shutdownCluster() {</span>
+<span class="source-line-no">994</span><span id="line-994"> String statusStr = "Cluster shutdown requested of master=" + this.master.getServerName();</span>
+<span class="source-line-no">995</span><span id="line-995"> LOG.info(statusStr);</span>
+<span class="source-line-no">996</span><span id="line-996"> this.clusterShutdown.set(true);</span>
+<span class="source-line-no">997</span><span id="line-997"> if (onlineServers.isEmpty()) {</span>
+<span class="source-line-no">998</span><span id="line-998"> // we do not synchronize here so this may cause a double stop, but not a big deal</span>
+<span class="source-line-no">999</span><span id="line-999"> master.stop("OnlineServer=0 right after cluster shutdown set");</span>
+<span class="source-line-no">1000</span><span id="line-1000"> }</span>
+<span class="source-line-no">1001</span><span id="line-1001"> }</span>
+<span class="source-line-no">1002</span><span id="line-1002"></span>
+<span class="source-line-no">1003</span><span id="line-1003"> public boolean isClusterShutdown() {</span>
+<span class="source-line-no">1004</span><span id="line-1004"> return this.clusterShutdown.get();</span>
+<span class="source-line-no">1005</span><span id="line-1005"> }</span>
+<span class="source-line-no">1006</span><span id="line-1006"></span>
+<span class="source-line-no">1007</span><span id="line-1007"> /**</span>
+<span class="source-line-no">1008</span><span id="line-1008"> * start chore in ServerManager</span>
+<span class="source-line-no">1009</span><span id="line-1009"> */</span>
+<span class="source-line-no">1010</span><span id="line-1010"> public void startChore() {</span>
+<span class="source-line-no">1011</span><span id="line-1011"> Configuration c = master.getConfiguration();</span>
+<span class="source-line-no">1012</span><span id="line-1012"> if (persistFlushedSequenceId) {</span>
+<span class="source-line-no">1013</span><span id="line-1013"> new Thread(() -> {</span>
+<span class="source-line-no">1014</span><span id="line-1014"> // after AM#loadMeta, RegionStates should be loaded, and some regions are</span>
+<span class="source-line-no">1015</span><span id="line-1015"> // deleted by drop/split/merge during removeDeletedRegionFromLoadedFlushedSequenceIds,</span>
+<span class="source-line-no">1016</span><span id="line-1016"> // but these deleted regions are not added back to RegionStates,</span>
+<span class="source-line-no">1017</span><span id="line-1017"> // so we can safely remove deleted regions.</span>
+<span class="source-line-no">1018</span><span id="line-1018"> removeDeletedRegionFromLoadedFlushedSequenceIds();</span>
+<span class="source-line-no">1019</span><span id="line-1019"> }, "RemoveDeletedRegionSyncThread").start();</span>
+<span class="source-line-no">1020</span><span id="line-1020"> int flushPeriod =</span>
+<span class="source-line-no">1021</span><span id="line-1021"> c.getInt(FLUSHEDSEQUENCEID_FLUSHER_INTERVAL, FLUSHEDSEQUENCEID_FLUSHER_INTERVAL_DEFAULT);</span>
+<span class="source-line-no">1022</span><span id="line-1022"> flushedSeqIdFlusher = new FlushedSequenceIdFlusher("FlushedSequenceIdFlusher", flushPeriod);</span>
+<span class="source-line-no">1023</span><span id="line-1023"> master.getChoreService().scheduleChore(flushedSeqIdFlusher);</span>
+<span class="source-line-no">1024</span><span id="line-1024"> }</span>
+<span class="source-line-no">1025</span><span id="line-1025"> }</span>
+<span class="source-line-no">1026</span><span id="line-1026"></span>
+<span class="source-line-no">1027</span><span id="line-1027"> /**</span>
+<span class="source-line-no">1028</span><span id="line-1028"> * Stop the ServerManager.</span>
+<span class="source-line-no">1029</span><span id="line-1029"> */</span>
+<span class="source-line-no">1030</span><span id="line-1030"> public void stop() {</span>
+<span class="source-line-no">1031</span><span id="line-1031"> if (flushedSeqIdFlusher != null) {</span>
+<span class="source-line-no">1032</span><span id="line-1032"> flushedSeqIdFlusher.shutdown();</span>
+<span class="source-line-no">1033</span><span id="line-1033"> }</span>
+<span class="source-line-no">1034</span><span id="line-1034"> if (persistFlushedSequenceId) {</span>
+<span class="source-line-no">1035</span><span id="line-1035"> try {</span>
+<span class="source-line-no">1036</span><span id="line-1036"> persistRegionLastFlushedSequenceIds();</span>
+<span class="source-line-no">1037</span><span id="line-1037"> } catch (IOException e) {</span>
+<span class="source-line-no">1038</span><span id="line-1038"> LOG.warn("Failed to persist last flushed sequence id of regions" + " to file system", e);</span>
+<span class="source-line-no">1039</span><span id="line-1039"> }</span>
+<span class="source-line-no">1040</span><span id="line-1040"> }</span>
+<span class="source-line-no">1041</span><span id="line-1041"> }</span>
+<span class="source-line-no">1042</span><span id="line-1042"></span>
+<span class="source-line-no">1043</span><span id="line-1043"> /**</span>
+<span class="source-line-no">1044</span><span id="line-1044"> * Creates a list of possible destinations for a region. It contains the online servers, but not</span>
+<span class="source-line-no">1045</span><span id="line-1045"> * the draining or dying servers.</span>
+<span class="source-line-no">1046</span><span id="line-1046"> * @param serversToExclude can be null if there is no server to exclude</span>
+<span class="source-line-no">1047</span><span id="line-1047"> */</span>
+<span class="source-line-no">1048</span><span id="line-1048"> public List<ServerName> createDestinationServersList(final List<ServerName> serversToExclude) {</span>
+<span class="source-line-no">1049</span><span id="line-1049"> Set<ServerName> destServers = new HashSet<>();</span>
+<span class="source-line-no">1050</span><span id="line-1050"> onlineServers.forEach((sn, sm) -> {</span>
+<span class="source-line-no">1051</span><span id="line-1051"> if (sm.getLastReportTimestamp() > 0) {</span>
+<span class="source-line-no">1052</span><span id="line-1052"> // This means we have already called regionServerReport at leaset once, then let's include</span>
+<span class="source-line-no">1053</span><span id="line-1053"> // this server for region assignment. This is an optimization to avoid assigning regions to</span>
+<span class="source-line-no">1054</span><span id="line-1054"> // an uninitialized server. See HBASE-25032 for more details.</span>
+<span class="source-line-no">1055</span><span id="line-1055"> destServers.add(sn);</span>
+<span class="source-line-no">1056</span><span id="line-1056"> }</span>
+<span class="source-line-no">1057</span><span id="line-1057"> });</span>
+<span class="source-line-no">1058</span><span id="line-1058"></span>
+<span class="source-line-no">1059</span><span id="line-1059"> if (serversToExclude != null) {</span>
+<span class="source-line-no">1060</span><span id="line-1060"> destServers.removeAll(serversToExclude);</span>
+<span class="source-line-no">1061</span><span id="line-1061"> }</span>
+<span class="source-line-no">1062</span><span id="line-1062"></span>
+<span class="source-line-no">1063</span><span id="line-1063"> // Loop through the draining server list and remove them from the server list</span>
+<span class="source-line-no">1064</span><span id="line-1064"> final List<ServerName> drainingServersCopy = getDrainingServersList();</span>
+<span class="source-line-no">1065</span><span id="line-1065"> destServers.removeAll(drainingServersCopy);</span>
<span class="source-line-no">1066</span><span id="line-1066"></span>
-<span class="source-line-no">1067</span><span id="line-1067"> /**</span>
-<span class="source-line-no">1068</span><span id="line-1068"> * Calls {@link #createDestinationServersList} without server to exclude.</span>
-<span class="source-line-no">1069</span><span id="line-1069"> */</span>
-<span class="source-line-no">1070</span><span id="line-1070"> public List<ServerName> createDestinationServersList() {</span>
-<span class="source-line-no">1071</span><span id="line-1071"> return createDestinationServersList(null);</span>
-<span class="source-line-no">1072</span><span id="line-1072"> }</span>
-<span class="source-line-no">1073</span><span id="line-1073"></span>
-<span class="source-line-no">1074</span><span id="line-1074"> /**</span>
-<span class="source-line-no">1075</span><span id="line-1075"> * To clear any dead server with same host name and port of any online server</span>
-<span class="source-line-no">1076</span><span id="line-1076"> */</span>
-<span class="source-line-no">1077</span><span id="line-1077"> void clearDeadServersWithSameHostNameAndPortOfOnlineServer() {</span>
-<span class="source-line-no">1078</span><span id="line-1078"> for (ServerName serverName : getOnlineServersList()) {</span>
-<span class="source-line-no">1079</span><span id="line-1079"> deadservers.cleanAllPreviousInstances(serverName);</span>
-<span class="source-line-no">1080</span><span id="line-1080"> }</span>
-<span class="source-line-no">1081</span><span id="line-1081"> }</span>
-<span class="source-line-no">1082</span><span id="line-1082"></span>
-<span class="source-line-no">1083</span><span id="line-1083"> /**</span>
-<span class="source-line-no">1084</span><span id="line-1084"> * Called by delete table and similar to notify the ServerManager that a region was removed.</span>
-<span class="source-line-no">1085</span><span id="line-1085"> */</span>
-<span class="source-line-no">1086</span><span id="line-1086"> public void removeRegion(final RegionInfo regionInfo) {</span>
-<span class="source-line-no">1087</span><span id="line-1087"> final byte[] encodedName = regionInfo.getEncodedNameAsBytes();</span>
-<span class="source-line-no">1088</span><span id="line-1088"> storeFlushedSequenceIdsByRegion.remove(encodedName);</span>
-<span class="source-line-no">1089</span><span id="line-1089"> flushedSequenceIdByRegion.remove(encodedName);</span>
-<span class="source-line-no">1090</span><span id="line-1090"> }</span>
-<span class="source-line-no">1091</span><span id="line-1091"></span>
-<span class="source-line-no">1092</span><span id="line-1092"> public boolean isRegionInServerManagerStates(final RegionInfo hri) {</span>
-<span class="source-line-no">1093</span><span id="line-1093"> final byte[] encodedName = hri.getEncodedNameAsBytes();</span>
-<span class="source-line-no">1094</span><span id="line-1094"> return (storeFlushedSequenceIdsByRegion.containsKey(encodedName)</span>
-<span class="source-line-no">1095</span><span id="line-1095"> || flushedSequenceIdByRegion.containsKey(encodedName));</span>
-<span class="source-line-no">1096</span><span id="line-1096"> }</span>
-<span class="source-line-no">1097</span><span id="line-1097"></span>
-<span class="source-line-no">1098</span><span id="line-1098"> /**</span>
-<span class="source-line-no">1099</span><span id="line-1099"> * Called by delete table and similar to notify the ServerManager that a region was removed.</span>
-<span class="source-line-no">1100</span><span id="line-1100"> */</span>
-<span class="source-line-no">1101</span><span id="line-1101"> public void removeRegions(final List<RegionInfo> regions) {</span>
-<span class="source-line-no">1102</span><span id="line-1102"> for (RegionInfo hri : regions) {</span>
-<span class="source-line-no">1103</span><span id="line-1103"> removeRegion(hri);</span>
-<span class="source-line-no">1104</span><span id="line-1104"> }</span>
-<span class="source-line-no">1105</span><span id="line-1105"> }</span>
-<span class="source-line-no">1106</span><span id="line-1106"></span>
-<span class="source-line-no">1107</span><span id="line-1107"> /**</span>
-<span class="source-line-no">1108</span><span id="line-1108"> * May return 0 when server is not online.</span>
-<span class="source-line-no">1109</span><span id="line-1109"> */</span>
-<span class="source-line-no">1110</span><span id="line-1110"> public int getVersionNumber(ServerName serverName) {</span>
-<span class="source-line-no">1111</span><span id="line-1111"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
-<span class="source-line-no">1112</span><span id="line-1112"> return serverMetrics != null ? serverMetrics.getVersionNumber() : 0;</span>
-<span class="source-line-no">1113</span><span id="line-1113"> }</span>
-<span class="source-line-no">1114</span><span id="line-1114"></span>
-<span class="source-line-no">1115</span><span id="line-1115"> /**</span>
-<span class="source-line-no">1116</span><span id="line-1116"> * May return "0.0.0" when server is not online</span>
-<span class="source-line-no">1117</span><span id="line-1117"> */</span>
-<span class="source-line-no">1118</span><span id="line-1118"> public String getVersion(ServerName serverName) {</span>
-<span class="source-line-no">1119</span><span id="line-1119"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
-<span class="source-line-no">1120</span><span id="line-1120"> return serverMetrics != null ? serverMetrics.getVersion() : "0.0.0";</span>
-<span class="source-line-no">1121</span><span id="line-1121"> }</span>
-<span class="source-line-no">1122</span><span id="line-1122"></span>
-<span class="source-line-no">1123</span><span id="line-1123"> public int getInfoPort(ServerName serverName) {</span>
-<span class="source-line-no">1124</span><span id="line-1124"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
-<span class="source-line-no">1125</span><span id="line-1125"> return serverMetrics != null ? serverMetrics.getInfoServerPort() : 0;</span>
-<span class="source-line-no">1126</span><span id="line-1126"> }</span>
-<span class="source-line-no">1127</span><span id="line-1127"></span>
-<span class="source-line-no">1128</span><span id="line-1128"> /**</span>
-<span class="source-line-no">1129</span><span id="line-1129"> * Persist last flushed sequence id of each region to HDFS</span>
-<span class="source-line-no">1130</span><span id="line-1130"> * @throws IOException if persit to HDFS fails</span>
-<span class="source-line-no">1131</span><span id="line-1131"> */</span>
-<span class="source-line-no">1132</span><span id="line-1132"> private void persistRegionLastFlushedSequenceIds() throws IOException {</span>
-<span class="source-line-no">1133</span><span id="line-1133"> if (isFlushSeqIdPersistInProgress) {</span>
-<span class="source-line-no">1134</span><span id="line-1134"> return;</span>
-<span class="source-line-no">1135</span><span id="line-1135"> }</span>
-<span class="source-line-no">1136</span><span id="line-1136"> isFlushSeqIdPersistInProgress = true;</span>
-<span class="source-line-no">1137</span><span id="line-1137"> try {</span>
-<span class="source-line-no">1138</span><span id="line-1138"> Configuration conf = master.getConfiguration();</span>
-<span class="source-line-no">1139</span><span id="line-1139"> Path rootDir = CommonFSUtils.getRootDir(conf);</span>
-<span class="source-line-no">1140</span><span id="line-1140"> Path lastFlushedSeqIdPath = new Path(rootDir, LAST_FLUSHED_SEQ_ID_FILE);</span>
-<span class="source-line-no">1141</span><span id="line-1141"> FileSystem fs = FileSystem.get(conf);</span>
-<span class="source-line-no">1142</span><span id="line-1142"> if (fs.exists(lastFlushedSeqIdPath)) {</span>
-<span class="source-line-no">1143</span><span id="line-1143"> LOG.info("Rewriting .lastflushedseqids file at: " + lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1144</span><span id="line-1144"> if (!fs.delete(lastFlushedSeqIdPath, false)) {</span>
-<span class="source-line-no">1145</span><span id="line-1145"> throw new IOException("Unable to remove existing " + lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1146</span><span id="line-1146"> }</span>
-<span class="source-line-no">1147</span><span id="line-1147"> } else {</span>
-<span class="source-line-no">1148</span><span id="line-1148"> LOG.info("Writing .lastflushedseqids file at: " + lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1149</span><span id="line-1149"> }</span>
-<span class="source-line-no">1150</span><span id="line-1150"> FSDataOutputStream out = fs.create(lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1151</span><span id="line-1151"> FlushedSequenceId.Builder flushedSequenceIdBuilder = FlushedSequenceId.newBuilder();</span>
-<span class="source-line-no">1152</span><span id="line-1152"> try {</span>
-<span class="source-line-no">1153</span><span id="line-1153"> for (Entry<byte[], Long> entry : flushedSequenceIdByRegion.entrySet()) {</span>
-<span class="source-line-no">1154</span><span id="line-1154"> FlushedRegionSequenceId.Builder flushedRegionSequenceIdBuilder =</span>
-<span class="source-line-no">1155</span><span id="line-1155"> FlushedRegionSequenceId.newBuilder();</span>
-<span class="source-line-no">1156</span><span id="line-1156"> flushedRegionSequenceIdBuilder.setRegionEncodedName(ByteString.copyFrom(entry.getKey()));</span>
-<span class="source-line-no">1157</span><span id="line-1157"> flushedRegionSequenceIdBuilder.setSeqId(entry.getValue());</span>
-<span class="source-line-no">1158</span><span id="line-1158"> ConcurrentNavigableMap<byte[], Long> storeSeqIds =</span>
-<span class="source-line-no">1159</span><span id="line-1159"> storeFlushedSequenceIdsByRegion.get(entry.getKey());</span>
-<span class="source-line-no">1160</span><span id="line-1160"> if (storeSeqIds != null) {</span>
-<span class="source-line-no">1161</span><span id="line-1161"> for (Entry<byte[], Long> store : storeSeqIds.entrySet()) {</span>
-<span class="source-line-no">1162</span><span id="line-1162"> FlushedStoreSequenceId.Builder flushedStoreSequenceIdBuilder =</span>
-<span class="source-line-no">1163</span><span id="line-1163"> FlushedStoreSequenceId.newBuilder();</span>
-<span class="source-line-no">1164</span><span id="line-1164"> flushedStoreSequenceIdBuilder.setFamily(ByteString.copyFrom(store.getKey()));</span>
-<span class="source-line-no">1165</span><span id="line-1165"> flushedStoreSequenceIdBuilder.setSeqId(store.getValue());</span>
-<span class="source-line-no">1166</span><span id="line-1166"> flushedRegionSequenceIdBuilder.addStores(flushedStoreSequenceIdBuilder);</span>
-<span class="source-line-no">1167</span><span id="line-1167"> }</span>
-<span class="source-line-no">1168</span><span id="line-1168"> }</span>
-<span class="source-line-no">1169</span><span id="line-1169"> flushedSequenceIdBuilder.addRegionSequenceId(flushedRegionSequenceIdBuilder);</span>
-<span class="source-line-no">1170</span><span id="line-1170"> }</span>
-<span class="source-line-no">1171</span><span id="line-1171"> flushedSequenceIdBuilder.build().writeDelimitedTo(out);</span>
-<span class="source-line-no">1172</span><span id="line-1172"> } finally {</span>
-<span class="source-line-no">1173</span><span id="line-1173"> if (out != null) {</span>
-<span class="source-line-no">1174</span><span id="line-1174"> out.close();</span>
-<span class="source-line-no">1175</span><span id="line-1175"> }</span>
-<span class="source-line-no">1176</span><span id="line-1176"> }</span>
-<span class="source-line-no">1177</span><span id="line-1177"> } finally {</span>
-<span class="source-line-no">1178</span><span id="line-1178"> isFlushSeqIdPersistInProgress = false;</span>
-<span class="source-line-no">1179</span><span id="line-1179"> }</span>
-<span class="source-line-no">1180</span><span id="line-1180"> }</span>
-<span class="source-line-no">1181</span><span id="line-1181"></span>
-<span class="source-line-no">1182</span><span id="line-1182"> /**</span>
-<span class="source-line-no">1183</span><span id="line-1183"> * Load last flushed sequence id of each region from HDFS, if persisted</span>
-<span class="source-line-no">1184</span><span id="line-1184"> */</span>
-<span class="source-line-no">1185</span><span id="line-1185"> public void loadLastFlushedSequenceIds() throws IOException {</span>
-<span class="source-line-no">1186</span><span id="line-1186"> if (!persistFlushedSequenceId) {</span>
-<span class="source-line-no">1187</span><span id="line-1187"> return;</span>
-<span class="source-line-no">1188</span><span id="line-1188"> }</span>
-<span class="source-line-no">1189</span><span id="line-1189"> Configuration conf = master.getConfiguration();</span>
-<span class="source-line-no">1190</span><span id="line-1190"> Path rootDir = CommonFSUtils.getRootDir(conf);</span>
-<span class="source-line-no">1191</span><span id="line-1191"> Path lastFlushedSeqIdPath = new Path(rootDir, LAST_FLUSHED_SEQ_ID_FILE);</span>
-<span class="source-line-no">1192</span><span id="line-1192"> FileSystem fs = FileSystem.get(conf);</span>
-<span class="source-line-no">1193</span><span id="line-1193"> if (!fs.exists(lastFlushedSeqIdPath)) {</span>
-<span class="source-line-no">1194</span><span id="line-1194"> LOG.info("No .lastflushedseqids found at " + lastFlushedSeqIdPath</span>
-<span class="source-line-no">1195</span><span id="line-1195"> + " will record last flushed sequence id"</span>
-<span class="source-line-no">1196</span><span id="line-1196"> + " for regions by regionserver report all over again");</span>
-<span class="source-line-no">1197</span><span id="line-1197"> return;</span>
-<span class="source-line-no">1198</span><span id="line-1198"> } else {</span>
-<span class="source-line-no">1199</span><span id="line-1199"> LOG.info("begin to load .lastflushedseqids at " + lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1200</span><span id="line-1200"> }</span>
-<span class="source-line-no">1201</span><span id="line-1201"> FSDataInputStream in = fs.open(lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1202</span><span id="line-1202"> try {</span>
-<span class="source-line-no">1203</span><span id="line-1203"> FlushedSequenceId flushedSequenceId = FlushedSequenceId.parseDelimitedFrom(in);</span>
-<span class="source-line-no">1204</span><span id="line-1204"> if (flushedSequenceId == null) {</span>
-<span class="source-line-no">1205</span><span id="line-1205"> LOG.info(".lastflushedseqids found at {} is empty", lastFlushedSeqIdPath);</span>
-<span class="source-line-no">1206</span><span id="line-1206"> return;</span>
-<span class="source-line-no">1207</span><span id="line-1207"> }</span>
-<span class="source-line-no">1208</span><span id="line-1208"> for (FlushedRegionSequenceId flushedRegionSequenceId : flushedSequenceId</span>
-<span class="source-line-no">1209</span><span id="line-1209"> .getRegionSequenceIdList()) {</span>
-<span class="source-line-no">1210</span><span id="line-1210"> byte[] encodedRegionName = flushedRegionSequenceId.getRegionEncodedName().toByteArray();</span>
-<span class="source-line-no">1211</span><span id="line-1211"> flushedSequenceIdByRegion.putIfAbsent(encodedRegionName,</span>
-<span class="source-line-no">1212</span><span id="line-1212"> flushedRegionSequenceId.getSeqId());</span>
-<span class="source-line-no">1213</span><span id="line-1213"> if (</span>
-<span class="source-line-no">1214</span><span id="line-1214"> flushedRegionSequenceId.getStoresList() != null</span>
-<span class="source-line-no">1215</span><span id="line-1215"> && flushedRegionSequenceId.getStoresList().size() != 0</span>
-<span class="source-line-no">1216</span><span id="line-1216"> ) {</span>
-<span class="source-line-no">1217</span><span id="line-1217"> ConcurrentNavigableMap<byte[], Long> storeFlushedSequenceId =</span>
-<span class="source-line-no">1218</span><span id="line-1218"> computeIfAbsent(storeFlushedSequenceIdsByRegion, encodedRegionName,</span>
-<span class="source-line-no">1219</span><span id="line-1219"> () -> new ConcurrentSkipListMap<>(Bytes.BYTES_COMPARATOR));</span>
-<span class="source-line-no">1220</span><span id="line-1220"> for (FlushedStoreSequenceId flushedStoreSequenceId : flushedRegionSequenceId</span>
-<span class="source-line-no">1221</span><span id="line-1221"> .getStoresList()) {</span>
-<span class="source-line-no">1222</span><span id="line-1222"> storeFlushedSequenceId.put(flushedStoreSequenceId.getFamily().toByteArray(),</span>
-<span class="source-line-no">1223</span><span id="line-1223"> flushedStoreSequenceId.getSeqId());</span>
-<span class="source-line-no">1224</span><span id="line-1224"> }</span>
-<span class="source-line-no">1225</span><span id="line-1225"> }</span>
-<span class="source-line-no">1226</span><span id="line-1226"> }</span>
-<span class="source-line-no">1227</span><span id="line-1227"> } finally {</span>
-<span class="source-line-no">1228</span><span id="line-1228"> in.close();</span>
-<span class="source-line-no">1229</span><span id="line-1229"> }</span>
-<span class="source-line-no">1230</span><span id="line-1230"> }</span>
-<span class="source-line-no">1231</span><span id="line-1231"></span>
-<span class="source-line-no">1232</span><span id="line-1232"> /**</span>
-<span class="source-line-no">1233</span><span id="line-1233"> * Regions may have been removed between latest persist of FlushedSequenceIds and master abort. So</span>
-<span class="source-line-no">1234</span><span id="line-1234"> * after loading FlushedSequenceIds from file, and after meta loaded, we need to remove the</span>
-<span class="source-line-no">1235</span><span id="line-1235"> * deleted region according to RegionStates.</span>
-<span class="source-line-no">1236</span><span id="line-1236"> */</span>
-<span class="source-line-no">1237</span><span id="line-1237"> public void removeDeletedRegionFromLoadedFlushedSequenceIds() {</span>
-<span class="source-line-no">1238</span><span id="line-1238"> RegionStates regionStates = master.getAssignmentManager().getRegionStates();</span>
-<span class="source-line-no">1239</span><span id="line-1239"> Iterator<byte[]> it = flushedSequenceIdByRegion.keySet().iterator();</span>
-<span class="source-line-no">1240</span><span id="line-1240"> while (it.hasNext()) {</span>
-<span class="source-line-no">1241</span><span id="line-1241"> byte[] regionEncodedName = it.next();</span>
-<span class="source-line-no">1242</span><span id="line-1242"> if (regionStates.getRegionState(Bytes.toStringBinary(regionEncodedName)) == null) {</span>
-<span class="source-line-no">1243</span><span id="line-1243"> it.remove();</span>
-<span class="source-line-no">1244</span><span id="line-1244"> storeFlushedSequenceIdsByRegion.remove(regionEncodedName);</span>
-<span class="source-line-no">1245</span><span id="line-1245"> }</span>
-<span class="source-line-no">1246</span><span id="line-1246"> }</span>
-<span class="source-line-no">1247</span><span id="line-1247"> }</span>
-<span class="source-line-no">1248</span><span id="line-1248"></span>
-<span class="source-line-no">1249</span><span id="line-1249"> private class FlushedSequenceIdFlusher extends ScheduledChore {</span>
-<span class="source-line-no">1250</span><span id="line-1250"></span>
-<span class="source-line-no">1251</span><span id="line-1251"> public FlushedSequenceIdFlusher(String name, int p) {</span>
-<span class="source-line-no">1252</span><span id="line-1252"> super(name, master, p, 60 * 1000); // delay one minute before first execute</span>
-<span class="source-line-no">1253</span><span id="line-1253"> }</span>
-<span class="source-line-no">1254</span><span id="line-1254"></span>
-<span class="source-line-no">1255</span><span id="line-1255"> @Override</span>
-<span class="source-line-no">1256</span><span id="line-1256"> protected void chore() {</span>
-<span class="source-line-no">1257</span><span id="line-1257"> try {</span>
-<span class="source-line-no">1258</span><span id="line-1258"> persistRegionLastFlushedSequenceIds();</span>
-<span class="source-line-no">1259</span><span id="line-1259"> } catch (IOException e) {</span>
-<span class="source-line-no">1260</span><span id="line-1260"> LOG.debug("Failed to persist last flushed sequence id of regions" + " to file system", e);</span>
-<span class="source-line-no">1261</span><span id="line-1261"> }</span>
-<span class="source-line-no">1262</span><span id="line-1262"> }</span>
-<span class="source-line-no">1263</span><span id="line-1263"> }</span>
-<span class="source-line-no">1264</span><span id="line-1264">}</span>
+<span class="source-line-no">1067</span><span id="line-1067"> return new ArrayList<>(destServers);</span>
+<span class="source-line-no">1068</span><span id="line-1068"> }</span>
+<span class="source-line-no">1069</span><span id="line-1069"></span>
+<span class="source-line-no">1070</span><span id="line-1070"> /**</span>
+<span class="source-line-no">1071</span><span id="line-1071"> * Calls {@link #createDestinationServersList} without server to exclude.</span>
+<span class="source-line-no">1072</span><span id="line-1072"> */</span>
+<span class="source-line-no">1073</span><span id="line-1073"> public List<ServerName> createDestinationServersList() {</span>
+<span class="source-line-no">1074</span><span id="line-1074"> return createDestinationServersList(null);</span>
+<span class="source-line-no">1075</span><span id="line-1075"> }</span>
+<span class="source-line-no">1076</span><span id="line-1076"></span>
+<span class="source-line-no">1077</span><span id="line-1077"> /**</span>
+<span class="source-line-no">1078</span><span id="line-1078"> * To clear any dead server with same host name and port of any online server</span>
+<span class="source-line-no">1079</span><span id="line-1079"> */</span>
+<span class="source-line-no">1080</span><span id="line-1080"> void clearDeadServersWithSameHostNameAndPortOfOnlineServer() {</span>
+<span class="source-line-no">1081</span><span id="line-1081"> for (ServerName serverName : getOnlineServersList()) {</span>
+<span class="source-line-no">1082</span><span id="line-1082"> deadservers.cleanAllPreviousInstances(serverName);</span>
+<span class="source-line-no">1083</span><span id="line-1083"> }</span>
+<span class="source-line-no">1084</span><span id="line-1084"> }</span>
+<span class="source-line-no">1085</span><span id="line-1085"></span>
+<span class="source-line-no">1086</span><span id="line-1086"> /**</span>
+<span class="source-line-no">1087</span><span id="line-1087"> * Called by delete table and similar to notify the ServerManager that a region was removed.</span>
+<span class="source-line-no">1088</span><span id="line-1088"> */</span>
+<span class="source-line-no">1089</span><span id="line-1089"> public void removeRegion(final RegionInfo regionInfo) {</span>
+<span class="source-line-no">1090</span><span id="line-1090"> final byte[] encodedName = regionInfo.getEncodedNameAsBytes();</span>
+<span class="source-line-no">1091</span><span id="line-1091"> storeFlushedSequenceIdsByRegion.remove(encodedName);</span>
+<span class="source-line-no">1092</span><span id="line-1092"> flushedSequenceIdByRegion.remove(encodedName);</span>
+<span class="source-line-no">1093</span><span id="line-1093"> }</span>
+<span class="source-line-no">1094</span><span id="line-1094"></span>
+<span class="source-line-no">1095</span><span id="line-1095"> public boolean isRegionInServerManagerStates(final RegionInfo hri) {</span>
+<span class="source-line-no">1096</span><span id="line-1096"> final byte[] encodedName = hri.getEncodedNameAsBytes();</span>
+<span class="source-line-no">1097</span><span id="line-1097"> return (storeFlushedSequenceIdsByRegion.containsKey(encodedName)</span>
+<span class="source-line-no">1098</span><span id="line-1098"> || flushedSequenceIdByRegion.containsKey(encodedName));</span>
+<span class="source-line-no">1099</span><span id="line-1099"> }</span>
+<span class="source-line-no">1100</span><span id="line-1100"></span>
+<span class="source-line-no">1101</span><span id="line-1101"> /**</span>
+<span class="source-line-no">1102</span><span id="line-1102"> * Called by delete table and similar to notify the ServerManager that a region was removed.</span>
+<span class="source-line-no">1103</span><span id="line-1103"> */</span>
+<span class="source-line-no">1104</span><span id="line-1104"> public void removeRegions(final List<RegionInfo> regions) {</span>
+<span class="source-line-no">1105</span><span id="line-1105"> for (RegionInfo hri : regions) {</span>
+<span class="source-line-no">1106</span><span id="line-1106"> removeRegion(hri);</span>
+<span class="source-line-no">1107</span><span id="line-1107"> }</span>
+<span class="source-line-no">1108</span><span id="line-1108"> }</span>
+<span class="source-line-no">1109</span><span id="line-1109"></span>
+<span class="source-line-no">1110</span><span id="line-1110"> /**</span>
+<span class="source-line-no">1111</span><span id="line-1111"> * May return 0 when server is not online.</span>
+<span class="source-line-no">1112</span><span id="line-1112"> */</span>
+<span class="source-line-no">1113</span><span id="line-1113"> public int getVersionNumber(ServerName serverName) {</span>
+<span class="source-line-no">1114</span><span id="line-1114"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
+<span class="source-line-no">1115</span><span id="line-1115"> return serverMetrics != null ? serverMetrics.getVersionNumber() : 0;</span>
+<span class="source-line-no">1116</span><span id="line-1116"> }</span>
+<span class="source-line-no">1117</span><span id="line-1117"></span>
+<span class="source-line-no">1118</span><span id="line-1118"> /**</span>
+<span class="source-line-no">1119</span><span id="line-1119"> * May return "0.0.0" when server is not online</span>
+<span class="source-line-no">1120</span><span id="line-1120"> */</span>
+<span class="source-line-no">1121</span><span id="line-1121"> public String getVersion(ServerName serverName) {</span>
+<span class="source-line-no">1122</span><span id="line-1122"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
+<span class="source-line-no">1123</span><span id="line-1123"> return serverMetrics != null ? serverMetrics.getVersion() : "0.0.0";</span>
+<span class="source-line-no">1124</span><span id="line-1124"> }</span>
+<span class="source-line-no">1125</span><span id="line-1125"></span>
+<span class="source-line-no">1126</span><span id="line-1126"> public int getInfoPort(ServerName serverName) {</span>
+<span class="source-line-no">1127</span><span id="line-1127"> ServerMetrics serverMetrics = onlineServers.get(serverName);</span>
+<span class="source-line-no">1128</span><span id="line-1128"> return serverMetrics != null ? serverMetrics.getInfoServerPort() : 0;</span>
+<span class="source-line-no">1129</span><span id="line-1129"> }</span>
+<span class="source-line-no">1130</span><span id="line-1130"></span>
+<span class="source-line-no">1131</span><span id="line-1131"> /**</span>
+<span class="source-line-no">1132</span><span id="line-1132"> * Persist last flushed sequence id of each region to HDFS</span>
+<span class="source-line-no">1133</span><span id="line-1133"> * @throws IOException if persit to HDFS fails</span>
+<span class="source-line-no">1134</span><span id="line-1134"> */</span>
+<span class="source-line-no">1135</span><span id="line-1135"> private void persistRegionLastFlushedSequenceIds() throws IOException {</span>
+<span class="source-line-no">1136</span><span id="line-1136"> if (isFlushSeqIdPersistInProgress) {</span>
+<span class="source-line-no">1137</span><span id="line-1137"> return;</span>
+<span class="source-line-no">1138</span><span id="line-1138"> }</span>
+<span class="source-line-no">1139</span><span id="line-1139"> isFlushSeqIdPersistInProgress = true;</span>
+<span class="source-line-no">1140</span><span id="line-1140"> try {</span>
+<span class="source-line-no">1141</span><span id="line-1141"> Configuration conf = master.getConfiguration();</span>
+<span class="source-line-no">1142</span><span id="line-1142"> Path rootDir = CommonFSUtils.getRootDir(conf);</span>
+<span class="source-line-no">1143</span><span id="line-1143"> Path lastFlushedSeqIdPath = new Path(rootDir, LAST_FLUSHED_SEQ_ID_FILE);</span>
+<span class="source-line-no">1144</span><span id="line-1144"> FileSystem fs = FileSystem.get(conf);</span>
+<span class="source-line-no">1145</span><span id="line-1145"> if (fs.exists(lastFlushedSeqIdPath)) {</span>
+<span class="source-line-no">1146</span><span id="line-1146"> LOG.info("Rewriting .lastflushedseqids file at: " + lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1147</span><span id="line-1147"> if (!fs.delete(lastFlushedSeqIdPath, false)) {</span>
+<span class="source-line-no">1148</span><span id="line-1148"> throw new IOException("Unable to remove existing " + lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1149</span><span id="line-1149"> }</span>
+<span class="source-line-no">1150</span><span id="line-1150"> } else {</span>
+<span class="source-line-no">1151</span><span id="line-1151"> LOG.info("Writing .lastflushedseqids file at: " + lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1152</span><span id="line-1152"> }</span>
+<span class="source-line-no">1153</span><span id="line-1153"> FSDataOutputStream out = fs.create(lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1154</span><span id="line-1154"> FlushedSequenceId.Builder flushedSequenceIdBuilder = FlushedSequenceId.newBuilder();</span>
+<span class="source-line-no">1155</span><span id="line-1155"> try {</span>
+<span class="source-line-no">1156</span><span id="line-1156"> for (Entry<byte[], Long> entry : flushedSequenceIdByRegion.entrySet()) {</span>
+<span class="source-line-no">1157</span><span id="line-1157"> FlushedRegionSequenceId.Builder flushedRegionSequenceIdBuilder =</span>
+<span class="source-line-no">1158</span><span id="line-1158"> FlushedRegionSequenceId.newBuilder();</span>
+<span class="source-line-no">1159</span><span id="line-1159"> flushedRegionSequenceIdBuilder.setRegionEncodedName(ByteString.copyFrom(entry.getKey()));</span>
+<span class="source-line-no">1160</span><span id="line-1160"> flushedRegionSequenceIdBuilder.setSeqId(entry.getValue());</span>
+<span class="source-line-no">1161</span><span id="line-1161"> ConcurrentNavigableMap<byte[], Long> storeSeqIds =</span>
+<span class="source-line-no">1162</span><span id="line-1162"> storeFlushedSequenceIdsByRegion.get(entry.getKey());</span>
+<span class="source-line-no">1163</span><span id="line-1163"> if (storeSeqIds != null) {</span>
+<span class="source-line-no">1164</span><span id="line-1164"> for (Entry<byte[], Long> store : storeSeqIds.entrySet()) {</span>
+<span class="source-line-no">1165</span><span id="line-1165"> FlushedStoreSequenceId.Builder flushedStoreSequenceIdBuilder =</span>
+<span class="source-line-no">1166</span><span id="line-1166"> FlushedStoreSequenceId.newBuilder();</span>
+<span class="source-line-no">1167</span><span id="line-1167"> flushedStoreSequenceIdBuilder.setFamily(ByteString.copyFrom(store.getKey()));</span>
+<span class="source-line-no">1168</span><span id="line-1168"> flushedStoreSequenceIdBuilder.setSeqId(store.getValue());</span>
+<span class="source-line-no">1169</span><span id="line-1169"> flushedRegionSequenceIdBuilder.addStores(flushedStoreSequenceIdBuilder);</span>
+<span class="source-line-no">1170</span><span id="line-1170"> }</span>
+<span class="source-line-no">1171</span><span id="line-1171"> }</span>
+<span class="source-line-no">1172</span><span id="line-1172"> flushedSequenceIdBuilder.addRegionSequenceId(flushedRegionSequenceIdBuilder);</span>
+<span class="source-line-no">1173</span><span id="line-1173"> }</span>
+<span class="source-line-no">1174</span><span id="line-1174"> flushedSequenceIdBuilder.build().writeDelimitedTo(out);</span>
+<span class="source-line-no">1175</span><span id="line-1175"> } finally {</span>
+<span class="source-line-no">1176</span><span id="line-1176"> if (out != null) {</span>
+<span class="source-line-no">1177</span><span id="line-1177"> out.close();</span>
+<span class="source-line-no">1178</span><span id="line-1178"> }</span>
+<span class="source-line-no">1179</span><span id="line-1179"> }</span>
+<span class="source-line-no">1180</span><span id="line-1180"> } finally {</span>
+<span class="source-line-no">1181</span><span id="line-1181"> isFlushSeqIdPersistInProgress = false;</span>
+<span class="source-line-no">1182</span><span id="line-1182"> }</span>
+<span class="source-line-no">1183</span><span id="line-1183"> }</span>
+<span class="source-line-no">1184</span><span id="line-1184"></span>
+<span class="source-line-no">1185</span><span id="line-1185"> /**</span>
+<span class="source-line-no">1186</span><span id="line-1186"> * Load last flushed sequence id of each region from HDFS, if persisted</span>
+<span class="source-line-no">1187</span><span id="line-1187"> */</span>
+<span class="source-line-no">1188</span><span id="line-1188"> public void loadLastFlushedSequenceIds() throws IOException {</span>
+<span class="source-line-no">1189</span><span id="line-1189"> if (!persistFlushedSequenceId) {</span>
+<span class="source-line-no">1190</span><span id="line-1190"> return;</span>
+<span class="source-line-no">1191</span><span id="line-1191"> }</span>
+<span class="source-line-no">1192</span><span id="line-1192"> Configuration conf = master.getConfiguration();</span>
+<span class="source-line-no">1193</span><span id="line-1193"> Path rootDir = CommonFSUtils.getRootDir(conf);</span>
+<span class="source-line-no">1194</span><span id="line-1194"> Path lastFlushedSeqIdPath = new Path(rootDir, LAST_FLUSHED_SEQ_ID_FILE);</span>
+<span class="source-line-no">1195</span><span id="line-1195"> FileSystem fs = FileSystem.get(conf);</span>
+<span class="source-line-no">1196</span><span id="line-1196"> if (!fs.exists(lastFlushedSeqIdPath)) {</span>
+<span class="source-line-no">1197</span><span id="line-1197"> LOG.info("No .lastflushedseqids found at " + lastFlushedSeqIdPath</span>
+<span class="source-line-no">1198</span><span id="line-1198"> + " will record last flushed sequence id"</span>
+<span class="source-line-no">1199</span><span id="line-1199"> + " for regions by regionserver report all over again");</span>
+<span class="source-line-no">1200</span><span id="line-1200"> return;</span>
+<span class="source-line-no">1201</span><span id="line-1201"> } else {</span>
+<span class="source-line-no">1202</span><span id="line-1202"> LOG.info("begin to load .lastflushedseqids at " + lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1203</span><span id="line-1203"> }</span>
+<span class="source-line-no">1204</span><span id="line-1204"> FSDataInputStream in = fs.open(lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1205</span><span id="line-1205"> try {</span>
+<span class="source-line-no">1206</span><span id="line-1206"> FlushedSequenceId flushedSequenceId = FlushedSequenceId.parseDelimitedFrom(in);</span>
+<span class="source-line-no">1207</span><span id="line-1207"> if (flushedSequenceId == null) {</span>
+<span class="source-line-no">1208</span><span id="line-1208"> LOG.info(".lastflushedseqids found at {} is empty", lastFlushedSeqIdPath);</span>
+<span class="source-line-no">1209</span><span id="line-1209"> return;</span>
+<span class="source-line-no">1210</span><span id="line-1210"> }</span>
+<span class="source-line-no">1211</span><span id="line-1211"> for (FlushedRegionSequenceId flushedRegionSequenceId : flushedSequenceId</span>
+<span class="source-line-no">1212</span><span id="line-1212"> .getRegionSequenceIdList()) {</span>
+<span class="source-line-no">1213</span><span id="line-1213"> byte[] encodedRegionName = flushedRegionSequenceId.getRegionEncodedName().toByteArray();</span>
+<span class="source-line-no">1214</span><span id="line-1214"> flushedSequenceIdByRegion.putIfAbsent(encodedRegionName,</span>
+<span class="source-line-no">1215</span><span id="line-1215"> flushedRegionSequenceId.getSeqId());</span>
+<span class="source-line-no">1216</span><span id="line-1216"> if (</span>
+<span class="source-line-no">1217</span><span id="line-1217"> flushedRegionSequenceId.getStoresList() != null</span>
+<span class="source-line-no">1218</span><span id="line-1218"> && flushedRegionSequenceId.getStoresList().size() != 0</span>
+<span class="source-line-no">1219</span><span id="line-1219"> ) {</span>
+<span class="source-line-no">1220</span><span id="line-1220"> ConcurrentNavigableMap<byte[], Long> storeFlushedSequenceId =</span>
+<span class="source-line-no">1221</span><span id="line-1221"> computeIfAbsent(storeFlushedSequenceIdsByRegion, encodedRegionName,</span>
+<span class="source-line-no">1222</span><span id="line-1222"> () -> new ConcurrentSkipListMap<>(Bytes.BYTES_COMPARATOR));</span>
+<span class="source-line-no">1223</span><span id="line-1223"> for (FlushedStoreSequenceId flushedStoreSequenceId : flushedRegionSequenceId</span>
+<span class="source-line-no">1224</span><span id="line-1224"> .getStoresList()) {</span>
+<span class="source-line-no">1225</span><span id="line-1225"> storeFlushedSequenceId.put(flushedStoreSequenceId.getFamily().toByteArray(),</span>
+<span class="source-line-no">1226</span><span id="line-1226"> flushedStoreSequenceId.getSeqId());</span>
+<span class="source-line-no">1227</span><span id="line-1227"> }</span>
+<span class="source-line-no">1228</span><span id="line-1228"> }</span>
+<span class="source-line-no">1229</span><span id="line-1229"> }</span>
+<span class="source-line-no">1230</span><span id="line-1230"> } finally {</span>
+<span class="source-line-no">1231</span><span id="line-1231"> in.close();</span>
+<span class="source-line-no">1232</span><span id="line-1232"> }</span>
+<span class="source-line-no">1233</span><span id="line-1233"> }</span>
+<span class="source-line-no">1234</span><span id="line-1234"></span>
+<span class="source-line-no">1235</span><span id="line-1235"> /**</span>
+<span class="source-line-no">1236</span><span id="line-1236"> * Regions may have been removed between latest persist of FlushedSequenceIds and master abort. So</span>
+<span class="source-line-no">1237</span><span id="line-1237"> * after loading FlushedSequenceIds from file, and after meta loaded, we need to remove the</span>
+<span class="source-line-no">1238</span><span id="line-1238"> * deleted region according to RegionStates.</span>
+<span class="source-line-no">1239</span><span id="line-1239"> */</span>
+<span class="source-line-no">1240</span><span id="line-1240"> public void removeDeletedRegionFromLoadedFlushedSequenceIds() {</span>
+<span class="source-line-no">1241</span><span id="line-1241"> RegionStates regionStates = master.getAssignmentManager().getRegionStates();</span>
+<span class="source-line-no">1242</span><span id="line-1242"> Iterator<byte[]> it = flushedSequenceIdByRegion.keySet().iterator();</span>
+<span class="source-line-no">1243</span><span id="line-1243"> while (it.hasNext()) {</span>
+<span class="source-line-no">1244</span><span id="line-1244"> byte[] regionEncodedName = it.next();</span>
+<span class="source-line-no">1245</span><span id="line-1245"> if (regionStates.getRegionState(Bytes.toStringBinary(regionEncodedName)) == null) {</span>
+<span class="source-line-no">1246</span><span id="line-1246"> it.remove();</span>
+<span class="source-line-no">1247</span><span id="line-1247"> storeFlushedSequenceIdsByRegion.remove(regionEncodedName);</span>
+<span class="source-line-no">1248</span><span id="line-1248"> }</span>
+<span class="source-line-no">1249</span><span id="line-1249"> }</span>
+<span class="source-line-no">1250</span><span id="line-1250"> }</span>
+<span class="source-line-no">1251</span><span id="line-1251"></span>
+<span class="source-line-no">1252</span><span id="line-1252"> private class FlushedSequenceIdFlusher extends ScheduledChore {</span>
+<span class="source-line-no">1253</span><span id="line-1253"></span>
+<span class="source-line-no">1254</span><span id="line-1254"> public FlushedSequenceIdFlusher(String name, int p) {</span>
+<span class="source-line-no">1255</span><span id="line-1255"> super(name, master, p, 60 * 1000); // delay one minute before first execute</span>
+<span class="source-line-no">1256</span><span id="line-1256"> }</span>
+<span class="source-line-no">1257</span><span id="line-1257"></span>
+<span class="source-line-no">1258</span><span id="line-1258"> @Override</span>
+<span class="source-line-no">1259</span><span id="line-1259"> protected void chore() {</span>
+<span class="source-line-no">1260</span><span id="line-1260"> try {</span>
+<span class="source-line-no">1261</span><span id="line-1261"> persistRegionLastFlushedSequenceIds();</span>
+<span class="source-line-no">1262</span><span id="line-1262"> } catch (IOException e) {</span>
+<span class="source-line-no">1263</span><span id="line-1263"> LOG.debug("Failed to persist last flushed sequence id of regions" + " to file system", e);</span>
+<span class="source-line-no">1264</span><span id="line-1264"> }</span>
+<span class="source-line-no">1265</span><span id="line-1265"> }</span>
+<span class="source-line-no">1266</span><span id="line-1266"> }</span>
+<span class="source-line-no">1267</span><span id="line-1267">}</span>
diff --git a/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.RegionEditTask.html b/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.RegionEditTask.html
index 57237aee4df..de6d16d7975 100644
--- a/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.RegionEditTask.html
+++ b/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.RegionEditTask.html
@@ -34,211 +34,239 @@
<span class="source-line-no">021</span><span id="line-21">import java.io.InterruptedIOException;</span>
<span class="source-line-no">022</span><span id="line-22">import java.util.ArrayList;</span>
<span class="source-line-no">023</span><span id="line-23">import java.util.Collection;</span>
-<span class="source-line-no">024</span><span id="line-24">import java.util.List;</span>
-<span class="source-line-no">025</span><span id="line-25">import java.util.concurrent.Callable;</span>
-<span class="source-line-no">026</span><span id="line-26">import java.util.concurrent.CompletionService;</span>
-<span class="source-line-no">027</span><span id="line-27">import java.util.concurrent.ExecutionException;</span>
-<span class="source-line-no">028</span><span id="line-28">import java.util.concurrent.ExecutorCompletionService;</span>
-<span class="source-line-no">029</span><span id="line-29">import java.util.concurrent.ThreadPoolExecutor;</span>
-<span class="source-line-no">030</span><span id="line-30">import java.util.concurrent.TimeUnit;</span>
-<span class="source-line-no">031</span><span id="line-31">import org.apache.hadoop.conf.Configuration;</span>
-<span class="source-line-no">032</span><span id="line-32">import org.apache.hadoop.fs.Path;</span>
-<span class="source-line-no">033</span><span id="line-33">import org.apache.hadoop.hbase.HConstants;</span>
-<span class="source-line-no">034</span><span id="line-34">import org.apache.hadoop.hbase.client.RegionInfo;</span>
-<span class="source-line-no">035</span><span id="line-35">import org.apache.hadoop.hbase.client.RegionInfoBuilder;</span>
-<span class="source-line-no">036</span><span id="line-36">import org.apache.hadoop.hbase.client.TableDescriptor;</span>
-<span class="source-line-no">037</span><span id="line-37">import org.apache.hadoop.hbase.master.procedure.MasterProcedureEnv;</span>
-<span class="source-line-no">038</span><span id="line-38">import org.apache.hadoop.hbase.regionserver.HRegion;</span>
-<span class="source-line-no">039</span><span id="line-39">import org.apache.yetus.audience.InterfaceAudience;</span>
-<span class="source-line-no">040</span><span id="line-40">import org.slf4j.Logger;</span>
-<span class="source-line-no">041</span><span id="line-41">import org.slf4j.LoggerFactory;</span>
-<span class="source-line-no">042</span><span id="line-42"></span>
-<span class="source-line-no">043</span><span id="line-43">import org.apache.hbase.thirdparty.com.google.common.util.concurrent.ThreadFactoryBuilder;</span>
-<span class="source-line-no">044</span><span id="line-44"></span>
-<span class="source-line-no">045</span><span id="line-45">/**</span>
-<span class="source-line-no">046</span><span id="line-46"> * Utility methods for interacting with the regions.</span>
-<span class="source-line-no">047</span><span id="line-47"> */</span>
-<span class="source-line-no">048</span><span id="line-48">@InterfaceAudience.Private</span>
-<span class="source-line-no">049</span><span id="line-49">public abstract class ModifyRegionUtils {</span>
-<span class="source-line-no">050</span><span id="line-50"> private static final Logger LOG = LoggerFactory.getLogger(ModifyRegionUtils.class);</span>
-<span class="source-line-no">051</span><span id="line-51"></span>
-<span class="source-line-no">052</span><span id="line-52"> private ModifyRegionUtils() {</span>
-<span class="source-line-no">053</span><span id="line-53"> }</span>
-<span class="source-line-no">054</span><span id="line-54"></span>
-<span class="source-line-no">055</span><span id="line-55"> public interface RegionFillTask {</span>
-<span class="source-line-no">056</span><span id="line-56"> void fillRegion(final HRegion region) throws IOException;</span>
-<span class="source-line-no">057</span><span id="line-57"> }</span>
-<span class="source-line-no">058</span><span id="line-58"></span>
-<span class="source-line-no">059</span><span id="line-59"> public interface RegionEditTask {</span>
-<span class="source-line-no">060</span><span id="line-60"> void editRegion(final RegionInfo region) throws IOException;</span>
-<span class="source-line-no">061</span><span id="line-61"> }</span>
-<span class="source-line-no">062</span><span id="line-62"></span>
-<span class="source-line-no">063</span><span id="line-63"> public static RegionInfo[] createRegionInfos(TableDescriptor tableDescriptor,</span>
-<span class="source-line-no">064</span><span id="line-64"> byte[][] splitKeys) {</span>
-<span class="source-line-no">065</span><span id="line-65"> long regionId = EnvironmentEdgeManager.currentTime();</span>
-<span class="source-line-no">066</span><span id="line-66"> RegionInfo[] hRegionInfos = null;</span>
-<span class="source-line-no">067</span><span id="line-67"> if (splitKeys == null || splitKeys.length == 0) {</span>
-<span class="source-line-no">068</span><span id="line-68"> hRegionInfos = new RegionInfo[] { RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
-<span class="source-line-no">069</span><span id="line-69"> .setStartKey(null).setEndKey(null).setSplit(false).setRegionId(regionId).build() };</span>
-<span class="source-line-no">070</span><span id="line-70"> } else {</span>
-<span class="source-line-no">071</span><span id="line-71"> int numRegions = splitKeys.length + 1;</span>
-<span class="source-line-no">072</span><span id="line-72"> hRegionInfos = new RegionInfo[numRegions];</span>
-<span class="source-line-no">073</span><span id="line-73"> byte[] startKey = null;</span>
-<span class="source-line-no">074</span><span id="line-74"> byte[] endKey = null;</span>
-<span class="source-line-no">075</span><span id="line-75"> for (int i = 0; i < numRegions; i++) {</span>
-<span class="source-line-no">076</span><span id="line-76"> endKey = (i == splitKeys.length) ? null : splitKeys[i];</span>
-<span class="source-line-no">077</span><span id="line-77"> hRegionInfos[i] = RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
-<span class="source-line-no">078</span><span id="line-78"> .setStartKey(startKey).setEndKey(endKey).setSplit(false).setRegionId(regionId).build();</span>
-<span class="source-line-no">079</span><span id="line-79"> startKey = endKey;</span>
-<span class="source-line-no">080</span><span id="line-80"> }</span>
-<span class="source-line-no">081</span><span id="line-81"> }</span>
-<span class="source-line-no">082</span><span id="line-82"> return hRegionInfos;</span>
-<span class="source-line-no">083</span><span id="line-83"> }</span>
-<span class="source-line-no">084</span><span id="line-84"></span>
-<span class="source-line-no">085</span><span id="line-85"> /**</span>
-<span class="source-line-no">086</span><span id="line-86"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
-<span class="source-line-no">087</span><span id="line-87"> * to hbase:meta after this operation.</span>
-<span class="source-line-no">088</span><span id="line-88"> * @param env {@link MasterProcedureEnv}</span>
-<span class="source-line-no">089</span><span id="line-89"> * @param rootDir Root directory for HBase instance</span>
-<span class="source-line-no">090</span><span id="line-90"> * @param tableDescriptor description of the table</span>
-<span class="source-line-no">091</span><span id="line-91"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
-<span class="source-line-no">092</span><span id="line-92"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
+<span class="source-line-no">024</span><span id="line-24">import java.util.HashSet;</span>
+<span class="source-line-no">025</span><span id="line-25">import java.util.List;</span>
+<span class="source-line-no">026</span><span id="line-26">import java.util.Objects;</span>
+<span class="source-line-no">027</span><span id="line-27">import java.util.Set;</span>
+<span class="source-line-no">028</span><span id="line-28">import java.util.concurrent.Callable;</span>
+<span class="source-line-no">029</span><span id="line-29">import java.util.concurrent.CompletionService;</span>
+<span class="source-line-no">030</span><span id="line-30">import java.util.concurrent.ExecutionException;</span>
+<span class="source-line-no">031</span><span id="line-31">import java.util.concurrent.ExecutorCompletionService;</span>
+<span class="source-line-no">032</span><span id="line-32">import java.util.concurrent.ThreadPoolExecutor;</span>
+<span class="source-line-no">033</span><span id="line-33">import java.util.concurrent.TimeUnit;</span>
+<span class="source-line-no">034</span><span id="line-34">import org.apache.hadoop.conf.Configuration;</span>
+<span class="source-line-no">035</span><span id="line-35">import org.apache.hadoop.fs.Path;</span>
+<span class="source-line-no">036</span><span id="line-36">import org.apache.hadoop.hbase.DoNotRetryIOException;</span>
+<span class="source-line-no">037</span><span id="line-37">import org.apache.hadoop.hbase.HConstants;</span>
+<span class="source-line-no">038</span><span id="line-38">import org.apache.hadoop.hbase.client.RegionInfo;</span>
+<span class="source-line-no">039</span><span id="line-39">import org.apache.hadoop.hbase.client.RegionInfoBuilder;</span>
+<span class="source-line-no">040</span><span id="line-40">import org.apache.hadoop.hbase.client.TableDescriptor;</span>
+<span class="source-line-no">041</span><span id="line-41">import org.apache.hadoop.hbase.master.assignment.RegionStates;</span>
+<span class="source-line-no">042</span><span id="line-42">import org.apache.hadoop.hbase.master.procedure.MasterProcedureEnv;</span>
+<span class="source-line-no">043</span><span id="line-43">import org.apache.hadoop.hbase.regionserver.HRegion;</span>
+<span class="source-line-no">044</span><span id="line-44">import org.apache.yetus.audience.InterfaceAudience;</span>
+<span class="source-line-no">045</span><span id="line-45">import org.slf4j.Logger;</span>
+<span class="source-line-no">046</span><span id="line-46">import org.slf4j.LoggerFactory;</span>
+<span class="source-line-no">047</span><span id="line-47"></span>
+<span class="source-line-no">048</span><span id="line-48">import org.apache.hbase.thirdparty.com.google.common.util.concurrent.ThreadFactoryBuilder;</span>
+<span class="source-line-no">049</span><span id="line-49"></span>
+<span class="source-line-no">050</span><span id="line-50">/**</span>
+<span class="source-line-no">051</span><span id="line-51"> * Utility methods for interacting with the regions.</span>
+<span class="source-line-no">052</span><span id="line-52"> */</span>
+<span class="source-line-no">053</span><span id="line-53">@InterfaceAudience.Private</span>
+<span class="source-line-no">054</span><span id="line-54">public abstract class ModifyRegionUtils {</span>
+<span class="source-line-no">055</span><span id="line-55"> private static final Logger LOG = LoggerFactory.getLogger(ModifyRegionUtils.class);</span>
+<span class="source-line-no">056</span><span id="line-56"></span>
+<span class="source-line-no">057</span><span id="line-57"> private ModifyRegionUtils() {</span>
+<span class="source-line-no">058</span><span id="line-58"> }</span>
+<span class="source-line-no">059</span><span id="line-59"></span>
+<span class="source-line-no">060</span><span id="line-60"> public interface RegionFillTask {</span>
+<span class="source-line-no">061</span><span id="line-61"> void fillRegion(final HRegion region) throws IOException;</span>
+<span class="source-line-no">062</span><span id="line-62"> }</span>
+<span class="source-line-no">063</span><span id="line-63"></span>
+<span class="source-line-no">064</span><span id="line-64"> public interface RegionEditTask {</span>
+<span class="source-line-no">065</span><span id="line-65"> void editRegion(final RegionInfo region) throws IOException;</span>
+<span class="source-line-no">066</span><span id="line-66"> }</span>
+<span class="source-line-no">067</span><span id="line-67"></span>
+<span class="source-line-no">068</span><span id="line-68"> public static RegionInfo[] createRegionInfos(TableDescriptor tableDescriptor,</span>
+<span class="source-line-no">069</span><span id="line-69"> byte[][] splitKeys) {</span>
+<span class="source-line-no">070</span><span id="line-70"> long regionId = EnvironmentEdgeManager.currentTime();</span>
+<span class="source-line-no">071</span><span id="line-71"> RegionInfo[] hRegionInfos = null;</span>
+<span class="source-line-no">072</span><span id="line-72"> if (splitKeys == null || splitKeys.length == 0) {</span>
+<span class="source-line-no">073</span><span id="line-73"> hRegionInfos = new RegionInfo[] { RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
+<span class="source-line-no">074</span><span id="line-74"> .setStartKey(null).setEndKey(null).setSplit(false).setRegionId(regionId).build() };</span>
+<span class="source-line-no">075</span><span id="line-75"> } else {</span>
+<span class="source-line-no">076</span><span id="line-76"> int numRegions = splitKeys.length + 1;</span>
+<span class="source-line-no">077</span><span id="line-77"> hRegionInfos = new RegionInfo[numRegions];</span>
+<span class="source-line-no">078</span><span id="line-78"> byte[] startKey = null;</span>
+<span class="source-line-no">079</span><span id="line-79"> byte[] endKey = null;</span>
+<span class="source-line-no">080</span><span id="line-80"> for (int i = 0; i < numRegions; i++) {</span>
+<span class="source-line-no">081</span><span id="line-81"> endKey = (i == splitKeys.length) ? null : splitKeys[i];</span>
+<span class="source-line-no">082</span><span id="line-82"> hRegionInfos[i] = RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
+<span class="source-line-no">083</span><span id="line-83"> .setStartKey(startKey).setEndKey(endKey).setSplit(false).setRegionId(regionId).build();</span>
+<span class="source-line-no">084</span><span id="line-84"> startKey = endKey;</span>
+<span class="source-line-no">085</span><span id="line-85"> }</span>
+<span class="source-line-no">086</span><span id="line-86"> }</span>
+<span class="source-line-no">087</span><span id="line-87"> return hRegionInfos;</span>
+<span class="source-line-no">088</span><span id="line-88"> }</span>
+<span class="source-line-no">089</span><span id="line-89"></span>
+<span class="source-line-no">090</span><span id="line-90"> /**</span>
+<span class="source-line-no">091</span><span id="line-91"> * Checks candidate regions for encoded\-name collisions. Ensures there are no duplicates in the</span>
+<span class="source-line-no">092</span><span id="line-92"> * input and no conflicts with existing region states.</span>
<span class="source-line-no">093</span><span id="line-93"> */</span>
-<span class="source-line-no">094</span><span id="line-94"> public static List<RegionInfo> createRegions(final MasterProcedureEnv env, final Path rootDir,</span>
-<span class="source-line-no">095</span><span id="line-95"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
-<span class="source-line-no">096</span><span id="line-96"> throws IOException {</span>
-<span class="source-line-no">097</span><span id="line-97"> if (newRegions == null) return null;</span>
-<span class="source-line-no">098</span><span id="line-98"> int regionNumber = newRegions.length;</span>
-<span class="source-line-no">099</span><span id="line-99"> ThreadPoolExecutor exec = getRegionOpenAndInitThreadPool(env.getMasterConfiguration(),</span>
-<span class="source-line-no">100</span><span id="line-100"> "RegionOpenAndInit-" + tableDescriptor.getTableName(), regionNumber);</span>
-<span class="source-line-no">101</span><span id="line-101"> try {</span>
-<span class="source-line-no">102</span><span id="line-102"> return createRegions(exec, env.getMasterConfiguration(), env, rootDir, tableDescriptor,</span>
-<span class="source-line-no">103</span><span id="line-103"> newRegions, task);</span>
-<span class="source-line-no">104</span><span id="line-104"> } finally {</span>
-<span class="source-line-no">105</span><span id="line-105"> exec.shutdownNow();</span>
-<span class="source-line-no">106</span><span id="line-106"> }</span>
-<span class="source-line-no">107</span><span id="line-107"> }</span>
-<span class="source-line-no">108</span><span id="line-108"></span>
-<span class="source-line-no">109</span><span id="line-109"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
-<span class="source-line-no">110</span><span id="line-110"> final Configuration conf, final Path rootDir, final TableDescriptor tableDescriptor,</span>
-<span class="source-line-no">111</span><span id="line-111"> final RegionInfo[] newRegions, final RegionFillTask task) throws IOException {</span>
-<span class="source-line-no">112</span><span id="line-112"> return createRegions(exec, conf, null, rootDir, tableDescriptor, newRegions, task);</span>
-<span class="source-line-no">113</span><span id="line-113"> }</span>
-<span class="source-line-no">114</span><span id="line-114"></span>
-<span class="source-line-no">115</span><span id="line-115"> /**</span>
-<span class="source-line-no">116</span><span id="line-116"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
-<span class="source-line-no">117</span><span id="line-117"> * to hbase:meta after this operation.</span>
-<span class="source-line-no">118</span><span id="line-118"> * @param exec Thread Pool Executor</span>
-<span class="source-line-no">119</span><span id="line-119"> * @param conf {@link Configuration}</span>
-<span class="source-line-no">120</span><span id="line-120"> * @param rootDir Root directory for HBase instance</span>
-<span class="source-line-no">121</span><span id="line-121"> * @param tableDescriptor description of the table</span>
-<span class="source-line-no">122</span><span id="line-122"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
-<span class="source-line-no">123</span><span id="line-123"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
-<span class="source-line-no">124</span><span id="line-124"> */</span>
-<span class="source-line-no">125</span><span id="line-125"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
-<span class="source-line-no">126</span><span id="line-126"> final Configuration conf, final MasterProcedureEnv env, final Path rootDir,</span>
-<span class="source-line-no">127</span><span id="line-127"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
-<span class="source-line-no">128</span><span id="line-128"> throws IOException {</span>
-<span class="source-line-no">129</span><span id="line-129"> if (newRegions == null) return null;</span>
-<span class="source-line-no">130</span><span id="line-130"> int regionNumber = newRegions.length;</span>
-<span class="source-line-no">131</span><span id="line-131"> CompletionService<RegionInfo> completionService = new ExecutorCompletionService<>(exec);</span>
-<span class="source-line-no">132</span><span id="line-132"> List<RegionInfo> regionInfos = new ArrayList<>();</span>
-<span class="source-line-no">133</span><span id="line-133"> for (final RegionInfo newRegion : newRegions) {</span>
-<span class="source-line-no">134</span><span id="line-134"> completionService.submit(new Callable<RegionInfo>() {</span>
-<span class="source-line-no">135</span><span id="line-135"> @Override</span>
-<span class="source-line-no">136</span><span id="line-136"> public RegionInfo call() throws IOException {</span>
-<span class="source-line-no">137</span><span id="line-137"> return createRegion(conf, env, rootDir, tableDescriptor, newRegion, task);</span>
-<span class="source-line-no">138</span><span id="line-138"> }</span>
-<span class="source-line-no">139</span><span id="line-139"> });</span>
-<span class="source-line-no">140</span><span id="line-140"> }</span>
-<span class="source-line-no">141</span><span id="line-141"> try {</span>
-<span class="source-line-no">142</span><span id="line-142"> // wait for all regions to finish creation</span>
-<span class="source-line-no">143</span><span id="line-143"> for (int i = 0; i < regionNumber; i++) {</span>
-<span class="source-line-no">144</span><span id="line-144"> regionInfos.add(completionService.take().get());</span>
-<span class="source-line-no">145</span><span id="line-145"> }</span>
-<span class="source-line-no">146</span><span id="line-146"> } catch (InterruptedException e) {</span>
-<span class="source-line-no">147</span><span id="line-147"> LOG.error("Caught " + e + " during region creation");</span>
-<span class="source-line-no">148</span><span id="line-148"> throw new InterruptedIOException(e.getMessage());</span>
-<span class="source-line-no">149</span><span id="line-149"> } catch (ExecutionException e) {</span>
-<span class="source-line-no">150</span><span id="line-150"> throw new IOException(e);</span>
-<span class="source-line-no">151</span><span id="line-151"> }</span>
-<span class="source-line-no">152</span><span id="line-152"> return regionInfos;</span>
-<span class="source-line-no">153</span><span id="line-153"> }</span>
-<span class="source-line-no">154</span><span id="line-154"></span>
-<span class="source-line-no">155</span><span id="line-155"> /**</span>
-<span class="source-line-no">156</span><span id="line-156"> * Create new set of regions on the specified file-system.</span>
-<span class="source-line-no">157</span><span id="line-157"> * @param conf {@link Configuration}</span>
-<span class="source-line-no">158</span><span id="line-158"> * @param rootDir Root directory for HBase instance</span>
-<span class="source-line-no">159</span><span id="line-159"> * @param tableDescriptor description of the table</span>
-<span class="source-line-no">160</span><span id="line-160"> * @param newRegion {@link RegionInfo} that describes the region to create</span>
-<span class="source-line-no">161</span><span id="line-161"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
-<span class="source-line-no">162</span><span id="line-162"> */</span>
-<span class="source-line-no">163</span><span id="line-163"> public static RegionInfo createRegion(final Configuration conf, final MasterProcedureEnv env,</span>
-<span class="source-line-no">164</span><span id="line-164"> final Path rootDir, final TableDescriptor tableDescriptor, final RegionInfo newRegion,</span>
-<span class="source-line-no">165</span><span id="line-165"> final RegionFillTask task) throws IOException {</span>
-<span class="source-line-no">166</span><span id="line-166"> // 1. Create HRegion</span>
-<span class="source-line-no">167</span><span id="line-167"> // The WAL subsystem will use the default rootDir rather than the passed in rootDir</span>
-<span class="source-line-no">168</span><span id="line-168"> // unless I pass along via the conf.</span>
-<span class="source-line-no">169</span><span id="line-169"> Configuration confForWAL = new Configuration(conf);</span>
-<span class="source-line-no">170</span><span id="line-170"> confForWAL.set(HConstants.HBASE_DIR, rootDir.toString());</span>
-<span class="source-line-no">171</span><span id="line-171"> HRegion region = HRegion.createHRegion(newRegion, rootDir, conf, tableDescriptor, null, false,</span>
-<span class="source-line-no">172</span><span id="line-172"> null, env == null ? null : env.getMasterServices());</span>
-<span class="source-line-no">173</span><span id="line-173"> try {</span>
-<span class="source-line-no">174</span><span id="line-174"> // 2. Custom user code to interact with the created region</span>
-<span class="source-line-no">175</span><span id="line-175"> if (task != null) {</span>
-<span class="source-line-no">176</span><span id="line-176"> task.fillRegion(region);</span>
-<span class="source-line-no">177</span><span id="line-177"> }</span>
-<span class="source-line-no">178</span><span id="line-178"> } finally {</span>
-<span class="source-line-no">179</span><span id="line-179"> // 3. Close the new region to flush to disk. Close log file too.</span>
-<span class="source-line-no">180</span><span id="line-180"> region.close(false, true);</span>
-<span class="source-line-no">181</span><span id="line-181"> }</span>
-<span class="source-line-no">182</span><span id="line-182"> return region.getRegionInfo();</span>
-<span class="source-line-no">183</span><span id="line-183"> }</span>
-<span class="source-line-no">184</span><span id="line-184"></span>
-<span class="source-line-no">185</span><span id="line-185"> /**</span>
-<span class="source-line-no">186</span><span id="line-186"> * Execute the task on the specified set of regions.</span>
-<span class="source-line-no">187</span><span id="line-187"> * @param exec Thread Pool Executor</span>
-<span class="source-line-no">188</span><span id="line-188"> * @param regions {@link RegionInfo} that describes the regions to edit</span>
-<span class="source-line-no">189</span><span id="line-189"> * @param task {@link RegionFillTask} custom code to edit the region</span>
+<span class="source-line-no">094</span><span id="line-94"> public static void checkForEncodedNameCollisions(final Collection<RegionInfo> candidates,</span>
+<span class="source-line-no">095</span><span id="line-95"> final RegionStates regionStates) throws IOException {</span>
+<span class="source-line-no">096</span><span id="line-96"> if (candidates == null || candidates.isEmpty()) {</span>
+<span class="source-line-no">097</span><span id="line-97"> return;</span>
+<span class="source-line-no">098</span><span id="line-98"> }</span>
+<span class="source-line-no">099</span><span id="line-99"> Objects.requireNonNull(regionStates, "regionStates is null");</span>
+<span class="source-line-no">100</span><span id="line-100"> Set<String> candidateNames = new HashSet<>();</span>
+<span class="source-line-no">101</span><span id="line-101"> for (RegionInfo ri : candidates) {</span>
+<span class="source-line-no">102</span><span id="line-102"> String encoded = ri.getEncodedName();</span>
+<span class="source-line-no">103</span><span id="line-103"> if (</span>
+<span class="source-line-no">104</span><span id="line-104"> !candidateNames.add(encoded)</span>
+<span class="source-line-no">105</span><span id="line-105"> || regionStates.getRegionStateNodeFromEncodedRegionName(encoded) != null</span>
+<span class="source-line-no">106</span><span id="line-106"> ) {</span>
+<span class="source-line-no">107</span><span id="line-107"> throw new DoNotRetryIOException("Encoded region name collision detected: '" + encoded</span>
+<span class="source-line-no">108</span><span id="line-108"> + "' for table " + ri.getTable() + ". Refusing to proceed.");</span>
+<span class="source-line-no">109</span><span id="line-109"> }</span>
+<span class="source-line-no">110</span><span id="line-110"> }</span>
+<span class="source-line-no">111</span><span id="line-111"> }</span>
+<span class="source-line-no">112</span><span id="line-112"></span>
+<span class="source-line-no">113</span><span id="line-113"> /**</span>
+<span class="source-line-no">114</span><span id="line-114"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
+<span class="source-line-no">115</span><span id="line-115"> * to hbase:meta after this operation.</span>
+<span class="source-line-no">116</span><span id="line-116"> * @param env {@link MasterProcedureEnv}</span>
+<span class="source-line-no">117</span><span id="line-117"> * @param rootDir Root directory for HBase instance</span>
+<span class="source-line-no">118</span><span id="line-118"> * @param tableDescriptor description of the table</span>
+<span class="source-line-no">119</span><span id="line-119"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
+<span class="source-line-no">120</span><span id="line-120"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
+<span class="source-line-no">121</span><span id="line-121"> */</span>
+<span class="source-line-no">122</span><span id="line-122"> public static List<RegionInfo> createRegions(final MasterProcedureEnv env, final Path rootDir,</span>
+<span class="source-line-no">123</span><span id="line-123"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
+<span class="source-line-no">124</span><span id="line-124"> throws IOException {</span>
+<span class="source-line-no">125</span><span id="line-125"> if (newRegions == null) return null;</span>
+<span class="source-line-no">126</span><span id="line-126"> int regionNumber = newRegions.length;</span>
+<span class="source-line-no">127</span><span id="line-127"> ThreadPoolExecutor exec = getRegionOpenAndInitThreadPool(env.getMasterConfiguration(),</span>
+<span class="source-line-no">128</span><span id="line-128"> "RegionOpenAndInit-" + tableDescriptor.getTableName(), regionNumber);</span>
+<span class="source-line-no">129</span><span id="line-129"> try {</span>
+<span class="source-line-no">130</span><span id="line-130"> return createRegions(exec, env.getMasterConfiguration(), env, rootDir, tableDescriptor,</span>
+<span class="source-line-no">131</span><span id="line-131"> newRegions, task);</span>
+<span class="source-line-no">132</span><span id="line-132"> } finally {</span>
+<span class="source-line-no">133</span><span id="line-133"> exec.shutdownNow();</span>
+<span class="source-line-no">134</span><span id="line-134"> }</span>
+<span class="source-line-no">135</span><span id="line-135"> }</span>
+<span class="source-line-no">136</span><span id="line-136"></span>
+<span class="source-line-no">137</span><span id="line-137"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
+<span class="source-line-no">138</span><span id="line-138"> final Configuration conf, final Path rootDir, final TableDescriptor tableDescriptor,</span>
+<span class="source-line-no">139</span><span id="line-139"> final RegionInfo[] newRegions, final RegionFillTask task) throws IOException {</span>
+<span class="source-line-no">140</span><span id="line-140"> return createRegions(exec, conf, null, rootDir, tableDescriptor, newRegions, task);</span>
+<span class="source-line-no">141</span><span id="line-141"> }</span>
+<span class="source-line-no">142</span><span id="line-142"></span>
+<span class="source-line-no">143</span><span id="line-143"> /**</span>
+<span class="source-line-no">144</span><span id="line-144"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
+<span class="source-line-no">145</span><span id="line-145"> * to hbase:meta after this operation.</span>
+<span class="source-line-no">146</span><span id="line-146"> * @param exec Thread Pool Executor</span>
+<span class="source-line-no">147</span><span id="line-147"> * @param conf {@link Configuration}</span>
+<span class="source-line-no">148</span><span id="line-148"> * @param rootDir Root directory for HBase instance</span>
+<span class="source-line-no">149</span><span id="line-149"> * @param tableDescriptor description of the table</span>
+<span class="source-line-no">150</span><span id="line-150"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
+<span class="source-line-no">151</span><span id="line-151"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
+<span class="source-line-no">152</span><span id="line-152"> */</span>
+<span class="source-line-no">153</span><span id="line-153"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
+<span class="source-line-no">154</span><span id="line-154"> final Configuration conf, final MasterProcedureEnv env, final Path rootDir,</span>
+<span class="source-line-no">155</span><span id="line-155"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
+<span class="source-line-no">156</span><span id="line-156"> throws IOException {</span>
+<span class="source-line-no">157</span><span id="line-157"> if (newRegions == null) return null;</span>
+<span class="source-line-no">158</span><span id="line-158"> int regionNumber = newRegions.length;</span>
+<span class="source-line-no">159</span><span id="line-159"> CompletionService<RegionInfo> completionService = new ExecutorCompletionService<>(exec);</span>
+<span class="source-line-no">160</span><span id="line-160"> List<RegionInfo> regionInfos = new ArrayList<>();</span>
+<span class="source-line-no">161</span><span id="line-161"> for (final RegionInfo newRegion : newRegions) {</span>
+<span class="source-line-no">162</span><span id="line-162"> completionService.submit(new Callable<RegionInfo>() {</span>
+<span class="source-line-no">163</span><span id="line-163"> @Override</span>
+<span class="source-line-no">164</span><span id="line-164"> public RegionInfo call() throws IOException {</span>
+<span class="source-line-no">165</span><span id="line-165"> return createRegion(conf, env, rootDir, tableDescriptor, newRegion, task);</span>
+<span class="source-line-no">166</span><span id="line-166"> }</span>
+<span class="source-line-no">167</span><span id="line-167"> });</span>
+<span class="source-line-no">168</span><span id="line-168"> }</span>
+<span class="source-line-no">169</span><span id="line-169"> try {</span>
+<span class="source-line-no">170</span><span id="line-170"> // wait for all regions to finish creation</span>
+<span class="source-line-no">171</span><span id="line-171"> for (int i = 0; i < regionNumber; i++) {</span>
+<span class="source-line-no">172</span><span id="line-172"> regionInfos.add(completionService.take().get());</span>
+<span class="source-line-no">173</span><span id="line-173"> }</span>
+<span class="source-line-no">174</span><span id="line-174"> } catch (InterruptedException e) {</span>
+<span class="source-line-no">175</span><span id="line-175"> LOG.error("Caught " + e + " during region creation");</span>
+<span class="source-line-no">176</span><span id="line-176"> throw new InterruptedIOException(e.getMessage());</span>
+<span class="source-line-no">177</span><span id="line-177"> } catch (ExecutionException e) {</span>
+<span class="source-line-no">178</span><span id="line-178"> throw new IOException(e);</span>
+<span class="source-line-no">179</span><span id="line-179"> }</span>
+<span class="source-line-no">180</span><span id="line-180"> return regionInfos;</span>
+<span class="source-line-no">181</span><span id="line-181"> }</span>
+<span class="source-line-no">182</span><span id="line-182"></span>
+<span class="source-line-no">183</span><span id="line-183"> /**</span>
+<span class="source-line-no">184</span><span id="line-184"> * Create new set of regions on the specified file-system.</span>
+<span class="source-line-no">185</span><span id="line-185"> * @param conf {@link Configuration}</span>
+<span class="source-line-no">186</span><span id="line-186"> * @param rootDir Root directory for HBase instance</span>
+<span class="source-line-no">187</span><span id="line-187"> * @param tableDescriptor description of the table</span>
+<span class="source-line-no">188</span><span id="line-188"> * @param newRegion {@link RegionInfo} that describes the region to create</span>
+<span class="source-line-no">189</span><span id="line-189"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
<span class="source-line-no">190</span><span id="line-190"> */</span>
-<span class="source-line-no">191</span><span id="line-191"> public static void editRegions(final ThreadPoolExecutor exec,</span>
-<span class="source-line-no">192</span><span id="line-192"> final Collection<RegionInfo> regions, final RegionEditTask task) throws IOException {</span>
-<span class="source-line-no">193</span><span id="line-193"> final ExecutorCompletionService<Void> completionService = new ExecutorCompletionService<>(exec);</span>
-<span class="source-line-no">194</span><span id="line-194"> for (final RegionInfo hri : regions) {</span>
-<span class="source-line-no">195</span><span id="line-195"> completionService.submit(new Callable<Void>() {</span>
-<span class="source-line-no">196</span><span id="line-196"> @Override</span>
-<span class="source-line-no">197</span><span id="line-197"> public Void call() throws IOException {</span>
-<span class="source-line-no">198</span><span id="line-198"> task.editRegion(hri);</span>
-<span class="source-line-no">199</span><span id="line-199"> return null;</span>
-<span class="source-line-no">200</span><span id="line-200"> }</span>
-<span class="source-line-no">201</span><span id="line-201"> });</span>
-<span class="source-line-no">202</span><span id="line-202"> }</span>
-<span class="source-line-no">203</span><span id="line-203"></span>
-<span class="source-line-no">204</span><span id="line-204"> try {</span>
-<span class="source-line-no">205</span><span id="line-205"> for (RegionInfo hri : regions) {</span>
-<span class="source-line-no">206</span><span id="line-206"> completionService.take().get();</span>
-<span class="source-line-no">207</span><span id="line-207"> }</span>
-<span class="source-line-no">208</span><span id="line-208"> } catch (InterruptedException e) {</span>
-<span class="source-line-no">209</span><span id="line-209"> throw new InterruptedIOException(e.getMessage());</span>
-<span class="source-line-no">210</span><span id="line-210"> } catch (ExecutionException e) {</span>
-<span class="source-line-no">211</span><span id="line-211"> throw new IOException(e.getCause());</span>
-<span class="source-line-no">212</span><span id="line-212"> }</span>
-<span class="source-line-no">213</span><span id="line-213"> }</span>
-<span class="source-line-no">214</span><span id="line-214"></span>
-<span class="source-line-no">215</span><span id="line-215"> /*</span>
-<span class="source-line-no">216</span><span id="line-216"> * used by createRegions() to get the thread pool executor based on the</span>
-<span class="source-line-no">217</span><span id="line-217"> * "hbase.hregion.open.and.init.threads.max" property.</span>
+<span class="source-line-no">191</span><span id="line-191"> public static RegionInfo createRegion(final Configuration conf, final MasterProcedureEnv env,</span>
+<span class="source-line-no">192</span><span id="line-192"> final Path rootDir, final TableDescriptor tableDescriptor, final RegionInfo newRegion,</span>
+<span class="source-line-no">193</span><span id="line-193"> final RegionFillTask task) throws IOException {</span>
+<span class="source-line-no">194</span><span id="line-194"> // 1. Create HRegion</span>
+<span class="source-line-no">195</span><span id="line-195"> // The WAL subsystem will use the default rootDir rather than the passed in rootDir</span>
+<span class="source-line-no">196</span><span id="line-196"> // unless I pass along via the conf.</span>
+<span class="source-line-no">197</span><span id="line-197"> Configuration confForWAL = new Configuration(conf);</span>
+<span class="source-line-no">198</span><span id="line-198"> confForWAL.set(HConstants.HBASE_DIR, rootDir.toString());</span>
+<span class="source-line-no">199</span><span id="line-199"> HRegion region = HRegion.createHRegion(newRegion, rootDir, conf, tableDescriptor, null, false,</span>
+<span class="source-line-no">200</span><span id="line-200"> null, env == null ? null : env.getMasterServices());</span>
+<span class="source-line-no">201</span><span id="line-201"> try {</span>
+<span class="source-line-no">202</span><span id="line-202"> // 2. Custom user code to interact with the created region</span>
+<span class="source-line-no">203</span><span id="line-203"> if (task != null) {</span>
+<span class="source-line-no">204</span><span id="line-204"> task.fillRegion(region);</span>
+<span class="source-line-no">205</span><span id="line-205"> }</span>
+<span class="source-line-no">206</span><span id="line-206"> } finally {</span>
+<span class="source-line-no">207</span><span id="line-207"> // 3. Close the new region to flush to disk. Close log file too.</span>
+<span class="source-line-no">208</span><span id="line-208"> region.close(false, true);</span>
+<span class="source-line-no">209</span><span id="line-209"> }</span>
+<span class="source-line-no">210</span><span id="line-210"> return region.getRegionInfo();</span>
+<span class="source-line-no">211</span><span id="line-211"> }</span>
+<span class="source-line-no">212</span><span id="line-212"></span>
+<span class="source-line-no">213</span><span id="line-213"> /**</span>
+<span class="source-line-no">214</span><span id="line-214"> * Execute the task on the specified set of regions.</span>
+<span class="source-line-no">215</span><span id="line-215"> * @param exec Thread Pool Executor</span>
+<span class="source-line-no">216</span><span id="line-216"> * @param regions {@link RegionInfo} that describes the regions to edit</span>
+<span class="source-line-no">217</span><span id="line-217"> * @param task {@link RegionFillTask} custom code to edit the region</span>
<span class="source-line-no">218</span><span id="line-218"> */</span>
-<span class="source-line-no">219</span><span id="line-219"> static ThreadPoolExecutor getRegionOpenAndInitThreadPool(final Configuration conf,</span>
-<span class="source-line-no">220</span><span id="line-220"> final String threadNamePrefix, int regionNumber) {</span>
-<span class="source-line-no">221</span><span id="line-221"> int maxThreads =</span>
-<span class="source-line-no">222</span><span id="line-222"> Math.min(regionNumber, conf.getInt("hbase.hregion.open.and.init.threads.max", 16));</span>
-<span class="source-line-no">223</span><span id="line-223"> ThreadPoolExecutor regionOpenAndInitThreadPool = Threads.getBoundedCachedThreadPool(maxThreads,</span>
-<span class="source-line-no">224</span><span id="line-224"> 30L, TimeUnit.SECONDS, new ThreadFactoryBuilder().setNameFormat(threadNamePrefix + "-pool-%d")</span>
-<span class="source-line-no">225</span><span id="line-225"> .setDaemon(true).setUncaughtExceptionHandler(Threads.LOGGING_EXCEPTION_HANDLER).build());</span>
-<span class="source-line-no">226</span><span id="line-226"> return regionOpenAndInitThreadPool;</span>
-<span class="source-line-no">227</span><span id="line-227"> }</span>
-<span class="source-line-no">228</span><span id="line-228">}</span>
+<span class="source-line-no">219</span><span id="line-219"> public static void editRegions(final ThreadPoolExecutor exec,</span>
+<span class="source-line-no">220</span><span id="line-220"> final Collection<RegionInfo> regions, final RegionEditTask task) throws IOException {</span>
+<span class="source-line-no">221</span><span id="line-221"> final ExecutorCompletionService<Void> completionService = new ExecutorCompletionService<>(exec);</span>
+<span class="source-line-no">222</span><span id="line-222"> for (final RegionInfo hri : regions) {</span>
+<span class="source-line-no">223</span><span id="line-223"> completionService.submit(new Callable<Void>() {</span>
+<span class="source-line-no">224</span><span id="line-224"> @Override</span>
+<span class="source-line-no">225</span><span id="line-225"> public Void call() throws IOException {</span>
+<span class="source-line-no">226</span><span id="line-226"> task.editRegion(hri);</span>
+<span class="source-line-no">227</span><span id="line-227"> return null;</span>
+<span class="source-line-no">228</span><span id="line-228"> }</span>
+<span class="source-line-no">229</span><span id="line-229"> });</span>
+<span class="source-line-no">230</span><span id="line-230"> }</span>
+<span class="source-line-no">231</span><span id="line-231"></span>
+<span class="source-line-no">232</span><span id="line-232"> try {</span>
+<span class="source-line-no">233</span><span id="line-233"> for (RegionInfo hri : regions) {</span>
+<span class="source-line-no">234</span><span id="line-234"> completionService.take().get();</span>
+<span class="source-line-no">235</span><span id="line-235"> }</span>
+<span class="source-line-no">236</span><span id="line-236"> } catch (InterruptedException e) {</span>
+<span class="source-line-no">237</span><span id="line-237"> throw new InterruptedIOException(e.getMessage());</span>
+<span class="source-line-no">238</span><span id="line-238"> } catch (ExecutionException e) {</span>
+<span class="source-line-no">239</span><span id="line-239"> throw new IOException(e.getCause());</span>
+<span class="source-line-no">240</span><span id="line-240"> }</span>
+<span class="source-line-no">241</span><span id="line-241"> }</span>
+<span class="source-line-no">242</span><span id="line-242"></span>
+<span class="source-line-no">243</span><span id="line-243"> /*</span>
+<span class="source-line-no">244</span><span id="line-244"> * used by createRegions() to get the thread pool executor based on the</span>
+<span class="source-line-no">245</span><span id="line-245"> * "hbase.hregion.open.and.init.threads.max" property.</span>
+<span class="source-line-no">246</span><span id="line-246"> */</span>
+<span class="source-line-no">247</span><span id="line-247"> static ThreadPoolExecutor getRegionOpenAndInitThreadPool(final Configuration conf,</span>
+<span class="source-line-no">248</span><span id="line-248"> final String threadNamePrefix, int regionNumber) {</span>
+<span class="source-line-no">249</span><span id="line-249"> int maxThreads =</span>
+<span class="source-line-no">250</span><span id="line-250"> Math.min(regionNumber, conf.getInt("hbase.hregion.open.and.init.threads.max", 16));</span>
+<span class="source-line-no">251</span><span id="line-251"> ThreadPoolExecutor regionOpenAndInitThreadPool = Threads.getBoundedCachedThreadPool(maxThreads,</span>
+<span class="source-line-no">252</span><span id="line-252"> 30L, TimeUnit.SECONDS, new ThreadFactoryBuilder().setNameFormat(threadNamePrefix + "-pool-%d")</span>
+<span class="source-line-no">253</span><span id="line-253"> .setDaemon(true).setUncaughtExceptionHandler(Threads.LOGGING_EXCEPTION_HANDLER).build());</span>
+<span class="source-line-no">254</span><span id="line-254"> return regionOpenAndInitThreadPool;</span>
+<span class="source-line-no">255</span><span id="line-255"> }</span>
+<span class="source-line-no">256</span><span id="line-256">}</span>
diff --git a/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.RegionFillTask.html b/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.RegionFillTask.html
index 7f632d2d742..11059223b1c 100644
--- a/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.RegionFillTask.html
+++ b/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.RegionFillTask.html
@@ -34,211 +34,239 @@
<span class="source-line-no">021</span><span id="line-21">import java.io.InterruptedIOException;</span>
<span class="source-line-no">022</span><span id="line-22">import java.util.ArrayList;</span>
<span class="source-line-no">023</span><span id="line-23">import java.util.Collection;</span>
-<span class="source-line-no">024</span><span id="line-24">import java.util.List;</span>
-<span class="source-line-no">025</span><span id="line-25">import java.util.concurrent.Callable;</span>
-<span class="source-line-no">026</span><span id="line-26">import java.util.concurrent.CompletionService;</span>
-<span class="source-line-no">027</span><span id="line-27">import java.util.concurrent.ExecutionException;</span>
-<span class="source-line-no">028</span><span id="line-28">import java.util.concurrent.ExecutorCompletionService;</span>
-<span class="source-line-no">029</span><span id="line-29">import java.util.concurrent.ThreadPoolExecutor;</span>
-<span class="source-line-no">030</span><span id="line-30">import java.util.concurrent.TimeUnit;</span>
-<span class="source-line-no">031</span><span id="line-31">import org.apache.hadoop.conf.Configuration;</span>
-<span class="source-line-no">032</span><span id="line-32">import org.apache.hadoop.fs.Path;</span>
-<span class="source-line-no">033</span><span id="line-33">import org.apache.hadoop.hbase.HConstants;</span>
-<span class="source-line-no">034</span><span id="line-34">import org.apache.hadoop.hbase.client.RegionInfo;</span>
-<span class="source-line-no">035</span><span id="line-35">import org.apache.hadoop.hbase.client.RegionInfoBuilder;</span>
-<span class="source-line-no">036</span><span id="line-36">import org.apache.hadoop.hbase.client.TableDescriptor;</span>
-<span class="source-line-no">037</span><span id="line-37">import org.apache.hadoop.hbase.master.procedure.MasterProcedureEnv;</span>
-<span class="source-line-no">038</span><span id="line-38">import org.apache.hadoop.hbase.regionserver.HRegion;</span>
-<span class="source-line-no">039</span><span id="line-39">import org.apache.yetus.audience.InterfaceAudience;</span>
-<span class="source-line-no">040</span><span id="line-40">import org.slf4j.Logger;</span>
-<span class="source-line-no">041</span><span id="line-41">import org.slf4j.LoggerFactory;</span>
-<span class="source-line-no">042</span><span id="line-42"></span>
-<span class="source-line-no">043</span><span id="line-43">import org.apache.hbase.thirdparty.com.google.common.util.concurrent.ThreadFactoryBuilder;</span>
-<span class="source-line-no">044</span><span id="line-44"></span>
-<span class="source-line-no">045</span><span id="line-45">/**</span>
-<span class="source-line-no">046</span><span id="line-46"> * Utility methods for interacting with the regions.</span>
-<span class="source-line-no">047</span><span id="line-47"> */</span>
-<span class="source-line-no">048</span><span id="line-48">@InterfaceAudience.Private</span>
-<span class="source-line-no">049</span><span id="line-49">public abstract class ModifyRegionUtils {</span>
-<span class="source-line-no">050</span><span id="line-50"> private static final Logger LOG = LoggerFactory.getLogger(ModifyRegionUtils.class);</span>
-<span class="source-line-no">051</span><span id="line-51"></span>
-<span class="source-line-no">052</span><span id="line-52"> private ModifyRegionUtils() {</span>
-<span class="source-line-no">053</span><span id="line-53"> }</span>
-<span class="source-line-no">054</span><span id="line-54"></span>
-<span class="source-line-no">055</span><span id="line-55"> public interface RegionFillTask {</span>
-<span class="source-line-no">056</span><span id="line-56"> void fillRegion(final HRegion region) throws IOException;</span>
-<span class="source-line-no">057</span><span id="line-57"> }</span>
-<span class="source-line-no">058</span><span id="line-58"></span>
-<span class="source-line-no">059</span><span id="line-59"> public interface RegionEditTask {</span>
-<span class="source-line-no">060</span><span id="line-60"> void editRegion(final RegionInfo region) throws IOException;</span>
-<span class="source-line-no">061</span><span id="line-61"> }</span>
-<span class="source-line-no">062</span><span id="line-62"></span>
-<span class="source-line-no">063</span><span id="line-63"> public static RegionInfo[] createRegionInfos(TableDescriptor tableDescriptor,</span>
-<span class="source-line-no">064</span><span id="line-64"> byte[][] splitKeys) {</span>
-<span class="source-line-no">065</span><span id="line-65"> long regionId = EnvironmentEdgeManager.currentTime();</span>
-<span class="source-line-no">066</span><span id="line-66"> RegionInfo[] hRegionInfos = null;</span>
-<span class="source-line-no">067</span><span id="line-67"> if (splitKeys == null || splitKeys.length == 0) {</span>
-<span class="source-line-no">068</span><span id="line-68"> hRegionInfos = new RegionInfo[] { RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
-<span class="source-line-no">069</span><span id="line-69"> .setStartKey(null).setEndKey(null).setSplit(false).setRegionId(regionId).build() };</span>
-<span class="source-line-no">070</span><span id="line-70"> } else {</span>
-<span class="source-line-no">071</span><span id="line-71"> int numRegions = splitKeys.length + 1;</span>
-<span class="source-line-no">072</span><span id="line-72"> hRegionInfos = new RegionInfo[numRegions];</span>
-<span class="source-line-no">073</span><span id="line-73"> byte[] startKey = null;</span>
-<span class="source-line-no">074</span><span id="line-74"> byte[] endKey = null;</span>
-<span class="source-line-no">075</span><span id="line-75"> for (int i = 0; i < numRegions; i++) {</span>
-<span class="source-line-no">076</span><span id="line-76"> endKey = (i == splitKeys.length) ? null : splitKeys[i];</span>
-<span class="source-line-no">077</span><span id="line-77"> hRegionInfos[i] = RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
-<span class="source-line-no">078</span><span id="line-78"> .setStartKey(startKey).setEndKey(endKey).setSplit(false).setRegionId(regionId).build();</span>
-<span class="source-line-no">079</span><span id="line-79"> startKey = endKey;</span>
-<span class="source-line-no">080</span><span id="line-80"> }</span>
-<span class="source-line-no">081</span><span id="line-81"> }</span>
-<span class="source-line-no">082</span><span id="line-82"> return hRegionInfos;</span>
-<span class="source-line-no">083</span><span id="line-83"> }</span>
-<span class="source-line-no">084</span><span id="line-84"></span>
-<span class="source-line-no">085</span><span id="line-85"> /**</span>
-<span class="source-line-no">086</span><span id="line-86"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
-<span class="source-line-no">087</span><span id="line-87"> * to hbase:meta after this operation.</span>
-<span class="source-line-no">088</span><span id="line-88"> * @param env {@link MasterProcedureEnv}</span>
-<span class="source-line-no">089</span><span id="line-89"> * @param rootDir Root directory for HBase instance</span>
-<span class="source-line-no">090</span><span id="line-90"> * @param tableDescriptor description of the table</span>
-<span class="source-line-no">091</span><span id="line-91"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
-<span class="source-line-no">092</span><span id="line-92"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
+<span class="source-line-no">024</span><span id="line-24">import java.util.HashSet;</span>
+<span class="source-line-no">025</span><span id="line-25">import java.util.List;</span>
+<span class="source-line-no">026</span><span id="line-26">import java.util.Objects;</span>
+<span class="source-line-no">027</span><span id="line-27">import java.util.Set;</span>
+<span class="source-line-no">028</span><span id="line-28">import java.util.concurrent.Callable;</span>
+<span class="source-line-no">029</span><span id="line-29">import java.util.concurrent.CompletionService;</span>
+<span class="source-line-no">030</span><span id="line-30">import java.util.concurrent.ExecutionException;</span>
+<span class="source-line-no">031</span><span id="line-31">import java.util.concurrent.ExecutorCompletionService;</span>
+<span class="source-line-no">032</span><span id="line-32">import java.util.concurrent.ThreadPoolExecutor;</span>
+<span class="source-line-no">033</span><span id="line-33">import java.util.concurrent.TimeUnit;</span>
+<span class="source-line-no">034</span><span id="line-34">import org.apache.hadoop.conf.Configuration;</span>
+<span class="source-line-no">035</span><span id="line-35">import org.apache.hadoop.fs.Path;</span>
+<span class="source-line-no">036</span><span id="line-36">import org.apache.hadoop.hbase.DoNotRetryIOException;</span>
+<span class="source-line-no">037</span><span id="line-37">import org.apache.hadoop.hbase.HConstants;</span>
+<span class="source-line-no">038</span><span id="line-38">import org.apache.hadoop.hbase.client.RegionInfo;</span>
+<span class="source-line-no">039</span><span id="line-39">import org.apache.hadoop.hbase.client.RegionInfoBuilder;</span>
+<span class="source-line-no">040</span><span id="line-40">import org.apache.hadoop.hbase.client.TableDescriptor;</span>
+<span class="source-line-no">041</span><span id="line-41">import org.apache.hadoop.hbase.master.assignment.RegionStates;</span>
+<span class="source-line-no">042</span><span id="line-42">import org.apache.hadoop.hbase.master.procedure.MasterProcedureEnv;</span>
+<span class="source-line-no">043</span><span id="line-43">import org.apache.hadoop.hbase.regionserver.HRegion;</span>
+<span class="source-line-no">044</span><span id="line-44">import org.apache.yetus.audience.InterfaceAudience;</span>
+<span class="source-line-no">045</span><span id="line-45">import org.slf4j.Logger;</span>
+<span class="source-line-no">046</span><span id="line-46">import org.slf4j.LoggerFactory;</span>
+<span class="source-line-no">047</span><span id="line-47"></span>
+<span class="source-line-no">048</span><span id="line-48">import org.apache.hbase.thirdparty.com.google.common.util.concurrent.ThreadFactoryBuilder;</span>
+<span class="source-line-no">049</span><span id="line-49"></span>
+<span class="source-line-no">050</span><span id="line-50">/**</span>
+<span class="source-line-no">051</span><span id="line-51"> * Utility methods for interacting with the regions.</span>
+<span class="source-line-no">052</span><span id="line-52"> */</span>
+<span class="source-line-no">053</span><span id="line-53">@InterfaceAudience.Private</span>
+<span class="source-line-no">054</span><span id="line-54">public abstract class ModifyRegionUtils {</span>
+<span class="source-line-no">055</span><span id="line-55"> private static final Logger LOG = LoggerFactory.getLogger(ModifyRegionUtils.class);</span>
+<span class="source-line-no">056</span><span id="line-56"></span>
+<span class="source-line-no">057</span><span id="line-57"> private ModifyRegionUtils() {</span>
+<span class="source-line-no">058</span><span id="line-58"> }</span>
+<span class="source-line-no">059</span><span id="line-59"></span>
+<span class="source-line-no">060</span><span id="line-60"> public interface RegionFillTask {</span>
+<span class="source-line-no">061</span><span id="line-61"> void fillRegion(final HRegion region) throws IOException;</span>
+<span class="source-line-no">062</span><span id="line-62"> }</span>
+<span class="source-line-no">063</span><span id="line-63"></span>
+<span class="source-line-no">064</span><span id="line-64"> public interface RegionEditTask {</span>
+<span class="source-line-no">065</span><span id="line-65"> void editRegion(final RegionInfo region) throws IOException;</span>
+<span class="source-line-no">066</span><span id="line-66"> }</span>
+<span class="source-line-no">067</span><span id="line-67"></span>
+<span class="source-line-no">068</span><span id="line-68"> public static RegionInfo[] createRegionInfos(TableDescriptor tableDescriptor,</span>
+<span class="source-line-no">069</span><span id="line-69"> byte[][] splitKeys) {</span>
+<span class="source-line-no">070</span><span id="line-70"> long regionId = EnvironmentEdgeManager.currentTime();</span>
+<span class="source-line-no">071</span><span id="line-71"> RegionInfo[] hRegionInfos = null;</span>
+<span class="source-line-no">072</span><span id="line-72"> if (splitKeys == null || splitKeys.length == 0) {</span>
+<span class="source-line-no">073</span><span id="line-73"> hRegionInfos = new RegionInfo[] { RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
+<span class="source-line-no">074</span><span id="line-74"> .setStartKey(null).setEndKey(null).setSplit(false).setRegionId(regionId).build() };</span>
+<span class="source-line-no">075</span><span id="line-75"> } else {</span>
+<span class="source-line-no">076</span><span id="line-76"> int numRegions = splitKeys.length + 1;</span>
+<span class="source-line-no">077</span><span id="line-77"> hRegionInfos = new RegionInfo[numRegions];</span>
+<span class="source-line-no">078</span><span id="line-78"> byte[] startKey = null;</span>
+<span class="source-line-no">079</span><span id="line-79"> byte[] endKey = null;</span>
+<span class="source-line-no">080</span><span id="line-80"> for (int i = 0; i < numRegions; i++) {</span>
+<span class="source-line-no">081</span><span id="line-81"> endKey = (i == splitKeys.length) ? null : splitKeys[i];</span>
+<span class="source-line-no">082</span><span id="line-82"> hRegionInfos[i] = RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
+<span class="source-line-no">083</span><span id="line-83"> .setStartKey(startKey).setEndKey(endKey).setSplit(false).setRegionId(regionId).build();</span>
+<span class="source-line-no">084</span><span id="line-84"> startKey = endKey;</span>
+<span class="source-line-no">085</span><span id="line-85"> }</span>
+<span class="source-line-no">086</span><span id="line-86"> }</span>
+<span class="source-line-no">087</span><span id="line-87"> return hRegionInfos;</span>
+<span class="source-line-no">088</span><span id="line-88"> }</span>
+<span class="source-line-no">089</span><span id="line-89"></span>
+<span class="source-line-no">090</span><span id="line-90"> /**</span>
+<span class="source-line-no">091</span><span id="line-91"> * Checks candidate regions for encoded\-name collisions. Ensures there are no duplicates in the</span>
+<span class="source-line-no">092</span><span id="line-92"> * input and no conflicts with existing region states.</span>
<span class="source-line-no">093</span><span id="line-93"> */</span>
-<span class="source-line-no">094</span><span id="line-94"> public static List<RegionInfo> createRegions(final MasterProcedureEnv env, final Path rootDir,</span>
-<span class="source-line-no">095</span><span id="line-95"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
-<span class="source-line-no">096</span><span id="line-96"> throws IOException {</span>
-<span class="source-line-no">097</span><span id="line-97"> if (newRegions == null) return null;</span>
-<span class="source-line-no">098</span><span id="line-98"> int regionNumber = newRegions.length;</span>
-<span class="source-line-no">099</span><span id="line-99"> ThreadPoolExecutor exec = getRegionOpenAndInitThreadPool(env.getMasterConfiguration(),</span>
-<span class="source-line-no">100</span><span id="line-100"> "RegionOpenAndInit-" + tableDescriptor.getTableName(), regionNumber);</span>
-<span class="source-line-no">101</span><span id="line-101"> try {</span>
-<span class="source-line-no">102</span><span id="line-102"> return createRegions(exec, env.getMasterConfiguration(), env, rootDir, tableDescriptor,</span>
-<span class="source-line-no">103</span><span id="line-103"> newRegions, task);</span>
-<span class="source-line-no">104</span><span id="line-104"> } finally {</span>
-<span class="source-line-no">105</span><span id="line-105"> exec.shutdownNow();</span>
-<span class="source-line-no">106</span><span id="line-106"> }</span>
-<span class="source-line-no">107</span><span id="line-107"> }</span>
-<span class="source-line-no">108</span><span id="line-108"></span>
-<span class="source-line-no">109</span><span id="line-109"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
-<span class="source-line-no">110</span><span id="line-110"> final Configuration conf, final Path rootDir, final TableDescriptor tableDescriptor,</span>
-<span class="source-line-no">111</span><span id="line-111"> final RegionInfo[] newRegions, final RegionFillTask task) throws IOException {</span>
-<span class="source-line-no">112</span><span id="line-112"> return createRegions(exec, conf, null, rootDir, tableDescriptor, newRegions, task);</span>
-<span class="source-line-no">113</span><span id="line-113"> }</span>
-<span class="source-line-no">114</span><span id="line-114"></span>
-<span class="source-line-no">115</span><span id="line-115"> /**</span>
-<span class="source-line-no">116</span><span id="line-116"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
-<span class="source-line-no">117</span><span id="line-117"> * to hbase:meta after this operation.</span>
-<span class="source-line-no">118</span><span id="line-118"> * @param exec Thread Pool Executor</span>
-<span class="source-line-no">119</span><span id="line-119"> * @param conf {@link Configuration}</span>
-<span class="source-line-no">120</span><span id="line-120"> * @param rootDir Root directory for HBase instance</span>
-<span class="source-line-no">121</span><span id="line-121"> * @param tableDescriptor description of the table</span>
-<span class="source-line-no">122</span><span id="line-122"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
-<span class="source-line-no">123</span><span id="line-123"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
-<span class="source-line-no">124</span><span id="line-124"> */</span>
-<span class="source-line-no">125</span><span id="line-125"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
-<span class="source-line-no">126</span><span id="line-126"> final Configuration conf, final MasterProcedureEnv env, final Path rootDir,</span>
-<span class="source-line-no">127</span><span id="line-127"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
-<span class="source-line-no">128</span><span id="line-128"> throws IOException {</span>
-<span class="source-line-no">129</span><span id="line-129"> if (newRegions == null) return null;</span>
-<span class="source-line-no">130</span><span id="line-130"> int regionNumber = newRegions.length;</span>
-<span class="source-line-no">131</span><span id="line-131"> CompletionService<RegionInfo> completionService = new ExecutorCompletionService<>(exec);</span>
-<span class="source-line-no">132</span><span id="line-132"> List<RegionInfo> regionInfos = new ArrayList<>();</span>
-<span class="source-line-no">133</span><span id="line-133"> for (final RegionInfo newRegion : newRegions) {</span>
-<span class="source-line-no">134</span><span id="line-134"> completionService.submit(new Callable<RegionInfo>() {</span>
-<span class="source-line-no">135</span><span id="line-135"> @Override</span>
-<span class="source-line-no">136</span><span id="line-136"> public RegionInfo call() throws IOException {</span>
-<span class="source-line-no">137</span><span id="line-137"> return createRegion(conf, env, rootDir, tableDescriptor, newRegion, task);</span>
-<span class="source-line-no">138</span><span id="line-138"> }</span>
-<span class="source-line-no">139</span><span id="line-139"> });</span>
-<span class="source-line-no">140</span><span id="line-140"> }</span>
-<span class="source-line-no">141</span><span id="line-141"> try {</span>
-<span class="source-line-no">142</span><span id="line-142"> // wait for all regions to finish creation</span>
-<span class="source-line-no">143</span><span id="line-143"> for (int i = 0; i < regionNumber; i++) {</span>
-<span class="source-line-no">144</span><span id="line-144"> regionInfos.add(completionService.take().get());</span>
-<span class="source-line-no">145</span><span id="line-145"> }</span>
-<span class="source-line-no">146</span><span id="line-146"> } catch (InterruptedException e) {</span>
-<span class="source-line-no">147</span><span id="line-147"> LOG.error("Caught " + e + " during region creation");</span>
-<span class="source-line-no">148</span><span id="line-148"> throw new InterruptedIOException(e.getMessage());</span>
-<span class="source-line-no">149</span><span id="line-149"> } catch (ExecutionException e) {</span>
-<span class="source-line-no">150</span><span id="line-150"> throw new IOException(e);</span>
-<span class="source-line-no">151</span><span id="line-151"> }</span>
-<span class="source-line-no">152</span><span id="line-152"> return regionInfos;</span>
-<span class="source-line-no">153</span><span id="line-153"> }</span>
-<span class="source-line-no">154</span><span id="line-154"></span>
-<span class="source-line-no">155</span><span id="line-155"> /**</span>
-<span class="source-line-no">156</span><span id="line-156"> * Create new set of regions on the specified file-system.</span>
-<span class="source-line-no">157</span><span id="line-157"> * @param conf {@link Configuration}</span>
-<span class="source-line-no">158</span><span id="line-158"> * @param rootDir Root directory for HBase instance</span>
-<span class="source-line-no">159</span><span id="line-159"> * @param tableDescriptor description of the table</span>
-<span class="source-line-no">160</span><span id="line-160"> * @param newRegion {@link RegionInfo} that describes the region to create</span>
-<span class="source-line-no">161</span><span id="line-161"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
-<span class="source-line-no">162</span><span id="line-162"> */</span>
-<span class="source-line-no">163</span><span id="line-163"> public static RegionInfo createRegion(final Configuration conf, final MasterProcedureEnv env,</span>
-<span class="source-line-no">164</span><span id="line-164"> final Path rootDir, final TableDescriptor tableDescriptor, final RegionInfo newRegion,</span>
-<span class="source-line-no">165</span><span id="line-165"> final RegionFillTask task) throws IOException {</span>
-<span class="source-line-no">166</span><span id="line-166"> // 1. Create HRegion</span>
-<span class="source-line-no">167</span><span id="line-167"> // The WAL subsystem will use the default rootDir rather than the passed in rootDir</span>
-<span class="source-line-no">168</span><span id="line-168"> // unless I pass along via the conf.</span>
-<span class="source-line-no">169</span><span id="line-169"> Configuration confForWAL = new Configuration(conf);</span>
-<span class="source-line-no">170</span><span id="line-170"> confForWAL.set(HConstants.HBASE_DIR, rootDir.toString());</span>
-<span class="source-line-no">171</span><span id="line-171"> HRegion region = HRegion.createHRegion(newRegion, rootDir, conf, tableDescriptor, null, false,</span>
-<span class="source-line-no">172</span><span id="line-172"> null, env == null ? null : env.getMasterServices());</span>
-<span class="source-line-no">173</span><span id="line-173"> try {</span>
-<span class="source-line-no">174</span><span id="line-174"> // 2. Custom user code to interact with the created region</span>
-<span class="source-line-no">175</span><span id="line-175"> if (task != null) {</span>
-<span class="source-line-no">176</span><span id="line-176"> task.fillRegion(region);</span>
-<span class="source-line-no">177</span><span id="line-177"> }</span>
-<span class="source-line-no">178</span><span id="line-178"> } finally {</span>
-<span class="source-line-no">179</span><span id="line-179"> // 3. Close the new region to flush to disk. Close log file too.</span>
-<span class="source-line-no">180</span><span id="line-180"> region.close(false, true);</span>
-<span class="source-line-no">181</span><span id="line-181"> }</span>
-<span class="source-line-no">182</span><span id="line-182"> return region.getRegionInfo();</span>
-<span class="source-line-no">183</span><span id="line-183"> }</span>
-<span class="source-line-no">184</span><span id="line-184"></span>
-<span class="source-line-no">185</span><span id="line-185"> /**</span>
-<span class="source-line-no">186</span><span id="line-186"> * Execute the task on the specified set of regions.</span>
-<span class="source-line-no">187</span><span id="line-187"> * @param exec Thread Pool Executor</span>
-<span class="source-line-no">188</span><span id="line-188"> * @param regions {@link RegionInfo} that describes the regions to edit</span>
-<span class="source-line-no">189</span><span id="line-189"> * @param task {@link RegionFillTask} custom code to edit the region</span>
+<span class="source-line-no">094</span><span id="line-94"> public static void checkForEncodedNameCollisions(final Collection<RegionInfo> candidates,</span>
+<span class="source-line-no">095</span><span id="line-95"> final RegionStates regionStates) throws IOException {</span>
+<span class="source-line-no">096</span><span id="line-96"> if (candidates == null || candidates.isEmpty()) {</span>
+<span class="source-line-no">097</span><span id="line-97"> return;</span>
+<span class="source-line-no">098</span><span id="line-98"> }</span>
+<span class="source-line-no">099</span><span id="line-99"> Objects.requireNonNull(regionStates, "regionStates is null");</span>
+<span class="source-line-no">100</span><span id="line-100"> Set<String> candidateNames = new HashSet<>();</span>
+<span class="source-line-no">101</span><span id="line-101"> for (RegionInfo ri : candidates) {</span>
+<span class="source-line-no">102</span><span id="line-102"> String encoded = ri.getEncodedName();</span>
+<span class="source-line-no">103</span><span id="line-103"> if (</span>
+<span class="source-line-no">104</span><span id="line-104"> !candidateNames.add(encoded)</span>
+<span class="source-line-no">105</span><span id="line-105"> || regionStates.getRegionStateNodeFromEncodedRegionName(encoded) != null</span>
+<span class="source-line-no">106</span><span id="line-106"> ) {</span>
+<span class="source-line-no">107</span><span id="line-107"> throw new DoNotRetryIOException("Encoded region name collision detected: '" + encoded</span>
+<span class="source-line-no">108</span><span id="line-108"> + "' for table " + ri.getTable() + ". Refusing to proceed.");</span>
+<span class="source-line-no">109</span><span id="line-109"> }</span>
+<span class="source-line-no">110</span><span id="line-110"> }</span>
+<span class="source-line-no">111</span><span id="line-111"> }</span>
+<span class="source-line-no">112</span><span id="line-112"></span>
+<span class="source-line-no">113</span><span id="line-113"> /**</span>
+<span class="source-line-no">114</span><span id="line-114"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
+<span class="source-line-no">115</span><span id="line-115"> * to hbase:meta after this operation.</span>
+<span class="source-line-no">116</span><span id="line-116"> * @param env {@link MasterProcedureEnv}</span>
+<span class="source-line-no">117</span><span id="line-117"> * @param rootDir Root directory for HBase instance</span>
+<span class="source-line-no">118</span><span id="line-118"> * @param tableDescriptor description of the table</span>
+<span class="source-line-no">119</span><span id="line-119"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
+<span class="source-line-no">120</span><span id="line-120"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
+<span class="source-line-no">121</span><span id="line-121"> */</span>
+<span class="source-line-no">122</span><span id="line-122"> public static List<RegionInfo> createRegions(final MasterProcedureEnv env, final Path rootDir,</span>
+<span class="source-line-no">123</span><span id="line-123"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
+<span class="source-line-no">124</span><span id="line-124"> throws IOException {</span>
+<span class="source-line-no">125</span><span id="line-125"> if (newRegions == null) return null;</span>
+<span class="source-line-no">126</span><span id="line-126"> int regionNumber = newRegions.length;</span>
+<span class="source-line-no">127</span><span id="line-127"> ThreadPoolExecutor exec = getRegionOpenAndInitThreadPool(env.getMasterConfiguration(),</span>
+<span class="source-line-no">128</span><span id="line-128"> "RegionOpenAndInit-" + tableDescriptor.getTableName(), regionNumber);</span>
+<span class="source-line-no">129</span><span id="line-129"> try {</span>
+<span class="source-line-no">130</span><span id="line-130"> return createRegions(exec, env.getMasterConfiguration(), env, rootDir, tableDescriptor,</span>
+<span class="source-line-no">131</span><span id="line-131"> newRegions, task);</span>
+<span class="source-line-no">132</span><span id="line-132"> } finally {</span>
+<span class="source-line-no">133</span><span id="line-133"> exec.shutdownNow();</span>
+<span class="source-line-no">134</span><span id="line-134"> }</span>
+<span class="source-line-no">135</span><span id="line-135"> }</span>
+<span class="source-line-no">136</span><span id="line-136"></span>
+<span class="source-line-no">137</span><span id="line-137"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
+<span class="source-line-no">138</span><span id="line-138"> final Configuration conf, final Path rootDir, final TableDescriptor tableDescriptor,</span>
+<span class="source-line-no">139</span><span id="line-139"> final RegionInfo[] newRegions, final RegionFillTask task) throws IOException {</span>
+<span class="source-line-no">140</span><span id="line-140"> return createRegions(exec, conf, null, rootDir, tableDescriptor, newRegions, task);</span>
+<span class="source-line-no">141</span><span id="line-141"> }</span>
+<span class="source-line-no">142</span><span id="line-142"></span>
+<span class="source-line-no">143</span><span id="line-143"> /**</span>
+<span class="source-line-no">144</span><span id="line-144"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
+<span class="source-line-no">145</span><span id="line-145"> * to hbase:meta after this operation.</span>
+<span class="source-line-no">146</span><span id="line-146"> * @param exec Thread Pool Executor</span>
+<span class="source-line-no">147</span><span id="line-147"> * @param conf {@link Configuration}</span>
+<span class="source-line-no">148</span><span id="line-148"> * @param rootDir Root directory for HBase instance</span>
+<span class="source-line-no">149</span><span id="line-149"> * @param tableDescriptor description of the table</span>
+<span class="source-line-no">150</span><span id="line-150"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
+<span class="source-line-no">151</span><span id="line-151"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
+<span class="source-line-no">152</span><span id="line-152"> */</span>
+<span class="source-line-no">153</span><span id="line-153"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
+<span class="source-line-no">154</span><span id="line-154"> final Configuration conf, final MasterProcedureEnv env, final Path rootDir,</span>
+<span class="source-line-no">155</span><span id="line-155"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
+<span class="source-line-no">156</span><span id="line-156"> throws IOException {</span>
+<span class="source-line-no">157</span><span id="line-157"> if (newRegions == null) return null;</span>
+<span class="source-line-no">158</span><span id="line-158"> int regionNumber = newRegions.length;</span>
+<span class="source-line-no">159</span><span id="line-159"> CompletionService<RegionInfo> completionService = new ExecutorCompletionService<>(exec);</span>
+<span class="source-line-no">160</span><span id="line-160"> List<RegionInfo> regionInfos = new ArrayList<>();</span>
+<span class="source-line-no">161</span><span id="line-161"> for (final RegionInfo newRegion : newRegions) {</span>
+<span class="source-line-no">162</span><span id="line-162"> completionService.submit(new Callable<RegionInfo>() {</span>
+<span class="source-line-no">163</span><span id="line-163"> @Override</span>
+<span class="source-line-no">164</span><span id="line-164"> public RegionInfo call() throws IOException {</span>
+<span class="source-line-no">165</span><span id="line-165"> return createRegion(conf, env, rootDir, tableDescriptor, newRegion, task);</span>
+<span class="source-line-no">166</span><span id="line-166"> }</span>
+<span class="source-line-no">167</span><span id="line-167"> });</span>
+<span class="source-line-no">168</span><span id="line-168"> }</span>
+<span class="source-line-no">169</span><span id="line-169"> try {</span>
+<span class="source-line-no">170</span><span id="line-170"> // wait for all regions to finish creation</span>
+<span class="source-line-no">171</span><span id="line-171"> for (int i = 0; i < regionNumber; i++) {</span>
+<span class="source-line-no">172</span><span id="line-172"> regionInfos.add(completionService.take().get());</span>
+<span class="source-line-no">173</span><span id="line-173"> }</span>
+<span class="source-line-no">174</span><span id="line-174"> } catch (InterruptedException e) {</span>
+<span class="source-line-no">175</span><span id="line-175"> LOG.error("Caught " + e + " during region creation");</span>
+<span class="source-line-no">176</span><span id="line-176"> throw new InterruptedIOException(e.getMessage());</span>
+<span class="source-line-no">177</span><span id="line-177"> } catch (ExecutionException e) {</span>
+<span class="source-line-no">178</span><span id="line-178"> throw new IOException(e);</span>
+<span class="source-line-no">179</span><span id="line-179"> }</span>
+<span class="source-line-no">180</span><span id="line-180"> return regionInfos;</span>
+<span class="source-line-no">181</span><span id="line-181"> }</span>
+<span class="source-line-no">182</span><span id="line-182"></span>
+<span class="source-line-no">183</span><span id="line-183"> /**</span>
+<span class="source-line-no">184</span><span id="line-184"> * Create new set of regions on the specified file-system.</span>
+<span class="source-line-no">185</span><span id="line-185"> * @param conf {@link Configuration}</span>
+<span class="source-line-no">186</span><span id="line-186"> * @param rootDir Root directory for HBase instance</span>
+<span class="source-line-no">187</span><span id="line-187"> * @param tableDescriptor description of the table</span>
+<span class="source-line-no">188</span><span id="line-188"> * @param newRegion {@link RegionInfo} that describes the region to create</span>
+<span class="source-line-no">189</span><span id="line-189"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
<span class="source-line-no">190</span><span id="line-190"> */</span>
-<span class="source-line-no">191</span><span id="line-191"> public static void editRegions(final ThreadPoolExecutor exec,</span>
-<span class="source-line-no">192</span><span id="line-192"> final Collection<RegionInfo> regions, final RegionEditTask task) throws IOException {</span>
-<span class="source-line-no">193</span><span id="line-193"> final ExecutorCompletionService<Void> completionService = new ExecutorCompletionService<>(exec);</span>
-<span class="source-line-no">194</span><span id="line-194"> for (final RegionInfo hri : regions) {</span>
-<span class="source-line-no">195</span><span id="line-195"> completionService.submit(new Callable<Void>() {</span>
-<span class="source-line-no">196</span><span id="line-196"> @Override</span>
-<span class="source-line-no">197</span><span id="line-197"> public Void call() throws IOException {</span>
-<span class="source-line-no">198</span><span id="line-198"> task.editRegion(hri);</span>
-<span class="source-line-no">199</span><span id="line-199"> return null;</span>
-<span class="source-line-no">200</span><span id="line-200"> }</span>
-<span class="source-line-no">201</span><span id="line-201"> });</span>
-<span class="source-line-no">202</span><span id="line-202"> }</span>
-<span class="source-line-no">203</span><span id="line-203"></span>
-<span class="source-line-no">204</span><span id="line-204"> try {</span>
-<span class="source-line-no">205</span><span id="line-205"> for (RegionInfo hri : regions) {</span>
-<span class="source-line-no">206</span><span id="line-206"> completionService.take().get();</span>
-<span class="source-line-no">207</span><span id="line-207"> }</span>
-<span class="source-line-no">208</span><span id="line-208"> } catch (InterruptedException e) {</span>
-<span class="source-line-no">209</span><span id="line-209"> throw new InterruptedIOException(e.getMessage());</span>
-<span class="source-line-no">210</span><span id="line-210"> } catch (ExecutionException e) {</span>
-<span class="source-line-no">211</span><span id="line-211"> throw new IOException(e.getCause());</span>
-<span class="source-line-no">212</span><span id="line-212"> }</span>
-<span class="source-line-no">213</span><span id="line-213"> }</span>
-<span class="source-line-no">214</span><span id="line-214"></span>
-<span class="source-line-no">215</span><span id="line-215"> /*</span>
-<span class="source-line-no">216</span><span id="line-216"> * used by createRegions() to get the thread pool executor based on the</span>
-<span class="source-line-no">217</span><span id="line-217"> * "hbase.hregion.open.and.init.threads.max" property.</span>
+<span class="source-line-no">191</span><span id="line-191"> public static RegionInfo createRegion(final Configuration conf, final MasterProcedureEnv env,</span>
+<span class="source-line-no">192</span><span id="line-192"> final Path rootDir, final TableDescriptor tableDescriptor, final RegionInfo newRegion,</span>
+<span class="source-line-no">193</span><span id="line-193"> final RegionFillTask task) throws IOException {</span>
+<span class="source-line-no">194</span><span id="line-194"> // 1. Create HRegion</span>
+<span class="source-line-no">195</span><span id="line-195"> // The WAL subsystem will use the default rootDir rather than the passed in rootDir</span>
+<span class="source-line-no">196</span><span id="line-196"> // unless I pass along via the conf.</span>
+<span class="source-line-no">197</span><span id="line-197"> Configuration confForWAL = new Configuration(conf);</span>
+<span class="source-line-no">198</span><span id="line-198"> confForWAL.set(HConstants.HBASE_DIR, rootDir.toString());</span>
+<span class="source-line-no">199</span><span id="line-199"> HRegion region = HRegion.createHRegion(newRegion, rootDir, conf, tableDescriptor, null, false,</span>
+<span class="source-line-no">200</span><span id="line-200"> null, env == null ? null : env.getMasterServices());</span>
+<span class="source-line-no">201</span><span id="line-201"> try {</span>
+<span class="source-line-no">202</span><span id="line-202"> // 2. Custom user code to interact with the created region</span>
+<span class="source-line-no">203</span><span id="line-203"> if (task != null) {</span>
+<span class="source-line-no">204</span><span id="line-204"> task.fillRegion(region);</span>
+<span class="source-line-no">205</span><span id="line-205"> }</span>
+<span class="source-line-no">206</span><span id="line-206"> } finally {</span>
+<span class="source-line-no">207</span><span id="line-207"> // 3. Close the new region to flush to disk. Close log file too.</span>
+<span class="source-line-no">208</span><span id="line-208"> region.close(false, true);</span>
+<span class="source-line-no">209</span><span id="line-209"> }</span>
+<span class="source-line-no">210</span><span id="line-210"> return region.getRegionInfo();</span>
+<span class="source-line-no">211</span><span id="line-211"> }</span>
+<span class="source-line-no">212</span><span id="line-212"></span>
+<span class="source-line-no">213</span><span id="line-213"> /**</span>
+<span class="source-line-no">214</span><span id="line-214"> * Execute the task on the specified set of regions.</span>
+<span class="source-line-no">215</span><span id="line-215"> * @param exec Thread Pool Executor</span>
+<span class="source-line-no">216</span><span id="line-216"> * @param regions {@link RegionInfo} that describes the regions to edit</span>
+<span class="source-line-no">217</span><span id="line-217"> * @param task {@link RegionFillTask} custom code to edit the region</span>
<span class="source-line-no">218</span><span id="line-218"> */</span>
-<span class="source-line-no">219</span><span id="line-219"> static ThreadPoolExecutor getRegionOpenAndInitThreadPool(final Configuration conf,</span>
-<span class="source-line-no">220</span><span id="line-220"> final String threadNamePrefix, int regionNumber) {</span>
-<span class="source-line-no">221</span><span id="line-221"> int maxThreads =</span>
-<span class="source-line-no">222</span><span id="line-222"> Math.min(regionNumber, conf.getInt("hbase.hregion.open.and.init.threads.max", 16));</span>
-<span class="source-line-no">223</span><span id="line-223"> ThreadPoolExecutor regionOpenAndInitThreadPool = Threads.getBoundedCachedThreadPool(maxThreads,</span>
-<span class="source-line-no">224</span><span id="line-224"> 30L, TimeUnit.SECONDS, new ThreadFactoryBuilder().setNameFormat(threadNamePrefix + "-pool-%d")</span>
-<span class="source-line-no">225</span><span id="line-225"> .setDaemon(true).setUncaughtExceptionHandler(Threads.LOGGING_EXCEPTION_HANDLER).build());</span>
-<span class="source-line-no">226</span><span id="line-226"> return regionOpenAndInitThreadPool;</span>
-<span class="source-line-no">227</span><span id="line-227"> }</span>
-<span class="source-line-no">228</span><span id="line-228">}</span>
+<span class="source-line-no">219</span><span id="line-219"> public static void editRegions(final ThreadPoolExecutor exec,</span>
+<span class="source-line-no">220</span><span id="line-220"> final Collection<RegionInfo> regions, final RegionEditTask task) throws IOException {</span>
+<span class="source-line-no">221</span><span id="line-221"> final ExecutorCompletionService<Void> completionService = new ExecutorCompletionService<>(exec);</span>
+<span class="source-line-no">222</span><span id="line-222"> for (final RegionInfo hri : regions) {</span>
+<span class="source-line-no">223</span><span id="line-223"> completionService.submit(new Callable<Void>() {</span>
+<span class="source-line-no">224</span><span id="line-224"> @Override</span>
+<span class="source-line-no">225</span><span id="line-225"> public Void call() throws IOException {</span>
+<span class="source-line-no">226</span><span id="line-226"> task.editRegion(hri);</span>
+<span class="source-line-no">227</span><span id="line-227"> return null;</span>
+<span class="source-line-no">228</span><span id="line-228"> }</span>
+<span class="source-line-no">229</span><span id="line-229"> });</span>
+<span class="source-line-no">230</span><span id="line-230"> }</span>
+<span class="source-line-no">231</span><span id="line-231"></span>
+<span class="source-line-no">232</span><span id="line-232"> try {</span>
+<span class="source-line-no">233</span><span id="line-233"> for (RegionInfo hri : regions) {</span>
+<span class="source-line-no">234</span><span id="line-234"> completionService.take().get();</span>
+<span class="source-line-no">235</span><span id="line-235"> }</span>
+<span class="source-line-no">236</span><span id="line-236"> } catch (InterruptedException e) {</span>
+<span class="source-line-no">237</span><span id="line-237"> throw new InterruptedIOException(e.getMessage());</span>
+<span class="source-line-no">238</span><span id="line-238"> } catch (ExecutionException e) {</span>
+<span class="source-line-no">239</span><span id="line-239"> throw new IOException(e.getCause());</span>
+<span class="source-line-no">240</span><span id="line-240"> }</span>
+<span class="source-line-no">241</span><span id="line-241"> }</span>
+<span class="source-line-no">242</span><span id="line-242"></span>
+<span class="source-line-no">243</span><span id="line-243"> /*</span>
+<span class="source-line-no">244</span><span id="line-244"> * used by createRegions() to get the thread pool executor based on the</span>
+<span class="source-line-no">245</span><span id="line-245"> * "hbase.hregion.open.and.init.threads.max" property.</span>
+<span class="source-line-no">246</span><span id="line-246"> */</span>
+<span class="source-line-no">247</span><span id="line-247"> static ThreadPoolExecutor getRegionOpenAndInitThreadPool(final Configuration conf,</span>
+<span class="source-line-no">248</span><span id="line-248"> final String threadNamePrefix, int regionNumber) {</span>
+<span class="source-line-no">249</span><span id="line-249"> int maxThreads =</span>
+<span class="source-line-no">250</span><span id="line-250"> Math.min(regionNumber, conf.getInt("hbase.hregion.open.and.init.threads.max", 16));</span>
+<span class="source-line-no">251</span><span id="line-251"> ThreadPoolExecutor regionOpenAndInitThreadPool = Threads.getBoundedCachedThreadPool(maxThreads,</span>
+<span class="source-line-no">252</span><span id="line-252"> 30L, TimeUnit.SECONDS, new ThreadFactoryBuilder().setNameFormat(threadNamePrefix + "-pool-%d")</span>
+<span class="source-line-no">253</span><span id="line-253"> .setDaemon(true).setUncaughtExceptionHandler(Threads.LOGGING_EXCEPTION_HANDLER).build());</span>
+<span class="source-line-no">254</span><span id="line-254"> return regionOpenAndInitThreadPool;</span>
+<span class="source-line-no">255</span><span id="line-255"> }</span>
+<span class="source-line-no">256</span><span id="line-256">}</span>
diff --git a/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.html b/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.html
index 9bb1e6ec8de..75f58d73478 100644
--- a/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.html
+++ b/apidocs/src-html/org/apache/hadoop/hbase/util/ModifyRegionUtils.html
@@ -34,211 +34,239 @@
<span class="source-line-no">021</span><span id="line-21">import java.io.InterruptedIOException;</span>
<span class="source-line-no">022</span><span id="line-22">import java.util.ArrayList;</span>
<span class="source-line-no">023</span><span id="line-23">import java.util.Collection;</span>
-<span class="source-line-no">024</span><span id="line-24">import java.util.List;</span>
-<span class="source-line-no">025</span><span id="line-25">import java.util.concurrent.Callable;</span>
-<span class="source-line-no">026</span><span id="line-26">import java.util.concurrent.CompletionService;</span>
-<span class="source-line-no">027</span><span id="line-27">import java.util.concurrent.ExecutionException;</span>
-<span class="source-line-no">028</span><span id="line-28">import java.util.concurrent.ExecutorCompletionService;</span>
-<span class="source-line-no">029</span><span id="line-29">import java.util.concurrent.ThreadPoolExecutor;</span>
-<span class="source-line-no">030</span><span id="line-30">import java.util.concurrent.TimeUnit;</span>
-<span class="source-line-no">031</span><span id="line-31">import org.apache.hadoop.conf.Configuration;</span>
-<span class="source-line-no">032</span><span id="line-32">import org.apache.hadoop.fs.Path;</span>
-<span class="source-line-no">033</span><span id="line-33">import org.apache.hadoop.hbase.HConstants;</span>
-<span class="source-line-no">034</span><span id="line-34">import org.apache.hadoop.hbase.client.RegionInfo;</span>
-<span class="source-line-no">035</span><span id="line-35">import org.apache.hadoop.hbase.client.RegionInfoBuilder;</span>
-<span class="source-line-no">036</span><span id="line-36">import org.apache.hadoop.hbase.client.TableDescriptor;</span>
-<span class="source-line-no">037</span><span id="line-37">import org.apache.hadoop.hbase.master.procedure.MasterProcedureEnv;</span>
-<span class="source-line-no">038</span><span id="line-38">import org.apache.hadoop.hbase.regionserver.HRegion;</span>
-<span class="source-line-no">039</span><span id="line-39">import org.apache.yetus.audience.InterfaceAudience;</span>
-<span class="source-line-no">040</span><span id="line-40">import org.slf4j.Logger;</span>
-<span class="source-line-no">041</span><span id="line-41">import org.slf4j.LoggerFactory;</span>
-<span class="source-line-no">042</span><span id="line-42"></span>
-<span class="source-line-no">043</span><span id="line-43">import org.apache.hbase.thirdparty.com.google.common.util.concurrent.ThreadFactoryBuilder;</span>
-<span class="source-line-no">044</span><span id="line-44"></span>
-<span class="source-line-no">045</span><span id="line-45">/**</span>
-<span class="source-line-no">046</span><span id="line-46"> * Utility methods for interacting with the regions.</span>
-<span class="source-line-no">047</span><span id="line-47"> */</span>
-<span class="source-line-no">048</span><span id="line-48">@InterfaceAudience.Private</span>
-<span class="source-line-no">049</span><span id="line-49">public abstract class ModifyRegionUtils {</span>
-<span class="source-line-no">050</span><span id="line-50"> private static final Logger LOG = LoggerFactory.getLogger(ModifyRegionUtils.class);</span>
-<span class="source-line-no">051</span><span id="line-51"></span>
-<span class="source-line-no">052</span><span id="line-52"> private ModifyRegionUtils() {</span>
-<span class="source-line-no">053</span><span id="line-53"> }</span>
-<span class="source-line-no">054</span><span id="line-54"></span>
-<span class="source-line-no">055</span><span id="line-55"> public interface RegionFillTask {</span>
-<span class="source-line-no">056</span><span id="line-56"> void fillRegion(final HRegion region) throws IOException;</span>
-<span class="source-line-no">057</span><span id="line-57"> }</span>
-<span class="source-line-no">058</span><span id="line-58"></span>
-<span class="source-line-no">059</span><span id="line-59"> public interface RegionEditTask {</span>
-<span class="source-line-no">060</span><span id="line-60"> void editRegion(final RegionInfo region) throws IOException;</span>
-<span class="source-line-no">061</span><span id="line-61"> }</span>
-<span class="source-line-no">062</span><span id="line-62"></span>
-<span class="source-line-no">063</span><span id="line-63"> public static RegionInfo[] createRegionInfos(TableDescriptor tableDescriptor,</span>
-<span class="source-line-no">064</span><span id="line-64"> byte[][] splitKeys) {</span>
-<span class="source-line-no">065</span><span id="line-65"> long regionId = EnvironmentEdgeManager.currentTime();</span>
-<span class="source-line-no">066</span><span id="line-66"> RegionInfo[] hRegionInfos = null;</span>
-<span class="source-line-no">067</span><span id="line-67"> if (splitKeys == null || splitKeys.length == 0) {</span>
-<span class="source-line-no">068</span><span id="line-68"> hRegionInfos = new RegionInfo[] { RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
-<span class="source-line-no">069</span><span id="line-69"> .setStartKey(null).setEndKey(null).setSplit(false).setRegionId(regionId).build() };</span>
-<span class="source-line-no">070</span><span id="line-70"> } else {</span>
-<span class="source-line-no">071</span><span id="line-71"> int numRegions = splitKeys.length + 1;</span>
-<span class="source-line-no">072</span><span id="line-72"> hRegionInfos = new RegionInfo[numRegions];</span>
-<span class="source-line-no">073</span><span id="line-73"> byte[] startKey = null;</span>
-<span class="source-line-no">074</span><span id="line-74"> byte[] endKey = null;</span>
-<span class="source-line-no">075</span><span id="line-75"> for (int i = 0; i < numRegions; i++) {</span>
-<span class="source-line-no">076</span><span id="line-76"> endKey = (i == splitKeys.length) ? null : splitKeys[i];</span>
-<span class="source-line-no">077</span><span id="line-77"> hRegionInfos[i] = RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
-<span class="source-line-no">078</span><span id="line-78"> .setStartKey(startKey).setEndKey(endKey).setSplit(false).setRegionId(regionId).build();</span>
-<span class="source-line-no">079</span><span id="line-79"> startKey = endKey;</span>
-<span class="source-line-no">080</span><span id="line-80"> }</span>
-<span class="source-line-no">081</span><span id="line-81"> }</span>
-<span class="source-line-no">082</span><span id="line-82"> return hRegionInfos;</span>
-<span class="source-line-no">083</span><span id="line-83"> }</span>
-<span class="source-line-no">084</span><span id="line-84"></span>
-<span class="source-line-no">085</span><span id="line-85"> /**</span>
-<span class="source-line-no">086</span><span id="line-86"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
-<span class="source-line-no">087</span><span id="line-87"> * to hbase:meta after this operation.</span>
-<span class="source-line-no">088</span><span id="line-88"> * @param env {@link MasterProcedureEnv}</span>
-<span class="source-line-no">089</span><span id="line-89"> * @param rootDir Root directory for HBase instance</span>
-<span class="source-line-no">090</span><span id="line-90"> * @param tableDescriptor description of the table</span>
-<span class="source-line-no">091</span><span id="line-91"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
-<span class="source-line-no">092</span><span id="line-92"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
+<span class="source-line-no">024</span><span id="line-24">import java.util.HashSet;</span>
+<span class="source-line-no">025</span><span id="line-25">import java.util.List;</span>
+<span class="source-line-no">026</span><span id="line-26">import java.util.Objects;</span>
+<span class="source-line-no">027</span><span id="line-27">import java.util.Set;</span>
+<span class="source-line-no">028</span><span id="line-28">import java.util.concurrent.Callable;</span>
+<span class="source-line-no">029</span><span id="line-29">import java.util.concurrent.CompletionService;</span>
+<span class="source-line-no">030</span><span id="line-30">import java.util.concurrent.ExecutionException;</span>
+<span class="source-line-no">031</span><span id="line-31">import java.util.concurrent.ExecutorCompletionService;</span>
+<span class="source-line-no">032</span><span id="line-32">import java.util.concurrent.ThreadPoolExecutor;</span>
+<span class="source-line-no">033</span><span id="line-33">import java.util.concurrent.TimeUnit;</span>
+<span class="source-line-no">034</span><span id="line-34">import org.apache.hadoop.conf.Configuration;</span>
+<span class="source-line-no">035</span><span id="line-35">import org.apache.hadoop.fs.Path;</span>
+<span class="source-line-no">036</span><span id="line-36">import org.apache.hadoop.hbase.DoNotRetryIOException;</span>
+<span class="source-line-no">037</span><span id="line-37">import org.apache.hadoop.hbase.HConstants;</span>
+<span class="source-line-no">038</span><span id="line-38">import org.apache.hadoop.hbase.client.RegionInfo;</span>
+<span class="source-line-no">039</span><span id="line-39">import org.apache.hadoop.hbase.client.RegionInfoBuilder;</span>
+<span class="source-line-no">040</span><span id="line-40">import org.apache.hadoop.hbase.client.TableDescriptor;</span>
+<span class="source-line-no">041</span><span id="line-41">import org.apache.hadoop.hbase.master.assignment.RegionStates;</span>
+<span class="source-line-no">042</span><span id="line-42">import org.apache.hadoop.hbase.master.procedure.MasterProcedureEnv;</span>
+<span class="source-line-no">043</span><span id="line-43">import org.apache.hadoop.hbase.regionserver.HRegion;</span>
+<span class="source-line-no">044</span><span id="line-44">import org.apache.yetus.audience.InterfaceAudience;</span>
+<span class="source-line-no">045</span><span id="line-45">import org.slf4j.Logger;</span>
+<span class="source-line-no">046</span><span id="line-46">import org.slf4j.LoggerFactory;</span>
+<span class="source-line-no">047</span><span id="line-47"></span>
+<span class="source-line-no">048</span><span id="line-48">import org.apache.hbase.thirdparty.com.google.common.util.concurrent.ThreadFactoryBuilder;</span>
+<span class="source-line-no">049</span><span id="line-49"></span>
+<span class="source-line-no">050</span><span id="line-50">/**</span>
+<span class="source-line-no">051</span><span id="line-51"> * Utility methods for interacting with the regions.</span>
+<span class="source-line-no">052</span><span id="line-52"> */</span>
+<span class="source-line-no">053</span><span id="line-53">@InterfaceAudience.Private</span>
+<span class="source-line-no">054</span><span id="line-54">public abstract class ModifyRegionUtils {</span>
+<span class="source-line-no">055</span><span id="line-55"> private static final Logger LOG = LoggerFactory.getLogger(ModifyRegionUtils.class);</span>
+<span class="source-line-no">056</span><span id="line-56"></span>
+<span class="source-line-no">057</span><span id="line-57"> private ModifyRegionUtils() {</span>
+<span class="source-line-no">058</span><span id="line-58"> }</span>
+<span class="source-line-no">059</span><span id="line-59"></span>
+<span class="source-line-no">060</span><span id="line-60"> public interface RegionFillTask {</span>
+<span class="source-line-no">061</span><span id="line-61"> void fillRegion(final HRegion region) throws IOException;</span>
+<span class="source-line-no">062</span><span id="line-62"> }</span>
+<span class="source-line-no">063</span><span id="line-63"></span>
+<span class="source-line-no">064</span><span id="line-64"> public interface RegionEditTask {</span>
+<span class="source-line-no">065</span><span id="line-65"> void editRegion(final RegionInfo region) throws IOException;</span>
+<span class="source-line-no">066</span><span id="line-66"> }</span>
+<span class="source-line-no">067</span><span id="line-67"></span>
+<span class="source-line-no">068</span><span id="line-68"> public static RegionInfo[] createRegionInfos(TableDescriptor tableDescriptor,</span>
+<span class="source-line-no">069</span><span id="line-69"> byte[][] splitKeys) {</span>
+<span class="source-line-no">070</span><span id="line-70"> long regionId = EnvironmentEdgeManager.currentTime();</span>
+<span class="source-line-no">071</span><span id="line-71"> RegionInfo[] hRegionInfos = null;</span>
+<span class="source-line-no">072</span><span id="line-72"> if (splitKeys == null || splitKeys.length == 0) {</span>
+<span class="source-line-no">073</span><span id="line-73"> hRegionInfos = new RegionInfo[] { RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
+<span class="source-line-no">074</span><span id="line-74"> .setStartKey(null).setEndKey(null).setSplit(false).setRegionId(regionId).build() };</span>
+<span class="source-line-no">075</span><span id="line-75"> } else {</span>
+<span class="source-line-no">076</span><span id="line-76"> int numRegions = splitKeys.length + 1;</span>
+<span class="source-line-no">077</span><span id="line-77"> hRegionInfos = new RegionInfo[numRegions];</span>
+<span class="source-line-no">078</span><span id="line-78"> byte[] startKey = null;</span>
+<span class="source-line-no">079</span><span id="line-79"> byte[] endKey = null;</span>
+<span class="source-line-no">080</span><span id="line-80"> for (int i = 0; i < numRegions; i++) {</span>
+<span class="source-line-no">081</span><span id="line-81"> endKey = (i == splitKeys.length) ? null : splitKeys[i];</span>
+<span class="source-line-no">082</span><span id="line-82"> hRegionInfos[i] = RegionInfoBuilder.newBuilder(tableDescriptor.getTableName())</span>
+<span class="source-line-no">083</span><span id="line-83"> .setStartKey(startKey).setEndKey(endKey).setSplit(false).setRegionId(regionId).build();</span>
+<span class="source-line-no">084</span><span id="line-84"> startKey = endKey;</span>
+<span class="source-line-no">085</span><span id="line-85"> }</span>
+<span class="source-line-no">086</span><span id="line-86"> }</span>
+<span class="source-line-no">087</span><span id="line-87"> return hRegionInfos;</span>
+<span class="source-line-no">088</span><span id="line-88"> }</span>
+<span class="source-line-no">089</span><span id="line-89"></span>
+<span class="source-line-no">090</span><span id="line-90"> /**</span>
+<span class="source-line-no">091</span><span id="line-91"> * Checks candidate regions for encoded\-name collisions. Ensures there are no duplicates in the</span>
+<span class="source-line-no">092</span><span id="line-92"> * input and no conflicts with existing region states.</span>
<span class="source-line-no">093</span><span id="line-93"> */</span>
-<span class="source-line-no">094</span><span id="line-94"> public static List<RegionInfo> createRegions(final MasterProcedureEnv env, final Path rootDir,</span>
-<span class="source-line-no">095</span><span id="line-95"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
-<span class="source-line-no">096</span><span id="line-96"> throws IOException {</span>
-<span class="source-line-no">097</span><span id="line-97"> if (newRegions == null) return null;</span>
-<span class="source-line-no">098</span><span id="line-98"> int regionNumber = newRegions.length;</span>
-<span class="source-line-no">099</span><span id="line-99"> ThreadPoolExecutor exec = getRegionOpenAndInitThreadPool(env.getMasterConfiguration(),</span>
-<span class="source-line-no">100</span><span id="line-100"> "RegionOpenAndInit-" + tableDescriptor.getTableName(), regionNumber);</span>
-<span class="source-line-no">101</span><span id="line-101"> try {</span>
-<span class="source-line-no">102</span><span id="line-102"> return createRegions(exec, env.getMasterConfiguration(), env, rootDir, tableDescriptor,</span>
-<span class="source-line-no">103</span><span id="line-103"> newRegions, task);</span>
-<span class="source-line-no">104</span><span id="line-104"> } finally {</span>
-<span class="source-line-no">105</span><span id="line-105"> exec.shutdownNow();</span>
-<span class="source-line-no">106</span><span id="line-106"> }</span>
-<span class="source-line-no">107</span><span id="line-107"> }</span>
-<span class="source-line-no">108</span><span id="line-108"></span>
-<span class="source-line-no">109</span><span id="line-109"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
-<span class="source-line-no">110</span><span id="line-110"> final Configuration conf, final Path rootDir, final TableDescriptor tableDescriptor,</span>
-<span class="source-line-no">111</span><span id="line-111"> final RegionInfo[] newRegions, final RegionFillTask task) throws IOException {</span>
-<span class="source-line-no">112</span><span id="line-112"> return createRegions(exec, conf, null, rootDir, tableDescriptor, newRegions, task);</span>
-<span class="source-line-no">113</span><span id="line-113"> }</span>
-<span class="source-line-no">114</span><span id="line-114"></span>
-<span class="source-line-no">115</span><span id="line-115"> /**</span>
-<span class="source-line-no">116</span><span id="line-116"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
-<span class="source-line-no">117</span><span id="line-117"> * to hbase:meta after this operation.</span>
-<span class="source-line-no">118</span><span id="line-118"> * @param exec Thread Pool Executor</span>
-<span class="source-line-no">119</span><span id="line-119"> * @param conf {@link Configuration}</span>
-<span class="source-line-no">120</span><span id="line-120"> * @param rootDir Root directory for HBase instance</span>
-<span class="source-line-no">121</span><span id="line-121"> * @param tableDescriptor description of the table</span>
-<span class="source-line-no">122</span><span id="line-122"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
-<span class="source-line-no">123</span><span id="line-123"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
-<span class="source-line-no">124</span><span id="line-124"> */</span>
-<span class="source-line-no">125</span><span id="line-125"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
-<span class="source-line-no">126</span><span id="line-126"> final Configuration conf, final MasterProcedureEnv env, final Path rootDir,</span>
-<span class="source-line-no">127</span><span id="line-127"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
-<span class="source-line-no">128</span><span id="line-128"> throws IOException {</span>
-<span class="source-line-no">129</span><span id="line-129"> if (newRegions == null) return null;</span>
-<span class="source-line-no">130</span><span id="line-130"> int regionNumber = newRegions.length;</span>
-<span class="source-line-no">131</span><span id="line-131"> CompletionService<RegionInfo> completionService = new ExecutorCompletionService<>(exec);</span>
-<span class="source-line-no">132</span><span id="line-132"> List<RegionInfo> regionInfos = new ArrayList<>();</span>
-<span class="source-line-no">133</span><span id="line-133"> for (final RegionInfo newRegion : newRegions) {</span>
-<span class="source-line-no">134</span><span id="line-134"> completionService.submit(new Callable<RegionInfo>() {</span>
-<span class="source-line-no">135</span><span id="line-135"> @Override</span>
-<span class="source-line-no">136</span><span id="line-136"> public RegionInfo call() throws IOException {</span>
-<span class="source-line-no">137</span><span id="line-137"> return createRegion(conf, env, rootDir, tableDescriptor, newRegion, task);</span>
-<span class="source-line-no">138</span><span id="line-138"> }</span>
-<span class="source-line-no">139</span><span id="line-139"> });</span>
-<span class="source-line-no">140</span><span id="line-140"> }</span>
-<span class="source-line-no">141</span><span id="line-141"> try {</span>
-<span class="source-line-no">142</span><span id="line-142"> // wait for all regions to finish creation</span>
-<span class="source-line-no">143</span><span id="line-143"> for (int i = 0; i < regionNumber; i++) {</span>
-<span class="source-line-no">144</span><span id="line-144"> regionInfos.add(completionService.take().get());</span>
-<span class="source-line-no">145</span><span id="line-145"> }</span>
-<span class="source-line-no">146</span><span id="line-146"> } catch (InterruptedException e) {</span>
-<span class="source-line-no">147</span><span id="line-147"> LOG.error("Caught " + e + " during region creation");</span>
-<span class="source-line-no">148</span><span id="line-148"> throw new InterruptedIOException(e.getMessage());</span>
-<span class="source-line-no">149</span><span id="line-149"> } catch (ExecutionException e) {</span>
-<span class="source-line-no">150</span><span id="line-150"> throw new IOException(e);</span>
-<span class="source-line-no">151</span><span id="line-151"> }</span>
-<span class="source-line-no">152</span><span id="line-152"> return regionInfos;</span>
-<span class="source-line-no">153</span><span id="line-153"> }</span>
-<span class="source-line-no">154</span><span id="line-154"></span>
-<span class="source-line-no">155</span><span id="line-155"> /**</span>
-<span class="source-line-no">156</span><span id="line-156"> * Create new set of regions on the specified file-system.</span>
-<span class="source-line-no">157</span><span id="line-157"> * @param conf {@link Configuration}</span>
-<span class="source-line-no">158</span><span id="line-158"> * @param rootDir Root directory for HBase instance</span>
-<span class="source-line-no">159</span><span id="line-159"> * @param tableDescriptor description of the table</span>
-<span class="source-line-no">160</span><span id="line-160"> * @param newRegion {@link RegionInfo} that describes the region to create</span>
-<span class="source-line-no">161</span><span id="line-161"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
-<span class="source-line-no">162</span><span id="line-162"> */</span>
-<span class="source-line-no">163</span><span id="line-163"> public static RegionInfo createRegion(final Configuration conf, final MasterProcedureEnv env,</span>
-<span class="source-line-no">164</span><span id="line-164"> final Path rootDir, final TableDescriptor tableDescriptor, final RegionInfo newRegion,</span>
-<span class="source-line-no">165</span><span id="line-165"> final RegionFillTask task) throws IOException {</span>
-<span class="source-line-no">166</span><span id="line-166"> // 1. Create HRegion</span>
-<span class="source-line-no">167</span><span id="line-167"> // The WAL subsystem will use the default rootDir rather than the passed in rootDir</span>
-<span class="source-line-no">168</span><span id="line-168"> // unless I pass along via the conf.</span>
-<span class="source-line-no">169</span><span id="line-169"> Configuration confForWAL = new Configuration(conf);</span>
-<span class="source-line-no">170</span><span id="line-170"> confForWAL.set(HConstants.HBASE_DIR, rootDir.toString());</span>
-<span class="source-line-no">171</span><span id="line-171"> HRegion region = HRegion.createHRegion(newRegion, rootDir, conf, tableDescriptor, null, false,</span>
-<span class="source-line-no">172</span><span id="line-172"> null, env == null ? null : env.getMasterServices());</span>
-<span class="source-line-no">173</span><span id="line-173"> try {</span>
-<span class="source-line-no">174</span><span id="line-174"> // 2. Custom user code to interact with the created region</span>
-<span class="source-line-no">175</span><span id="line-175"> if (task != null) {</span>
-<span class="source-line-no">176</span><span id="line-176"> task.fillRegion(region);</span>
-<span class="source-line-no">177</span><span id="line-177"> }</span>
-<span class="source-line-no">178</span><span id="line-178"> } finally {</span>
-<span class="source-line-no">179</span><span id="line-179"> // 3. Close the new region to flush to disk. Close log file too.</span>
-<span class="source-line-no">180</span><span id="line-180"> region.close(false, true);</span>
-<span class="source-line-no">181</span><span id="line-181"> }</span>
-<span class="source-line-no">182</span><span id="line-182"> return region.getRegionInfo();</span>
-<span class="source-line-no">183</span><span id="line-183"> }</span>
-<span class="source-line-no">184</span><span id="line-184"></span>
-<span class="source-line-no">185</span><span id="line-185"> /**</span>
-<span class="source-line-no">186</span><span id="line-186"> * Execute the task on the specified set of regions.</span>
-<span class="source-line-no">187</span><span id="line-187"> * @param exec Thread Pool Executor</span>
-<span class="source-line-no">188</span><span id="line-188"> * @param regions {@link RegionInfo} that describes the regions to edit</span>
-<span class="source-line-no">189</span><span id="line-189"> * @param task {@link RegionFillTask} custom code to edit the region</span>
+<span class="source-line-no">094</span><span id="line-94"> public static void checkForEncodedNameCollisions(final Collection<RegionInfo> candidates,</span>
+<span class="source-line-no">095</span><span id="line-95"> final RegionStates regionStates) throws IOException {</span>
+<span class="source-line-no">096</span><span id="line-96"> if (candidates == null || candidates.isEmpty()) {</span>
+<span class="source-line-no">097</span><span id="line-97"> return;</span>
+<span class="source-line-no">098</span><span id="line-98"> }</span>
+<span class="source-line-no">099</span><span id="line-99"> Objects.requireNonNull(regionStates, "regionStates is null");</span>
+<span class="source-line-no">100</span><span id="line-100"> Set<String> candidateNames = new HashSet<>();</span>
+<span class="source-line-no">101</span><span id="line-101"> for (RegionInfo ri : candidates) {</span>
+<span class="source-line-no">102</span><span id="line-102"> String encoded = ri.getEncodedName();</span>
+<span class="source-line-no">103</span><span id="line-103"> if (</span>
+<span class="source-line-no">104</span><span id="line-104"> !candidateNames.add(encoded)</span>
+<span class="source-line-no">105</span><span id="line-105"> || regionStates.getRegionStateNodeFromEncodedRegionName(encoded) != null</span>
+<span class="source-line-no">106</span><span id="line-106"> ) {</span>
+<span class="source-line-no">107</span><span id="line-107"> throw new DoNotRetryIOException("Encoded region name collision detected: '" + encoded</span>
+<span class="source-line-no">108</span><span id="line-108"> + "' for table " + ri.getTable() + ". Refusing to proceed.");</span>
+<span class="source-line-no">109</span><span id="line-109"> }</span>
+<span class="source-line-no">110</span><span id="line-110"> }</span>
+<span class="source-line-no">111</span><span id="line-111"> }</span>
+<span class="source-line-no">112</span><span id="line-112"></span>
+<span class="source-line-no">113</span><span id="line-113"> /**</span>
+<span class="source-line-no">114</span><span id="line-114"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
+<span class="source-line-no">115</span><span id="line-115"> * to hbase:meta after this operation.</span>
+<span class="source-line-no">116</span><span id="line-116"> * @param env {@link MasterProcedureEnv}</span>
+<span class="source-line-no">117</span><span id="line-117"> * @param rootDir Root directory for HBase instance</span>
+<span class="source-line-no">118</span><span id="line-118"> * @param tableDescriptor description of the table</span>
+<span class="source-line-no">119</span><span id="line-119"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
+<span class="source-line-no">120</span><span id="line-120"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
+<span class="source-line-no">121</span><span id="line-121"> */</span>
+<span class="source-line-no">122</span><span id="line-122"> public static List<RegionInfo> createRegions(final MasterProcedureEnv env, final Path rootDir,</span>
+<span class="source-line-no">123</span><span id="line-123"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
+<span class="source-line-no">124</span><span id="line-124"> throws IOException {</span>
+<span class="source-line-no">125</span><span id="line-125"> if (newRegions == null) return null;</span>
+<span class="source-line-no">126</span><span id="line-126"> int regionNumber = newRegions.length;</span>
+<span class="source-line-no">127</span><span id="line-127"> ThreadPoolExecutor exec = getRegionOpenAndInitThreadPool(env.getMasterConfiguration(),</span>
+<span class="source-line-no">128</span><span id="line-128"> "RegionOpenAndInit-" + tableDescriptor.getTableName(), regionNumber);</span>
+<span class="source-line-no">129</span><span id="line-129"> try {</span>
+<span class="source-line-no">130</span><span id="line-130"> return createRegions(exec, env.getMasterConfiguration(), env, rootDir, tableDescriptor,</span>
+<span class="source-line-no">131</span><span id="line-131"> newRegions, task);</span>
+<span class="source-line-no">132</span><span id="line-132"> } finally {</span>
+<span class="source-line-no">133</span><span id="line-133"> exec.shutdownNow();</span>
+<span class="source-line-no">134</span><span id="line-134"> }</span>
+<span class="source-line-no">135</span><span id="line-135"> }</span>
+<span class="source-line-no">136</span><span id="line-136"></span>
+<span class="source-line-no">137</span><span id="line-137"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
+<span class="source-line-no">138</span><span id="line-138"> final Configuration conf, final Path rootDir, final TableDescriptor tableDescriptor,</span>
+<span class="source-line-no">139</span><span id="line-139"> final RegionInfo[] newRegions, final RegionFillTask task) throws IOException {</span>
+<span class="source-line-no">140</span><span id="line-140"> return createRegions(exec, conf, null, rootDir, tableDescriptor, newRegions, task);</span>
+<span class="source-line-no">141</span><span id="line-141"> }</span>
+<span class="source-line-no">142</span><span id="line-142"></span>
+<span class="source-line-no">143</span><span id="line-143"> /**</span>
+<span class="source-line-no">144</span><span id="line-144"> * Create new set of regions on the specified file-system. NOTE: that you should add the regions</span>
+<span class="source-line-no">145</span><span id="line-145"> * to hbase:meta after this operation.</span>
+<span class="source-line-no">146</span><span id="line-146"> * @param exec Thread Pool Executor</span>
+<span class="source-line-no">147</span><span id="line-147"> * @param conf {@link Configuration}</span>
+<span class="source-line-no">148</span><span id="line-148"> * @param rootDir Root directory for HBase instance</span>
+<span class="source-line-no">149</span><span id="line-149"> * @param tableDescriptor description of the table</span>
+<span class="source-line-no">150</span><span id="line-150"> * @param newRegions {@link RegionInfo} that describes the regions to create</span>
+<span class="source-line-no">151</span><span id="line-151"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
+<span class="source-line-no">152</span><span id="line-152"> */</span>
+<span class="source-line-no">153</span><span id="line-153"> public static List<RegionInfo> createRegions(final ThreadPoolExecutor exec,</span>
+<span class="source-line-no">154</span><span id="line-154"> final Configuration conf, final MasterProcedureEnv env, final Path rootDir,</span>
+<span class="source-line-no">155</span><span id="line-155"> final TableDescriptor tableDescriptor, final RegionInfo[] newRegions, final RegionFillTask task)</span>
+<span class="source-line-no">156</span><span id="line-156"> throws IOException {</span>
+<span class="source-line-no">157</span><span id="line-157"> if (newRegions == null) return null;</span>
+<span class="source-line-no">158</span><span id="line-158"> int regionNumber = newRegions.length;</span>
+<span class="source-line-no">159</span><span id="line-159"> CompletionService<RegionInfo> completionService = new ExecutorCompletionService<>(exec);</span>
+<span class="source-line-no">160</span><span id="line-160"> List<RegionInfo> regionInfos = new ArrayList<>();</span>
+<span class="source-line-no">161</span><span id="line-161"> for (final RegionInfo newRegion : newRegions) {</span>
+<span class="source-line-no">162</span><span id="line-162"> completionService.submit(new Callable<RegionInfo>() {</span>
+<span class="source-line-no">163</span><span id="line-163"> @Override</span>
+<span class="source-line-no">164</span><span id="line-164"> public RegionInfo call() throws IOException {</span>
+<span class="source-line-no">165</span><span id="line-165"> return createRegion(conf, env, rootDir, tableDescriptor, newRegion, task);</span>
+<span class="source-line-no">166</span><span id="line-166"> }</span>
+<span class="source-line-no">167</span><span id="line-167"> });</span>
+<span class="source-line-no">168</span><span id="line-168"> }</span>
+<span class="source-line-no">169</span><span id="line-169"> try {</span>
+<span class="source-line-no">170</span><span id="line-170"> // wait for all regions to finish creation</span>
+<span class="source-line-no">171</span><span id="line-171"> for (int i = 0; i < regionNumber; i++) {</span>
+<span class="source-line-no">172</span><span id="line-172"> regionInfos.add(completionService.take().get());</span>
+<span class="source-line-no">173</span><span id="line-173"> }</span>
+<span class="source-line-no">174</span><span id="line-174"> } catch (InterruptedException e) {</span>
+<span class="source-line-no">175</span><span id="line-175"> LOG.error("Caught " + e + " during region creation");</span>
+<span class="source-line-no">176</span><span id="line-176"> throw new InterruptedIOException(e.getMessage());</span>
+<span class="source-line-no">177</span><span id="line-177"> } catch (ExecutionException e) {</span>
+<span class="source-line-no">178</span><span id="line-178"> throw new IOException(e);</span>
+<span class="source-line-no">179</span><span id="line-179"> }</span>
+<span class="source-line-no">180</span><span id="line-180"> return regionInfos;</span>
+<span class="source-line-no">181</span><span id="line-181"> }</span>
+<span class="source-line-no">182</span><span id="line-182"></span>
+<span class="source-line-no">183</span><span id="line-183"> /**</span>
+<span class="source-line-no">184</span><span id="line-184"> * Create new set of regions on the specified file-system.</span>
+<span class="source-line-no">185</span><span id="line-185"> * @param conf {@link Configuration}</span>
+<span class="source-line-no">186</span><span id="line-186"> * @param rootDir Root directory for HBase instance</span>
+<span class="source-line-no">187</span><span id="line-187"> * @param tableDescriptor description of the table</span>
+<span class="source-line-no">188</span><span id="line-188"> * @param newRegion {@link RegionInfo} that describes the region to create</span>
+<span class="source-line-no">189</span><span id="line-189"> * @param task {@link RegionFillTask} custom code to populate region after creation</span>
<span class="source-line-no">190</span><span id="line-190"> */</span>
-<span class="source-line-no">191</span><span id="line-191"> public static void editRegions(final ThreadPoolExecutor exec,</span>
-<span class="source-line-no">192</span><span id="line-192"> final Collection<RegionInfo> regions, final RegionEditTask task) throws IOException {</span>
-<span class="source-line-no">193</span><span id="line-193"> final ExecutorCompletionService<Void> completionService = new ExecutorCompletionService<>(exec);</span>
-<span class="source-line-no">194</span><span id="line-194"> for (final RegionInfo hri : regions) {</span>
-<span class="source-line-no">195</span><span id="line-195"> completionService.submit(new Callable<Void>() {</span>
-<span class="source-line-no">196</span><span id="line-196"> @Override</span>
-<span class="source-line-no">197</span><span id="line-197"> public Void call() throws IOException {</span>
-<span class="source-line-no">198</span><span id="line-198"> task.editRegion(hri);</span>
-<span class="source-line-no">199</span><span id="line-199"> return null;</span>
-<span class="source-line-no">200</span><span id="line-200"> }</span>
-<span class="source-line-no">201</span><span id="line-201"> });</span>
-<span class="source-line-no">202</span><span id="line-202"> }</span>
-<span class="source-line-no">203</span><span id="line-203"></span>
-<span class="source-line-no">204</span><span id="line-204"> try {</span>
-<span class="source-line-no">205</span><span id="line-205"> for (RegionInfo hri : regions) {</span>
-<span class="source-line-no">206</span><span id="line-206"> completionService.take().get();</span>
-<span class="source-line-no">207</span><span id="line-207"> }</span>
-<span class="source-line-no">208</span><span id="line-208"> } catch (InterruptedException e) {</span>
-<span class="source-line-no">209</span><span id="line-209"> throw new InterruptedIOException(e.getMessage());</span>
-<span class="source-line-no">210</span><span id="line-210"> } catch (ExecutionException e) {</span>
-<span class="source-line-no">211</span><span id="line-211"> throw new IOException(e.getCause());</span>
-<span class="source-line-no">212</span><span id="line-212"> }</span>
-<span class="source-line-no">213</span><span id="line-213"> }</span>
-<span class="source-line-no">214</span><span id="line-214"></span>
-<span class="source-line-no">215</span><span id="line-215"> /*</span>
-<span class="source-line-no">216</span><span id="line-216"> * used by createRegions() to get the thread pool executor based on the</span>
-<span class="source-line-no">217</span><span id="line-217"> * "hbase.hregion.open.and.init.threads.max" property.</span>
+<span class="source-line-no">191</span><span id="line-191"> public static RegionInfo createRegion(final Configuration conf, final MasterProcedureEnv env,</span>
+<span class="source-line-no">192</span><span id="line-192"> final Path rootDir, final TableDescriptor tableDescriptor, final RegionInfo newRegion,</span>
+<span class="source-line-no">193</span><span id="line-193"> final RegionFillTask task) throws IOException {</span>
+<span class="source-line-no">194</span><span id="line-194"> // 1. Create HRegion</span>
+<span class="source-line-no">195</span><span id="line-195"> // The WAL subsystem will use the default rootDir rather than the passed in rootDir</span>
+<span class="source-line-no">196</span><span id="line-196"> // unless I pass along via the conf.</span>
+<span class="source-line-no">197</span><span id="line-197"> Configuration confForWAL = new Configuration(conf);</span>
+<span class="source-line-no">198</span><span id="line-198"> confForWAL.set(HConstants.HBASE_DIR, rootDir.toString());</span>
+<span class="source-line-no">199</span><span id="line-199"> HRegion region = HRegion.createHRegion(newRegion, rootDir, conf, tableDescriptor, null, false,</span>
+<span class="source-line-no">200</span><span id="line-200"> null, env == null ? null : env.getMasterServices());</span>
+<span class="source-line-no">201</span><span id="line-201"> try {</span>
+<span class="source-line-no">202</span><span id="line-202"> // 2. Custom user code to interact with the created region</span>
+<span class="source-line-no">203</span><span id="line-203"> if (task != null) {</span>
+<span class="source-line-no">204</span><span id="line-204"> task.fillRegion(region);</span>
+<span class="source-line-no">205</span><span id="line-205"> }</span>
+<span class="source-line-no">206</span><span id="line-206"> } finally {</span>
+<span class="source-line-no">207</span><span id="line-207"> // 3. Close the new region to flush to disk. Close log file too.</span>
+<span class="source-line-no">208</span><span id="line-208"> region.close(false, true);</span>
+<span class="source-line-no">209</span><span id="line-209"> }</span>
+<span class="source-line-no">210</span><span id="line-210"> return region.getRegionInfo();</span>
+<span class="source-line-no">211</span><span id="line-211"> }</span>
+<span class="source-line-no">212</span><span id="line-212"></span>
+<span class="source-line-no">213</span><span id="line-213"> /**</span>
+<span class="source-line-no">214</span><span id="line-214"> * Execute the task on the specified set of regions.</span>
+<span class="source-line-no">215</span><span id="line-215"> * @param exec Thread Pool Executor</span>
+<span class="source-line-no">216</span><span id="line-216"> * @param regions {@link RegionInfo} that describes the regions to edit</span>
+<span class="source-line-no">217</span><span id="line-217"> * @param task {@link RegionFillTask} custom code to edit the region</span>
<span class="source-line-no">218</span><span id="line-218"> */</span>
-<span class="source-line-no">219</span><span id="line-219"> static ThreadPoolExecutor getRegionOpenAndInitThreadPool(final Configuration conf,</span>
-<span class="source-line-no">220</span><span id="line-220"> final String threadNamePrefix, int regionNumber) {</span>
-<span class="source-line-no">221</span><span id="line-221"> int maxThreads =</span>
-<span class="source-line-no">222</span><span id="line-222"> Math.min(regionNumber, conf.getInt("hbase.hregion.open.and.init.threads.max", 16));</span>
-<span class="source-line-no">223</span><span id="line-223"> ThreadPoolExecutor regionOpenAndInitThreadPool = Threads.getBoundedCachedThreadPool(maxThreads,</span>
-<span class="source-line-no">224</span><span id="line-224"> 30L, TimeUnit.SECONDS, new ThreadFactoryBuilder().setNameFormat(threadNamePrefix + "-pool-%d")</span>
-<span class="source-line-no">225</span><span id="line-225"> .setDaemon(true).setUncaughtExceptionHandler(Threads.LOGGING_EXCEPTION_HANDLER).build());</span>
-<span class="source-line-no">226</span><span id="line-226"> return regionOpenAndInitThreadPool;</span>
-<span class="source-line-no">227</span><span id="line-227"> }</span>
-<span class="source-line-no">228</span><span id="line-228">}</span>
+<span class="source-line-no">219</span><span id="line-219"> public static void editRegions(final ThreadPoolExecutor exec,</span>
+<span class="source-line-no">220</span><span id="line-220"> final Collection<RegionInfo> regions, final RegionEditTask task) throws IOException {</span>
+<span class="source-line-no">221</span><span id="line-221"> final ExecutorCompletionService<Void> completionService = new ExecutorCompletionService<>(exec);</span>
+<span class="source-line-no">222</span><span id="line-222"> for (final RegionInfo hri : regions) {</span>
+<span class="source-line-no">223</span><span id="line-223"> completionService.submit(new Callable<Void>() {</span>
+<span class="source-line-no">224</span><span id="line-224"> @Override</span>
+<span class="source-line-no">225</span><span id="line-225"> public Void call() throws IOException {</span>
+<span class="source-line-no">226</span><span id="line-226"> task.editRegion(hri);</span>
+<span class="source-line-no">227</span><span id="line-227"> return null;</span>
+<span class="source-line-no">228</span><span id="line-228"> }</span>
+<span class="source-line-no">229</span><span id="line-229"> });</span>
+<span class="source-line-no">230</span><span id="line-230"> }</span>
+<span class="source-line-no">231</span><span id="line-231"></span>
+<span class="source-line-no">232</span><span id="line-232"> try {</span>
+<span class="source-line-no">233</span><span id="line-233"> for (RegionInfo hri : regions) {</span>
+<span class="source-line-no">234</span><span id="line-234"> completionService.take().get();</span>
+<span class="source-line-no">235</span><span id="line-235"> }</span>
+<span class="source-line-no">236</span><span id="line-236"> } catch (InterruptedException e) {</span>
+<span class="source-line-no">237</span><span id="line-237"> throw new InterruptedIOException(e.getMessage());</span>
+<span class="source-line-no">238</span><span id="line-238"> } catch (ExecutionException e) {</span>
+<span class="source-line-no">239</span><span id="line-239"> throw new IOException(e.getCause());</span>
+<span class="source-line-no">240</span><span id="line-240"> }</span>
+<span class="source-line-no">241</span><span id="line-241"> }</span>
+<span class="source-line-no">242</span><span id="line-242"></span>
+<span class="source-line-no">243</span><span id="line-243"> /*</span>
+<span class="source-line-no">244</span><span id="line-244"> * used by createRegions() to get the thread pool executor based on the</span>
+<span class="source-line-no">245</span><span id="line-245"> * "hbase.hregion.open.and.init.threads.max" property.</span>
+<span class="source-line-no">246</span><span id="line-246"> */</span>
+<span class="source-line-no">247</span><span id="line-247"> static ThreadPoolExecutor getRegionOpenAndInitThreadPool(final Configuration conf,</span>
+<span class="source-line-no">248</span><span id="line-248"> final String threadNamePrefix, int regionNumber) {</span>
+<span class="source-line-no">249</span><span id="line-249"> int maxThreads =</span>
+<span class="source-line-no">250</span><span id="line-250"> Math.min(regionNumber, conf.getInt("hbase.hregion.open.and.init.threads.max", 16));</span>
+<span class="source-line-no">251</span><span id="line-251"> ThreadPoolExecutor regionOpenAndInitThreadPool = Threads.getBoundedCachedThreadPool(maxThreads,</span>
+<span class="source-line-no">252</span><span id="line-252"> 30L, TimeUnit.SECONDS, new ThreadFactoryBuilder().setNameFormat(threadNamePrefix + "-pool-%d")</span>
+<span class="source-line-no">253</span><span id="line-253"> .setDaemon(true).setUncaughtExceptionHandler(Threads.LOGGING_EXCEPTION_HANDLER).build());</span>
+<span class="source-line-no">254</span><span id="line-254"> return regionOpenAndInitThreadPool;</span>
+<span class="source-line-no">255</span><span id="line-255"> }</span>
+<span class="source-line-no">256</span><span id="line-256">}</span>
diff --git a/assets/docs-Dp5xyhQm.js b/assets/docs-Dp5xyhQm.js
new file mode 100644
index 00000000000..b02515d3d89
--- /dev/null
+++ b/assets/docs-Dp5xyhQm.js
@@ -0,0 +1,4 @@
+const __vite__mapDeps=(i,m=__vite__mapDeps,d=(m.f||(m.f=["assets/acl-matrix-VSE2-lpy.js","assets/chunk-QUQL4437-Bywy9pC_.js","assets/amv2-DQb5put0.js","assets/bulk-loading-la8-yQC-.js","assets/catalog-tables-DdCt-Bwy.js","assets/client-request-filters-DZpvsGlA.js","assets/client-CrTcFlQm.js","assets/hbase-mob-D-7Idz0a.js","assets/hdfs-C9tORJGT.js","assets/index-8HyJ24Ay.js","assets/master-BhshdDVg.js","assets/overview-vtwu4gCT.js","assets/regions-CLA1l9-E.js","assets/region_states-Dumv7s [...]
+import{r as l,j as s,y as Pt,B as tn,w as rn}from"./chunk-QUQL4437-Bywy9pC_.js";import{_ as m,u as xe,e as yt,c as jt,a as U,z as nn,b as on}from"./index-DWtaWGM5.js";import{b as V,c as St}from"./button-CZBw5Jwh.js";import{L as F,d as sn,C as an,a as cn}from"./mdx-oaHE65CA.js";import{p as $,k as ge,c as Rt}from"./index-DmTM9tZB.js";import{u as Y,f as Se,P as te,p as ln,a as dn,d as B,b as W,t as At,w as Ct,r as Ce,v as Tt,g as un,o as fn,s as mn,h as pn,i as hn,j as xn,k as gn,m as vn,l [...]
+ "sidebar toc-popover toc"
+ "sidebar main toc" 1fr / minmax(var(--fd-sidebar-col), 1fr) minmax(0, calc(var(--fd-layout-width,97rem) - var(--fd-sidebar-width) - var(--fd-toc-width))) minmax(min-content, 1fr)`,"--fd-docs-row-1":"var(--fd-banner-height, 0px)","--fd-docs-row-2":"calc(var(--fd-docs-row-1) + var(--fd-header-height))","--fd-docs-row-3":"calc(var(--fd-docs-row-2) + var(--fd-toc-popover-height))","--fd-sidebar-col":n?"0px":"var(--fd-sidebar-width)",...t},...o,children:r})}function Is({options:e,...t [...]
diff --git a/assets/index-feH7IxLp.js b/assets/index-feH7IxLp.js
new file mode 100644
index 00000000000..8ed0c2b26d6
--- /dev/null
+++ b/assets/index-feH7IxLp.js
@@ -0,0 +1,48983 @@
+import{j as e}from"./chunk-QUQL4437-Bywy9pC_.js";import{_ as l,a as h}from"./WAL_splitting-S_OUAgmz.js";import{_ as c}from"./region_states-Dumv7s9S.js";import{_ as d}from"./timeline_consistency-Bs28jTFK.js";import{_ as p,a as g}from"./bytebuff-allocator-stats-C6KiUNbS.js";import{_ as u,a as m,b as k}from"./backup-cloud-appliance--qbLnXgy.js";import{_ as f}from"./backup-app-components-ChSULF98.js";import{_ as b,a as y,b as x,c as j,d as E,e as v,f as w,g as F}from"./empty-snapshots-CrCCrR [...]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+# Preface
+
+Herein you will find either the definitive documentation on an HBase topic as of its
+standing when the referenced HBase version shipped, or it will point to the location
+in [Javadoc](https://hbase.apache.org/apidocs/index.html) or
+[JIRA](https://issues.apache.org/jira/browse/HBASE) where the pertinent information can be found.
+
+## About This Guide
+
+This reference guide is a work in progress. The source for this guide can be found in the
+*hbase-website/app/pages/\\_docs/docs/\\_mdx/(multi-page)* directory of the HBase source. This reference guide is marked up
+using [MDX](https://mdxjs.com/) (just extended markdown) powered by [Fumadocs](https://fumadocs.dev/) from which the finished guide is generated as part of the
+'site' build target. Run
+
+\`\`\`bash
+mvn site
+\`\`\`
+
+to generate this documentation.
+Amendments and improvements to the documentation are welcomed.
+Click
+[this link](https://issues.apache.org/jira/secure/CreateIssueDetails!init.jspa?pid=12310753\\&issuetype=1\\&components=12312132\\&summary=SHORT+DESCRIPTION)
+to file a new documentation bug against Apache HBase with some values pre-selected.
+
+## Contributing to the Documentation
+
+For an overview and suggestions to get started contributing to the documentation,
+see the [relevant section later in this documentation](/docs/contributing-to-documentation).
+
+## Heads-up if this is your first foray into the world of distributed computing...
+
+If this is your first foray into the wonderful world of Distributed Computing, then you are in for some interesting times.
+First off, distributed systems are hard; making a distributed system hum requires a disparate skillset that spans systems (hardware and software) and networking.
+
+Your cluster's operation can hiccup because of any of a myriad set of reasons from bugs in HBase itself through misconfigurations — misconfiguration of HBase but also operating system misconfigurations — through to hardware problems whether it be a bug in your network card drivers or an underprovisioned RAM bus (to mention two recent examples of hardware issues that manifested as "HBase is slow"). You will also need to do a recalibration if up to this your computing has been bound to a s [...]
+Here is one good starting point: [Fallacies of Distributed Computing](http://en.wikipedia.org/wiki/Fallacies_of_Distributed_Computing).
+
+That said, you are welcome.<br />
+It's a fun place to be.<br />
+Yours, the HBase Community.
+
+## Reporting Bugs
+
+Please use [JIRA](https://issues.apache.org/jira/browse/hbase) to report non-security-related bugs.
+
+To protect existing HBase installations from new vulnerabilities, please **do not** use JIRA to report security-related bugs. Instead, send your report to the mailing list [private@hbase.apache.org](mailto:private@hbase.apache.org), which allows anyone to send messages, but restricts who can read them. Someone on that list will contact you to follow up on your report.
+
+## Support and Testing Expectations
+
+The phrases *supported*, *not supported*, *tested*, and *not tested* occur several
+places throughout this guide. In the interest of clarity, here is a brief explanation
+of what is generally meant by these phrases, in the context of HBase.
+
+<Callout type="info">
+ Commercial technical support for Apache HBase is provided by many Hadoop vendors. This is not the
+ sense in which the term *support* is used in the context of the Apache HBase project. The Apache
+ HBase team assumes no responsibility for your HBase clusters, your configuration, or your data.
+</Callout>
+
+### Supported
+
+In the context of Apache HBase, *supported* means that HBase is designed to work
+in the way described, and deviation from the defined behavior or functionality should
+be reported as a bug.
+
+### Not Supported
+
+In the context of Apache HBase, *not supported* means that a use case or use pattern
+is not expected to work and should be considered an antipattern. If you think this
+designation should be reconsidered for a given feature or use pattern, file a JIRA
+or start a discussion on one of the mailing lists.
+
+### Tested
+
+In the context of Apache HBase, *tested* means that a feature is covered by unit
+or integration tests, and has been proven to work as expected.
+
+### Not Tested
+
+In the context of Apache HBase, *not tested* means that a feature or use pattern
+may or may not work in a given way, and may or may not corrupt your data or cause
+operational issues. It is an unknown, and there are no guarantees. If you can provide
+proof that a feature designated as *not tested* does work in a given way, please
+submit the tests and/or the metrics so that other users can gain certainty about
+such features or use patterns.
+
+***
+
+# Getting Started
+
+## Quick Start - Standalone HBase
+
+This section describes the setup of a single-node standalone HBase. A *standalone* instance has all HBase daemons — the Master, RegionServers, and ZooKeeper — running in a single JVM persisting to the local filesystem. It is our most basic deploy profile. We will show you how to create a table in HBase using the \`hbase shell\` CLI, insert rows into the table, perform put and scan operations against the table, enable or disable the table, and start and stop HBase.
+
+Apart from downloading HBase, this procedure should take less than 10 minutes.
+
+## JDK Version Requirements
+
+HBase requires that a JDK be installed. See [Java](/docs/configuration/basic-prerequisites#configuration-basic-prerequisites-java) for information about supported JDK versions.
+
+## Get Started with HBase
+
+### Procedure: Download, Configure, and Start HBase in Standalone Mode
+
+<Steps>
+ <Step>
+ Choose a download site from this list of [Apache Download Mirrors](https://www.apache.org/dyn/closer.lua/hbase/). Click on the suggested top link. This will take you to a mirror of *HBase Releases*. Click on the folder named *stable* and then download the binary file that ends in *.tar.gz* to your local filesystem. Do not download the file ending in *src.tar.gz* for now.
+ </Step>
+
+ <Step>
+ Extract the downloaded file, and change to the newly-created directory.
+
+ \`\`\`bash
+ tar xzvf <FILE_NAME>.tar.gz
+ cd <DIRECTORY_NAME>
+ \`\`\`
+ </Step>
+
+ <Step>
+ You must set the \`JAVA_HOME\` environment variable before starting HBase. To make this easier, HBase lets you set it within the *conf/hbase-env.sh* file. You must locate where Java is installed on your machine, and one way to find this is by using the *whereis java* command. Once you have the location, edit the *conf/hbase-env.sh* file and uncomment the line starting with *#export JAVA\\_HOME=*, and then set it to your Java installation path.
+
+ *Example extract from *hbase-env.sh* where *JAVA\\_HOME* is set*
+
+ \`\`\`bash
+ # Set environment variables here.
+ # The java implementation to use.
+ export JAVA_HOME=/usr/jdk64/jdk1.8.0_112
+ \`\`\`
+ </Step>
+
+ <Step>
+ The *bin/start-hbase.sh* script is provided as a convenient way to start HBase. Issue the command, and if all goes well, a message is logged to standard output showing that HBase started successfully. You can use the \`jps\` command to verify that you have one running process called \`HMaster\`. In standalone mode HBase runs all daemons within this single JVM, i.e. the HMaster, a single HRegionServer, and the ZooKeeper daemon. Go to *[http://localhost:16010](http://localhost:16010)* [...]
+ </Step>
+</Steps>
+
+### Procedure: Use HBase For the First Time
+
+<Steps>
+ <Step>
+ #### Connect to HBase
+
+ Connect to your running instance of HBase using the \`hbase shell\` command, located in the *bin/* directory of your HBase install. In this example, some usage and version information that is printed when you start HBase Shell has been omitted. The HBase Shell prompt ends with a \`>\` character.
+
+ \`\`\`bash
+ $ ./bin/hbase shell
+ hbase(main):001:0>
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### Display HBase Shell Help Text
+
+ Type \`help\` and press Enter, to display some basic usage information for HBase Shell, as well as several example commands. Notice that table names, rows, columns all must be enclosed in quote characters.
+ </Step>
+
+ <Step>
+ #### Create a table
+
+ Use the \`create\` command to create a new table. You must specify the table name and the ColumnFamily name.
+
+ \`\`\`bash
+ hbase(main):001:0> create 'test', 'cf'
+ 0 row(s) in 0.4170 seconds
+
+ => Hbase::Table - test
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### List Information About your Table
+
+ Use the \`list\` command to confirm your table exists
+
+ \`\`\`bash
+ hbase(main):002:0> list 'test'
+ TABLE
+ test
+ 1 row(s) in 0.0180 seconds
+
+ => ["test"]
+ \`\`\`
+
+ Now use the \`describe\` command to see details, including configuration defaults
+
+ \`\`\`bash
+ hbase(main):003:0> describe 'test'
+ Table test is ENABLED
+ test
+ COLUMN FAMILIES DESCRIPTION
+ {NAME => 'cf', VERSIONS => '1', EVICT_BLOCKS_ON_CLOSE => 'false', NEW_VERSION_BEHAVIOR => 'false', KEEP_DELETED_CELLS => 'FALSE', CACHE_DATA_ON_WRITE =>
+ 'false', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', CACHE_INDEX_ON_WRITE => 'f
+ alse', IN_MEMORY => 'false', CACHE_BLOOMS_ON_WRITE => 'false', PREFETCH_BLOCKS_ON_OPEN => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE
+ => '65536'}
+ 1 row(s)
+ Took 0.9998 seconds
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### Put data into your table
+
+ To put data into your table, use the \`put\` command.
+
+ \`\`\`bash
+ hbase(main):003:0> put 'test', 'row1', 'cf:a', 'value1'
+ 0 row(s) in 0.0850 seconds
+
+ hbase(main):004:0> put 'test', 'row2', 'cf:b', 'value2'
+ 0 row(s) in 0.0110 seconds
+
+ hbase(main):005:0> put 'test', 'row3', 'cf:c', 'value3'
+ 0 row(s) in 0.0100 seconds
+ \`\`\`
+
+ Here, we insert three values, one at a time. The first insert is at \`row1\`, column \`cf:a\`, with a value of \`value1\`. Columns in HBase are comprised of a column family prefix, \`cf\` in this example, followed by a colon and then a column qualifier suffix, \`a\` in this case.
+ </Step>
+
+ <Step>
+ #### Scan the table for all data at once
+
+ One of the ways to get data from HBase is to scan. Use the \`scan\` command to scan the table for data. You can limit your scan, but for now, all data is fetched.
+
+ \`\`\`bash
+ hbase(main):006:0> scan 'test'
+ ROW COLUMN+CELL
+ row1 column=cf:a, timestamp=1421762485768, value=value1
+ row2 column=cf:b, timestamp=1421762491785, value=value2
+ row3 column=cf:c, timestamp=1421762496210, value=value3
+ 3 row(s) in 0.0230 seconds
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### Get a single row of data
+
+ To get a single row of data at a time, use the \`get\` command.
+
+ \`\`\`bash
+ hbase(main):007:0> get 'test', 'row1'
+ COLUMN CELL
+ cf:a timestamp=1421762485768, value=value1
+ 1 row(s) in 0.0350 seconds
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### Disable a table
+
+ If you want to delete a table or change its settings, as well as in some other situations, you need to disable the table first, using the \`disable\` command. You can re-enable it using the \`enable\` command.
+
+ \`\`\`bash
+ hbase(main):008:0> disable 'test'
+ 0 row(s) in 1.1820 seconds
+
+ hbase(main):009:0> enable 'test'
+ 0 row(s) in 0.1770 seconds
+ \`\`\`
+
+ Disable the table again if you tested the \`enable\` command above:
+
+ \`\`\`bash
+ hbase(main):010:0> disable 'test'
+ 0 row(s) in 1.1820 seconds
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### Drop the table
+
+ To drop (delete) a table, use the \`drop\` command.
+
+ \`\`\`bash
+ hbase(main):011:0> drop 'test'
+ 0 row(s) in 0.1370 seconds
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### Exit the HBase Shell
+
+ To exit the HBase Shell and disconnect from your cluster, use the \`quit\` command. HBase is still running in the background.
+ </Step>
+</Steps>
+
+### Procedure: Stop HBase
+
+<Steps>
+ <Step>
+ In the same way that the *bin/start-hbase.sh* script is provided to conveniently start all HBase daemons, the *bin/stop-hbase.sh* script stops them.
+
+ \`\`\`bash
+ $ ./bin/stop-hbase.sh
+ stopping hbase....................
+ \`\`\`
+ </Step>
+
+ <Step>
+ After issuing the command, it can take several minutes for the processes to shut down. Use the \`jps\` to be sure that the HMaster and HRegionServer processes are shut down.
+ </Step>
+</Steps>
+
+The above has shown you how to start and stop a standalone instance of HBase. In the next sections we give a quick overview of other modes of hbase deploy.
+
+## Pseudo-Distributed for Local Testing
+
+After working your way through [quickstart](/docs/getting-started#quick-start---standalone-hbase) standalone mode, you can re-configure HBase to run in pseudo-distributed mode. Pseudo-distributed mode means that HBase still runs completely on a single host, but each HBase daemon (HMaster, HRegionServer, and ZooKeeper) runs as a separate process: in standalone mode all daemons ran in one jvm process/instance. By default, unless you configure the \`hbase.rootdir\` property as described in [...]
+
+<Callout type="info">
+ This procedure assumes that you have configured Hadoop and HDFS on your local system and/or a
+ remote system, and that they are running and available. It also assumes you are using Hadoop 2.
+ The guide on [Setting up a Single Node
+ Cluster](https://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-common/SingleCluster.html)
+ in the Hadoop documentation is a good starting point.
+</Callout>
+
+<Steps>
+ <Step>
+ #### Stop HBase if it is running
+
+ If you have just finished [quickstart](/docs/getting-started#quick-start---standalone-hbase) and HBase is still running, stop it. This procedure will create a totally new directory where HBase will store its data, so any databases you created before will be lost.
+ </Step>
+
+ <Step>
+ #### Configure HBase
+
+ Edit the *hbase-site.xml* configuration. First, add the following property which directs HBase to run in distributed mode, with one JVM instance per daemon.
+
+ \`\`\`xml
+ <property>
+ <name>hbase.cluster.distributed</name>
+ <value>true</value>
+ </property>
+ \`\`\`
+
+ Next, add a configuration for \`hbase.rootdir\`, pointing to the address of your HDFS instance, using the \`hdfs:////\` URI syntax. In this example, HDFS is running on the localhost at port 8020.
+
+ \`\`\`xml
+ <property>
+ <name>hbase.rootdir</name>
+ <value>hdfs://localhost:9000/hbase</value>
+ </property>
+ \`\`\`
+
+ You do not need to create the directory in HDFS. HBase will do this for you. If you create the directory, HBase will attempt to do a migration, which is not what you want.
+
+ Finally, remove existing configuration for \`hbase.tmp.dir\` and \`hbase.unsafe.stream.capability.enforce\`.
+ </Step>
+
+ <Step>
+ #### Start HBase
+
+ Use the *bin/start-hbase.sh* command to start HBase. If your system is configured correctly, the \`jps\` command should show the HMaster and HRegionServer processes running.
+ </Step>
+
+ <Step>
+ #### Check the HBase directory in HDFS
+
+ If everything worked correctly, HBase created its directory in HDFS. In the configuration above, it is stored in */hbase/* on HDFS. You can use the \`hadoop fs\` command in Hadoop's *bin/* directory to list this directory.
+
+ \`\`\`bash
+ $ ./bin/hadoop fs -ls /hbase
+ Found 7 items
+ drwxr-xr-x - hbase users 0 2014-06-25 18:58 /hbase/.tmp
+ drwxr-xr-x - hbase users 0 2014-06-25 21:49 /hbase/WALs
+ drwxr-xr-x - hbase users 0 2014-06-25 18:48 /hbase/corrupt
+ drwxr-xr-x - hbase users 0 2014-06-25 18:58 /hbase/data
+ -rw-r--r-- 3 hbase users 42 2014-06-25 18:41 /hbase/hbase.id
+ -rw-r--r-- 3 hbase users 7 2014-06-25 18:41 /hbase/hbase.version
+ drwxr-xr-x - hbase users 0 2014-06-25 21:49 /hbase/oldWALs
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### Create a table and populate it with data
+
+ You can use the HBase Shell to create a table, populate it with data, scan and get values from it, using the same procedure as in [shell exercises](/docs/getting-started#procedure-use-hbase-for-the-first-time).
+ </Step>
+
+ <Step>
+ #### Start and stop a backup HBase Master (HMaster) server
+
+ <Callout type="info">
+ Running multiple HMaster instances on the same hardware does not make sense in a production
+ environment, in the same way that running a pseudo-distributed cluster does not make sense for
+ production. This step is offered for testing and learning purposes only.
+ </Callout>
+
+ The HMaster server controls the HBase cluster. You can start up to 9 backup HMaster servers, which makes 10 total HMasters, counting the primary. To start a backup HMaster, use the \`local-master-backup.sh\`. For each backup master you want to start, add a parameter representing the port offset for that master. Each HMaster uses two ports (16000 and 16010 by default). The port offset is added to these ports, so using an offset of 2, the backup HMaster would use ports 16002 and 16012. [...]
+
+ \`\`\`bash
+ ./bin/local-master-backup.sh start 2 3 5
+ \`\`\`
+
+ To kill a backup master without killing the entire cluster, you need to find its process ID (PID). The PID is stored in a file with a name like */tmp/hbase-USER-X-master.pid*. The only contents of the file is the PID. You can use the \`kill -9\` command to kill that PID. The following command will kill the master with port offset 1, but leave the cluster running:
+
+ \`\`\`bash
+ cat /tmp/hbase-testuser-1-master.pid |xargs kill -9
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### Start and stop additional RegionServers
+
+ The HRegionServer manages the data in its StoreFiles as directed by the HMaster. Generally, one HRegionServer runs per node in the cluster. Running multiple HRegionServers on the same system can be useful for testing in pseudo-distributed mode. The \`local-regionservers.sh\` command allows you to run multiple RegionServers. It works in a similar way to the \`local-master-backup.sh\` command, in that each parameter you provide represents the port offset for an instance. Each RegionSer [...]
+
+ \`\`\`bash
+ ./bin/local-regionservers.sh start 2 3 4 5
+ \`\`\`
+
+ To stop a RegionServer manually, use the \`local-regionservers.sh\` command with the \`stop\` parameter and the offset of the server to stop.
+
+ \`\`\`bash
+ ./bin/local-regionservers.sh stop 3
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### Stop HBase
+
+ You can stop HBase the same way as in the [quickstart](/docs/getting-started#quick-start---standalone-hbase) procedure, using the *bin/stop-hbase.sh* command.
+ </Step>
+</Steps>
+
+## Fully Distributed for Production
+
+In reality, you need a fully-distributed configuration to fully test HBase and to use it in real-world scenarios. In a distributed configuration, the cluster contains multiple nodes, each of which runs one or more HBase daemon. These include primary and backup Master instances, multiple ZooKeeper nodes, and multiple RegionServer nodes.
+
+This advanced quickstart adds two more nodes to your cluster. The architecture will be as follows:
+
+| Node Name | Master | ZooKeeper | RegionServer |
+| ------------------ | ------ | --------- | ------------ |
+| node-a.example.com | yes | yes | no |
+| node-b.example.com | backup | yes | yes |
+| node-c.example.com | no | yes | yes |
+
+Distributed Cluster Demo Architecture
+
+This quickstart assumes that each node is a virtual machine and that they are all on the same network. It builds upon the previous quickstart, [Pseudo-Distributed for Local Testing](/docs/getting-started#pseudo-distributed-for-local-testing), assuming that the system you configured in that procedure is now \`node-a\`. Stop HBase on \`node-a\` before continuing.
+
+<Callout type="info">
+ Be sure that all the nodes have full access to communicate, and that no firewall rules are in
+ place which could prevent them from talking to each other. If you see any errors like \`no route to
+ host\`, check your firewall.
+</Callout>
+
+### Procedure: Configure Passwordless SSH Access
+
+\`node-a\` needs to be able to log into \`node-b\` and \`node-c\` (and to itself) in order to start the daemons. The easiest way to accomplish this is to use the same username on all hosts, and configure password-less SSH login from \`node-a\` to each of the others.
+
+<Steps>
+ <Step>
+ #### On \`node-a\`, generate a key pair
+
+ While logged in as the user who will run HBase, generate a SSH key pair, using the following command:
+
+ \`\`\`bash
+ ssh-keygen -t rsa
+ \`\`\`
+
+ If the command succeeds, the location of the key pair is printed to standard output. The default name of the public key is *id\\_rsa.pub*.
+ </Step>
+
+ <Step>
+ #### Create the directory that will hold the shared keys on the other nodes
+
+ On \`node-b\` and \`node-c\`, log in as the HBase user and create a *.ssh/* directory in the user's home directory, if it does not already exist. If it already exists, be aware that it may already contain other keys.
+ </Step>
+
+ <Step>
+ #### Copy the public key to the other nodes
+
+ Securely copy the public key from \`node-a\` to each of the nodes, by using the \`scp\` or some other secure means. On each of the other nodes, create a new file called *.ssh/authorized\\_keys* *if it does not already exist*, and append the contents of the *id\\_rsa.pub* file to the end of it. Note that you also need to do this for \`node-a\` itself.
+
+ \`\`\`bash
+ cat id_rsa.pub >> ~/.ssh/authorized_keys
+ \`\`\`
+ </Step>
+
+ <Step>
+ #### Test password-less login
+
+ If you performed the procedure correctly, you should not be prompted for a password when you SSH from \`node-a\` to either of the other nodes using the same username.
+ </Step>
+
+ <Step>
+ Since \`node-b\` will run a backup Master, repeat the procedure above, substituting \`node-b\` everywhere you see \`node-a\`. Be sure not to overwrite your existing *.ssh/authorized\\_keys* files, but concatenate the new key onto the existing file using the \`>>\` operator rather than the \`>\` operator.
+ </Step>
+</Steps>
+
+### Procedure: Prepare \`node-a\`
+
+\`node-a\` will run your primary master and ZooKeeper processes, but no RegionServers. Stop the RegionServer from starting on \`node-a\`.
+
+<Steps>
+ <Step>
+ Edit *conf/regionservers* and remove the line which contains \`localhost\`. Add lines with the hostnames or IP addresses for \`node-b\` and \`node-c\`.
+
+ Even if you did want to run a RegionServer on \`node-a\`, you should refer to it by the hostname the other servers would use to communicate with it. In this case, that would be \`node-a.example.com\`. This enables you to distribute the configuration to each node of your cluster any hostname conflicts. Save the file.
+ </Step>
+
+ <Step>
+ #### Configure HBase to use \`node-b\` as a backup master
+
+ Create a new file in *conf/* called *backup-masters*, and add a new line to it with the hostname for \`node-b\`. In this demonstration, the hostname is \`node-b.example.com\`.
+ </Step>
+
+ <Step>
+ #### Configure ZooKeeper
+
+ In reality, you should carefully consider your ZooKeeper configuration. You can find out more about configuring ZooKeeper in [zookeeper](/docs/zookeeper) section. This configuration will direct HBase to start and manage a ZooKeeper instance on each node of the cluster.
+
+ On \`node-a\`, edit *conf/hbase-site.xml* and add the following properties.
+
+ \`\`\`xml
+ <property>
+ <name>hbase.zookeeper.quorum</name>
+ <value>node-a.example.com,node-b.example.com,node-c.example.com</value>
+ </property>
+ <property>
+ <name>hbase.zookeeper.property.dataDir</name>
+ <value>/usr/local/zookeeper</value>
+ </property>
+ \`\`\`
+ </Step>
+
+ <Step>
+ Everywhere in your configuration that you have referred to \`node-a\` as \`localhost\`, change the reference to point to the hostname that the other nodes will use to refer to \`node-a\`. In these examples, the hostname is \`node-a.example.com\`.
+ </Step>
+</Steps>
+
+### Procedure: Prepare \`node-b\` and \`node-c\`
+
+\`node-b\` will run a backup master server and a ZooKeeper instance.
+
+<Steps>
+ <Step>
+ #### Download and unpack HBase
+
+ Download and unpack HBase to \`node-b\`, just as you did for the standalone and pseudo-distributed quickstarts.
+ </Step>
+
+ <Step>
+ #### Copy the configuration files from \`node-a\` to \`node-b\`.and \`node-c\`
+
+ Each node of your cluster needs to have the same configuration information. Copy the contents of the *conf/* directory to the *conf/* directory on \`node-b\` and \`node-c\`.
+ </Step>
+</Steps>
+
+### Procedure: Start and Test Your Cluster
+
+<Steps>
+ <Step>
+ #### Be sure HBase is not running on any node
+
+ If you forgot to stop HBase from previous testing, you will have errors. Check to see whether HBase is running on any of your nodes by using the \`jps\` command. Look for the processes \`HMaster\`, \`HRegionServer\`, and \`HQuorumPeer\`. If they exist, kill them.
+ </Step>
+
+ <Step>
+ #### Start the cluster
+
+ On \`node-a\`, issue the \`start-hbase.sh\` command. Your output will be similar to that below.
+
+ \`\`\`bash
+ $ bin/start-hbase.sh
+ node-c.example.com: starting zookeeper, logging to /home/hbuser/hbase-0.98.3-hadoop2/bin/../logs/hbase-hbuser-zookeeper-node-c.example.com.out
+ node-a.example.com: starting zookeeper, logging to /home/hbuser/hbase-0.98.3-hadoop2/bin/../logs/hbase-hbuser-zookeeper-node-a.example.com.out
+ node-b.example.com: starting zookeeper, logging to /home/hbuser/hbase-0.98.3-hadoop2/bin/../logs/hbase-hbuser-zookeeper-node-b.example.com.out
+ starting master, logging to /home/hbuser/hbase-0.98.3-hadoop2/bin/../logs/hbase-hbuser-master-node-a.example.com.out
+ node-c.example.com: starting regionserver, logging to /home/hbuser/hbase-0.98.3-hadoop2/bin/../logs/hbase-hbuser-regionserver-node-c.example.com.out
+ node-b.example.com: starting regionserver, logging to /home/hbuser/hbase-0.98.3-hadoop2/bin/../logs/hbase-hbuser-regionserver-node-b.example.com.out
+ node-b.example.com: starting master, logging to /home/hbuser/hbase-0.98.3-hadoop2/bin/../logs/hbase-hbuser-master-nodeb.example.com.out
+ \`\`\`
+
+ ZooKeeper starts first, followed by the master, then the RegionServers, and finally the backup masters.
+ </Step>
+
+ <Step>
+ #### Verify that the processes are running
+
+ On each node of the cluster, run the \`jps\` command and verify that the correct processes are running on each server. You may see additional Java processes running on your servers as well, if they are used for other purposes.
+
+ \`node-a\` \`jps\` Output
+
+ \`\`\`bash
+ $ jps
+ 20355 Jps
+ 20071 HQuorumPeer
+ 20137 HMaster
+ \`\`\`
+
+ \`node-b\` \`jps\` Output
+
+ \`\`\`bash
+ $ jps
+ 15930 HRegionServer
+ 16194 Jps
+ 15838 HQuorumPeer
+ 16010 HMaster
+ \`\`\`
+
+ \`node-c\` \`jps\` Output
+
+ \`\`\`bash
+ $ jps
+ 13901 Jps
+ 13639 HQuorumPeer
+ 13737 HRegionServer
+ \`\`\`
+
+ <Callout type="info">
+ The \`HQuorumPeer\` process is a ZooKeeper instance which is controlled and started by HBase. If you
+ use ZooKeeper this way, it is limited to one instance per cluster node and is appropriate for
+ testing only. If ZooKeeper is run outside of HBase, the process is called \`QuorumPeer\`. For more
+ about ZooKeeper configuration, including using an external ZooKeeper instance with HBase, see
+ [zookeeper](/docs/zookeeper) section.
+ </Callout>
+ </Step>
+
+ <Step>
+ #### Browse to the Web UI
+
+ If everything is set up correctly, you should be able to connect to the UI for the Master \`http://node-a.example.com:16010/\` or the secondary master at \`http://node-b.example.com:16010/\` using a web browser. If you can connect via \`localhost\` but not from another host, check your firewall rules. You can see the web UI for each of the RegionServers at port 16030 of their IP addresses, or by clicking their links in the web UI for the Master.
+ </Step>
+
+ <Step>
+ #### Test what happens when nodes or services disappear
+
+ With a three-node cluster you have configured, things will not be very resilient. You can still test the behavior of the primary Master or a RegionServer by killing the associated processes and watching the logs.
+ </Step>
+</Steps>
+
+## Where to go next
+
+The next chapter, [configuration](/docs/configuration), gives more information about the different HBase run modes, system requirements for running HBase, and critical configuration areas for setting up a distributed HBase cluster.
+
+***
+
+# Configuration
+
+This chapter expands upon the [Getting Started](/docs/getting-started) chapter to further explain configuration of Apache HBase. Please read this chapter carefully, especially the [Basic Prerequisites](/docs/configuration/basic-prerequisites) to ensure that your HBase testing and deployment goes smoothly. Familiarize yourself with [Support and Testing Expectations](/docs#support-and-testing-expectations) as well.
+
+## Configuration Files
+
+Apache HBase uses the same configuration system as Apache Hadoop. All configuration files are located in the *conf/* directory, which needs to be kept in sync for each node on your cluster.
+
+***backup-masters***\\
+Not present by default. A plain-text file which lists hosts on which the Master should start a backup Master process, one host per line.
+
+***hadoop-metrics2-hbase.properties***\\
+Used to connect HBase Hadoop's Metrics2 framework. See the [Hadoop Wiki entry](https://cwiki.apache.org/confluence/display/HADOOP2/HADOOP-6728-MetricsV2) for more information on Metrics2. Contains only commented-out examples by default.
+
+***hbase-env.cmd* and *hbase-env.sh***\\
+Script for Windows and Linux / Unix environments to set up the working environment for HBase, including the location of Java, Java options, and other environment variables. The file contains many commented-out examples to provide guidance.
+
+***hbase-policy.xml***\\
+The default policy configuration file used by RPC servers to make authorization decisions on client requests. Only used if HBase [security](/docs/security) is enabled.
+
+***hbase-site.xml***\\
+The main HBase configuration file. This file specifies configuration options which override HBase's default configuration. You can view (but do not edit) the default configuration file at *hbase-common/src/main/resources/hbase-default.xml*. You can also view the entire effective configuration for your cluster (defaults and overrides) in the **HBase Configuration** tab of the HBase Web UI.
+
+***log4j2.properties***\\
+Configuration file for HBase logging via \`log4j2\`.
+
+***regionservers***\\
+A plain-text file containing a list of hosts which should run a RegionServer in your HBase cluster. By default, this file contains the single entry \`localhost\`. It should contain a list of hostnames or IP addresses, one per line, and should only contain \`localhost\` if each node in your cluster will run a RegionServer on its \`localhost\` interface.
+
+<Callout type="tip">
+ When you edit XML, it is a good idea to use an XML-aware editor to be sure that your syntax is
+ correct and your XML is well-formed. You can also use the \`xmllint\` utility to check that your XML
+ is well-formed. By default, \`xmllint\` re-flows and prints the XML to standard output. To check for
+ well-formedness and only print output if errors exist, use the command \`xmllint -noout
+ filename.xml\`.
+</Callout>
+
+<Callout type="warn">
+ When running in distributed mode, after you make an edit to an HBase configuration, make sure you
+ copy the contents of the *conf/* directory to all nodes of the cluster. HBase will not do this for
+ you. Use a configuration management tool for managing and copying the configuration files to your
+ nodes. For most configurations, a restart is needed for servers to pick up changes. Dynamic
+ configuration is an exception to this, to be described later below.
+</Callout>
+
+## Basic Prerequisites
+
+## Java
+
+HBase runs on the Java Virtual Machine, thus all HBase deployments require a JVM runtime.
+
+The following table summarizes the recommendations of the HBase community with respect to running on various Java versions. The ✅ symbol indicates a base level of testing and willingness to help diagnose and address issues you might run into; these are the expected deployment combinations. An entry of ⚠️ means that there may be challenges with this combination, and you should look for more information before deciding to pursue this as your deployment strategy. The ❌ means this combinatio [...]
+
+<Callout type="warn">
+ HBase recommends downstream users rely only on JDK releases that are marked as Long-Term Supported
+ (LTS), either from the OpenJDK project or vendors. At the time of this writing, the following JDK
+ releases are NOT LTS releases and are NOT tested or advocated for use by the Apache HBase
+ community: JDK9, JDK10, JDK12, JDK13, and JDK14. Community discussion around this decision is
+ recorded on [HBASE-20264](https://issues.apache.org/jira/browse/HBASE-20264).
+</Callout>
+
+<Callout type="tip">
+ At this time, all testing performed by the Apache HBase project runs on the HotSpot variant of the
+ JVM. When selecting your JDK distribution, please take this into consideration.
+</Callout>
+
+**Java support by release line**
+
+| HBase Version | JDK 6 | JDK 7 | JDK 8 | JDK 11 | JDK 17 |
+| :-----------: | :---: | :---: | :---: | :----: | :----: |
+| HBase 2.6 | ❌ | ❌ | ✅ | ✅ | ✅ |
+| HBase 2.5 | ❌ | ❌ | ✅ | ✅ | ⚠️\\* |
+| HBase 2.4 | ❌ | ❌ | ✅ | ✅ | ❌ |
+| HBase 2.3 | ❌ | ❌ | ✅ | ⚠️\\* | ❌ |
+| HBase 2.0-2.2 | ❌ | ❌ | ✅ | ❌ | ❌ |
+| HBase 1.2+ | ❌ | ✅ | ✅ | ❌ | ❌ |
+| HBase 1.0-1.1 | ❌ | ✅ | ⚠️ | ❌ | ❌ |
+| HBase 0.98 | ✅ | ✅ | ⚠️ | ❌ | ❌ |
+| HBase 0.94 | ✅ | ✅ | ❌ | ❌ | ❌ |
+
+<Callout type="warn">
+ Preliminary support for JDK11 is introduced with HBase 2.3.0, and for JDK17 is introduced with HBase 2.5.x. We will compile and run test suites with JDK11/17 in pre commit checks and nightly checks. We will mark the support as ✅ as long as we have run some ITs with the JDK version and also there are users in the community use the JDK version in real production clusters.
+
+ For JDK11/JDK17 support in HBase, please refer to [HBASE-22972](https://issues.apache.org/jira/browse/HBASE-22972) and [HBASE-26038](https://issues.apache.org/jira/browse/HBASE-26038)
+
+ For JDK11/JDK17 support in Hadoop, which may also affect HBase, please refer to [HADOOP-15338](https://issues.apache.org/jira/browse/HADOOP-15338) and [HADOOP-17177](https://issues.apache.org/jira/browse/HADOOP-17177)
+</Callout>
+
+<Callout type="info">
+ You must set \`JAVA_HOME\` on each node of your cluster. *hbase-env.sh* provides a handy mechanism
+ to do this.
+</Callout>
+
+### Operating System Utilities
+
+#### ssh
+
+HBase uses the Secure Shell (ssh) command and utilities extensively to communicate between cluster nodes. Each server in the cluster must be running \`ssh\` so that the Hadoop and HBase daemons can be managed. You must be able to connect to all nodes via SSH, including the local node, from the Master as well as any backup Master, using a shared key rather than a password. You can see the basic methodology for such a set-up in Linux or Unix systems at "[Procedure: Configure Passwordless S [...]
+
+#### DNS
+
+HBase uses the local hostname to self-report its IP address.
+
+#### NTP
+
+The clocks on cluster nodes should be synchronized. A small amount of variation is acceptable, but larger amounts of skew can cause erratic and unexpected behavior. Time synchronization is one of the first things to check if you see unexplained problems in your cluster. It is recommended that you run a Network Time Protocol (NTP) service, or another time-synchronization mechanism on your cluster and that all nodes look to the same service for time synchronization. See the [Basic NTP Conf [...]
+
+#### Limits on Number of Files and Processes (ulimit)
+
+Apache HBase is a database. It requires the ability to open a large number of files at once. Many Linux distributions limit the number of files a single user is allowed to open to \`1024\` (or \`256\` on older versions of OS X). You can check this limit on your servers by running the command \`ulimit -n\` when logged in as the user which runs HBase. See [the Troubleshooting section](/docs/troubleshooting#javaioioexceptiontoo-many-open-files) for some of the problems you may experience if [...]
+
+\`\`\`text
+2010-04-06 03:04:37,542 INFO org.apache.hadoop.hdfs.DFSClient: Exception increateBlockOutputStream java.io.EOFException
+2010-04-06 03:04:37,542 INFO org.apache.hadoop.hdfs.DFSClient: Abandoning block blk_-6935524980745310745_1391901
+\`\`\`
+
+It is recommended to raise the ulimit to at least 10,000, but more likely 10,240, because the value is usually expressed in multiples of 1024. Each ColumnFamily has at least one StoreFile, and possibly more than six StoreFiles if the region is under load. The number of open files required depends upon the number of ColumnFamilies and the number of regions. The following is a rough formula for calculating the potential number of open files on a RegionServer.
+
+**Calculate the Potential Number of Open Files:**
+
+\`\`\`text
+(StoreFiles per ColumnFamily) x (regions per RegionServer)
+\`\`\`
+
+For example, assuming that a schema had 3 ColumnFamilies per region with an average of 3 StoreFiles per ColumnFamily, and there are 100 regions per RegionServer, the JVM will open \`3 * 3 * 100 = 900\` file descriptors, not counting open JAR files, configuration files, and others. Opening a file does not take many resources, and the risk of allowing a user to open too many files is minimal.
+
+Another related setting is the number of processes a user is allowed to run at once. In Linux and Unix, the number of processes is set using the \`ulimit -u\` command. This should not be confused with the \`nproc\` command, which controls the number of CPUs available to a given user. Under load, a \`ulimit -u\` that is too low can cause OutOfMemoryError exceptions.
+
+Configuring the maximum number of file descriptors and processes for the user who is running the HBase process is an operating system configuration, rather than an HBase configuration. It is also important to be sure that the settings are changed for the user that actually runs HBase. To see which user started HBase, and that user's ulimit configuration, look at the first line of the HBase log for that instance.
+
+#### Example: \`ulimit\` Settings on Ubuntu \\[!toc]
+
+To configure ulimit settings on Ubuntu, edit */etc/security/limits.conf*, which is a space-delimited file with four columns. Refer to the man page for *limits.conf* for details about the format of this file. In the following example, the first line sets both soft and hard limits for the number of open files (nofile) to 32768 for the operating system user with the username hadoop. The second line sets the number of processes to 32000 for the same user.
+
+\`\`\`text
+hadoop - nofile 32768
+hadoop - nproc 32000
+\`\`\`
+
+The settings are only applied if the Pluggable Authentication Module (PAM) environment is directed to use them. To configure PAM to use these limits, be sure that the */etc/pam.d/common-session* file contains the following line:
+
+\`\`\`text
+session required pam_limits.so
+\`\`\`
+
+#### Linux Shell
+
+All of the shell scripts that come with HBase rely on the [GNU Bash](http://www.gnu.org/software/bash) shell.
+
+#### Windows
+
+Running production systems on Windows machines is not recommended.
+
+## Hadoop
+
+The following table summarizes the versions of [Hadoop](https://hadoop.apache.org) supported with each version of HBase. Older versions not appearing in this table are considered unsupported and likely missing necessary features, while newer versions are untested but may be suitable.
+
+Based on the version of HBase, you should select the most appropriate version of Hadoop. You can use Apache Hadoop, or a vendor's distribution of Hadoop. No distinction is made here. See [the Hadoop wiki](https://cwiki.apache.org/confluence/display/HADOOP2/Distributions+and+Commercial+Support) for information about vendors of Hadoop.
+
+<Callout type="tip">
+ Comparing to Hadoop 1.x, Hadoop 2.x is faster and includes features, such as short-circuit reads (see [Leveraging local data](/docs/performance#leveraging-local-data)), which will help improve your HBase random read profile. Hadoop 2.x also includes important bug fixes that will improve your overall HBase experience. HBase does not support running with earlier versions of Hadoop. See the table below for requirements specific to different HBase versions.
+
+ Today, Hadoop 3.x is recommended as the last Hadoop 2.x release 2.10.2 was released years ago, and there is no release for Hadoop 2.x for a very long time, although the Hadoop community does not officially EOL Hadoop 2.x yet.
+</Callout>
+
+Use the following legend to interpret these tables:
+
+* ✅ = Tested to be fully-functional
+* ❌ = Known to not be fully-functional, or there are [CVEs](https://hadoop.apache.org/cve_list.html) so we drop the support in newer minor releases
+* ⚠️ = Not tested, may/may-not function
+
+| | HBase-2.5.x | HBase-2.6.x |
+| ------------------ | ----------- | ----------- |
+| Hadoop-2.10.\\[0-1] | ❌ | ❌ |
+| Hadoop-2.10.2+ | ✅ | ✅ |
+| Hadoop-3.1.0 | ❌ | ❌ |
+| Hadoop-3.1.1+ | ❌ | ❌ |
+| Hadoop-3.2.\\[0-2] | ❌ | ❌ |
+| Hadoop-3.2.3+ | ✅ | ❌ |
+| Hadoop-3.3.\\[0-1] | ❌ | ❌ |
+| Hadoop-3.3.\\[2-4] | ✅ | ❌ |
+| Hadoop-3.3.5+ | ✅ | ✅ |
+| Hadoop-3.4.0+ | ✅ (2.5.11+) | ✅ (2.6.2+) |
+
+### Hadoop version support matrix for active release lines
+
+| | HBase-2.3.x | HBase-2.4.x |
+| ------------- | ----------- | ----------- |
+| Hadoop-2.10.x | ✅ | ✅ |
+| Hadoop-3.1.0 | ❌ | ❌ |
+| Hadoop-3.1.1+ | ✅ | ✅ |
+| Hadoop-3.2.x | ✅ | ✅ |
+| Hadoop-3.3.x | ✅ | ✅ |
+
+### Hadoop version support matrix for EOM 2.3+ release lines
+
+| | HBase-2.0.x | HBase-2.1.x | HBase-2.2.x |
+| ----------------- | ----------- | ----------- | ----------- |
+| Hadoop-2.6.1+ | ✅ | ❌ | ❌ |
+| Hadoop-2.7.\\[0-6] | ❌ | ❌ | ❌ |
+| Hadoop-2.7.7+ | ✅ | ✅ | ❌ |
+| Hadoop-2.8.\\[0-2] | ❌ | ❌ | ❌ |
+| Hadoop-2.8.\\[3-4] | ✅ | ✅ | ❌ |
+| Hadoop-2.8.5+ | ✅ | ✅ | ✅ |
+| Hadoop-2.9.\\[0-1] | ⚠️ | ❌ | ❌ |
+| Hadoop-2.9.2+ | ⚠️ | ⚠️ | ✅ |
+| Hadoop-3.0.\\[0-2] | ❌ | ❌ | ❌ |
+| Hadoop-3.0.3+ | ❌ | ✅ | ❌ |
+| Hadoop-3.1.0 | ❌ | ❌ | ❌ |
+| Hadoop-3.1.1+ | ❌ | ✅ | ✅ |
+
+### Hadoop version support matrix for EOM 2.x release lines
+
+| | HBase-1.5.x | HBase-1.6.x | HBase-1.7.x |
+| ----------------- | ----------- | ----------- | ----------- |
+| Hadoop-2.7.7+ | ✅ | ❌ | ❌ |
+| Hadoop-2.8.\\[0-4] | ❌ | ❌ | ❌ |
+| Hadoop-2.8.5+ | ✅ | ✅ | ✅ |
+| Hadoop-2.9.\\[0-1] | ❌ | ❌ | ❌ |
+| Hadoop-2.9.2+ | ✅ | ✅ | ✅ |
+| Hadoop-2.10.x | ⚠️ | ✅ | ✅ |
+
+### Hadoop version support matrix for EOM 1.5+ release lines
+
+| | HBase-1.0.x (Hadoop 1.x is NOT supported) | HBase-1.1.x | HBase-1.2.x | HBase-1.3.x | HBase-1.4.x |
+| ------------- | ----------------------------------------- | ----------- | ----------- | ----------- | ----------- |
+| Hadoop-2.4.x | ✅ | ✅ | ✅ | ✅ | ❌ |
+| Hadoop-2.5.x | ✅ | ✅ | ✅ | ✅ | ❌ |
+| Hadoop-2.6.0 | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Hadoop-2.6.1+ | ⚠️ | ⚠️ | ✅ | ✅ | ❌ |
+| Hadoop-2.7.0 | ❌ | ❌ | ❌ | ❌ | ❌ |
+| Hadoop-2.7.1+ | ⚠️ | ⚠️ | ✅ | ✅ | ✅ |
+
+### Hadoop version support matrix for EOM 1.x release lines
+
+| | HBase-0.92.x | HBase-0.94.x | HBase-0.96.x | HBase-0.98.x (Support for Hadoop 1.1+ is deprecated.) |
+| ------------------ | ------------ | ------------ | ------------ | ----------------------------------------------------- |
+| Hadoop-0.20.205 | ✅ | ❌ | ❌ | ❌ |
+| Hadoop-0.22.x | ✅ | ❌ | ❌ | ❌ |
+| Hadoop-1.0.x | ❌ | ❌ | ❌ | ❌ |
+| Hadoop-1.1.x | ⚠️ | ✅ | ✅ | ⚠️ |
+| Hadoop-0.23.x | ❌ | ✅ | ⚠️ | ❌ |
+| Hadoop-2.0.x-alpha | ❌ | ⚠️ | ❌ | ❌ |
+| Hadoop-2.1.0-beta | ❌ | ⚠️ | ✅ | ❌ |
+| Hadoop-2.2.0 | ❌ | ⚠️ | ✅ | ✅ |
+| Hadoop-2.3.x | ❌ | ⚠️ | ✅ | ✅ |
+| Hadoop-2.4.x | ❌ | ⚠️ | ✅ | ✅ |
+| Hadoop-2.5.x | ❌ | ⚠️ | ✅ | ✅ |
+
+### Hadoop version support matrix for EOM pre-1.0 release lines
+
+<Callout type="idea">
+ Starting around the time of Hadoop version 2.7.0, the Hadoop PMC got into the habit of calling out
+ new minor releases on their major version 2 release line as not stable / production ready. As
+ such, HBase expressly advises downstream users to avoid running on top of these releases. Note
+ that additionally the 2.8.1 release was given the same caveat by the Hadoop PMC. For reference,
+ see the release announcements for [Apache Hadoop
+ 2.7.0](https://s.apache.org/hadoop-2.7.0-announcement), [Apache Hadoop
+ 2.8.0](https://s.apache.org/hadoop-2.8.0-announcement), [Apache Hadoop
+ 2.8.1](https://s.apache.org/hadoop-2.8.1-announcement), and [Apache Hadoop
+ 2.9.0](https://s.apache.org/hadoop-2.9.0-announcement).
+</Callout>
+
+<Callout type="idea">
+ The Hadoop PMC called out the 3.1.0 release as not stable / production ready. As such, HBase
+ expressly advises downstream users to avoid running on top of this release. For reference, see the
+ [release announcement for Hadoop 3.1.0](https://s.apache.org/hadoop-3.1.0-announcement).
+</Callout>
+
+<Callout type="info">
+ Because HBase depends on Hadoop, it bundles Hadoop jars under its *lib* directory. The bundled
+ jars are ONLY for use in stand-alone mode. In distributed mode, it is *critical* that the version
+ of Hadoop that is out on your cluster match what is under HBase. Replace the hadoop jars found in
+ the HBase lib directory with the equivalent hadoop jars from the version you are running on your
+ cluster to avoid version mismatch issues. Make sure you replace the jars under HBase across your
+ whole cluster. Hadoop version mismatch issues have various manifestations. Check for mismatch if
+ HBase appears hung.
+</Callout>
+
+### Hadoop 3 Support for the HBase Binary Releases and Maven Artifacts
+
+For HBase 2.5.1 and earlier, the official HBase binary releases and Maven artifacts were built with Hadoop 2.x.
+
+Starting with HBase 2.5.2, HBase provides binary releases and Maven artifacts built with both Hadoop 2.x and Hadoop 3.x. The Hadoop 2 artifacts do not have any version suffix, the Hadoop 3 artifacts add the \`-hadoop-3\` suffix to the version. i.e. \`hbase-2.5.2-bin.tar.gz.asc\` is the Binary release built with Hadoop2, and \`hbase-2.5.2-hadoop3-bin.tar.gz\` is the release built with Hadoop 3.
+
+### Hadoop 3 version policy
+
+Each HBase release has a default Hadoop 3 version. This is used when the Hadoop 3 version is not specified during build, and for building the official binary releases and artifacts. Generally when a new minor version is released (i.e. 2.5.0) the default version is set to the latest supported Hadoop 3 version at the start of the release process.
+
+Up to HBase 2.5.10 and 2.6.1 even if HBase added support for newer Hadoop 3 releases in a patch release, the default Hadoop 3 version (and the one used in the official binary releases) was not updated. This simplified upgrading, but meant that HBase releases often included old unfixed CVEs both from Hadoop and Hadoop's dependencies, even when newer Hadoop releases with fixes were available.
+
+Starting with HBase 2.5.11 and 2.6.2, the default Hadoop 3 version is always set to the latest supported Hadoop 3 version, and is also used for the \`-hadoop3\` binary releases and artifacts. This will drastically reduce the number of known CVEs shipped in the HBase binary releases, and make sure that all fixes and improvements in Hadoop are included.
+
+### \`dfs.datanode.max.transfer.threads\`
+
+An HDFS DataNode has an upper bound on the number of files that it will serve at any one time. Before doing any loading, make sure you have configured Hadoop's *conf/hdfs-site.xml*, setting the \`dfs.datanode.max.transfer.threads\` value to at least the following:
+
+\`\`\`xml
+<property>
+ <name>dfs.datanode.max.transfer.threads</name>
+ <value>4096</value>
+</property>
+\`\`\`
+
+Be sure to restart your HDFS after making the above configuration.
+
+Not having this configuration in place makes for strange-looking failures. One manifestation is a complaint about missing blocks. For example:
+
+\`\`\`text
+10/12/08 20:10:31 INFO hdfs.DFSClient: Could not obtain block
+ blk_XXXXXXXXXXXXXXXXXXXXXX_YYYYYYYY from any node: java.io.IOException: No live nodes
+ contain current block. Will get new block locations from namenode and retry...
+\`\`\`
+
+See also [Case Studies](/docs/case-studies#case-study-4-maxtransferthreads-config) and note that this property was previously known as \`dfs.datanode.max.xcievers\` (e.g. [Hadoop HDFS: Deceived by Xciever](http://ccgtech.blogspot.com/2010/02/hadoop-hdfs-deceived-by-xciever.html)).
+
+## ZooKeeper Requirements
+
+An Apache ZooKeeper quorum is required. The exact version depends on your version of HBase, though the minimum ZooKeeper version is 3.4.x due to the \`useMulti\` feature made default in 1.0.0 (see [HBASE-16598](https://issues.apache.org/jira/browse/HBASE-16598)).
+
+## HBase run modes: Standalone and Distributed
+
+HBase has two run modes: [standalone](/docs/configuration/hbase-run-models#standalone-hbase) and [distributed](/docs/configuration/hbase-run-models#distributed). Out of the box, HBase runs in standalone mode. Whatever your mode, you will need to configure HBase by editing files in the HBase *conf* directory. At a minimum, you must edit \`conf/hbase-env.sh\` to tell HBase which java to use. In this file you set HBase environment variables such as the heapsize and other options for the \`J [...]
+
+## Standalone HBase
+
+This is the default mode. Standalone mode is what is described in the [quickstart](/docs/getting-started#quick-start---standalone-hbase) section. In standalone mode, HBase does not use HDFS — it uses the local filesystem instead — and it runs all HBase daemons and a local ZooKeeper all up in the same JVM. ZooKeeper binds to a well-known port so clients may talk to HBase.
+
+### Standalone HBase over HDFS
+
+A sometimes useful variation on standalone hbase has all daemons running inside the one JVM but rather than persist to the local filesystem, instead they persist to an HDFS instance.
+
+You might consider this profile when you are intent on a simple deploy profile, the loading is light, but the data must persist across node comings and goings. Writing to HDFS where data is replicated ensures the latter.
+
+To configure this standalone variant, edit your *hbase-site.xml* setting *hbase.rootdir* to point at a directory in your HDFS instance but then set *hbase.cluster.distributed* to *false*. For example:
+
+\`\`\`xml
+<configuration>
+ <property>
+ <name>hbase.rootdir</name>
+ <value>hdfs://namenode.example.org:9000/hbase</value>
+ </property>
+ <property>
+ <name>hbase.cluster.distributed</name>
+ <value>false</value>
+ </property>
+</configuration>
+\`\`\`
+
+## Distributed
+
+Distributed mode can be subdivided into distributed but all daemons run on a single node — a.k.a. *pseudo-distributed* — and *fully-distributed* where the daemons are spread across all nodes in the cluster. The *pseudo-distributed* vs. *fully-distributed* nomenclature comes from Hadoop.
+
+Pseudo-distributed mode can run against the local filesystem or it can run against an instance of the *Hadoop Distributed File System* (HDFS). Fully-distributed mode can ONLY run on HDFS. See the Hadoop [documentation](https://hadoop.apache.org/docs/current/) for how to set up HDFS. A good walk-through for setting up HDFS on Hadoop 2 can be found at [https://web.archive.org/web/20221007121526/https://www.alexjf.net/blog/distributed-systems/hadoop-yarn-installation-definitive-guide/](http [...]
+
+### Pseudo-distributed
+
+<Callout type="info">
+ A quickstart has been added to the
+ [quickstart](/docs/getting-started#quick-start---standalone-hbase) chapter. See
+ [quickstart-pseudo](/docs/getting-started#pseudo-distributed-for-local-testing). Some of the
+ information that was originally in this section has been moved there.
+</Callout>
+
+A pseudo-distributed mode is simply a fully-distributed mode run on a single host. Use this HBase configuration for testing and prototyping purposes only. Do not use this configuration for production or for performance evaluation.
+
+## Fully-distributed
+
+By default, HBase runs in stand-alone mode. Both stand-alone mode and pseudo-distributed mode are provided for the purposes of small-scale testing. For a production environment, distributed mode is advised. In distributed mode, multiple instances of HBase daemons run on multiple servers in the cluster.
+
+Just as in pseudo-distributed mode, a fully distributed configuration requires that you set the \`hbase.cluster.distributed\` property to \`true\`. Typically, the \`hbase.rootdir\` is configured to point to a highly-available HDFS filesystem.
+
+In addition, the cluster is configured so that multiple cluster nodes enlist as RegionServers, ZooKeeper QuorumPeers, and backup HMaster servers. These configuration basics are all demonstrated in [quickstart-fully-distributed](/docs/getting-started#fully-distributed-for-production).
+
+### Distributed RegionServers
+
+Typically, your cluster will contain multiple RegionServers all running on different servers, as well as primary and backup Master and ZooKeeper daemons. The *conf/regionservers* file on the master server contains a list of hosts whose RegionServers are associated with this cluster. Each host is on a separate line. All hosts listed in this file will have their RegionServer processes started and stopped when the master server starts or stops.
+
+### ZooKeeper and HBase
+
+See the [ZooKeeper](/docs/zookeeper) section for ZooKeeper setup instructions for HBase.
+
+### Example: Distributed HBase Cluster
+
+This is a bare-bones *conf/hbase-site.xml* for a distributed HBase cluster. A cluster that is used for real-world work would contain more custom configuration parameters. Most HBase configuration directives have default values, which are used unless the value is overridden in the *hbase-site.xml*. See "[Configuration Files](/docs/configuration/default)" for more information.
+
+\`\`\`xml
+<configuration>
+ <property>
+ <name>hbase.rootdir</name>
+ <value>hdfs://namenode.example.org:9000/hbase</value>
+ </property>
+ <property>
+ <name>hbase.cluster.distributed</name>
+ <value>true</value>
+ </property>
+ <property>
+ <name>hbase.zookeeper.quorum</name>
+ <value>node-a.example.com,node-b.example.com,node-c.example.com</value>
+ </property>
+</configuration>
+\`\`\`
+
+This is an example *conf/regionservers* file, which contains a list of nodes that should run a RegionServer in the cluster. These nodes need HBase installed and they need to use the same contents of the *conf/* directory as the Master server.
+
+\`\`\`text
+node-a.example.com
+node-b.example.com
+node-c.example.com
+\`\`\`
+
+This is an example *conf/backup-masters* file, which contains a list of each node that should run a backup Master instance. The backup Master instances will sit idle unless the main Master becomes unavailable.
+
+\`\`\`text
+node-b.example.com
+node-c.example.com
+\`\`\`
+
+### Distributed HBase Quickstart
+
+See [quickstart-fully-distributed](/docs/getting-started#fully-distributed-for-production) for a walk-through of a simple three-node cluster configuration with multiple ZooKeeper, backup HMaster, and RegionServer instances.
+
+### Procedure: HDFS Client Configuration
+
+1. Of note, if you have made HDFS client configuration changes on your Hadoop cluster, such as configuration directives for HDFS clients, as opposed to server-side configurations, you must use one of the following methods to enable HBase to see and use these configuration changes:
+ * Add a pointer to your \`HADOOP_CONF_DIR\` to the \`HBASE_CLASSPATH\` environment variable in *hbase-env.sh*.
+ * Add a copy of *hdfs-site.xml* (or *hadoop-site.xml*) or, better, symlinks, under \`$HBASE_HOME/conf\`, or
+ * if only a small set of HDFS client configurations, add them to *hbase-site.xml*.
+
+An example of such an HDFS client configuration is \`dfs.replication\`. If for example, you want to run with a replication factor of 5, HBase will create files with the default of 3 unless you do the above to make the configuration available to HBase.
+
+## Choosing between the Classic Package and the BYO Hadoop Package
+
+Starting with HBase 3.0, HBase includes two binary packages. The classic package includes both the HBase and Hadoop components, while the Hadoop-less "Bring Your Own Hadoop" package omits the Hadoop components, and uses the files from an existing Hadoop installation. The classic binary package filename is named \`hbase-VERSION-bin.tar.gz\` (e.g. *hbase-3.0.0-bin.tar.gz*), while the Hadoop-less package is \`hbase-byo-hadoop-VERSION-bin.tar.gz\` (e.g. *hbase-byo-hadoop-3.0.0-bin.tar.gz*).
+
+If the cluster nodes already have Hadoop installed, you can use the Hadoop-less package. In this case you need to make sure that the \`HADOOP_HOME\` environment variable is set and points to the Hadoop installation. The easiest way to ensure this is to set it in *hbase-env.sh*. You still need to make sure that the Hadoop configuration files are present on the HBase classpath, as described above.
+
+## Advantages of the BYO Hadoop package:
+
+* There is no need to replace the Hadoop libraries.
+* It is easier to upgrade Hadoop and HBase independently (as long as compatible versions are used).
+* Both the package and installed size are about 100 MB smaller.
+
+## Running and Confirming Your Installation
+
+Make sure HDFS is running first. Start and stop the Hadoop HDFS daemons by running *bin/start-hdfs.sh* over in the \`HADOOP_HOME\` directory. You can ensure it started properly by testing the \`put\` and \`get\` of files into the Hadoop filesystem. HBase does not normally use the MapReduce or YARN daemons. These do not need to be started.
+
+*If* you are managing your own ZooKeeper, start it and confirm it's running, else HBase will start up ZooKeeper for you as part of its start process.
+
+Start HBase with the following command:
+
+\`\`\`bash
+bin/start-hbase.sh
+\`\`\`
+
+Run the above from the \`HBASE_HOME\` directory.
+
+You should now have a running HBase instance. HBase logs can be found in the *logs* subdirectory. Check them out especially if HBase had trouble starting.
+
+HBase also puts up a UI listing vital attributes. By default it's deployed on the Master host at port 16010 (HBase RegionServers listen on port 16020 by default and put up an informational HTTP server at port 16030). If the Master is running on a host named \`master.example.org\` on the default port, point your browser at [http://master.example.org:16010](http://master.example.org:16010) to see the web interface.
+
+Once HBase has started, see the [shell exercises](/docs/getting-started#procedure-use-hbase-for-the-first-time) documentation for how to create tables, add data, scan your insertions, and finally disable and drop your tables.
+
+To stop HBase after exiting the HBase shell enter
+
+\`\`\`bash
+$ ./bin/stop-hbase.sh
+stopping hbase...............
+\`\`\`
+
+Shutdown can take a moment to complete. It can take longer if your cluster is comprised of many machines. If you are running a distributed operation, be sure to wait until HBase has shut down completely before stopping the Hadoop daemons.
+
+## Default Configuration
+
+## *hbase-site.xml* and *hbase-default.xml*
+
+Just as in Hadoop where you add site-specific HDFS configuration to the *hdfs-site.xml* file, for HBase, site specific customizations go into the file *conf/hbase-site.xml*. For the list of configurable properties, see [hbase default configurations](/docs/configuration/default#configuration-default-hbase-default-configuration) below or view the raw *hbase-default.xml* source file in the HBase source code at *src/main/resources*.
+
+Not all configuration options make it out to *hbase-default.xml*. Some configurations would only appear in source code; the only way to identify these changes are through code review.
+
+Currently, changes here will require a cluster restart for HBase to notice the change.
+
+## HBase Default configuration
+
+The documentation below is generated using the default hbase configuration file, *hbase-default.xml*, as source.
+
+#### \`hbase.tmp.dir\` \\[!toc]
+
+**Description:** Temporary directory on the local filesystem. Change this setting to point to a location more permanent than '/tmp', the usual resolve for java.io.tmpdir, as the '/tmp' directory is cleared on machine restart.\\
+**Default:** \`\${java.io.tmpdir}/hbase-\${user.name}\`
+
+#### \`hbase.rootdir\` \\[!toc]
+
+**Description:** The directory shared by region servers and into which HBase persists. The URL should be 'fully-qualified' to include the filesystem scheme. For example, to specify the HDFS directory '/hbase' where the HDFS instance's namenode is running at namenode.example.org on port 9000, set this value to: hdfs\\://namenode.example.org:9000/hbase. By default, we write to whatever $\\{hbase.tmp.dir} is set too -- usually /tmp -- so change this configuration or else all data will be lo [...]
+**Default:** \`\${hbase.tmp.dir}/hbase\`
+
+#### \`hbase.cluster.distributed\` \\[!toc]
+
+**Description:** The mode the cluster will be in. Possible values are false for standalone mode and true for distributed mode. If false, startup will run all HBase and ZooKeeper daemons together in the one JVM.\\
+**Default:** \`false\`
+
+#### \`hbase.zookeeper.quorum\` \\[!toc]
+
+**Description:** Comma separated list of servers in the ZooKeeper ensemble (This config. should have been named hbase.zookeeper.ensemble). For example, "host1.mydomain.com,host2.mydomain.com,host3.mydomain.com". By default this is set to localhost for local and pseudo-distributed modes of operation. For a fully-distributed setup, this should be set to a full list of ZooKeeper ensemble servers. If HBASE\\_MANAGES\\_ZK is set in hbase-env.sh this is the list of servers which hbase will sta [...]
+**Default:** \`127.0.0.1\`
+
+#### \`zookeeper.recovery.retry.maxsleeptime\` \\[!toc]
+
+**Description:** Max sleep time before retry zookeeper operations in milliseconds, a max time is needed here so that sleep time won't grow unboundedly\\
+**Default:** \`60000\`
+
+#### \`hbase.local.dir\` \\[!toc]
+
+**Description:** Directory on the local filesystem to be used as a local storage.\\
+**Default:** \`\${hbase.tmp.dir}/local/\`
+
+#### \`hbase.master.port\` \\[!toc]
+
+**Description:** The port the HBase Master should bind to.\\
+**Default:** \`16000\`
+
+#### \`hbase.master.info.port\` \\[!toc]
+
+**Description:** The port for the HBase Master web UI. Set to -1 if you do not want a UI instance run.\\
+**Default:** \`16010\`
+
+#### \`hbase.master.info.bindAddress\` \\[!toc]
+
+**Description:** The bind address for the HBase Master web UI\\
+**Default:** \`0.0.0.0\`
+
+#### \`hbase.master.logcleaner.plugins\` \\[!toc]
+
+**Description:** A comma-separated list of BaseLogCleanerDelegate invoked by the LogsCleaner service. These WAL cleaners are called in order, so put the cleaner that prunes the most files in front. To implement your own BaseLogCleanerDelegate, just put it in HBase's classpath and add the fully qualified class name here. Always add the above default log cleaners in the list.\\
+**Default:** \`org.apache.hadoop.hbase.master.cleaner.TimeToLiveLogCleaner,org.apache.hadoop.hbase.master.cleaner.TimeToLiveProcedureWALCleaner,org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreWALCleaner\`
+
+#### \`hbase.master.logcleaner.ttl\` \\[!toc]
+
+**Description:** How long a WAL remain in the archive (\\{hbase.rootdir}/oldWALs) directory, after which it will be cleaned by a Master thread. The value is in milliseconds.\\
+**Default:** \`600000\`
+
+#### \`hbase.master.hfilecleaner.plugins\` \\[!toc]
+
+**Description:** A comma-separated list of BaseHFileCleanerDelegate invoked by the HFileCleaner service. These HFiles cleaners are called in order, so put the cleaner that prunes the most files in front. To implement your own BaseHFileCleanerDelegate, just put it in HBase's classpath and add the fully qualified class name here. Always add the above default hfile cleaners in the list as they will be overwritten in hbase-site.xml.\\
+**Default:** \`org.apache.hadoop.hbase.master.cleaner.TimeToLiveHFileCleaner,org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreHFileCleaner\`
+
+#### \`hbase.master.infoserver.redirect\` \\[!toc]
+
+**Description:** Whether or not the Master listens to the Master web UI port (hbase.master.info.port) and redirects requests to the web UI server shared by the Master and RegionServer. Config. makes sense when Master is serving Regions (not the default).\\
+**Default:** \`true\`
+
+#### \`hbase.master.fileSplitTimeout\` \\[!toc]
+
+**Description:** Splitting a region, how long to wait on the file-splitting step before aborting the attempt. Default: 600000. This setting used to be known as hbase.regionserver.fileSplitTimeout in hbase-1.x. Split is now run master-side hence the rename (If a 'hbase.master.fileSplitTimeout' setting found, will use it to prime the current 'hbase.master.fileSplitTimeout' Configuration.\\
+**Default:** \`600000\`
+
+#### \`hbase.regionserver.port\` \\[!toc]
+
+**Description:** The port the HBase RegionServer binds to.\\
+**Default:** \`16020\`
+
+#### \`hbase.regionserver.info.port\` \\[!toc]
+
+**Description:** The port for the HBase RegionServer web UI Set to -1 if you do not want the RegionServer UI to run.\\
+**Default:** \`16030\`
+
+#### \`hbase.regionserver.info.bindAddress\` \\[!toc]
+
+**Description:** The address for the HBase RegionServer web UI\\
+**Default:** \`0.0.0.0\`
+
+#### \`hbase.regionserver.info.port.auto\` \\[!toc]
+
+**Description:** Whether or not the Master or RegionServer UI should search for a port to bind to. Enables automatic port search if hbase.regionserver.info.port is already in use. Useful for testing, turned off by default.\\
+**Default:** \`false\`
+
+#### \`hbase.regionserver.handler.count\` \\[!toc]
+
+**Description:** Count of RPC Listener instances spun up on RegionServers. Same property is used by the Master for count of master handlers. Too many handlers can be counter-productive. Make it a multiple of CPU count. If mostly read-only, handlers count close to cpu count does well. Start with twice the CPU count and tune from there.\\
+**Default:** \`30\`
+
+#### \`hbase.ipc.server.callqueue.handler.factor\` \\[!toc]
+
+**Description:** Factor to determine the number of call queues. A value of 0 means a single queue shared between all the handlers. A value of 1 means that each handler has its own queue.\\
+**Default:** \`0.1\`
+
+#### \`hbase.ipc.server.callqueue.read.ratio\` \\[!toc]
+
+**Description:** Split the call queues into read and write queues. The specified interval (which should be between 0.0 and 1.0) will be multiplied by the number of call queues. A value of 0 indicate to not split the call queues, meaning that both read and write requests will be pushed to the same set of queues. A value lower than 0.5 means that there will be less read queues than write queues. A value of 0.5 means there will be the same number of read and write queues. A value greater th [...]
+**Default:** \`0\`
+
+#### \`hbase.ipc.server.callqueue.scan.ratio\` \\[!toc]
+
+**Description:** Given the number of read call queues, calculated from the total number of call queues multiplied by the callqueue.read.ratio, the scan.ratio property will split the read call queues into small-read and long-read queues. A value lower than 0.5 means that there will be less long-read queues than short-read queues. A value of 0.5 means that there will be the same number of short-read and long-read queues. A value greater than 0.5 means that there will be more long-read queu [...]
+**Default:** \`0\`
+
+#### \`hbase.regionserver.msginterval\` \\[!toc]
+
+**Description:** Interval between messages from the RegionServer to Master in milliseconds.\\
+**Default:** \`3000\`
+
+#### \`hbase.regionserver.logroll.period\` \\[!toc]
+
+**Description:** Period at which we will roll the commit log regardless of how many edits it has.\\
+**Default:** \`3600000\`
+
+#### \`hbase.regionserver.logroll.errors.tolerated\` \\[!toc]
+
+**Description:** The number of consecutive WAL close errors we will allow before triggering a server abort. A setting of 0 will cause the region server to abort if closing the current WAL writer fails during log rolling. Even a small value (2 or 3) will allow a region server to ride over transient HDFS errors.\\
+**Default:** \`2\`
+
+#### \`hbase.regionserver.free.heap.min.memory.size\` \\[!toc]
+
+**Description:** Defines the minimum amount of heap memory that must remain free for the RegionServer to start, specified in bytes or human-readable formats like '512m' for megabytes or '4g' for gigabytes. If not set, the default is 20% of the total heap size. To disable the check entirely, set this value to 0. If the combined memory usage of memstore and block cache exceeds (total heap - this value), the RegionServer will fail to start.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.regionserver.global.memstore.size\` \\[!toc]
+
+**Description:** Maximum size of all memstores in a region server before new updates are blocked and flushes are forced. Defaults to 40% of heap (0.4). Updates are blocked and flushes are forced until size of all memstores in a region server hits hbase.regionserver.global.memstore.size.lower.limit. The default value in this configuration has been intentionally left empty in order to honor the old hbase.regionserver.global.memstore.upperLimit property if present.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.regionserver.global.memstore.memory.size\` \\[!toc]
+
+**Description:** Maximum size of all memstores in a region server before new updates are blocked and flushes are forced, specified in bytes or human-readable formats like '10m' for megabytes or '10g' for gigabytes. This configuration allows setting an absolute memory size instead of a percentage of the maximum heap. Takes precedence over hbase.regionserver.global.memstore.size if both are specified.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.regionserver.global.memstore.size.lower.limit\` \\[!toc]
+
+**Description:** Maximum size of all memstores in a region server before flushes are forced. Defaults to 95% of hbase.regionserver.global.memstore.size (0.95). A 100% value for this value causes the minimum possible flushing to occur when updates are blocked due to memstore limiting. The default value in this configuration has been intentionally left empty in order to honor the old hbase.regionserver.global.memstore.lowerLimit property if present.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.systemtables.compacting.memstore.type\` \\[!toc]
+
+**Description:** Determines the type of memstore to be used for system tables like META, namespace tables etc. By default NONE is the type and hence we use the default memstore for all the system tables. If we need to use compacting memstore for system tables then set this property to BASIC/EAGER\\
+**Default:** \`NONE\`
+
+#### \`hbase.regionserver.optionalcacheflushinterval\` \\[!toc]
+
+**Description:** Maximum amount of time an edit lives in memory before being automatically flushed. Default 1 hour. Set it to 0 to disable automatic flushing.\\
+**Default:** \`3600000\`
+
+#### \`hbase.regionserver.dns.interface\` \\[!toc]
+
+**Description:** The name of the Network Interface from which a region server should report its IP address.\\
+**Default:** \`default\`
+
+#### \`hbase.regionserver.dns.nameserver\` \\[!toc]
+
+**Description:** The host name or IP address of the name server (DNS) which a region server should use to determine the host name used by the master for communication and display purposes.\\
+**Default:** \`default\`
+
+#### \`hbase.regionserver.region.split.policy\` \\[!toc]
+
+**Description:** A split policy determines when a region should be split. The various other split policies that are available currently are BusyRegionSplitPolicy, ConstantSizeRegionSplitPolicy, DisabledRegionSplitPolicy, DelimitedKeyPrefixRegionSplitPolicy, KeyPrefixRegionSplitPolicy, and SteppingSplitPolicy. DisabledRegionSplitPolicy blocks manual region splitting.\\
+**Default:** \`org.apache.hadoop.hbase.regionserver.SteppingSplitPolicy\`
+
+#### \`hbase.regionserver.regionSplitLimit\` \\[!toc]
+
+**Description:** Limit for the number of regions after which no more region splitting should take place. This is not hard limit for the number of regions but acts as a guideline for the regionserver to stop splitting after a certain limit. Default is set to 1000.\\
+**Default:** \`1000\`
+
+#### \`zookeeper.session.timeout\` \\[!toc]
+
+**Description:** ZooKeeper session timeout in milliseconds. It is used in two different ways. First, this value is used in the ZK client that HBase uses to connect to the ensemble. It is also used by HBase when it starts a ZK server and it is passed as the 'maxSessionTimeout'. See [https://zookeeper.apache.org/doc/current/zookeeperProgrammers.html#ch\\_zkSessions](https://zookeeper.apache.org/doc/current/zookeeperProgrammers.html#ch_zkSessions). For example, if an HBase region server con [...]
+**Default:** \`90000\`
+
+#### \`zookeeper.znode.parent\` \\[!toc]
+
+**Description:** Root ZNode for HBase in ZooKeeper. All of HBase's ZooKeeper files that are configured with a relative path will go under this node. By default, all of HBase's ZooKeeper file paths are configured with a relative path, so they will all go under this directory unless changed.\\
+**Default:** \`/hbase\`
+
+#### \`zookeeper.znode.acl.parent\` \\[!toc]
+
+**Description:** Root ZNode for access control lists.\\
+**Default:** \`acl\`
+
+#### \`hbase.zookeeper.dns.interface\` \\[!toc]
+
+**Description:** The name of the Network Interface from which a ZooKeeper server should report its IP address.\\
+**Default:** \`default\`
+
+#### \`hbase.zookeeper.dns.nameserver\` \\[!toc]
+
+**Description:** The host name or IP address of the name server (DNS) which a ZooKeeper server should use to determine the host name used by the master for communication and display purposes.\\
+**Default:** \`default\`
+
+#### \`hbase.zookeeper.peerport\` \\[!toc]
+
+**Description:** Port used by ZooKeeper peers to talk to each other. See [https://zookeeper.apache.org/doc/r3.4.10/zookeeperStarted.html#sc\\_RunningReplicatedZooKeeper](https://zookeeper.apache.org/doc/r3.4.10/zookeeperStarted.html#sc_RunningReplicatedZooKeeper) for more information.\\
+**Default:** \`2888\`
+
+#### \`hbase.zookeeper.leaderport\` \\[!toc]
+
+**Description:** Port used by ZooKeeper for leader election. See [https://zookeeper.apache.org/doc/r3.4.10/zookeeperStarted.html#sc\\_RunningReplicatedZooKeeper](https://zookeeper.apache.org/doc/r3.4.10/zookeeperStarted.html#sc_RunningReplicatedZooKeeper) for more information.\\
+**Default:** \`3888\`
+
+#### \`hbase.zookeeper.property.initLimit\` \\[!toc]
+
+**Description:** Property from ZooKeeper's config zoo.cfg. The number of ticks that the initial synchronization phase can take.\\
+**Default:** \`10\`
+
+#### \`hbase.zookeeper.property.syncLimit\` \\[!toc]
+
+**Description:** Property from ZooKeeper's config zoo.cfg. The number of ticks that can pass between sending a request and getting an acknowledgment.\\
+**Default:** \`5\`
+
+#### \`hbase.zookeeper.property.dataDir\` \\[!toc]
+
+**Description:** Property from ZooKeeper's config zoo.cfg. The directory where the snapshot is stored.\\
+**Default:** \`\${hbase.tmp.dir}/zookeeper\`
+
+#### \`hbase.zookeeper.property.clientPort\` \\[!toc]
+
+**Description:** Property from ZooKeeper's config zoo.cfg. The port at which the clients will connect.\\
+**Default:** \`2181\`
+
+#### \`hbase.zookeeper.property.maxClientCnxns\` \\[!toc]
+
+**Description:** Property from ZooKeeper's config zoo.cfg. Limit on number of concurrent connections (at the socket level) that a single client, identified by IP address, may make to a single member of the ZooKeeper ensemble. Set high to avoid zk connection issues running standalone and pseudo-distributed.\\
+**Default:** \`300\`
+
+#### \`hbase.client.write.buffer\` \\[!toc]
+
+**Description:** Default size of the BufferedMutator write buffer in bytes. A bigger buffer takes more memory -- on both the client and server side since server instantiates the passed write buffer to process it -- but a larger buffer size reduces the number of RPCs made. For an estimate of server-side memory-used, evaluate hbase.client.write.buffer \\* hbase.regionserver.handler.count\\
+**Default:** \`2097152\`
+
+#### \`hbase.client.pause\` \\[!toc]
+
+**Description:** General client pause value. Used mostly as value to wait before running a retry of a failed get, region lookup, etc. See hbase.client.retries.number for description of how we backoff from this initial pause amount and how this pause works w/ retries.\\
+**Default:** \`100\`
+
+#### \`hbase.client.pause.server.overloaded\` \\[!toc]
+
+**Description:** Pause time when encountering an exception indicating a server is overloaded, CallQueueTooBigException or CallDroppedException. Set this property to a higher value than hbase.client.pause if you observe frequent CallQueueTooBigException or CallDroppedException from the same RegionServer and the call queue there keeps filling up. This config used to be called hbase.client.pause.cqtbe, which has been deprecated as of 2.5.0.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.client.retries.number\` \\[!toc]
+
+**Description:** Maximum retries. Used as maximum for all retryable operations such as the getting of a cell's value, starting a row update, etc. Retry interval is a rough function based on hbase.client.pause. At first we retry at this interval but then with backoff, we pretty quickly reach retrying every ten seconds. See HConstants#RETRY\\_BACKOFF for how the backup ramps up. Change this setting and hbase.client.pause to suit your workload.\\
+**Default:** \`15\`
+
+#### \`hbase.client.max.total.tasks\` \\[!toc]
+
+**Description:** The maximum number of concurrent mutation tasks a single HTable instance will send to the cluster.\\
+**Default:** \`100\`
+
+#### \`hbase.client.max.perserver.tasks\` \\[!toc]
+
+**Description:** The maximum number of concurrent mutation tasks a single HTable instance will send to a single region server.\\
+**Default:** \`2\`
+
+#### \`hbase.client.max.perregion.tasks\` \\[!toc]
+
+**Description:** The maximum number of concurrent mutation tasks the client will maintain to a single Region. That is, if there is already hbase.client.max.perregion.tasks writes in progress for this region, new puts won't be sent to this region until some writes finishes.\\
+**Default:** \`1\`
+
+#### \`hbase.client.perserver.requests.threshold\` \\[!toc]
+
+**Description:** The max number of concurrent pending requests for one server in all client threads (process level). Exceeding requests will be thrown ServerTooBusyException immediately to prevent user's threads being occupied and blocked by only one slow region server. If you use a fix number of threads to access HBase in a synchronous way, set this to a suitable value which is related to the number of threads will help you. See [https://issues.apache.org/jira/browse/HBASE-16388](https: [...]
+**Default:** \`2147483647\`
+
+#### \`hbase.client.scanner.caching\` \\[!toc]
+
+**Description:** Number of rows that we try to fetch when calling next on a scanner if it is not served from (local, client) memory. This configuration works together with hbase.client.scanner.max.result.size to try and use the network efficiently. The default value is Integer.MAX\\_VALUE by default so that the network will fill the chunk size defined by hbase.client.scanner.max.result.size rather than be limited by a particular number of rows since the size of rows varies table to table [...]
+**Default:** \`2147483647\`
+
+#### \`hbase.client.keyvalue.maxsize\` \\[!toc]
+
+**Description:** Specifies the combined maximum allowed size of a KeyValue instance. This is to set an upper boundary for a single entry saved in a storage file. Since they cannot be split it helps avoiding that a region cannot be split any further because the data is too large. It seems wise to set this to a fraction of the maximum region size. Setting it to zero or less disables the check.\\
+**Default:** \`10485760\`
+
+#### \`hbase.server.keyvalue.maxsize\` \\[!toc]
+
+**Description:** Maximum allowed size of an individual cell, inclusive of value and all key components. A value of 0 or less disables the check. The default value is 10MB. This is a safety setting to protect the server from OOM situations.\\
+**Default:** \`10485760\`
+
+#### \`hbase.client.scanner.timeout.period\` \\[!toc]
+
+**Description:** Client scanner lease period in milliseconds.\\
+**Default:** \`60000\`
+
+#### \`hbase.client.localityCheck.threadPoolSize\` \\[!toc]
+
+**Description:**\\
+**Default:** \`2\`
+
+#### \`hbase.bulkload.retries.number\` \\[!toc]
+
+**Description:** Maximum retries. This is maximum number of iterations to atomic bulk loads are attempted in the face of splitting operations 0 means never give up.\\
+**Default:** \`10\`
+
+#### \`hbase.compaction.after.bulkload.enable\` \\[!toc]
+
+**Description:** Request Compaction after bulkload immediately. If bulkload is continuous, the triggered compactions may increase load, bring about performance side effect.\\
+**Default:** \`false\`
+
+#### \`hbase.master.balancer.maxRitPercent\` \\[!toc]
+
+**Description:** The max percent of regions in transition when balancing. The default value is 1.0. So there are no balancer throttling. If set this config to 0.01, It means that there are at most 1% regions in transition when balancing. Then the cluster's availability is at least 99% when balancing.\\
+**Default:** \`1.0\`
+
+#### \`hbase.balancer.period\` \\[!toc]
+
+**Description:** Period at which the region balancer runs in the Master, in milliseconds.\\
+**Default:** \`300000\`
+
+#### \`hbase.master.oldwals.dir.updater.period\` \\[!toc]
+
+**Description:** Period at which the oldWALs directory size calculator/updater will run in the Master, in milliseconds.\\
+**Default:** \`300000\`
+
+#### \`hbase.regions.slop\` \\[!toc]
+
+**Description:** The load balancer can trigger for several reasons. This value controls one of those reasons. Run the balancer if any regionserver has a region count outside the range of average +/- (average \\* slop) regions. If the value of slop is negative, disable sloppiness checks. The balancer can still run for other reasons, but sloppiness will not be one of them. If the value of slop is 0, run the balancer if any server has a region count more than 1 from the average. If the valu [...]
+**Default:** \`0.2\`
+
+#### \`hbase.normalizer.period\` \\[!toc]
+
+**Description:** Period at which the region normalizer runs in the Master, in milliseconds.\\
+**Default:** \`300000\`
+
+#### \`hbase.normalizer.split.enabled\` \\[!toc]
+
+**Description:** Whether to split a region as part of normalization.\\
+**Default:** \`true\`
+
+#### \`hbase.normalizer.merge.enabled\` \\[!toc]
+
+**Description:** Whether to merge a region as part of normalization.\\
+**Default:** \`true\`
+
+#### \`hbase.normalizer.merge.min.region.count\` \\[!toc]
+
+**Description:** The minimum number of regions in a table to consider it for merge normalization.\\
+**Default:** \`3\`
+
+#### \`hbase.normalizer.merge.min_region_age.days\` \\[!toc]
+
+**Description:** The minimum age for a region to be considered for a merge, in days.\\
+**Default:** \`3\`
+
+#### \`hbase.normalizer.merge.min_region_size.mb\` \\[!toc]
+
+**Description:** The minimum size for a region to be considered for a merge, in whole MBs.\\
+**Default:** \`1\`
+
+#### \`hbase.normalizer.merge.merge_request_max_number_of_regions\` \\[!toc]
+
+**Description:** The maximum number of region count in a merge request for merge normalization.\\
+**Default:** \`100\`
+
+#### \`hbase.table.normalization.enabled\` \\[!toc]
+
+**Description:** This config is used to set default behaviour of normalizer at table level. To override this at table level one can set NORMALIZATION\\_ENABLED at table descriptor level and that property will be honored\\
+**Default:** \`false\`
+
+#### \`hbase.server.thread.wakefrequency\` \\[!toc]
+
+**Description:** In master side, this config is the period used for FS related behaviors: checking if hdfs is out of safe mode, setting or checking hbase.version file, setting or checking hbase.id file. Using default value should be fine. In regionserver side, this config is used in several places: flushing check interval, compaction check interval, wal rolling check interval. Specially, admin can tune flushing and compaction check interval by hbase.regionserver.flush.check.period and hb [...]
+**Default:** \`10000\`
+
+#### \`hbase.regionserver.flush.check.period\` \\[!toc]
+
+**Description:** It determines the flushing check period of PeriodicFlusher in regionserver. If unset, it uses hbase.server.thread.wakefrequency as default value. (in milliseconds)\\
+**Default:** \`\${hbase.server.thread.wakefrequency}\`
+
+#### \`hbase.regionserver.compaction.check.period\` \\[!toc]
+
+**Description:** It determines the compaction check period of CompactionChecker in regionserver. If unset, it uses hbase.server.thread.wakefrequency as default value. (in milliseconds)\\
+**Default:** \`\${hbase.server.thread.wakefrequency}\`
+
+#### \`hbase.server.versionfile.writeattempts\` \\[!toc]
+
+**Description:** How many times to retry attempting to write a version file before just aborting. Each attempt is separated by the hbase.server.thread.wakefrequency milliseconds.\\
+**Default:** \`3\`
+
+#### \`hbase.hregion.memstore.flush.size\` \\[!toc]
+
+**Description:** Memstore will be flushed to disk if size of the memstore exceeds this number of bytes. Value is checked by a thread that runs every hbase.server.thread.wakefrequency.\\
+**Default:** \`134217728\`
+
+#### \`hbase.hregion.percolumnfamilyflush.size.lower.bound.min\` \\[!toc]
+
+**Description:** If FlushLargeStoresPolicy is used and there are multiple column families, then every time that we hit the total memstore limit, we find out all the column families whose memstores exceed a "lower bound" and only flush them while retaining the others in memory. The "lower bound" will be "hbase.hregion.memstore.flush.size / column\\_family\\_number" by default unless value of this property is larger than that. If none of the families have their memstore size more than lowe [...]
+**Default:** \`16777216\`
+
+#### \`hbase.hregion.preclose.flush.size\` \\[!toc]
+
+**Description:** If the memstores in a region are this size or larger when we go to close, run a "pre-flush" to clear out memstores before we put up the region closed flag and take the region offline. On close, a flush is run under the close flag to empty memory. During this time the region is offline and we are not taking on any writes. If the memstore content is large, this flush could take a long time to complete. The preflush is meant to clean out the bulk of the memstore before putt [...]
+**Default:** \`5242880\`
+
+#### \`hbase.hregion.memstore.block.multiplier\` \\[!toc]
+
+**Description:** Block updates if memstore has hbase.hregion.memstore.block.multiplier times hbase.hregion.memstore.flush.size bytes. Useful preventing runaway memstore during spikes in update traffic. Without an upper-bound, memstore fills such that when it flushes the resultant flush files take a long time to compact or split, or worse, we OOME.\\
+**Default:** \`4\`
+
+#### \`hbase.hregion.memstore.mslab.enabled\` \\[!toc]
+
+**Description:** Enables the MemStore-Local Allocation Buffer, a feature which works to prevent heap fragmentation under heavy write loads. This can reduce the frequency of stop-the-world GC pauses on large heaps.\\
+**Default:** \`true\`
+
+#### \`hbase.hregion.memstore.mslab.chunksize\` \\[!toc]
+
+**Description:** The maximum byte size of a chunk in the MemStoreLAB. Unit: bytes\\
+**Default:** \`2097152\`
+
+#### \`hbase.regionserver.offheap.global.memstore.size\` \\[!toc]
+
+**Description:** The amount of off-heap memory all MemStores in a RegionServer may use. A value of 0 means that no off-heap memory will be used and all chunks in MSLAB will be HeapByteBuffer, otherwise the non-zero value means how many megabyte of off-heap memory will be used for chunks in MSLAB and all chunks in MSLAB will be DirectByteBuffer. Unit: megabytes.\\
+**Default:** \`0\`
+
+#### \`hbase.hregion.memstore.mslab.max.allocation\` \\[!toc]
+
+**Description:** The maximal size of one allocation in the MemStoreLAB, if the desired byte size exceed this threshold then it will be just allocated from JVM heap rather than MemStoreLAB.\\
+**Default:** \`262144\`
+
+#### \`hbase.hregion.max.filesize\` \\[!toc]
+
+**Description:** Maximum file size. If the sum of the sizes of a region's HFiles has grown to exceed this value, the region is split in two. There are two choices of how this option works, the first is when any store's size exceed the threshold then split, and the other is overall region's size exceed the threshold then split, it can be configed by hbase.hregion.split.overallfiles.\\
+**Default:** \`10737418240\`
+
+#### \`hbase.hregion.split.overallfiles\` \\[!toc]
+
+**Description:** If we should sum overall region files size when check to split.\\
+**Default:** \`true\`
+
+#### \`hbase.hregion.majorcompaction\` \\[!toc]
+
+**Description:** Time between major compactions, expressed in milliseconds. Set to 0 to disable time-based automatic major compactions. User-requested and size-based major compactions will still run. This value is multiplied by hbase.hregion.majorcompaction.jitter to cause compaction to start at a somewhat-random time during a given window of time. The default value is 7 days, expressed in milliseconds. If major compactions are causing disruption in your environment, you can configure th [...]
+**Default:** \`604800000\`
+
+#### \`hbase.hregion.majorcompaction.jitter\` \\[!toc]
+
+**Description:** A multiplier applied to hbase.hregion.majorcompaction to cause compaction to occur a given amount of time either side of hbase.hregion.majorcompaction. The smaller the number, the closer the compactions will happen to the hbase.hregion.majorcompaction interval.\\
+**Default:** \`0.50\`
+
+#### \`hbase.hstore.compactionThreshold\` \\[!toc]
+
+**Description:** If more than or equal to this number of StoreFiles exist in any one Store (one StoreFile is written per flush of MemStore), a compaction is run to rewrite all StoreFiles into a single StoreFile. Larger values delay compaction, but when compaction does occur, it takes longer to complete.\\
+**Default:** \`3\`
+
+#### \`hbase.regionserver.compaction.enabled\` \\[!toc]
+
+**Description:** Enable/disable compactions on by setting true/false. We can further switch compactions dynamically with the compaction\\_switch shell command.\\
+**Default:** \`true\`
+
+#### \`hbase.hstore.flusher.count\` \\[!toc]
+
+**Description:** The number of flush threads. With fewer threads, the MemStore flushes will be queued. With more threads, the flushes will be executed in parallel, increasing the load on HDFS, and potentially causing more compactions.\\
+**Default:** \`2\`
+
+#### \`hbase.hstore.blockingStoreFiles\` \\[!toc]
+
+**Description:** If more than this number of StoreFiles exist in any one Store (one StoreFile is written per flush of MemStore), updates are blocked for this region until a compaction is completed, or until hbase.hstore.blockingWaitTime has been exceeded.\\
+**Default:** \`16\`
+
+#### \`hbase.hstore.blockingWaitTime\` \\[!toc]
+
+**Description:** The time for which a region will block updates after reaching the StoreFile limit defined by hbase.hstore.blockingStoreFiles. After this time has elapsed, the region will stop blocking updates even if a compaction has not been completed.\\
+**Default:** \`90000\`
+
+#### \`hbase.hstore.compaction.min\` \\[!toc]
+
+**Description:** The minimum number of StoreFiles which must be eligible for compaction before compaction can run. The goal of tuning hbase.hstore.compaction.min is to avoid ending up with too many tiny StoreFiles to compact. Setting this value to 2 would cause a minor compaction each time you have two StoreFiles in a Store, and this is probably not appropriate. If you set this value too high, all the other values will need to be adjusted accordingly. For most cases, the default value is [...]
+**Default:** \`(empty)\`
+
+#### \`hbase.hstore.compaction.max\` \\[!toc]
+
+**Description:** The maximum number of StoreFiles which will be selected for a single minor compaction, regardless of the number of eligible StoreFiles. Effectively, the value of hbase.hstore.compaction.max controls the length of time it takes a single compaction to complete. Setting it larger means that more StoreFiles are included in a compaction. For most cases, the default value is appropriate.\\
+**Default:** \`10\`
+
+#### \`hbase.hstore.compaction.min.size\` \\[!toc]
+
+**Description:** A StoreFile (or a selection of StoreFiles, when using ExploringCompactionPolicy) smaller than this size will always be eligible for minor compaction. HFiles this size or larger are evaluated by hbase.hstore.compaction.ratio to determine if they are eligible. Because this limit represents the "automatic include" limit for all StoreFiles smaller than this value, this value may need to be reduced in write-heavy environments where many StoreFiles in the 1-2 MB range are bein [...]
+**Default:** \`134217728\`
+
+#### \`hbase.hstore.compaction.max.size\` \\[!toc]
+
+**Description:** A StoreFile (or a selection of StoreFiles, when using ExploringCompactionPolicy) larger than this size will be excluded from compaction. The effect of raising hbase.hstore.compaction.max.size is fewer, larger StoreFiles that do not get compacted often. If you feel that compaction is happening too often without much benefit, you can try raising this value. Default: the value of LONG.MAX\\_VALUE, expressed in bytes.\\
+**Default:** \`9223372036854775807\`
+
+#### \`hbase.hstore.compaction.ratio\` \\[!toc]
+
+**Description:** For minor compaction, this ratio is used to determine whether a given StoreFile which is larger than hbase.hstore.compaction.min.size is eligible for compaction. Its effect is to limit compaction of large StoreFiles. The value of hbase.hstore.compaction.ratio is expressed as a floating-point decimal. A large ratio, such as 10, will produce a single giant StoreFile. Conversely, a low value, such as .25, will produce behavior similar to the BigTable compaction algorithm, p [...]
+**Default:** \`1.2F\`
+
+#### \`hbase.hstore.compaction.ratio.offpeak\` \\[!toc]
+
+**Description:** Allows you to set a different (by default, more aggressive) ratio for determining whether larger StoreFiles are included in compactions during off-peak hours. Works in the same way as hbase.hstore.compaction.ratio. Only applies if hbase.offpeak.start.hour and hbase.offpeak.end.hour are also enabled.\\
+**Default:** \`5.0F\`
+
+#### \`hbase.hstore.time.to.purge.deletes\` \\[!toc]
+
+**Description:** The amount of time to delay purging of delete markers with future timestamps. If unset, or set to 0, all delete markers, including those with future timestamps, are purged during the next major compaction. Otherwise, a delete marker is kept until the major compaction which occurs after the marker's timestamp plus the value of this setting, in milliseconds.\\
+**Default:** \`0\`
+
+#### \`hbase.offpeak.start.hour\` \\[!toc]
+
+**Description:** The start of off-peak hours, expressed as an integer between 0 and 23, inclusive. Set to -1 to disable off-peak.\\
+**Default:** \`-1\`
+
+#### \`hbase.offpeak.end.hour\` \\[!toc]
+
+**Description:** The end of off-peak hours, expressed as an integer between 0 and 23, inclusive. Set to -1 to disable off-peak.\\
+**Default:** \`-1\`
+
+#### \`hbase.regionserver.thread.compaction.throttle\` \\[!toc]
+
+**Description:** There are two different thread pools for compactions, one for large compactions and the other for small compactions. This helps to keep compaction of lean tables (such as hbase:meta) fast. If a compaction is larger than this threshold, it goes into the large compaction pool. In most cases, the default value is appropriate. Default: 2 x hbase.hstore.compaction.max x hbase.hregion.memstore.flush.size (which defaults to 128MB). The value field assumes that the value of hbas [...]
+**Default:** \`2684354560\`
+
+#### \`hbase.regionserver.majorcompaction.pagecache.drop\` \\[!toc]
+
+**Description:** Specifies whether to drop pages read/written into the system page cache by major compactions. Setting it to true helps prevent major compactions from polluting the page cache, which is almost always required, especially for clusters with low/moderate memory to storage ratio.\\
+**Default:** \`true\`
+
+#### \`hbase.regionserver.minorcompaction.pagecache.drop\` \\[!toc]
+
+**Description:** Specifies whether to drop pages read/written into the system page cache by minor compactions. Setting it to true helps prevent minor compactions from polluting the page cache, which is most beneficial on clusters with low memory to storage ratio or very write heavy clusters. You may want to set it to false under moderate to low write workload when bulk of the reads are on the most recently written data.\\
+**Default:** \`true\`
+
+#### \`hbase.hstore.compaction.kv.max\` \\[!toc]
+
+**Description:** The maximum number of KeyValues to read and then write in a batch when flushing or compacting. Set this lower if you have big KeyValues and problems with Out Of Memory Exceptions Set this higher if you have wide, small rows.\\
+**Default:** \`10\`
+
+#### \`hbase.storescanner.parallel.seek.enable\` \\[!toc]
+
+**Description:** Enables StoreFileScanner parallel-seeking in StoreScanner, a feature which can reduce response latency under special conditions.\\
+**Default:** \`false\`
+
+#### \`hbase.storescanner.parallel.seek.threads\` \\[!toc]
+
+**Description:** The default thread pool size if parallel-seeking feature enabled.\\
+**Default:** \`10\`
+
+#### \`hfile.block.cache.policy\` \\[!toc]
+
+**Description:** The eviction policy for the L1 block cache (LRU or TinyLFU).\\
+**Default:** \`LRU\`
+
+#### \`hfile.block.cache.size\` \\[!toc]
+
+**Description:** Percentage of maximum heap (-Xmx setting) to allocate to block cache used by a StoreFile. Default of 0.4 means allocate 40%. Set to 0 to disable but it's not recommended; you need at least enough cache to hold the storefile indices.\\
+**Default:** \`0.4\`
+
+#### \`hfile.block.cache.memory.size\` \\[!toc]
+
+**Description:** Defines the maximum heap memory allocated for the HFile block cache, specified in bytes or human-readable formats like '10m' for megabytes or '10g' for gigabytes. This configuration allows setting an absolute memory size instead of a percentage of the maximum heap. Takes precedence over hfile.block.cache.size if both are specified.\\
+**Default:** \`(empty)\`
+
+#### \`hfile.block.index.cacheonwrite\` \\[!toc]
+
+**Description:** This allows to put non-root multi-level index blocks into the block cache at the time the index is being written.\\
+**Default:** \`false\`
+
+#### \`hfile.index.block.max.size\` \\[!toc]
+
+**Description:** When the size of a leaf-level, intermediate-level, or root-level index block in a multi-level block index grows to this size, the block is written out and a new block is started.\\
+**Default:** \`131072\`
+
+#### \`hbase.bucketcache.ioengine\` \\[!toc]
+
+**Description:** Where to store the contents of the bucketcache. One of: offheap, file, files, mmap or pmem. If a file or files, set it to file(s):PATH\\_TO\\_FILE. mmap means the content will be in an mmaped file. Use mmap:PATH\\_TO\\_FILE. 'pmem' is bucket cache over a file on the persistent memory device. Use pmem:PATH\\_TO\\_FILE. See [https://hbase.apache.org/docs/architecture/regionserver#off-heap-block-cache](https://hbase.apache.org/docs/architecture/regionserver#off-heap-block-c [...]
+**Default:** \`(empty)\`
+
+#### \`hbase.hstore.compaction.throughput.lower.bound\` \\[!toc]
+
+**Description:** The target lower bound on aggregate compaction throughput, in bytes/sec. Allows you to tune the minimum available compaction throughput when the PressureAwareCompactionThroughputController throughput controller is active. (It is active by default.)\\
+**Default:** \`52428800\`
+
+#### \`hbase.hstore.compaction.throughput.higher.bound\` \\[!toc]
+
+**Description:** The target upper bound on aggregate compaction throughput, in bytes/sec. Allows you to control aggregate compaction throughput demand when the PressureAwareCompactionThroughputController throughput controller is active. (It is active by default.) The maximum throughput will be tuned between the lower and upper bounds when compaction pressure is within the range \\[0.0, 1.0]. If compaction pressure is 1.0 or greater the higher bound will be ignored until pressure returns [...]
+**Default:** \`104857600\`
+
+#### \`hbase.bucketcache.size\` \\[!toc]
+
+**Description:** It is the total capacity in megabytes of BucketCache. Default: 0.0\\
+**Default:** \`(empty)\`
+
+#### \`hbase.bucketcache.bucket.sizes\` \\[!toc]
+
+**Description:** A comma-separated list of sizes for buckets for the bucketcache. Can be multiple sizes. List block sizes in order from smallest to largest. The sizes you use will depend on your data access patterns. Must be a multiple of 256 else you will run into 'java.io.IOException: Invalid HFile block magic' when you go to read from cache. If you specify no values here, then you pick up the default bucketsizes set in code (See BucketAllocator#DEFAULT\\_BUCKET\\_SIZES).\\
+**Default:** \`(empty)\`
+
+#### \`hfile.format.version\` \\[!toc]
+
+**Description:** The HFile format version to use for new files. Version 3 adds support for tags in hfiles (See [https://hbase.apache.org/docs/security/data-access#tags](https://hbase.apache.org/docs/security/data-access#tags)). Also see the configuration 'hbase.replication.rpc.codec'.\\
+**Default:** \`3\`
+
+#### \`hfile.block.bloom.cacheonwrite\` \\[!toc]
+
+**Description:** Enables cache-on-write for inline blocks of a compound Bloom filter.\\
+**Default:** \`false\`
+
+#### \`io.storefile.bloom.block.size\` \\[!toc]
+
+**Description:** The size in bytes of a single block ("chunk") of a compound Bloom filter. This size is approximate, because Bloom blocks can only be inserted at data block boundaries, and the number of keys per data block varies.\\
+**Default:** \`131072\`
+
+#### \`hbase.rs.cacheblocksonwrite\` \\[!toc]
+
+**Description:** Whether an HFile block should be added to the block cache when the block is finished.\\
+**Default:** \`false\`
+
+#### \`hbase.rpc.timeout\` \\[!toc]
+
+**Description:** This is for the RPC layer to define how long (millisecond) HBase client applications take for a remote call to time out. It uses pings to check connections but will eventually throw a TimeoutException.\\
+**Default:** \`60000\`
+
+#### \`hbase.client.operation.timeout\` \\[!toc]
+
+**Description:** Operation timeout is a top-level restriction (millisecond) that makes sure a blocking operation in Table will not be blocked more than this. In each operation, if rpc request fails because of timeout or other reason, it will retry until success or throw RetriesExhaustedException. But if the total time being blocking reach the operation timeout before retries exhausted, it will break early and throw SocketTimeoutException.\\
+**Default:** \`1200000\`
+
+#### \`hbase.client.connection.metacache.invalidate-interval.ms\` \\[!toc]
+
+**Description:** Interval in milliseconds of checking and invalidating meta cache when table disabled or dropped, when set to zero means disable checking, suggest set it to 24h or a higher value, because disable/delete table usually not very frequently.\\
+**Default:** \`0\`
+
+#### \`hbase.cells.scanned.per.heartbeat.check\` \\[!toc]
+
+**Description:** The number of cells scanned in between heartbeat checks. Heartbeat checks occur during the processing of scans to determine whether or not the server should stop scanning in order to send back a heartbeat message to the client. Heartbeat messages are used to keep the client-server connection alive during long running scans. Small values mean that the heartbeat checks will occur more often and thus will provide a tighter bound on the execution time of the scan. Larger val [...]
+**Default:** \`10000\`
+
+#### \`hbase.rpc.shortoperation.timeout\` \\[!toc]
+
+**Description:** This is another version of "hbase.rpc.timeout". For those RPC operation within cluster, we rely on this configuration to set a short timeout limitation for short operation. For example, short rpc timeout for region server's trying to report to active master can benefit quicker master failover process.\\
+**Default:** \`10000\`
+
+#### \`hbase.ipc.client.tcpnodelay\` \\[!toc]
+
+**Description:** Set no delay on rpc socket connections. See [http://docs.oracle.com/javase/1.5.0/docs/api/java/net/Socket.html#getTcpNoDelay()](http://docs.oracle.com/javase/1.5.0/docs/api/java/net/Socket.html#getTcpNoDelay\\(\\))\\
+**Default:** \`true\`
+
+#### \`hbase.unsafe.regionserver.hostname\` \\[!toc]
+
+**Description:** This config is for experts: don't set its value unless you really know what you are doing. When set to a non-empty value, this represents the (external facing) hostname for the underlying server. See [https://issues.apache.org/jira/browse/HBASE-12954](https://issues.apache.org/jira/browse/HBASE-12954) for details.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.unsafe.regionserver.hostname.disable.master.reversedns\` \\[!toc]
+
+**Description:** This config is for experts: don't set its value unless you really know what you are doing. When set to true, regionserver will use the current node hostname for the servername and HMaster will skip reverse DNS lookup and use the hostname sent by regionserver instead. Note that this config and hbase.unsafe.regionserver.hostname are mutually exclusive. See [https://issues.apache.org/jira/browse/HBASE-18226](https://issues.apache.org/jira/browse/HBASE-18226) for more details.\\
+**Default:** \`false\`
+
+#### \`hbase.master.keytab.file\` \\[!toc]
+
+**Description:** Full path to the kerberos keytab file to use for logging in the configured HMaster server principal.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.master.kerberos.principal\` \\[!toc]
+
+**Description:** Ex. "hbase/\\_[HOST@EXAMPLE.COM](mailto:HOST@EXAMPLE.COM)". The kerberos principal name that should be used to run the HMaster process. The principal name should be in the form: user/hostname\\@DOMAIN. If "\\_HOST" is used as the hostname portion, it will be replaced with the actual hostname of the running instance.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.regionserver.keytab.file\` \\[!toc]
+
+**Description:** Full path to the kerberos keytab file to use for logging in the configured HRegionServer server principal.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.regionserver.kerberos.principal\` \\[!toc]
+
+**Description:** Ex. "hbase/\\_[HOST@EXAMPLE.COM](mailto:HOST@EXAMPLE.COM)". The kerberos principal name that should be used to run the HRegionServer process. The principal name should be in the form: user/hostname\\@DOMAIN. If "\\_HOST" is used as the hostname portion, it will be replaced with the actual hostname of the running instance. An entry for this principal must exist in the file specified in hbase.regionserver.keytab.file\\
+**Default:** \`(empty)\`
+
+#### \`hadoop.policy.file\` \\[!toc]
+
+**Description:** The policy configuration file used by RPC servers to make authorization decisions on client requests. Only used when HBase security is enabled.\\
+**Default:** \`hbase-policy.xml\`
+
+#### \`hbase.superuser\` \\[!toc]
+
+**Description:** List of users or groups (comma-separated), who are allowed full privileges, regardless of stored ACLs, across the cluster. Only used when HBase security is enabled. Group names should be prefixed with "@".\\
+**Default:** \`(empty)\`
+
+#### \`hbase.auth.key.update.interval\` \\[!toc]
+
+**Description:** The update interval for master key for authentication tokens in servers in milliseconds. Only used when HBase security is enabled.\\
+**Default:** \`86400000\`
+
+#### \`hbase.auth.token.max.lifetime\` \\[!toc]
+
+**Description:** The maximum lifetime in milliseconds after which an authentication token expires. Only used when HBase security is enabled.\\
+**Default:** \`604800000\`
+
+#### \`hbase.ipc.client.fallback-to-simple-auth-allowed\` \\[!toc]
+
+**Description:** When a client is configured to attempt a secure connection, but attempts to connect to an insecure server, that server may instruct the client to switch to SASL SIMPLE (unsecure) authentication. This setting controls whether or not the client will accept this instruction from the server. When false (the default), the client will not allow the fallback to SIMPLE authentication, and will abort the connection.\\
+**Default:** \`false\`
+
+#### \`hbase.ipc.server.fallback-to-simple-auth-allowed\` \\[!toc]
+
+**Description:** When a server is configured to require secure connections, it will reject connection attempts from clients using SASL SIMPLE (unsecure) authentication. This setting allows secure servers to accept SASL SIMPLE connections from clients when the client requests. When false (the default), the server will not allow the fallback to SIMPLE authentication, and will reject the connection. WARNING: This setting should ONLY be used as a temporary measure while converting clients ov [...]
+**Default:** \`false\`
+
+#### \`hbase.unsafe.client.kerberos.hostname.disable.reversedns\` \\[!toc]
+
+**Description:** This config is for experts: don't set its value unless you really know what you are doing. When set to true, HBase client using SASL Kerberos will skip reverse DNS lookup and use provided hostname of the destination for the principal instead. See [https://issues.apache.org/jira/browse/HBASE-25665](https://issues.apache.org/jira/browse/HBASE-25665) for more details.\\
+**Default:** \`false\`
+
+#### \`hbase.display.keys\` \\[!toc]
+
+**Description:** When this is set to true the webUI and such will display all start/end keys as part of the table details, region names, etc. When this is set to false, the keys are hidden.\\
+**Default:** \`true\`
+
+#### \`hbase.coprocessor.enabled\` \\[!toc]
+
+**Description:** Enables or disables coprocessor loading. If 'false' (disabled), any other coprocessor related configuration will be ignored.\\
+**Default:** \`true\`
+
+#### \`hbase.coprocessor.user.enabled\` \\[!toc]
+
+**Description:** Enables or disables user (aka. table) coprocessor loading. If 'false' (disabled), any table coprocessor attributes in table descriptors will be ignored. If "hbase.coprocessor.enabled" is 'false' this setting has no effect.\\
+**Default:** \`true\`
+
+#### \`hbase.coprocessor.region.classes\` \\[!toc]
+
+**Description:** A comma-separated list of region observer or endpoint coprocessors that are loaded by default on all tables. For any override coprocessor method, these classes will be called in order. After implementing your own Coprocessor, add it to HBase's classpath and add the fully qualified class name here. A coprocessor can also be loaded on demand by setting HTableDescriptor or the HBase shell.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.coprocessor.master.classes\` \\[!toc]
+
+**Description:** A comma-separated list of org.apache.hadoop.hbase.coprocessor.MasterObserver coprocessors that are loaded by default on the active HMaster process. For any implemented coprocessor methods, the listed classes will be called in order. After implementing your own MasterObserver, just put it in HBase's classpath and add the fully qualified class name here.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.coprocessor.abortonerror\` \\[!toc]
+
+**Description:** Set to true to cause the hosting server (master or regionserver) to abort if a coprocessor fails to load, fails to initialize, or throws an unexpected Throwable object. Setting this to false will allow the server to continue execution but the system wide state of the coprocessor in question will become inconsistent as it will be properly executing in only a subset of servers, so this is most useful for debugging only.\\
+**Default:** \`true\`
+
+#### \`hbase.rest.port\` \\[!toc]
+
+**Description:** The port for the HBase REST server.\\
+**Default:** \`8080\`
+
+#### \`hbase.rest.readonly\` \\[!toc]
+
+**Description:** Defines the mode the REST server will be started in. Possible values are: false: All HTTP methods are permitted - GET/PUT/POST/DELETE. true: Only the GET method is permitted.\\
+**Default:** \`false\`
+
+#### \`hbase.rest.threads.max\` \\[!toc]
+
+**Description:** The maximum number of threads of the REST server thread pool. Threads in the pool are reused to process REST requests. This controls the maximum number of requests processed concurrently. It may help to control the memory used by the REST server to avoid OOM issues. If the thread pool is full, incoming requests will be queued up and wait for some free threads.\\
+**Default:** \`100\`
+
+#### \`hbase.rest.threads.min\` \\[!toc]
+
+**Description:** The minimum number of threads of the REST server thread pool. The thread pool always has at least these number of threads so the REST server is ready to serve incoming requests.\\
+**Default:** \`2\`
+
+#### \`hbase.rest.support.proxyuser\` \\[!toc]
+
+**Description:** Enables running the REST server to support proxy-user mode.\\
+**Default:** \`false\`
+
+#### \`hbase.defaults.for.version.skip\` \\[!toc]
+
+**Description:** Set to true to skip the 'hbase.defaults.for.version' check. Setting this to true can be useful in contexts other than the other side of a maven generation; i.e. running in an IDE. You'll want to set this boolean to true to avoid seeing the RuntimeException complaint: "hbase-default.xml file seems to be for and old version of HBase ($\\{hbase.version}), this version is X.X.X-SNAPSHOT"\\
+**Default:** \`false\`
+
+#### \`hbase.table.lock.enable\` \\[!toc]
+
+**Description:** Set to true to enable locking the table in zookeeper for schema change operations. Table locking from master prevents concurrent schema modifications to corrupt table state.\\
+**Default:** \`true\`
+
+#### \`hbase.table.max.rowsize\` \\[!toc]
+
+**Description:** Maximum size of single row in bytes (default is 1 Gb) for Get'ting or Scan'ning without in-row scan flag set. If row size exceeds this limit RowTooBigException is thrown to client.\\
+**Default:** \`1073741824\`
+
+#### \`hbase.thrift.minWorkerThreads\` \\[!toc]
+
+**Description:** The "core size" of the thread pool. New threads are created on every connection until this many threads are created.\\
+**Default:** \`16\`
+
+#### \`hbase.thrift.maxWorkerThreads\` \\[!toc]
+
+**Description:** The maximum size of the thread pool. When the pending request queue overflows, new threads are created until their number reaches this number. After that, the server starts dropping connections.\\
+**Default:** \`1000\`
+
+#### \`hbase.thrift.maxQueuedRequests\` \\[!toc]
+
+**Description:** The maximum number of pending Thrift connections waiting in the queue. If there are no idle threads in the pool, the server queues requests. Only when the queue overflows, new threads are added, up to hbase.thrift.maxQueuedRequests threads.\\
+**Default:** \`1000\`
+
+#### \`hbase.regionserver.thrift.framed\` \\[!toc]
+
+**Description:** Use Thrift TFramedTransport on the server side. This is the recommended transport for thrift servers and requires a similar setting on the client side. Changing this to false will select the default transport, vulnerable to DoS when malformed requests are issued due to THRIFT-601.\\
+**Default:** \`false\`
+
+#### \`hbase.regionserver.thrift.framed.max_frame_size_in_mb\` \\[!toc]
+
+**Description:** Default frame size when using framed transport, in MB\\
+**Default:** \`2\`
+
+#### \`hbase.regionserver.thrift.compact\` \\[!toc]
+
+**Description:** Use Thrift TCompactProtocol binary serialization protocol.\\
+**Default:** \`false\`
+
+#### \`hbase.rootdir.perms\` \\[!toc]
+
+**Description:** FS Permissions for the root data subdirectory in a secure (kerberos) setup. When master starts, it creates the rootdir with this permissions or sets the permissions if it does not match.\\
+**Default:** \`700\`
+
+#### \`hbase.wal.dir.perms\` \\[!toc]
+
+**Description:** FS Permissions for the root WAL directory in a secure(kerberos) setup. When master starts, it creates the WAL dir with this permissions or sets the permissions if it does not match.\\
+**Default:** \`700\`
+
+#### \`hbase.data.umask.enable\` \\[!toc]
+
+**Description:** Enable, if true, that file permissions should be assigned to the files written by the regionserver\\
+**Default:** \`false\`
+
+#### \`hbase.data.umask\` \\[!toc]
+
+**Description:** File permissions that should be used to write data files when hbase.data.umask.enable is true\\
+**Default:** \`000\`
+
+#### \`hbase.snapshot.enabled\` \\[!toc]
+
+**Description:** Set to true to allow snapshots to be taken / restored / cloned.\\
+**Default:** \`true\`
+
+#### \`hbase.snapshot.restore.take.failsafe.snapshot\` \\[!toc]
+
+**Description:** Set to true to take a snapshot before the restore operation. The snapshot taken will be used in case of failure, to restore the previous state. At the end of the restore operation this snapshot will be deleted\\
+**Default:** \`true\`
+
+#### \`hbase.snapshot.restore.failsafe.name\` \\[!toc]
+
+**Description:** Name of the failsafe snapshot taken by the restore operation. You can use the \\{snapshot.name}, \\{table.name} and \\{restore.timestamp} variables to create a name based on what you are restoring.\\
+**Default:** \`hbase-failsafe-{snapshot.name}-{restore.timestamp}\`
+
+#### \`hbase.snapshot.working.dir\` \\[!toc]
+
+**Description:** Location where the snapshotting process will occur. The location of the completed snapshots will not change, but the temporary directory where the snapshot process occurs will be set to this location. This can be a separate filesystem than the root directory, for performance increase purposes. See HBASE-21098 for more information\\
+**Default:** \`(empty)\`
+
+#### \`hbase.server.compactchecker.interval.multiplier\` \\[!toc]
+
+**Description:** The number that determines how often we scan to see if compaction is necessary. Normally, compactions are done after some events (such as memstore flush), but if region didn't receive a lot of writes for some time, or due to different compaction policies, it may be necessary to check it periodically. The interval between checks is hbase.server.compactchecker.interval.multiplier multiplied by hbase.server.thread.wakefrequency.\\
+**Default:** \`1000\`
+
+#### \`hbase.lease.recovery.timeout\` \\[!toc]
+
+**Description:** How long we wait on dfs lease recovery in total before giving up.\\
+**Default:** \`900000\`
+
+#### \`hbase.lease.recovery.dfs.timeout\` \\[!toc]
+
+**Description:** How long between dfs recover lease invocations. Should be larger than the sum of the time it takes for the namenode to issue a block recovery command as part of datanode; dfs.heartbeat.interval and the time it takes for the primary datanode, performing block recovery to timeout on a dead datanode; usually dfs.client.socket-timeout. See the end of HBASE-8389 for more.\\
+**Default:** \`64000\`
+
+#### \`hbase.column.max.version\` \\[!toc]
+
+**Description:** New column family descriptors will use this value as the default number of versions to keep.\\
+**Default:** \`1\`
+
+#### \`dfs.client.read.shortcircuit\` \\[!toc]
+
+**Description:** If set to true, this configuration parameter enables short-circuit local reads.\\
+**Default:** \`(empty)\`
+
+#### \`dfs.domain.socket.path\` \\[!toc]
+
+**Description:** This is a path to a UNIX domain socket that will be used for communication between the DataNode and local HDFS clients, if dfs.client.read.shortcircuit is set to true. If the string "\\_PORT" is present in this path, it will be replaced by the TCP port of the DataNode. Be careful about permissions for the directory that hosts the shared domain socket; dfsclient will complain if open to other users than the HBase user.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.dfs.client.read.shortcircuit.buffer.size\` \\[!toc]
+
+**Description:** If the DFSClient configuration dfs.client.read.shortcircuit.buffer.size is unset, we will use what is configured here as the short circuit read default direct byte buffer size. DFSClient native default is 1MB; HBase keeps its HDFS files open so number of file blocks \\* 1MB soon starts to add up and threaten OOME because of a shortage of direct memory. So, we set it down from the default. Make it > the default hbase block size set in the HColumnDescriptor which is usuall [...]
+**Default:** \`131072\`
+
+#### \`hbase.regionserver.checksum.verify\` \\[!toc]
+
+**Description:** If set to true (the default), HBase verifies the checksums for hfile blocks. HBase writes checksums inline with the data when it writes out hfiles. HDFS (as of this writing) writes checksums to a separate file than the data file necessitating extra seeks. Setting this flag saves some on i/o. Checksum verification by HDFS will be internally disabled on hfile streams when this flag is set. If the hbase-checksum verification fails, we will switch back to using HDFS checksum [...]
+**Default:** \`true\`
+
+#### \`hbase.hstore.bytes.per.checksum\` \\[!toc]
+
+**Description:** Number of bytes in a newly created checksum chunk for HBase-level checksums in hfile blocks.\\
+**Default:** \`16384\`
+
+#### \`hbase.hstore.checksum.algorithm\` \\[!toc]
+
+**Description:** Name of an algorithm that is used to compute checksums. Possible values are NULL, CRC32, CRC32C.\\
+**Default:** \`CRC32C\`
+
+#### \`hbase.client.scanner.max.result.size\` \\[!toc]
+
+**Description:** Maximum number of bytes returned when calling a scanner's next method. Note that when a single row is larger than this limit the row is still returned completely. The default value is 2MB, which is good for 1ge networks. With faster and/or high latency networks this value should be increased.\\
+**Default:** \`2097152\`
+
+#### \`hbase.server.scanner.max.result.size\` \\[!toc]
+
+**Description:** Maximum number of bytes returned when calling a scanner's next method. Note that when a single row is larger than this limit the row is still returned completely. The default value is 100MB. This is a safety setting to protect the server from OOM situations.\\
+**Default:** \`104857600\`
+
+#### \`hbase.status.published\` \\[!toc]
+
+**Description:** This setting activates the publication by the master of the status of the region server. When a region server dies and its recovery starts, the master will push this information to the client application, to let them cut the connection immediately instead of waiting for a timeout.\\
+**Default:** \`false\`
+
+#### \`hbase.status.publisher.class\` \\[!toc]
+
+**Description:** Implementation of the status publication with a multicast message.\\
+**Default:** \`org.apache.hadoop.hbase.master.ClusterStatusPublisher$MulticastPublisher\`
+
+#### \`hbase.status.listener.class\` \\[!toc]
+
+**Description:** Implementation of the status listener with a multicast message.\\
+**Default:** \`org.apache.hadoop.hbase.client.ClusterStatusListener$MulticastListener\`
+
+#### \`hbase.status.multicast.address.ip\` \\[!toc]
+
+**Description:** Multicast address to use for the status publication by multicast.\\
+**Default:** \`226.1.1.3\`
+
+#### \`hbase.status.multicast.address.port\` \\[!toc]
+
+**Description:** Multicast port to use for the status publication by multicast.\\
+**Default:** \`16100\`
+
+#### \`hbase.dynamic.jars.dir\` \\[!toc]
+
+**Description:** The directory from which the custom filter JARs can be loaded dynamically by the region server without the need to restart. However, an already loaded filter/co-processor class would not be un-loaded. See HBASE-1936 for more details. Does not apply to coprocessors.\\
+**Default:** \`\${hbase.rootdir}/lib\`
+
+#### \`hbase.security.authentication\` \\[!toc]
+
+**Description:** Controls whether or not secure authentication is enabled for HBase. Possible values are 'simple' (no authentication), and 'kerberos'.\\
+**Default:** \`simple\`
+
+#### \`hbase.rest.filter.classes\` \\[!toc]
+
+**Description:** Servlet filters for REST service.\\
+**Default:** \`org.apache.hadoop.hbase.rest.filter.GzipFilter\`
+
+#### \`hbase.master.loadbalancer.class\` \\[!toc]
+
+**Description:** Class used to execute the regions balancing when the period occurs. See the class comment for more on how it works [http://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.html](http://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.html) It replaces the DefaultLoadBalancer as the default (since renamed as the SimpleLoadBalancer).\\
+**Default:** \`org.apache.hadoop.hbase.master.balancer.StochasticLoadBalancer\`
+
+#### \`hbase.master.loadbalance.bytable\` \\[!toc]
+
+**Description:** Factor Table name when the balancer runs. Default: false.\\
+**Default:** \`false\`
+
+#### \`hbase.master.normalizer.class\` \\[!toc]
+
+**Description:** Class used to execute the region normalization when the period occurs. See the class comment for more on how it works [http://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/master/normalizer/SimpleRegionNormalizer.html](http://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/master/normalizer/SimpleRegionNormalizer.html)\\
+**Default:** \`org.apache.hadoop.hbase.master.normalizer.SimpleRegionNormalizer\`
+
+#### \`hbase.rest.csrf.enabled\` \\[!toc]
+
+**Description:** Set to true to enable protection against cross-site request forgery (CSRF)\\
+**Default:** \`false\`
+
+#### \`hbase.rest-csrf.browser-useragents-regex\` \\[!toc]
+
+**Description:** A comma-separated list of regular expressions used to match against an HTTP request's User-Agent header when protection against cross-site request forgery (CSRF) is enabled for REST server by setting hbase.rest.csrf.enabled to true. If the incoming User-Agent matches any of these regular expressions, then the request is considered to be sent by a browser, and therefore CSRF prevention is enforced. If the request's User-Agent does not match any of these regular expression [...]
+**Default:** \`^Mozilla.*,^Opera.*\`
+
+#### \`hbase.security.exec.permission.checks\` \\[!toc]
+
+**Description:** If this setting is enabled and ACL based access control is active (the AccessController coprocessor is installed either as a system coprocessor or on a table as a table coprocessor) then you must grant all relevant users EXEC privilege if they require the ability to execute coprocessor endpoint calls. EXEC privilege, like any other permission, can be granted globally to a user, or to a user on a per table or per namespace basis. For more information on coprocessor endpoi [...]
+**Default:** \`false\`
+
+#### \`hbase.procedure.regionserver.classes\` \\[!toc]
+
+**Description:** A comma-separated list of org.apache.hadoop.hbase.procedure.RegionServerProcedureManager procedure managers that are loaded by default on the active HRegionServer process. The lifecycle methods (init/start/stop) will be called by the active HRegionServer process to perform the specific globally barriered procedure. After implementing your own RegionServerProcedureManager, just put it in HBase's classpath and add the fully qualified class name here.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.procedure.master.classes\` \\[!toc]
+
+**Description:** A comma-separated list of org.apache.hadoop.hbase.procedure.MasterProcedureManager procedure managers that are loaded by default on the active HMaster process. A procedure is identified by its signature and users can use the signature and an instant name to trigger an execution of a globally barriered procedure. After implementing your own MasterProcedureManager, just put it in HBase's classpath and add the fully qualified class name here.\\
+**Default:** \`(empty)\`
+
+#### \`hbase.coordinated.state.manager.class\` \\[!toc]
+
+**Description:** Fully qualified name of class implementing coordinated state manager.\\
+**Default:** \`org.apache.hadoop.hbase.coordination.ZkCoordinatedStateManager\`
+
+#### \`hbase.regionserver.storefile.refresh.period\` \\[!toc]
+
+**Description:** The period (in milliseconds) for refreshing the store files for the secondary regions. 0 means this feature is disabled. Secondary regions sees new files (from flushes and compactions) from primary once the secondary region refreshes the list of files in the region (there is no notification mechanism). But too frequent refreshes might cause extra Namenode pressure. If the files cannot be refreshed for longer than HFile TTL (hbase.master.hfilecleaner.ttl) the requests are [...]
+**Default:** \`0\`
+
+#### \`hbase.region.replica.replication.enabled\` \\[!toc]
+
+**Description:** Whether asynchronous WAL replication to the secondary region replicas is enabled or not. We have a separated implementation for replicating the WAL without using the general inter-cluster replication framework, so now we will not add any replication peers.\\
+**Default:** \`false\`
+
+#### \`hbase.http.filter.initializers\` \\[!toc]
+
+**Description:** A comma separated list of class names. Each class in the list must extend org.apache.hadoop.hbase.http.FilterInitializer. The corresponding Filter will be initialized. Then, the Filter will be applied to all user facing jsp and servlet web pages. The ordering of the list defines the ordering of the filters. The default StaticUserWebFilter add a user principal as defined by the hbase.http.staticuser.user property.\\
+**Default:** \`org.apache.hadoop.hbase.http.lib.StaticUserWebFilter\`
+
+#### \`hbase.security.visibility.mutations.checkauths\` \\[!toc]
+
+**Description:** This property if enabled, will check whether the labels in the visibility expression are associated with the user issuing the mutation\\
+**Default:** \`false\`
+
+#### \`hbase.http.max.threads\` \\[!toc]
+
+**Description:** The maximum number of threads that the HTTP Server will create in its ThreadPool.\\
+**Default:** \`16\`
+
+#### \`hbase.http.metrics.servlets\` \\[!toc]
+
+**Description:** Comma separated list of servlet names to enable for metrics collection. Supported servlets are jmx, metrics, prometheus\\
+**Default:** \`jmx,metrics,prometheus\`
+
+#### \`hbase.profiler.enabled\` \\[!toc]
+
+**Description:** Whether the async-profiler /prof endpoint is enabled. When false, the endpoint is registered as a disabled stub (HTTP 500) regardless of whether the async-profiler library or ASYNC\\_PROFILER\\_HOME is present. Security note: when the async-profiler Maven dependency is present on the classpath (built with -Pasync-profiler), the /prof endpoint is registered as a privileged servlet by default (this property defaults to true). Access is gated by hadoop.security.instrumentat [...]
+**Default:** \`true\`
+
+#### \`hbase.replication.rpc.codec\` \\[!toc]
+
+**Description:** The codec that is to be used when replication is enabled so that the tags are also replicated. This is used along with HFileV3 which supports tags in them. If tags are not used or if the hfile version used is HFileV2 then KeyValueCodec can be used as the replication codec. Note that using KeyValueCodecWithTags for replication when there are no tags causes no harm.\\
+**Default:** \`org.apache.hadoop.hbase.codec.KeyValueCodecWithTags\`
+
+#### \`hbase.replication.source.maxthreads\` \\[!toc]
+
+**Description:** The maximum number of threads any replication source will use for shipping edits to the sinks in parallel. This also limits the number of chunks each replication batch is broken into. Larger values can improve the replication throughput between the master and slave clusters. The default of 10 will rarely need to be changed.\\
+**Default:** \`10\`
+
+#### \`hbase.http.staticuser.user\` \\[!toc]
+
+**Description:** The user name to filter as, on static web filters while rendering content. An example use is the HDFS web UI (user to be used for browsing files).\\
+**Default:** \`dr.stack\`
+
+#### \`hbase.regionserver.handler.abort.on.error.percent\` \\[!toc]
+
+**Description:** The percent of region server RPC threads failed to abort RS. -1 Disable aborting; 0 Abort if even a single handler has died; 0.x Abort only when this percent of handlers have died; 1 Abort only all of the handers have died.\\
+**Default:** \`0.5\`
+
+#### \`hbase.mob.file.cache.size\` \\[!toc]
+
+**Description:** Number of opened file handlers to cache. A larger value will benefit reads by providing more file handlers per mob file cache and would reduce frequent file opening and closing. However, if this is set too high, this could lead to a "too many opened file handlers" The default value is 1000.\\
+**Default:** \`1000\`
+
+#### \`hbase.mob.cache.evict.period\` \\[!toc]
+
+**Description:** The amount of time in seconds before the mob cache evicts cached mob files. The default value is 3600 seconds.\\
+**Default:** \`3600\`
+
+#### \`hbase.mob.cache.evict.remain.ratio\` \\[!toc]
+
+**Description:** The ratio (between 0.0 and 1.0) of files that remains cached after an eviction is triggered when the number of cached mob files exceeds the hbase.mob.file.cache.size. The default value is 0.5f.\\
+**Default:** \`0.5f\`
+
+#### \`hbase.master.mob.cleaner.period\` \\[!toc]
+
+**Description:** The period that MobFileCleanerChore runs. The unit is second. The default value is one day. The MOB file name uses only the date part of the file creation time in it. We use this time for deciding TTL expiry of the files. So the removal of TTL expired files might be delayed. The max delay might be 24 hrs.\\
+**Default:** \`86400\`
+
+#### \`hbase.mob.major.compaction.region.batch.size\` \\[!toc]
+
+**Description:** The max number of a MOB table regions that is allowed in a batch of the mob compaction. By setting this number to a custom value, users can control the overall effect of a major compaction of a large MOB-enabled table. Default is 0 - means no limit - all regions of a MOB table will be compacted at once\\
+**Default:** \`0\`
+
+#### \`hbase.mob.compaction.chore.period\` \\[!toc]
+
+**Description:** The period that MobCompactionChore runs. The unit is second. The default value is one week.\\
+**Default:** \`604800\`
+
+#### \`hbase.mob.compaction.read.cache.blocks\` \\[!toc]
+
+**Description:** Whether MOB compaction should cache blocks while reading existing MOB files to resolve references during compaction. The default value is true to preserve the previous behavior. Set to false to avoid polluting the block cache with background compaction reads.\\
+**Default:** \`true\`
+
+#### \`hbase.snapshot.master.timeout.millis\` \\[!toc]
+
+**Description:** Timeout for master for the snapshot procedure execution.\\
+**Default:** \`300000\`
+
+#### \`hbase.snapshot.region.timeout\` \\[!toc]
+
+**Description:** Timeout for regionservers to keep threads in snapshot request pool waiting.\\
+**Default:** \`300000\`
+
+#### \`hbase.rpc.rows.warning.threshold\` \\[!toc]
+
+**Description:** Number of rows in a batch operation above which a warning will be logged. If hbase.client.write.buffer.maxmutations is not set, this will be used as fallback for that setting.\\
+**Default:** \`5000\`
+
+#### \`hbase.master.wait.on.service.seconds\` \\[!toc]
+
+**Description:** Default is 5 minutes. Make it 30 seconds for tests. See HBASE-19794 for some context.\\
+**Default:** \`30\`
+
+#### \`hbase.master.cleaner.snapshot.interval\` \\[!toc]
+
+**Description:** Snapshot Cleanup chore interval in milliseconds. The cleanup thread keeps running at this interval to find all snapshots that are expired based on TTL and delete them.\\
+**Default:** \`1800000\`
+
+#### \`hbase.master.snapshot.ttl\` \\[!toc]
+
+**Description:** Default Snapshot TTL to be considered when the user does not specify TTL while creating snapshot. Default value 0 indicates FOREVERE - snapshot should not be automatically deleted until it is manually deleted\\
+**Default:** \`0\`
+
+#### \`hbase.master.regions.recovery.check.interval\` \\[!toc]
+
+**Description:** Regions Recovery Chore interval in milliseconds. This chore keeps running at this interval to find all regions with configurable max store file ref count and reopens them.\\
+**Default:** \`1200000\`
+
+#### \`hbase.regions.recovery.store.file.ref.count\` \\[!toc]
+
+**Description:** Very large number of ref count on a compacted store file indicates that it is a ref leak on that object(compacted store file). Such files can not be removed after it is invalidated via compaction. Only way to recover in such scenario is to reopen the region which can release all resources, like the refcount, leases, etc. This config represents Store files Ref Count threshold value considered for reopening regions. Any region with compacted store files ref count > this va [...]
+**Default:** \`-1\`
+
+#### \`hbase.regionserver.slowlog.ringbuffer.size\` \\[!toc]
+
+**Description:** Default size of ringbuffer to be maintained by each RegionServer in order to store online slowlog responses. This is an in-memory ring buffer of requests that were judged to be too slow in addition to the responseTooSlow logging. The in-memory representation would be complete. For more details, please look into Doc Section: Get Slow Response Log from shell\\
+**Default:** \`256\`
+
+#### \`hbase.regionserver.slowlog.buffer.enabled\` \\[!toc]
+
+**Description:** Indicates whether RegionServers have ring buffer running for storing Online Slow logs in FIFO manner with limited entries. The size of the ring buffer is indicated by config: hbase.regionserver.slowlog.ringbuffer.size The default value is false, turn this on and get latest slowlog responses with complete data.\\
+**Default:** \`false\`
+
+#### \`hbase.regionserver.slowlog.systable.enabled\` \\[!toc]
+
+**Description:** Should be enabled only if hbase.regionserver.slowlog.buffer.enabled is enabled. If enabled (true), all slow/large RPC logs would be persisted to system table hbase:slowlog (in addition to in-memory ring buffer at each RegionServer). The records are stored in increasing order of time. Operators can scan the table with various combination of ColumnValueFilter. More details are provided in the doc section: "Get Slow/Large Response Logs from System table hbase:slowlog"\\
+**Default:** \`false\`
+
+#### \`hbase.master.metafixer.max.merge.count\` \\[!toc]
+
+**Description:** Maximum regions to merge at a time when we fix overlaps noted in CJ consistency report, but avoid merging 100 regions in one go!\\
+**Default:** \`64\`
+
+#### \`hbase.rpc.rows.size.threshold.reject\` \\[!toc]
+
+**Description:** If value is true, RegionServer will abort batch requests of Put/Delete with number of rows in a batch operation exceeding threshold defined by value of config: hbase.rpc.rows.warning.threshold. The default value is false and hence, by default, only warning will be logged. This config should be turned on to prevent RegionServer from serving very large batch size of rows and this way we can improve CPU usages by discarding too large batch request.\\
+**Default:** \`false\`
+
+#### \`hbase.namedqueue.provider.classes\` \\[!toc]
+
+**Description:** Default values for NamedQueueService implementors. This comma separated full class names represent all implementors of NamedQueueService that we would like to be invoked by LogEvent handler service. One example of NamedQueue service is SlowLogQueueService which is used to store slow/large RPC logs in ringbuffer at each RegionServer. All implementors of NamedQueueService should be found under package: "org.apache.hadoop.hbase.namequeues.impl"\\
+**Default:** \`org.apache.hadoop.hbase.namequeues.impl.SlowLogQueueService,org.apache.hadoop.hbase.namequeues.impl.BalancerDecisionQueueService,org.apache.hadoop.hbase.namequeues.impl.BalancerRejectionQueueService,org.apache.hadoop.hbase.namequeues.WALEventTrackerQueueService\`
+
+#### \`hbase.master.balancer.decision.buffer.enabled\` \\[!toc]
+
+**Description:** Indicates whether active HMaster has ring buffer running for storing balancer decisions in FIFO manner with limited entries. The size of the ring buffer is indicated by config: hbase.master.balancer.decision.queue.size\\
+**Default:** \`false\`
+
+#### \`hbase.master.balancer.rejection.buffer.enabled\` \\[!toc]
+
+**Description:** Indicates whether active HMaster has ring buffer running for storing balancer rejection in FIFO manner with limited entries. The size of the ring buffer is indicated by config: hbase.master.balancer.rejection.queue.size\\
+**Default:** \`false\`
+
+#### \`hbase.locality.inputstream.derive.enabled\` \\[!toc]
+
+**Description:** If true, derive StoreFile locality metrics from the underlying DFSInputStream backing reads for that StoreFile. This value will update as the DFSInputStream's block locations are updated over time. Otherwise, locality is computed on StoreFile open, and cached until the StoreFile is closed.\\
+**Default:** \`false\`
+
+#### \`hbase.locality.inputstream.derive.cache.period\` \\[!toc]
+
+**Description:** If deriving StoreFile locality metrics from the underlying DFSInputStream, how long should the derived values be cached for. The derivation process may involve hitting the namenode, if the DFSInputStream's block list is incomplete.\\
+**Default:** \`60000\`
+
+## hbase-env.sh
+
+Set HBase environment variables in this file. Examples include options to pass the JVM on start of an HBase daemon such as heap size and garbage collector configs. You can also set configurations for HBase configuration, log directories, niceness, ssh options, where to locate process pid files, etc. Open the file at *conf/hbase-env.sh* and peruse its content. Each option is fairly well documented. Add your own environment variables here if you want them read by HBase daemons on startup.
+
+Changes here will require a cluster restart for HBase to notice the change.
+
+## *log4j2.properties*
+
+Since version 2.5.0, HBase has upgraded to Log4j2, so the configuration file name and format has changed. Read more in [Apache Log4j2](https://logging.apache.org/log4j/2.x/index.html).
+
+Edit this file to change rate at which HBase files are rolled and to change the level at which HBase logs messages.
+
+Changes here will require a cluster restart for HBase to notice the change though log levels can be changed for particular daemons via the HBase UI.
+
+## Client configuration and dependencies connecting to an HBase cluster
+
+If you are running HBase in standalone mode, you don't need to configure anything for your client to work provided that they are all on the same machine.
+
+Starting release 3.0.0, the default connection registry has been switched to a rpc based implementation. Refer to [Rpc Connection Registry (new as of 2.5.0)](/docs/architecture/client#rpc-connection-registry-new-as-of-250). Depending on your HBase version, following is the expected minimal client configuration.
+
+### Up until 2.x.y releases
+
+In 2.x.y releases, the default connection registry was based on ZooKeeper as the source of truth. This means that the clients always looked up ZooKeeper znodes to fetch the required metadata. For example, if an active master crashed and the a new master is elected, clients looked up the master znode to fetch the active master address (similarly for meta locations). This meant that the clients needed to have access to ZooKeeper and need to know the ZooKeeper ensemble information before th [...]
+
+\`\`\`xml
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<configuration>
+ <property>
+ <name>hbase.zookeeper.quorum</name>
+ <value>example1,example2,example3</value>
+ <description>Zookeeper ensemble information</description>
+ </property>
+</configuration>
+\`\`\`
+
+### Starting from 3.0.0 release
+
+The default implementation was switched to a rpc based connection registry. With this implementation, by default clients contact the active or stand-by master RPC end points to fetch the connection registry information. This means that the clients should have access to the list of active and master end points before they can do anything. This can be configured in the client configuration xml as follows:
+
+\`\`\`xml
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<configuration>
+ <property>
+ <name>hbase.masters</name>
+ <value>example1,example2,example3</value>
+ <description>List of master rpc end points for the hbase cluster.</description>
+ </property>
+</configuration>
+\`\`\`
+
+The configuration value for *hbase.masters* is a comma separated list of *host:port* values. If no port value is specified, the default of *16000* is assumed.
+
+Of course you are free to specify bootstrap nodes other than masters, like:
+
+\`\`\`xml
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<property>
+ <name>hbase.client.bootstrap.servers</name>
+ <value>server1:16020,server2:16020,server3:16020</value>
+</property>
+\`\`\`
+
+The configuration value for *hbase.client.bootstrap.servers* is a comma separated list of *host:port* values. Notice that port must be specified here.
+
+Usually these configurations are kept out in the *hbase-site.xml* and is picked up by the client from the \`CLASSPATH\`.
+
+If you are configuring an IDE to run an HBase client, you should include the *conf/* directory on your classpath so *hbase-site.xml* settings can be found (or add *src/test/resources* to pick up the hbase-site.xml used by tests).
+
+For Java applications using Maven, including the hbase-shaded-client module is the recommended dependency when connecting to a cluster:
+
+\`\`\`xml
+<dependency>
+ <groupId>org.apache.hbase</groupId>
+ <artifactId>hbase-shaded-client</artifactId>
+ <version>2.0.0</version>
+</dependency>
+\`\`\`
+
+### Java client configuration
+
+The configuration used by a Java client is kept in an [HBaseConfiguration](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/HBaseConfiguration) instance.
+
+The factory method on HBaseConfiguration, \`HBaseConfiguration.create();\`, on invocation, will read in the content of the first *hbase-site.xml* found on the client's \`CLASSPATH\`, if one is present (Invocation will also factor in any *hbase-default.xml* found; an *hbase-default.xml* ships inside the *hbase.X.X.X.jar*). It is also possible to specify configuration directly without having to read from a *hbase-site.xml*.
+
+For example, to set the ZooKeeper ensemble or bootstrap nodes for the cluster programmatically do as follows:
+
+\`\`\`java
+Configuration config = HBaseConfiguration.create();
+config.set("hbase.zookeeper.quorum", "localhost"); // Until 2.x.y versions
+// ---- or ----
+config.set("hbase.client.bootstrap.servers", "localhost:1234"); // Starting 3.0.0 version
+\`\`\`
+
+## Timeout settings
+
+HBase provides a wide variety of timeout settings to limit the execution time of various remote operations.
+
+* hbase.rpc.timeout
+* hbase.rpc.read.timeout
+* hbase.rpc.write.timeout
+* hbase.client.operation.timeout
+* hbase.client.meta.operation.timeout
+* hbase.client.scanner.timeout.period
+
+The \`hbase.rpc.timeout\` property limits how long a single RPC call can run before timing out. To fine tune read or write related RPC timeouts set \`hbase.rpc.read.timeout\` and \`hbase.rpc.write.timeout\` configuration properties. In the absence of these properties \`hbase.rpc.timeout\` will be used.
+
+A higher-level timeout is \`hbase.client.operation.timeout\` which is valid for each client call. When an RPC call fails for instance for a timeout due to \`hbase.rpc.timeout\` it will be retried until \`hbase.client.operation.timeout\` is reached. Client operation timeout for system tables can be fine tuned by setting \`hbase.client.meta.operation.timeout\` configuration value. When this is not set its value will use \`hbase.client.operation.timeout\`.
+
+Timeout for scan operations is controlled differently. Use \`hbase.client.scanner.timeout.period\` property to set this timeout.
+
+## Example Configurations
+
+## Basic Distributed HBase Install
+
+Here is a basic configuration example for a distributed ten node cluster: \\* The nodes are named \`example0\`, \`example1\`, etc., through node \`example9\` in this example. \\* The HBase Master and the HDFS NameNode are running on the node \`example0\`. \\* RegionServers run on nodes \`example1\`-\`example9\`. \\* A 3-node ZooKeeper ensemble runs on \`example1\`, \`example2\`, and \`example3\` on the default ports. \\* ZooKeeper data is persisted to the directory */export/zookeeper*.
+
+Below we show what the main configuration files — *hbase-site.xml*, *regionservers*, and *hbase-env.sh* — found in the HBase *conf* directory might look like.
+
+### hbase-site.xml
+
+\`\`\`xml
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<configuration>
+ <property>
+ <name>hbase.zookeeper.quorum</name>
+ <value>example1,example2,example3</value>
+ <description>The directory shared by RegionServers.</description>
+ </property>
+ <property>
+ <name>hbase.zookeeper.property.dataDir</name>
+ <value>/export/zookeeper</value>
+ <description>Property from ZooKeeper config zoo.cfg.
+ The directory where the snapshot is stored.
+ </description>
+ </property>
+ <property>
+ <name>hbase.rootdir</name>
+ <value>hdfs://example0:9000/hbase</value>
+ <description>The directory shared by RegionServers.</description>
+ </property>
+ <property>
+ <name>hbase.cluster.distributed</name>
+ <value>true</value>
+ <description>The mode the cluster will be in. Possible values are
+ false: standalone and pseudo-distributed setups with managed ZooKeeper
+ true: fully-distributed with unmanaged ZooKeeper Quorum (see hbase-env.sh)
+ </description>
+ </property>
+</configuration>
+\`\`\`
+
+### *regionservers*
+
+In this file you list the nodes that will run RegionServers. In our case, these nodes are \`example1\`-\`example9\`.
+
+\`\`\`text
+example1
+example2
+example3
+example4
+example5
+example6
+example7
+example8
+example9
+\`\`\`
+
+### hbase-env.sh
+
+The following lines in the *hbase-env.sh* file show how to set the \`JAVA_HOME\` environment variable (required for HBase) and set the heap to 4 GB (rather than the default value of 1 GB). If you copy and paste this example, be sure to adjust the \`JAVA_HOME\` to suit your environment.
+
+\`\`\`bash
+# The java implementation to use.
+export JAVA_HOME=/usr/java/jdk1.8.0/
+
+# The maximum amount of heap to use. Default is left to JVM default.
+export HBASE_HEAPSIZE=4G
+\`\`\`
+
+Use rsync to copy the content of the *conf* directory to all nodes of the cluster.
+
+## The Important Configurations
+
+## Required Configurations
+
+Review the [os](/docs/configuration/basic-prerequisites#operating-system-utilities) and [hadoop](/docs/configuration/basic-prerequisites#hadoop) sections.
+
+### Big Cluster Configurations
+
+If you have a cluster with a lot of regions, it is possible that a Regionserver checks in briefly after the Master starts while all the remaining RegionServers lag behind. This first server to check in will be assigned all regions which is not optimal. To prevent the above scenario from happening, up the \`hbase.master.wait.on.regionservers.mintostart\` property from its default value of 1. See [HBASE-6389 Modify the conditions to ensure that Master waits for sufficient number of Region [...]
+
+## Recommended Configurations
+
+### ZooKeeper Configuration
+
+#### \`zookeeper.session.timeout\`
+
+The default timeout is 90 seconds (specified in milliseconds). This means that if a server crashes, it will be 90 seconds before the Master notices the crash and starts recovery. You might need to tune the timeout down to a minute or even less so the Master notices failures sooner. Before changing this value, be sure you have your JVM garbage collection configuration under control, otherwise, a long garbage collection that lasts beyond the ZooKeeper session timeout will take out your Reg [...]
+
+To change this configuration, edit *hbase-site.xml*, copy the changed file across the cluster and restart.
+
+We set this value high to save our having to field questions up on the mailing lists asking why a RegionServer went down during a massive import. The usual cause is that their JVM is untuned and they are running into long GC pauses. Our thinking is that while users are getting familiar with HBase, we'd save them having to know all of its intricacies. Later when they've built some confidence, then they can play with configuration such as this.
+
+#### Number of ZooKeeper Instances
+
+See [zookeeper](/docs/zookeeper).
+
+### HDFS Configurations
+
+#### \`dfs.datanode.failed.volumes.tolerated\`
+
+This is the "...number of volumes that are allowed to fail before a DataNode stops offering service. By default, any volume failure will cause a datanode to shutdown" from the *hdfs-default.xml* description. You might want to set this to about half the amount of your available disks.
+
+#### \`hbase.regionserver.handler.count\`
+
+This setting defines the number of threads that are kept open to answer incoming requests to user tables. The rule of thumb is to keep this number low when the payload per request approaches the MB (big puts, scans using a large cache) and high when the payload is small (gets, small puts, ICVs, deletes). The total size of the queries in progress is limited by the setting \`hbase.ipc.server.max.callqueue.size\`.
+
+It is safe to set that number to the maximum number of incoming clients if their payload is small, the typical example being a cluster that serves a website since puts aren't typically buffered and most of the operations are gets.
+
+The reason why it is dangerous to keep this setting high is that the aggregate size of all the puts that are currently happening in a region server may impose too much pressure on its memory, or even trigger an OutOfMemoryError. A RegionServer running on low memory will trigger its JVM's garbage collector to run more frequently up to a point where GC pauses become noticeable (the reason being that all the memory used to keep all the requests' payloads cannot be trashed, no matter how har [...]
+
+You can get a sense of whether you have too little or too many handlers by [rpc.logging](/docs/troubleshooting#enabling-rpc-level-logging) on an individual RegionServer then tailing its logs (Queued requests consume memory).
+
+### Configuration for large memory machines
+
+HBase ships with a reasonable, conservative configuration that will work on nearly all machine types that people might want to test with. If you have larger machines — HBase has 8G and larger heap — you might find the following configuration options helpful. TODO.
+
+### Compression
+
+You should consider enabling ColumnFamily compression. There are several options that are near-frictionless and in most all cases boost performance by reducing the size of StoreFiles and thus reducing I/O.
+
+See [compression](/docs/compression) for more information.
+
+### Configuring the size and number of WAL files
+
+HBase uses \\[wal]/docs/architecture/regionserver#write-ahead-log-wal to recover the memstore data that has not been flushed to disk in case of an RS failure. These WAL files should be configured to be slightly smaller than HDFS block (by default a HDFS block is 64Mb and a WAL file is \\~60Mb).
+
+HBase also has a limit on the number of WAL files, designed to ensure there's never too much data that needs to be replayed during recovery. This limit needs to be set according to memstore configuration, so that all the necessary data would fit. It is recommended to allocate enough WAL files to store at least that much data (when all memstores are close to full). For example, with 16Gb RS heap, default memstore settings (0.4), and default WAL file size (\\~60Mb), 16Gb\\*0.4/60, the star [...]
+
+### Managed Splitting
+
+HBase generally handles splitting of your regions based upon the settings in your *hbase-default.xml* and *hbase-site.xml* configuration files. Important settings include \`hbase.regionserver.region.split.policy\`, \`hbase.hregion.max.filesize\`, \`hbase.regionserver.regionSplitLimit\`. A simplistic view of splitting is that when a region grows to \`hbase.hregion.max.filesize\`, it is split. For most usage patterns, you should use automatic splitting. See [manual region splitting decisio [...]
+
+Instead of allowing HBase to split your regions automatically, you can choose to manage the splitting yourself. Manually managing splits works if you know your keyspace well, otherwise let HBase figure where to split for you. Manual splitting can mitigate region creation and movement under load. It also makes it so region boundaries are known and invariant (if you disable region splitting). If you use manual splits, it is easier doing staggered, time-based major compactions to spread out [...]
+
+#### Disable Automatic Splitting
+
+To disable automatic splitting, you can set region split policy in either cluster configuration or table configuration to be \`org.apache.hadoop.hbase.regionserver.DisabledRegionSplitPolicy\`
+
+<Callout type="info">
+ If you disable automatic splits to diagnose a problem or during a period of fast data growth, it
+ is recommended to re-enable them when your situation becomes more stable. The potential benefits
+ of managing region splits yourself are not undisputed.
+</Callout>
+
+#### Determine the Optimal Number of Pre-Split Regions
+
+The optimal number of pre-split regions depends on your application and environment. A good rule of thumb is to start with 10 pre-split regions per server and watch as data grows over time. It is better to err on the side of too few regions and perform rolling splits later. The optimal number of regions depends upon the largest StoreFile in your region. The size of the largest StoreFile will increase with time if the amount of data grows. The goal is for the largest region to be just lar [...]
+
+If the regions are split into too many large regions, you can increase the major compaction interval by configuring \`HConstants.MAJOR_COMPACTION_PERIOD\`. The \`org.apache.hadoop.hbase.util.RegionSplitter\` utility also provides a network-IO-safe rolling split of all regions.
+
+### Managed Compactions
+
+By default, major compactions are scheduled to run once in a 7-day period.
+
+If you need to control exactly when and how often major compaction runs, you can disable managed major compactions. See the entry for \`hbase.hregion.majorcompaction\` in the [compaction.parameters](/docs/architecture/regions#parameters-used-by-compaction-algorithm) table for details.
+
+<Callout type="warn">
+ Major compactions are absolutely necessary for StoreFile clean-up. Do not disable them altogether.
+ You can run major compactions manually via the HBase shell or via the [Admin
+ API](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Admin.html#majorCompact\\(org.apache.hadoop.hbase.TableName\\)).
+</Callout>
+
+For more information about compactions and the compaction file selection process, see [compaction](/docs/architecture/regions#compaction)
+
+### Speculative Execution
+
+Speculative Execution of MapReduce tasks is on by default, and for HBase clusters it is generally advised to turn off Speculative Execution at a system-level unless you need it for a specific case, where it can be configured per-job. Set the properties \`mapreduce.map.speculative\` and \`mapreduce.reduce.speculative\` to false.
+
+## Other Configurations
+
+### Balancer
+
+The balancer is a periodic operation which is run on the master to redistribute regions on the cluster. It is configured via \`hbase.balancer.period\` and defaults to 300000 (5 minutes).
+
+See [master.processes.loadbalancer](/docs/architecture/master#loadbalancer) for more information on the LoadBalancer.
+
+### Disabling Blockcache
+
+Do not turn off block cache (You'd do it by setting \`hfile.block.cache.size\` to zero). Currently, we do not do well if you do this because the RegionServer will spend all its time loading HFile indices over and over again. If your working set is such that block cache does you no good, at least size the block cache such that HFile indices will stay up in the cache (you can get a rough idea on the size you need by surveying RegionServer UIs; you'll see index block size accounted near the [...]
+
+### Nagle's or the small package problem
+
+If a big 40ms or so occasional delay is seen in operations against HBase, try the [Nagle's](https://en.wikipedia.org/wiki/Nagle%27s_algorithm) setting. For example, see the user mailing list thread, [Inconsistent scan performance with caching set to 1](https://lists.apache.org/thread.html/3d7ceb41c04a955b1b1c80480cdba95208ca3e97bf6895a40e0c1bbb%401346186127%40%3Cuser.hbase.apache.org%3E) and the issue cited therein where setting \`notcpdelay\` improved scan speeds. You might also see the [...]
+
+### Better Mean Time to Recover (MTTR)
+
+This section is about configurations that will make servers come back faster after a fail. See the Deveraj Das and Nicolas Liochon blog post [Introduction to HBase Mean Time to Recover (MTTR)](http://hortonworks.com/blog/introduction-to-hbase-mean-time-to-recover-mttr/) for a brief introduction.
+
+The issue [HBASE-8354 forces Namenode into loop with lease recovery requests](https://issues.apache.org/jira/browse/HBASE-8389) is messy but has a bunch of good discussion toward the end on low timeouts and how to cause faster recovery including citation of fixes added to HDFS. Read the Varun Sharma comments. The below suggested configurations are Varun's suggestions distilled and tested. Make sure you are running on a late-version HDFS so you have the fixes he refers to and himself adds [...]
+
+\`\`\`xml
+<property>
+ <name>hbase.lease.recovery.dfs.timeout</name>
+ <value>23000</value>
+ <description>How much time we allow elapse between calls to recover lease.
+ Should be larger than the dfs timeout.</description>
+</property>
+<property>
+ <name>dfs.client.socket-timeout</name>
+ <value>10000</value>
+ <description>Down the DFS timeout from 60 to 10 seconds.</description>
+</property>
+\`\`\`
+
+And on the NameNode/DataNode side, set the following to enable 'staleness' introduced in HDFS-3703, HDFS-3912.
+
+\`\`\`xml
+<property>
+ <name>dfs.client.socket-timeout</name>
+ <value>10000</value>
+ <description>Down the DFS timeout from 60 to 10 seconds.</description>
+</property>
+<property>
+ <name>dfs.datanode.socket.write.timeout</name>
+ <value>10000</value>
+ <description>Down the DFS timeout from 8 * 60 to 10 seconds.</description>
+</property>
+<property>
+ <name>ipc.client.connect.timeout</name>
+ <value>3000</value>
+ <description>Down from 60 seconds to 3.</description>
+</property>
+<property>
+ <name>ipc.client.connect.max.retries.on.timeouts</name>
+ <value>2</value>
+ <description>Down from 45 seconds to 3 (2 == 3 retries).</description>
+</property>
+<property>
+ <name>dfs.namenode.avoid.read.stale.datanode</name>
+ <value>true</value>
+ <description>Enable stale state in hdfs</description>
+</property>
+<property>
+ <name>dfs.namenode.stale.datanode.interval</name>
+ <value>20000</value>
+ <description>Down from default 30 seconds</description>
+</property>
+<property>
+ <name>dfs.namenode.avoid.write.stale.datanode</name>
+ <value>true</value>
+ <description>Enable stale state in hdfs</description>
+</property>
+\`\`\`
+
+### JMX
+
+JMX (Java Management Extensions) provides built-in instrumentation that enables you to monitor and manage the Java VM. To enable monitoring and management from remote systems, you need to set system property \`com.sun.management.jmxremote.port\` (the port number through which you want to enable JMX RMI connections) when you start the Java VM. See the [official documentation](http://docs.oracle.com/javase/8/docs/technotes/guides/management/agent.html) for more information. Historically, b [...]
+
+As an alternative, you can use the coprocessor-based JMX implementation provided by HBase. To enable it, add below property in *hbase-site.xml*:
+
+\`\`\`xml
+<property>
+ <name>hbase.coprocessor.regionserver.classes</name>
+ <value>org.apache.hadoop.hbase.JMXListener</value>
+</property>
+\`\`\`
+
+<Callout type="info">
+ DO NOT set \`com.sun.management.jmxremote.port\` for Java VM at the same time.
+</Callout>
+
+Currently it supports Master and RegionServer Java VM. By default, the JMX listens on TCP port 10102, you can further configure the port using below properties:
+
+\`\`\`xml
+<property>
+ <name>regionserver.rmi.registry.port</name>
+ <value>61130</value>
+</property>
+<property>
+ <name>regionserver.rmi.connector.port</name>
+ <value>61140</value>
+</property>
+\`\`\`
+
+The registry port can be shared with connector port in most cases, so you only need to configure \`regionserver.rmi.registry.port\`. However, if you want to use SSL communication, the 2 ports must be configured to different values.
+
+By default the password authentication and SSL communication is disabled. To enable password authentication, you need to update *hbase-env.sh* like below:
+
+\`\`\`bash
+export HBASE_JMX_BASE="-Dcom.sun.management.jmxremote.authenticate=true \\
+ -Dcom.sun.management.jmxremote.password.file=your_password_file \\
+ -Dcom.sun.management.jmxremote.access.file=your_access_file"
+
+export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS $HBASE_JMX_BASE "
+export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS $HBASE_JMX_BASE "
+\`\`\`
+
+See example password/access file under \`$JRE_HOME/lib/management\`.
+
+To enable SSL communication with password authentication, follow below steps:
+
+\`\`\`bash
+#1. generate a key pair, stored in myKeyStore
+keytool -genkey -alias jconsole -keystore myKeyStore
+
+#2. export it to file jconsole.cert
+keytool -export -alias jconsole -keystore myKeyStore -file jconsole.cert
+
+#3. copy jconsole.cert to jconsole client machine, import it to jconsoleKeyStore
+keytool -import -alias jconsole -keystore jconsoleKeyStore -file jconsole.cert
+\`\`\`
+
+And then update *hbase-env.sh* like below:
+
+\`\`\`bash
+export HBASE_JMX_BASE="-Dcom.sun.management.jmxremote.ssl=true \\
+ -Djavax.net.ssl.keyStore=/home/tianq/myKeyStore \\
+ -Djavax.net.ssl.keyStorePassword=your_password_in_step_1 \\
+ -Dcom.sun.management.jmxremote.authenticate=true \\
+ -Dcom.sun.management.jmxremote.password.file=your_password file \\
+ -Dcom.sun.management.jmxremote.access.file=your_access_file"
+
+export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS $HBASE_JMX_BASE "
+export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS $HBASE_JMX_BASE "
+\`\`\`
+
+Finally start \`jconsole\` on the client using the key store:
+
+\`\`\`bash
+jconsole -J-Djavax.net.ssl.trustStore=/home/tianq/jconsoleKeyStore
+\`\`\`
+
+<Callout type="info">
+ To enable the HBase JMX implementation on Master, you also need to add below property in
+ *hbase-site.xml*:
+</Callout>
+
+\`\`\`xml
+<property>
+ <name>hbase.coprocessor.master.classes</name>
+ <value>org.apache.hadoop.hbase.JMXListener</value>
+</property>
+\`\`\`
+
+The corresponding properties for port configuration are \`master.rmi.registry.port\` (by default 10101) and \`master.rmi.connector.port\` (by default the same as registry.port)
+
+## Dynamic Configuration
+
+It is possible to change a subset of the configuration without requiring a server restart. In the HBase shell, the operations \`update_config\`, \`update_all_config\` and \`update_rsgroup_config\` will prompt a server, all servers or all servers in the RSGroup to reload configuration.
+
+Only a subset of all configurations can currently be changed in the running server. Here are those configurations:
+
+Configurations that support dynamically change
+
+| Key |
+| ---------------------------------------------------------------------- |
+| hbase.ipc.server.fallback-to-simple-auth-allowed |
+| hbase.cleaner.scan.dir.concurrent.size |
+| hbase.coprocessor.master.classes |
+| hbase.coprocessor.region.classes |
+| hbase.coprocessor.regionserver.classes |
+| hbase.coprocessor.user.region.classes |
+| hbase.regionserver.thread.compaction.large |
+| hbase.regionserver.thread.compaction.small |
+| hbase.regionserver.thread.split |
+| hbase.regionserver.throughput.controller |
+| hbase.regionserver.thread.hfilecleaner.throttle |
+| hbase.regionserver.hfilecleaner.large.queue.size |
+| hbase.regionserver.hfilecleaner.small.queue.size |
+| hbase.regionserver.hfilecleaner.large.thread.count |
+| hbase.regionserver.hfilecleaner.small.thread.count |
+| hbase.regionserver.hfilecleaner.thread.timeout.msec |
+| hbase.regionserver.hfilecleaner.thread.check.interval.msec |
+| hbase.regionserver.flush.throughput.controller |
+| hbase.hstore.compaction.max.size |
+| hbase.hstore.compaction.max.size.offpeak |
+| hbase.hstore.compaction.min.size |
+| hbase.hstore.compaction.min |
+| hbase.hstore.compaction.max |
+| hbase.hstore.compaction.ratio |
+| hbase.hstore.compaction.ratio.offpeak |
+| hbase.regionserver.thread.compaction.throttle |
+| hbase.hregion.majorcompaction |
+| hbase.hregion.majorcompaction.jitter |
+| hbase.hstore.min.locality.to.skip.major.compact |
+| hbase.hstore.compaction.date.tiered.max.storefile.age.millis |
+| hbase.hstore.compaction.date.tiered.incoming.window\\.min |
+| hbase.hstore.compaction.date.tiered.window\\.policy.class |
+| hbase.hstore.compaction.date.tiered.single.output.for.minor.compaction |
+| hbase.hstore.compaction.date.tiered.window\\.factory.class |
+| hbase.offpeak.start.hour |
+| hbase.offpeak.end.hour |
+| hbase.oldwals.cleaner.thread.size |
+| hbase.oldwals.cleaner.thread.timeout.msec |
+| hbase.oldwals.cleaner.thread.check.interval.msec |
+| hbase.procedure.worker.keep.alive.time.msec |
+| hbase.procedure.worker.add.stuck.percentage |
+| hbase.procedure.worker.monitor.interval.msec |
+| hbase.procedure.worker.stuck.threshold.msec |
+| hbase.regions.slop |
+| hbase.regions.overallSlop |
+| hbase.balancer.tablesOnMaster |
+| hbase.balancer.tablesOnMaster.systemTablesOnly |
+| hbase.util.ip.to.rack.determiner |
+| hbase.ipc.server.max.callqueue.length |
+| hbase.ipc.server.priority.max.callqueue.length |
+| hbase.ipc.server.callqueue.type |
+| hbase.ipc.server.callqueue.codel.target.delay |
+| hbase.ipc.server.callqueue.codel.interval |
+| hbase.ipc.server.callqueue.codel.lifo.threshold |
+| hbase.master.balancer.stochastic.maxSteps |
+| hbase.master.balancer.stochastic.stepsPerRegion |
+| hbase.master.balancer.stochastic.maxRunningTime |
+| hbase.master.balancer.stochastic.runMaxSteps |
+| hbase.master.balancer.stochastic.numRegionLoadsToRemember |
+| hbase.master.loadbalance.bytable |
+| hbase.master.balancer.stochastic.minCostNeedBalance |
+| hbase.master.balancer.stochastic.localityCost |
+| hbase.master.balancer.stochastic.rackLocalityCost |
+| hbase.master.balancer.stochastic.readRequestCost |
+| hbase.master.balancer.stochastic.writeRequestCost |
+| hbase.master.balancer.stochastic.memstoreSizeCost |
+| hbase.master.balancer.stochastic.storefileSizeCost |
+| hbase.master.balancer.stochastic.regionReplicaHostCostKey |
+| hbase.master.balancer.stochastic.regionReplicaRackCostKey |
+| hbase.master.balancer.stochastic.regionCountCost |
+| hbase.master.balancer.stochastic.primaryRegionCountCost |
+| hbase.master.balancer.stochastic.moveCost |
+| hbase.master.balancer.stochastic.moveCost.offpeak |
+| hbase.master.balancer.stochastic.maxMovePercent |
+| hbase.master.balancer.stochastic.tableSkewCost |
+| hbase.master.regions.recovery.check.interval |
+| hbase.regions.recovery.store.file.ref.count |
+| hbase.rsgroup.fallback.enable |
+
+***
+
+# Upgrading
+
+You cannot skip major versions when upgrading. If you are upgrading from version 0.98.x to 2.x, you must first go from 0.98.x to 1.2.x and then go from 1.2.x to 2.x.
+
+Review [Apache HBase Configuration](/docs/configuration), in particular [Hadoop](/docs/configuration/basic-prerequisites#hadoop). Familiarize yourself with [Support and Testing Expectations](/docs#support-and-testing-expectations).
+
+## HBase version number and compatibility
+
+## Aspirational Semantic Versioning
+
+Starting with the 1.0.0 release, HBase is working towards [Semantic Versioning](http://semver.org/) for its release versioning. In summary:
+
+#### Given a version number MAJOR.MINOR.PATCH, increment the: \\[!toc]
+
+* MAJOR version when you make incompatible API changes,
+* MINOR version when you add functionality in a backwards-compatible manner, and
+* PATCH version when you make backwards-compatible bug fixes.
+* Additional labels for pre-release and build metadata are available as extensions to the MAJOR.MINOR.PATCH format.
+
+#### Compatibility Dimensions \\[!toc]
+
+In addition to the usual API versioning considerations HBase has other compatibility dimensions that we need to consider.
+
+#### Client-Server wire protocol compatibility \\[!toc]
+
+* Allows updating client and server out of sync.
+* We could only allow upgrading the server first. I.e. the server would be backward compatible to an old client, that way new APIs are OK.
+* Example: A user should be able to use an old client to connect to an upgraded cluster.
+
+#### Server-Server protocol compatibility \\[!toc]
+
+* Servers of different versions can co-exist in the same cluster.
+* The wire protocol between servers is compatible.
+* Workers for distributed tasks, such as replication and log splitting, can co-exist in the same cluster.
+* Dependent protocols (such as using ZK for coordination) will also not be changed.
+* Example: A user can perform a rolling upgrade.
+
+#### File format compatibility \\[!toc]
+
+* Support file formats backward and forward compatible
+* Example: File, ZK encoding, directory layout is upgraded automatically as part of an HBase upgrade. User can downgrade to the older version and everything will continue to work.
+
+#### Client API compatibility \\[!toc]
+
+* Allow changing or removing existing client APIs.
+* An API needs to be deprecated for a whole major version before we will change/remove it.
+ * An example: An API was deprecated in 2.0.1 and will be marked for deletion in 4.0.0. On the other hand, an API deprecated in 2.0.0 can be removed in 3.0.0.
+ * Occasionally mistakes are made and internal classes are marked with a higher access level than they should. In these rare circumstances, we will accelerate the deprecation schedule to the next major version (i.e., deprecated in 2.2.x, marked \`IA.Private\` 3.0.0). Such changes are communicated and explained via release note in Jira.
+* APIs available in a patch version will be available in all later patch versions. However, new APIs may be added which will not be available in earlier patch versions.
+* New APIs introduced in a patch version will only be added in a source compatible way: i.e. code that implements public APIs will continue to compile. [^1]
+ * Example: A user using a newly deprecated API does not need to modify application code with HBase API calls until the next major version. \\*
+
+#### Client Binary compatibility \\[!toc]
+
+* Client code written to APIs available in a given patch release can run unchanged (no recompilation needed) against the new jars of later patch versions.
+* Client code written to APIs available in a given patch release might not run against the old jars from an earlier patch version.
+ * Example: Old compiled client code will work unchanged with the new jars.
+* If a Client implements an HBase Interface, a recompile MAY be required upgrading to a newer minor version (See release notes for warning about incompatible changes). All effort will be made to provide a default implementation so this case should not arise.
+
+#### Server-Side Limited API compatibility (taken from Hadoop) \\[!toc]
+
+* Internal APIs are marked as Stable, Evolving, or Unstable
+* This implies binary compatibility for coprocessors and plugins (pluggable classes, including replication) as long as these are only using marked interfaces/classes.
+* Example: Old compiled Coprocessor, Filter, or Plugin code will work unchanged with the new jars.
+
+#### Dependency Compatibility \\[!toc]
+
+* An upgrade of HBase will not require an incompatible upgrade of a dependent project, except for Apache Hadoop.
+* An upgrade of HBase will not require an incompatible upgrade of the Java runtime.
+* Example: Upgrading HBase to a version that supports *Dependency Compatibility* won't require that you upgrade your Apache ZooKeeper service.
+* Example: If your current version of HBase supported running on JDK 8, then an upgrade to a version that supports *Dependency Compatibility* will also run on JDK 8.
+
+<Callout type="tip">
+ Previously, we tried to maintain dependency compatibility for the underly Hadoop service but over
+ the last few years this has proven untenable. While the HBase project attempts to maintain support
+ for older versions of Hadoop, we drop the "supported" designator for minor versions that fail to
+ continue to see releases. Additionally, the Hadoop project has its own set of compatibility
+ guidelines, which means in some cases having to update to a newer supported minor release might
+ break some of our compatibility promises.
+</Callout>
+
+#### Operational Compatibility \\[!toc]
+
+* Metric changes
+* Behavioral changes of services
+* JMX APIs exposed via the \`/jmx/\` endpoint
+
+#### Summary \\[!toc]
+
+* A patch upgrade is a drop-in replacement. Any change that is not Java binary and source compatible would not be allowed.[^2] Downgrading versions within patch releases may not be compatible.
+* A minor upgrade requires no application/client code modification. Ideally it would be a drop-in replacement but client code, coprocessors, filters, etc might have to be recompiled if new jars are used.
+* A major upgrade allows the HBase community to make breaking changes.
+
+#### Compatibility Matrix: \\[!toc]
+
+<Callout type="warn">
+ *Please note, this indicates what could break, not that it will break. We will/should add
+ specifics in our release notes.*
+</Callout>
+
+| | Major | Minor | Patch |
+| ----------------------------------------- | :----: | :---: | :---: |
+| Client-Server wire Compatibility | N | Y | Y |
+| Server-Server Compatibility | N | Y | Y |
+| File Format Compatibility | N [^3] | Y | Y |
+| Client API Compatibility | N | Y | Y |
+| Client Binary Compatibility | N | N | Y |
+| **Server-Side Limited API Compatibility** | | | |
+| → Stable | N | Y | Y |
+| → Evolving | N | N | Y |
+| → Unstable | N | N | N |
+| Dependency Compatibility | N | Y | Y |
+| Operational Compatibility | N | N | Y |
+
+<Callout type="warn">
+ HBase 1.7.0 release violated client-server wire compatibility guarantees and was subsequently
+ withdrawn after the incompatibilities were reported and fixed in 1.7.1. If you are considering an
+ upgrade to 1.7.x line, see [Upgrading to 1.7.1+](/docs/upgrading/paths#upgrading-to-171).
+</Callout>
+
+## HBase API Surface
+
+HBase has a lot of API points, but for the compatibility matrix above, we differentiate between Client API, Limited Private API, and Private API. HBase uses [Apache Yetus Audience Annotations](https://yetus.apache.org/documentation/in-progress/interface-classification/) to guide downstream expectations for stability.
+
+* InterfaceAudience ([javadocs](https://yetus.apache.org/documentation/in-progress/javadocs/org/apache/yetus/audience/InterfaceAudience.html)): captures the intended audience, possible values include:
+ * Public: safe for end users and external projects
+ * LimitedPrivate: used for internals we expect to be pluggable, such as coprocessors
+ * Private: strictly for use within HBase itself Classes which are defined as \`IA.Private\` may be used as parameters or return values for interfaces which are declared \`IA.LimitedPrivate\`. Treat the \`IA.Private\` object as opaque; do not try to access its methods or fields directly.
+* InterfaceStability ([javadocs](https://yetus.apache.org/documentation/in-progress/javadocs/org/apache/yetus/audience/InterfaceStability.html)): describes what types of interface changes are permitted. Possible values include:
+ * Stable: the interface is fixed and is not expected to change
+ * Evolving: the interface may change in future minor versions
+ * Unstable: the interface may change at any time
+
+Please keep in mind the following interactions between the \`InterfaceAudience\` and \`InterfaceStability\` annotations within the HBase project:
+
+* \`IA.Public\` classes are inherently stable and adhere to our stability guarantees relating to the type of upgrade (major, minor, or patch).
+* \`IA.LimitedPrivate\` classes should always be annotated with one of the given \`InterfaceStability\` values. If they are not, you should presume they are \`IS.Unstable\`.
+* \`IA.Private\` classes should be considered implicitly unstable, with no guarantee of stability between releases.
+
+### HBase Client API
+
+HBase Client API consists of all the classes or methods that are marked with InterfaceAudience.Public interface. All main classes in hbase-client and dependent modules have either InterfaceAudience.Public, InterfaceAudience.LimitedPrivate, or InterfaceAudience.Private marker. Not all classes in other modules (hbase-server, etc) have the marker. If a class is not annotated with one of these, it is assumed to be a InterfaceAudience.Private class.
+
+### HBase LimitedPrivate API
+
+LimitedPrivate annotation comes with a set of target consumers for the interfaces. Those consumers are coprocessors, phoenix, replication endpoint implementations or similar. At this point, HBase only guarantees source and binary compatibility for these interfaces between patch versions.
+
+### HBase Private API
+
+All classes annotated with InterfaceAudience.Private or all classes that do not have the annotation are for HBase internal use only. The interfaces and method signatures can change at any point in time. If you are relying on a particular interface that is marked Private, you should open a jira to propose changing the interface to be Public or LimitedPrivate, or an interface exposed for this purpose.
+
+### Binary Compatibility
+
+When we say two HBase versions are compatible, we mean that the versions are wire and binary compatible. Compatible HBase versions means that clients can talk to compatible but differently versioned servers. It means too that you can just swap out the jars of one version and replace them with the jars of another, compatible version and all will just work. Unless otherwise specified, HBase point versions are (mostly) binary compatible. You can safely do rolling upgrades between binary com [...]
+
+[^1]: See 'Source Compatibility' [https://wiki.openjdk.org/spaces/csr/pages/32342052/Kinds+of+Compatibility](https://wiki.openjdk.org/spaces/csr/pages/32342052/Kinds+of+Compatibility)
+
+[^2]: See [http://docs.oracle.com/javase/specs/jls/se8/html/jls-13.html](http://docs.oracle.com/javase/specs/jls/se8/html/jls-13.html).
+
+[^3]: Running an offline upgrade tool without downgrade might be needed. We will typically only support migrating data from major version X to major version X+1.
+
+## Rolling Upgrades
+
+A rolling upgrade is the process by which you update the servers in your cluster a server at a time. You can rolling upgrade across HBase versions if they are binary or wire compatible. See the "Rolling Upgrade Between Versions that are Binary/Wire Compatible" section below for more on what this means. Coarsely, a rolling upgrade is a graceful stop each server, update the software, and then restart. You do this for each server in the cluster. Usually you upgrade the Master first and then [...]
+
+For example, in the below, HBase was symlinked to the actual HBase install. On upgrade, before running a rolling restart over the cluster, we changed the symlink to point at the new HBase software version and then ran
+
+\`\`\`bash
+$ HADOOP_HOME=~/hadoop-2.6.0-CRC-SNAPSHOT ~/hbase/bin/rolling-restart.sh --config ~/conf_hbase
+\`\`\`
+
+The rolling-restart script will first gracefully stop and restart the master, and then each of the RegionServers in turn. Because the symlink was changed, on restart the server will come up using the new HBase version. Check logs for errors as the rolling upgrade proceeds.
+
+#### Rolling Upgrade Between Versions that are Binary/Wire Compatible \\[!toc]
+
+Unless otherwise specified, HBase minor versions are binary compatible. You can do a rolling upgrades between HBase point versions. For example, you can go to 1.4.4 from 1.4.6 by doing a rolling upgrade across the cluster replacing the 1.4.4 binary with a 1.4.6 binary.
+
+In the minor version-particular sections below, we call out where the versions are wire/protocol compatible and in this case, it is also possible to do a rolling upgrade.
+
+## Rollback
+
+Sometimes things don't go as planned when attempting an upgrade. This section explains how to perform a *rollback* to an earlier HBase release. Note that this should only be needed between Major and some Minor releases. You should always be able to *downgrade* between HBase Patch releases within the same Minor version. These instructions may require you to take steps before you start the upgrade process, so be sure to read through this section beforehand.
+
+## Caveats
+
+### Rollback vs Downgrade
+
+This section describes how to perform a *rollback* on an upgrade between HBase minor and major versions. In this document, rollback refers to the process of taking an upgraded cluster and restoring it to the old version *while losing all changes that have occurred since upgrade*. By contrast, a cluster *downgrade* would restore an upgraded cluster to the old version while maintaining any data written since the upgrade. We currently only offer instructions to rollback HBase clusters. Furt [...]
+
+When these instructions talk about rollback vs downgrade of prerequisite cluster services (i.e. HDFS), you should treat leaving the service version the same as a degenerate case of downgrade.
+
+### Replication
+
+Unless you are doing an all-service rollback, the HBase cluster will lose any configured peers for HBase replication. If your cluster is configured for HBase replication, then prior to following these instructions you should document all replication peers. After performing the rollback you should then add each documented peer back to the cluster. Note also that data written to the cluster since the upgrade may or may not have already been replicated to any peers. Determining which, if an [...]
+
+### Data Locality
+
+Unless you are doing an all-service rollback, going through a rollback procedure will likely destroy all locality for Region Servers. You should expect degraded performance until after the cluster has had time to go through compactions to restore data locality. Optionally, you can force a compaction to speed this process up at the cost of generating cluster load.
+
+### Configurable Locations
+
+The instructions below assume default locations for the HBase data directory and the HBase znode. Both of these locations are configurable and you should verify the value used in your cluster before proceeding. In the event that you have a different value, just replace the default with the one found in your configuration \\* HBase data directory is configured via the key 'hbase.rootdir' and has a default value of '/hbase'. \\* HBase znode is configured via the key 'zookeeper.znode.parent [...]
+
+## All service rollback
+
+If you will be performing a rollback of both the HDFS and ZooKeeper services, then HBase's data will be rolled back in the process.
+
+### Requirements
+
+* Ability to rollback HDFS and ZooKeeper
+
+### Before upgrade
+
+No additional steps are needed pre-upgrade. As an extra precautionary measure, you may wish to use distcp to back up the HBase data off of the cluster to be upgraded. To do so, follow the steps in the 'Before upgrade' section of 'Rollback after HDFS downgrade' but copy to another HDFS instance instead of within the same instance.
+
+### Performing a rollback
+
+<Steps>
+ <Step>
+ Stop HBase
+ </Step>
+
+ <Step>
+ Perform a rollback for HDFS and ZooKeeper (HBase should remain stopped)
+ </Step>
+
+ <Step>
+ Change the installed version of HBase to the previous version
+ </Step>
+
+ <Step>
+ Start HBase
+ </Step>
+
+ <Step>
+ Verify HBase contents — use the HBase shell to list tables and scan some known values.
+ </Step>
+</Steps>
+
+## Rollback after HDFS rollback and ZooKeeper downgrade
+
+If you will be rolling back HDFS but going through a ZooKeeper downgrade, then HBase will be in an inconsistent state. You must ensure the cluster is not started until you complete this process.
+
+### Requirements
+
+* Ability to rollback HDFS
+* Ability to downgrade ZooKeeper
+
+### Before upgrade
+
+No additional steps are needed pre-upgrade. As an extra precautionary measure, you may wish to use distcp to back up the HBase data off of the cluster to be upgraded. To do so, follow the steps in the 'Before upgrade' section of 'Rollback after HDFS downgrade' but copy to another HDFS instance instead of within the same instance.
+
+### Performing a rollback
+
+<Steps>
+ <Step>
+ Stop HBase
+ </Step>
+
+ <Step>
+ Perform a rollback for HDFS and a downgrade for ZooKeeper (HBase should remain stopped)
+ </Step>
+
+ <Step>
+ Change the installed version of HBase to the previous version
+ </Step>
+
+ <Step>
+ Clean out ZooKeeper information related to HBase. WARNING: This step will permanently destroy all replication peers. Please see the section on HBase Replication under Caveats for more information.
+
+ **Clean HBase information out of ZooKeeper:**
+
+ \`\`\`bash
+ [hpnewton@gateway_node.example.com ~]$ zookeeper-client -server zookeeper1.example.com:2181,zookeeper2.example.com:2181,zookeeper3.example.com:2181
+ Welcome to ZooKeeper!
+ JLine support is disabled
+ rmr /hbase
+ quit
+ Quitting...
+ \`\`\`
+ </Step>
+
+ <Step>
+ Start HBase
+ </Step>
+
+ <Step>
+ Verify HBase contents—use the HBase shell to list tables and scan some known values.
+ </Step>
+</Steps>
+
+## Rollback after HDFS downgrade
+
+If you will be performing an HDFS downgrade, then you'll need to follow these instructions regardless of whether ZooKeeper goes through rollback, downgrade, or reinstallation.
+
+### Requirements
+
+* Ability to downgrade HDFS
+* Pre-upgrade cluster must be able to run MapReduce jobs
+* HDFS super user access
+* Sufficient space in HDFS for at least two copies of the HBase data directory
+
+### Before upgrade
+
+Before beginning the upgrade process, you must take a complete backup of HBase's backing data. The following instructions cover backing up the data within the current HDFS instance. Alternatively, you can use the distcp command to copy the data to another HDFS cluster.
+
+<Steps>
+ <Step>
+ Stop the HBase cluster
+ </Step>
+
+ <Step>
+ Copy the HBase data directory to a backup location using the [distcp command](https://hadoop.apache.org/docs/current/hadoop-distcp/DistCp.html) as the HDFS super user (shown below on a security enabled cluster)
+
+ **Using distcp to backup the HBase data directory:**
+
+ \`\`\`bash
+ [hpnewton@gateway_node.example.com ~]$ kinit -k -t hdfs.keytab hdfs@EXAMPLE.COM
+ [hpnewton@gateway_node.example.com ~]$ hadoop distcp /hbase /hbase-pre-upgrade-backup
+ \`\`\`
+ </Step>
+
+ <Step>
+ Distcp will launch a mapreduce job to handle copying the files in a distributed fashion. Check the output of the distcp command to ensure this job completed successfully.
+ </Step>
+</Steps>
+
+### Performing a rollback
+
+<Steps>
+ <Step>
+ Stop HBase
+ </Step>
+
+ <Step>
+ Perform a downgrade for HDFS and a downgrade/rollback for ZooKeeper (HBase should remain stopped)
+ </Step>
+
+ <Step>
+ Change the installed version of HBase to the previous version
+ </Step>
+
+ <Step>
+ Restore the HBase data directory from prior to the upgrade. Restore the HBase data directory from prior to the upgrade as the HDFS super user (shown below on a security enabled cluster). If you backed up your data on another HDFS cluster instead of locally, you will need to use the distcp command to copy it back to the current HDFS cluster.
+
+ **Restore the HBase data directory:**
+
+ \`\`\`bash
+ [hpnewton@gateway_node.example.com ~]$ kinit -k -t hdfs.keytab hdfs@EXAMPLE.COM
+ [hpnewton@gateway_node.example.com ~]$ hdfs dfs -mv /hbase /hbase-upgrade-rollback
+ [hpnewton@gateway_node.example.com ~]$ hdfs dfs -mv /hbase-pre-upgrade-backup /hbase
+ \`\`\`
+ </Step>
+
+ <Step>
+ Clean out ZooKeeper information related to HBase. WARNING: This step will permanently destroy all replication peers. Please see the section on HBase Replication under Caveats for more information.
+
+ **Clean HBase information out of ZooKeeper:**
+
+ \`\`\`bash
+ [hpnewton@gateway_node.example.com ~]$ zookeeper-client -server zookeeper1.example.com:2181,zookeeper2.example.com:2181,zookeeper3.example.com:2181
+ Welcome to ZooKeeper!
+ JLine support is disabled
+ rmr /hbase
+ quit
+ Quitting...
+ \`\`\`
+ </Step>
+
+ <Step>
+ Start HBase
+ </Step>
+
+ <Step>
+ Verify HBase contents–use the HBase shell to list tables and scan some known values.
+ </Step>
+</Steps>
+
+## Upgrade Paths
+
+## Upgrade from 2.x to 3.x
+
+The RegionServer Grouping feature has been reimplemented. See section [Migrating From Old Implementation](/docs/operational-management/region-and-capacity#migrating-from-old-implementation) in [Apache HBase Operational Management](/docs/operational-management) for more details.
+
+The \`hbase:namespace\` table has been removed and fold into \`hbase:meta\`. See [Data Model](/docs/datamodel) for more details.
+
+There is no special consideration upgrading to hbase-2.4.x from 2.3.x. And for earlier versions, just follow the [Upgrade from 2.0.x-2.2.x to 2.3+](/docs/upgrading/paths#upgrade-from-20x-22x-to-23) guide. In general, 2.2.x should be rolling upgradeable, for 2.1.x or 2.0.x, you will need to clear the [Upgrade from 2.0 or 2.1 to 2.2+](/docs/upgrading/paths#upgrade-from-20-or-21-to-22) hurdle first.
+
+## Upgrade from 2.0.x-2.2.x to 2.3+
+
+There is no special consideration upgrading to hbase-2.3.x from earlier versions. From 2.2.x, it should be rolling upgradeable. From 2.1.x or 2.0.x, you will need to clear the [Upgrade from 2.0 or 2.1 to 2.2+](/docs/upgrading/paths#upgrade-from-20-or-21-to-22) hurdle first.
+
+### Upgraded ZooKeeper Dependency Version
+
+Our dependency on Apache ZooKeeper has been upgraded to 3.5.7 ([HBASE-24132](https://issues.apache.org/jira/browse/HBASE-24132)), as 3.4.x is EOL. The newer 3.5.x client is compatible with the older 3.4.x server. However, if you're using HBase in stand-alone mode and perform an in-place upgrade, there are some upgrade steps [documented by the ZooKeeper community](https://cwiki.apache.org/confluence/display/ZOOKEEPER/Upgrade+FAQ). This doesn't impact a production deployment, but would imp [...]
+
+### New In-Master Procedure Store
+
+Of note, HBase 2.3.0 changes the in-Master Procedure Store implementation. It was a dedicated custom store to instead use a standard HBase Region ([HBASE-23326](https://issues.apache.org/jira/browse/HBASE-23326)). The migration from the old to new format is automatic run by the new 2.3.0 Master on startup. The old *MasterProcWALs* dir which hosted the old custom implementation files in *$\\{hbase.rootdir}* is deleted on successful migration. A new *MasterProc* sub-directory replaces it t [...]
+
+Notice that, after the migration, you should make sure to not start an active master with old code, as it can not recognize the new procedure store. So it is suggested to upgrade backup master(s) to new 2.3 first, and then upgrade the active master. And unless explicitly mentioned, this is the suggested way for all upgrading, i.e, upgrading backup master(s) first, then active master, and then region servers.
+
+## Upgrade from 2.0 or 2.1 to 2.2+
+
+HBase 2.2+ uses a new Procedure form assigning/unassigning/moving Regions. It does not process HBase 2.1 and 2.0's Unassign/Assign Procedure types. Upgrade requires that we first drain the Master Procedure Store of old style Procedures before starting the new 2.2 Master. So you need to make sure that before you kill the old version (2.0 or 2.1) Master, there is no region in transition. And once the new version (2.2+) Master is up, you can rolling upgrade RegionServers one by one.
+
+And there is a more safer way if you are running 2.1.1+ or 2.0.3+ cluster. It need four steps to upgrade Master.
+
+1. Shutdown both active and standby Masters (Your cluster will continue to server reads and writes without interruption).
+2. Set the property hbase.procedure.upgrade-to-2-2 to true in hbase-site.xml for the Master, and start only one Master, still using the 2.1.1+ (or 2.0.3+) version.
+3. Wait until the Master quits. Confirm that there is a 'UPGRADE OK: All existed procedures have been finished, quit...' message in the Master log as the cause of the shutdown. The Procedure Store is now empty.
+4. Start new Masters with the new 2.2+ version.
+
+Then you can rolling upgrade RegionServers one by one. See [HBASE-21075](https://issues.apache.org/jira/browse/HBASE-21075) for more details.
+
+In case these steps are not done, on starting 2.2+ master, you would see the following exception in the master logs:
+
+\`org.apache.hadoop.hbase.HBaseIOException: Unsupported procedure type class org.apache.hadoop.hbase.master.assignment.UnassignProcedure found\`
+
+## Upgrading from 1.x to 2.x
+
+In this section we will first call out significant changes compared to the prior stable HBase release and then go over the upgrade process. Be sure to read the former with care so you avoid surprises.
+
+### Changes of Note!
+
+First we'll cover deployment / operational changes that you might hit when upgrading to HBase 2.0+. After that we'll call out changes for downstream applications. Please note that Coprocessors are covered in the operational section. Also note that this section is not meant to convey information about new features that may be of interest to you. For a complete summary of changes, please see the CHANGES.txt file in the source release artifact for the version you are planning to upgrade to.
+
+#### Update to basic prerequisite minimums in HBase 2.0+ \\[!toc]
+
+As noted in the [Basic Prerequisites](/docs/configuration/basic-prerequisites) section, HBase 2.0+ requires a minimum of Java 8 and Hadoop 2.6. The HBase community recommends ensuring you have already completed any needed upgrades in prerequisites prior to upgrading your HBase version.
+
+#### HBCK must match HBase server version \\[!toc]
+
+You **must not** use an HBase 1.x version of HBCK against an HBase 2.0+ cluster. HBCK is strongly tied to the HBase server version. Using the HBCK tool from an earlier release against an HBase 2.0+ cluster will destructively alter said cluster in unrecoverable ways.
+
+As of HBase 2.0, HBCK (A.K.A *HBCK1* or *hbck1*) is a read-only tool that can report the status of some non-public system internals but will often misread state because it does not understand the workings of hbase2.
+
+To read about HBCK's replacement, see [Operations and Management](/docs/operational-management) documentation.
+
+<Callout type="warn">
+ Related, before you upgrade, ensure that *hbck1* reports no \`INCONSISTENCIES\`. Fixing hbase1-type
+ inconsistencies post-upgrade is an involved process.
+</Callout>
+
+#### Configuration settings no longer in HBase 2.0+ \\[!toc]
+
+The following configuration settings are no longer applicable or available. For details, please see the detailed release notes.
+
+* hbase.config.read.zookeeper.config (see [upgrade2.0.zkconfig](/docs/upgrading/paths#zookeeper-configs-no-longer-read-from-zoocfg-toc) for migration details)
+* hbase.zookeeper.useMulti (HBase now always uses ZK's multi functionality)
+* hbase.rpc.client.threads.max
+* hbase.rpc.client.nativetransport
+* hbase.fs.tmp.dir
+* hbase.bucketcache.combinedcache.enabled
+* hbase.bucketcache.ioengine no longer supports the 'heap' value.
+* hbase.bulkload.staging.dir
+* hbase.balancer.tablesOnMaster wasn't removed, strictly speaking, but its meaning has fundamentally changed and users should not set it. See the section [upgrade2.0.regions.on.master](/docs/upgrading/paths#master-hosting-regions-feature-broken-and-unsupported-toc) for details.
+* hbase.master.distributed.log.replay See the section [upgrade2.0.distributed.log.replay](/docs/upgrading/paths#distributed-log-replay-feature-broken-and-removed-toc) for details
+* hbase.regionserver.disallow\\.writes.when.recovering See the section [upgrade2.0.distributed.log.replay](/docs/upgrading/paths#distributed-log-replay-feature-broken-and-removed-toc) for details
+* hbase.regionserver.wal.logreplay.batch.size See the section [upgrade2.0.distributed.log.replay](/docs/upgrading/paths#distributed-log-replay-feature-broken-and-removed-toc) for details
+* hbase.master.catalog.timeout
+* hbase.regionserver.catalog.timeout
+* hbase.metrics.exposeOperationTimes
+* hbase.metrics.showTableName
+* hbase.online.schema.update.enable (HBase now always supports this)
+* hbase.thrift.htablepool.size.max
+
+#### Configuration properties that were renamed in HBase 2.0+ \\[!toc]
+
+The following properties have been renamed. Attempts to set the old property will be ignored at run time.
+
+| Old name | New name |
+| --------------------------------------------------- | ------------------------------------------------------- |
+| hbase.rpc.server.nativetransport | hbase.netty.nativetransport |
+| hbase.netty.rpc.server.worker.count | hbase.netty.worker.count |
+| hbase.hfile.compactions.discharger.interval | hbase.hfile.compaction.discharger.interval |
+| hbase.hregion.percolumnfamilyflush.size.lower.bound | hbase.hregion.percolumnfamilyflush.size.lower.bound.min |
+
+#### Configuration settings with different defaults in HBase 2.0+ \\[!toc]
+
+The following configuration settings changed their default value. Where applicable, the value to set to restore the behavior of HBase 1.2 is given.
+
+* hbase.security.authorization now defaults to false. set to true to restore same behavior as previous default.
+* hbase.client.retries.number is now set to 10. Previously it was 35. Downstream users are advised to use client timeouts as described in [Configuration](/docs/configuration/default#timeout-settings) instead.
+* hbase.client.serverside.retries.multiplier is now set to 3. Previously it was 10. Downstream users are advised to use client timeouts as described in [Configuration](/docs/configuration/default#timeout-settings) instead.
+* hbase.master.fileSplitTimeout is now set to 10 minutes. Previously it was 30 seconds.
+* hbase.regionserver.logroll.multiplier is now set to 0.5. Previously it was 0.95. This change is tied with the following doubling of block size. Combined, these two configuration changes should make for WALs of about the same size as those in hbase-1.x but there should be less incidence of small blocks because we fail to roll the WAL before we hit the blocksize threshold. See [HBASE-19148](https://issues.apache.org/jira/browse/HBASE-19148) for discussion.
+* hbase.regionserver.hlog.blocksize defaults to 2x the HDFS default block size for the WAL dir. Previously it was equal to the HDFS default block size for the WAL dir.
+* hbase.client.start.log.errors.counter changed to 5. Previously it was 9.
+* hbase.ipc.server.callqueue.type changed to 'fifo'. In HBase versions 1.0 - 1.2 it was 'deadline'. In prior and later 1.x versions it already defaults to 'fifo'.
+* hbase.hregion.memstore.chunkpool.maxsize is 1.0 by default. Previously it was 0.0. Effectively, this means previously we would not use a chunk pool when our memstore is onheap and now we will. See the section [Long GC pauses](/docs/performance#long-gc-pauses) for more information about the MSLAB chunk pool.
+* hbase.master.cleaner.interval is now set to 10 minutes. Previously it was 1 minute.
+* hbase.master.procedure.threads will now default to 1/4 of the number of available CPUs, but not less than 16 threads. Previously it would be number of threads equal to number of CPUs.
+* hbase.hstore.blockingStoreFiles is now 16. Previously it was 10.
+* hbase.http.max.threads is now 16. Previously it was 10.
+* hbase.client.max.perserver.tasks is now 2. Previously it was 5.
+* hbase.normalizer.period is now 5 minutes. Previously it was 30 minutes.
+* hbase.regionserver.region.split.policy is now SteppingSplitPolicy. Previously it was IncreasingToUpperBoundRegionSplitPolicy.
+* replication.source.ratio is now 0.5. Previously it was 0.1.
+
+#### "Master hosting regions" feature broken and unsupported \\[!toc]
+
+The feature "Master acts as region server" and associated follow-on work available in HBase 1.y is non-functional in HBase 2.y and should not be used in a production setting due to deadlock on Master initialization. Downstream users are advised to treat related configuration settings as experimental and the feature as inappropriate for production settings.
+
+A brief summary of related changes:
+
+* Master no longer carries regions by default
+* hbase.balancer.tablesOnMaster is a boolean, default false (if it holds an HBase 1.x list of tables, will default to false)
+* hbase.balancer.tablesOnMaster.systemTablesOnly is boolean to keep user tables off master. default false
+* those wishing to replicate old list-of-servers config should deploy a stand-alone RegionServer process and then rely on Region Server Groups
+
+#### "Distributed Log Replay" feature broken and removed \\[!toc]
+
+The Distributed Log Replay feature was broken and has been removed from HBase 2.y+. As a consequence all related configs, metrics, RPC fields, and logging have also been removed. Note that this feature was found to be unreliable in the run up to HBase 1.0, defaulted to being unused, and was effectively removed in HBase 1.2.0 when we started ignoring the config that turns it on ([HBASE-14465](https://issues.apache.org/jira/browse/HBASE-14465)). If you are currently using the feature, be s [...]
+
+#### *prefix-tree* encoding removed \\[!toc]
+
+The prefix-tree encoding was removed from HBase 2.0.0 ([HBASE-19179](https://issues.apache.org/jira/browse/HBASE-19179)). It was (late!) deprecated in hbase-1.2.7, hbase-1.4.0, and hbase-1.3.2.
+
+This feature was removed because it as not being actively maintained. If interested in reviving this sweet facility which improved random read latencies at the expensive of slowed writes, write the HBase developers list at *dev at hbase dot apache dot org*.
+
+The prefix-tree encoding needs to be removed from all tables before upgrading to HBase 2.0+. To do that first you need to change the encoding from PREFIX\\_TREE to something else that is supported in HBase 2.0. After that you have to major compact the tables that were using PREFIX\\_TREE encoding before. To check which column families are using incompatible data block encoding you can use [Pre-Upgrade Validator](/docs/operational-management/tools#pre-upgrade-validator).
+
+#### Changed metrics \\[!toc]
+
+The following metrics have changed names:
+
+* Metrics previously published under the name "AssignmentManger" \\[sic] are now published under the name "AssignmentManager"
+
+The following metrics have changed their meaning:
+
+* The metric 'blockCacheEvictionCount' published on a per-region server basis no longer includes blocks removed from the cache due to the invalidation of the hfiles they are from (e.g. via compaction).
+* The metric 'totalRequestCount' increments once per request; previously it incremented by the number of \`Actions\` carried in the request; e.g. if a request was a \`multi\` made of four Gets and two Puts, we'd increment 'totalRequestCount' by six; now we increment by one regardless. Expect to see lower values for this metric in hbase-2.0.0.
+* The 'readRequestCount' now counts reads that return a non-empty row where in older hbases, we'd increment 'readRequestCount' whether a Result or not. This change will flatten the profile of the read-requests graphs if requests for non-existent rows. A YCSB read-heavy workload can do this dependent on how the database was loaded.
+
+The following metrics have been removed:
+
+* Metrics related to the Distributed Log Replay feature are no longer present. They were previously found in the region server context under the name 'replay'. See the section ["Distributed Log Replay" feature broken and removed](/docs/upgrading/paths#distributed-log-replay-feature-broken-and-removed-toc) for details.
+
+The following metrics have been added:
+
+* 'totalRowActionRequestCount' is a count of region row actions summing reads and writes.
+
+#### Changed logging \\[!toc]
+
+HBase-2.0.0 now uses [slf4j](https://www.slf4j.org/) as its logging frontend. Previously, we used [log4j (1.2)](http://logging.apache.org/log4j/1.2/). For most the transition should be seamless; slf4j does a good job interpreting *log4j.properties* logging configuration files such that you should not notice any difference in your log system emissions.
+
+That said, your *log4j.properties* may need freshening. See [HBASE-20351](https://issues.apache.org/jira/browse/HBASE-20351) for example, where a stale log configuration file manifest as netty configuration being dumped at DEBUG level as preamble on every shell command invocation.
+
+#### ZooKeeper configs no longer read from zoo.cfg \\[!toc]
+
+HBase no longer optionally reads the 'zoo.cfg' file for ZooKeeper related configuration settings. If you previously relied on the 'hbase.config.read.zookeeper.config' config for this functionality, you should migrate any needed settings to the hbase-site.xml file while adding the prefix 'hbase.zookeeper.property.' to each property name.
+
+#### Changes in permissions \\[!toc]
+
+The following permission related changes either altered semantics or defaults:
+
+* Permissions granted to a user now merge with existing permissions for that user, rather than over-writing them. (see [the release note on HBASE-17472](https://issues.apache.org/jira/browse/HBASE-17472) for details)
+* Region Server Group commands (added in 1.4.0) now require admin privileges.
+
+#### Most Admin APIs don't work against an HBase 2.0+ cluster from pre-HBase 2.0 clients \\[!toc]
+
+A number of admin commands are known to not work when used from a pre-HBase 2.0 client. This includes an HBase Shell that has the library jars from pre-HBase 2.0. You will need to plan for an outage of use of admin APIs and commands until you can also update to the needed client version.
+
+The following client operations do not work against HBase 2.0+ cluster when executed from a pre-HBase 2.0 client:
+
+* list\\_procedures
+* split
+* merge\\_region
+* list\\_quotas
+* enable\\_table\\_replication
+* disable\\_table\\_replication
+* Snapshot related commands
+
+#### Deprecated in 1.0 admin commands have been removed. \\[!toc]
+
+The following commands that were deprecated in 1.0 have been removed. Where applicable the replacement command is listed.
+
+* The 'hlog' command has been removed. Downstream users should rely on the 'wal' command instead.
+
+#### Region Server memory consumption changes. \\[!toc]
+
+Users upgrading from versions prior to HBase 1.4 should read the instructions in section [Region Server memory consumption changes.](/docs/upgrading/paths#region-server-memory-consumption-changes).
+
+Additionally, HBase 2.0 has changed how memstore memory is tracked for flushing decisions. Previously, both the data size and overhead for storage were used to calculate utilization against the flush threshold. Now, only data size is used to make these per-region decisions. Globally the addition of the storage overhead is used to make decisions about forced flushes.
+
+#### Web UI for splitting and merging operate on row prefixes \\[!toc]
+
+Previously, the Web UI included functionality on table status pages to merge or split based on an encoded region name. In HBase 2.0, instead this functionality works by taking a row prefix.
+
+#### Special upgrading for Replication users from pre-HBase 1.4 \\[!toc]
+
+User running versions of HBase prior to the 1.4.0 release that make use of replication should be sure to read the instructions in the section [Replication peer's TableCFs config](/docs/upgrading/paths#replication-peers-tablecfs-config).
+
+#### HBase shell changes \\[!toc]
+
+The HBase shell command relies on a bundled JRuby instance. This bundled JRuby been updated from version 1.6.8 to version 9.1.10.0. The represents a change from Ruby 1.8 to Ruby 2.3.3, which introduces non-compatible language changes for user scripts.
+
+The HBase shell command now ignores the '--return-values' flag that was present in early HBase 1.4 releases. Instead the shell always behaves as though that flag were passed. If you wish to avoid having expression results printed in the console you should alter your IRB configuration.
+
+#### Coprocessor APIs have changed in HBase 2.0+ \\[!toc]
+
+All Coprocessor APIs have been refactored to improve supportability around binary API compatibility for future versions of HBase. If you or applications you rely on have custom HBase coprocessors, you should read [the release notes for HBASE-18169](https://issues.apache.org/jira/browse/HBASE-18169) for details of changes you will need to make prior to upgrading to HBase 2.0+.
+
+For example, if you had a BaseRegionObserver in HBase 1.2 then at a minimum you will need to update it to implement both RegionObserver and RegionCoprocessor and add the method
+
+\`\`\`java
+...
+ @Override
+ public Optional<RegionObserver> getRegionObserver() {
+ return Optional.of(this);
+ }
+...
+\`\`\`
+
+For more information, see [Upgrading Coprocessors to 2.0](/docs/upgrading/paths#upgrading-coprocessors-to-20).
+
+#### HBase 2.0+ can no longer write HFile v2 files. \\[!toc]
+
+HBase has simplified our internal HFile handling. As a result, we can no longer write HFile versions earlier than the default of version 3. Upgrading users should ensure that hfile.format.version is not set to 2 in hbase-site.xml before upgrading. Failing to do so will cause Region Server failure. HBase can still read HFiles written in the older version 2 format.
+
+#### HBase 2.0+ can no longer read Sequence File based WAL file. \\[!toc]
+
+HBase can no longer read the deprecated WAL files written in the Apache Hadoop Sequence File format. The hbase.regionserver.hlog.reader.impl and hbase.regionserver.hlog.writer.impl configuration entries should be set to use the Protobuf based WAL reader / writer classes. This implementation has been the default since HBase 0.96, so legacy WAL files should not be a concern for most downstream users.
+
+Starting from 2.6.0, the hbase.regionserver.hlog.reader.impl and hbase.regionserver.hlog.writer.impl configuration entries are removed since the only valid values are protobuf based reader/writer. Setting them in *hbase-site.xml* will have no real effect.
+
+A clean cluster shutdown should ensure there are no WAL files. If you are unsure of a given WAL file's format you can use the \`hbase wal\` command to parse files while the HBase cluster is offline. In HBase 2.0+, this command will not be able to read a Sequence File based WAL.
+
+#### Change in behavior for filters \\[!toc]
+
+The Filter ReturnCode NEXT\\_ROW has been redefined as skipping to next row in current family, not to next row in all family. it's more reasonable, because ReturnCode is a concept in store level, not in region level.
+
+#### Downstream HBase 2.0+ users should use the shaded client \\[!toc]
+
+Downstream users are strongly urged to rely on the Maven coordinates org.apache.hbase:hbase-shaded-client for their runtime use. This artifact contains all the needed implementation details for talking to an HBase cluster while minimizing the number of third party dependencies exposed.
+
+Note that this artifact exposes some classes in the org.apache.hadoop package space (e.g. o.a.h.configuration.Configuration) so that we can maintain source compatibility with our public API. Those classes are included so that they can be altered to use the same relocated third party dependencies as the rest of the HBase client code. In the event that you need to **also** use Hadoop in your code, you should ensure all Hadoop related jars precede the HBase client jar in your classpath.
+
+#### Downstream HBase 2.0+ users of MapReduce must switch to new artifact \\[!toc]
+
+Downstream users of HBase's integration for Apache Hadoop MapReduce must switch to relying on the org.apache.hbase:hbase-shaded-mapreduce module for their runtime use. Historically, downstream users relied on either the org.apache.hbase:hbase-server or org.apache.hbase:hbase-shaded-server artifacts for these classes. Both uses are no longer supported and in the vast majority of cases will fail at runtime.
+
+Note that this artifact exposes some classes in the org.apache.hadoop package space (e.g. o.a.h.configuration.Configuration) so that we can maintain source compatibility with our public API. Those classes are included so that they can be altered to use the same relocated third party dependencies as the rest of the HBase client code. In the event that you need to **also** use Hadoop in your code, you should ensure all Hadoop related jars precede the HBase client jar in your classpath.
+
+#### Significant changes to runtime classpath \\[!toc]
+
+A number of internal dependencies for HBase were updated or removed from the runtime classpath. Downstream client users who do not follow the guidance in [Downstream HBase 2.0+ users should use the shaded client](/docs/upgrading/paths#downstream-hbase-20-users-should-use-the-shaded-client-toc) will have to examine the set of dependencies Maven pulls in for impact. Downstream users of LimitedPrivate Coprocessor APIs will need to examine the runtime environment for impact.
+
+#### Multiple breaking changes to source and binary compatibility for client API \\[!toc]
+
+The Java client API for HBase has a number of changes that break both source and binary compatibility for details see the Compatibility Check Report for the release you'll be upgrading to.
+
+#### Tracing implementation changes \\[!toc]
+
+The backing implementation of HBase's tracing features was updated from Apache HTrace 3 to HTrace 4, which includes several breaking changes. While HTrace 3 and 4 can coexist in the same runtime, they will not integrate with each other, leading to disjoint trace information.
+
+The internal changes to HBase during this upgrade were sufficient for compilation, but it has not been confirmed that there are no regressions in tracing functionality. Please consider this feature experimental for the immediate future.
+
+If you previously relied on client side tracing integrated with HBase operations, it is recommended that you upgrade your usage to HTrace 4 as well.
+
+After the Apache HTrace project moved to the Attic/retired, the traces in HBase are left broken and unmaintained since HBase 2.0. A new project [HBASE-22120](https://issues.apache.org/jira/browse/HBASE-22120) will replace HTrace with OpenTelemetry. It will be shipped in 3.0.0 release. Please see the [Tracing](/docs/tracing) documentation for more details.
+
+#### HFile lose forward compatibility \\[!toc]
+
+HFiles generated by 2.0.0, 2.0.1, 2.1.0 are not forward compatible to 1.4.6-, 1.3.2.1-, 1.2.6.1-, and other inactive releases. Why HFile lose compatibility is hbase in new versions (2.0.0, 2.0.1, 2.1.0) use protobuf to serialize/deserialize TimeRangeTracker (TRT) while old versions use DataInput/DataOutput. To solve this, We have to put [HBASE-21012](https://issues.apache.org/jira/browse/HBASE-21012) to 2.x and put [HBASE-21013](https://issues.apache.org/jira/browse/HBASE-21013) in 1.x. [...]
+
+#### Performance \\[!toc]
+
+You will likely see a change in the performance profile on upgrade to hbase-2.0.0 given read and write paths have undergone significant change. On release, writes may be slower with reads about the same or much better, dependent on context. Be prepared to spend time re-tuning (See [Performance](/docs/performance)). Performance is also an area that is now under active review so look forward to improvement in coming releases (See [HBASE-20188 TESTING Performance](https://issues.apache.org/ [...]
+
+#### Integration Tests and Kerberos \\[!toc]
+
+Integration Tests (\`IntegrationTests*\`) used to rely on the Kerberos credential cache for authentication against secured clusters. This used to lead to tests failing due to authentication failures when the tickets in the credential cache expired. As of hbase-2.0.0 (and hbase-1.3.0+), the integration test clients will make use of the configuration properties \`hbase.client.keytab.file\` and \`hbase.client.kerberos.principal\`. They are required. The clients will perform a login from the [...]
+
+#### Default Compaction Throughput \\[!toc]
+
+HBase 2.x comes with default limits to the speed at which compactions can execute. This limit is defined per RegionServer. In previous versions of HBase earlier than 1.5, there was no limit to the speed at which a compaction could run by default. Applying a limit to the throughput of a compaction should ensure more stable operations from RegionServers.
+
+Take care to notice that this limit is *per RegionServer*, not *per compaction*.
+
+The throughput limit is defined as a range of bytes written per second, and is allowed to vary within the given lower and upper bound. RegionServers observe the current throughput of a compaction and apply a linear formula to adjust the allowed throughput, within the lower and upper bound, with respect to external pressure. For compactions, external pressure is defined as the number of store files with respect to the maximum number of allowed store files. The more store files, the higher [...]
+
+Configuration of this throughput is governed by the following properties.
+
+* The lower bound is defined by \`hbase.hstore.compaction.throughput.lower.bound\` and defaults to 50 MB/s (\`52428800\`).
+* The upper bound is defined by \`hbase.hstore.compaction.throughput.higher.bound\` and defaults to 100 MB/s (\`104857600\`).
+
+To revert this behavior to the unlimited compaction throughput of earlier versions of HBase, please set the following property to the implementation that applies no limits to compactions.
+
+\`hbase.regionserver.throughput.controller=org.apache.hadoop.hbase.regionserver.throttle.NoLimitThroughputController\`
+
+### Upgrading Coprocessors to 2.0
+
+Coprocessors have changed substantially in 2.0 ranging from top level design changes in class hierarchies to changed/removed methods, interfaces, etc. (Parent jira: [HBASE-18169 Coprocessor fix and cleanup before 2.0.0 release](https://issues.apache.org/jira/browse/HBASE-18169)). Some of the reasons for such widespread changes:
+
+1. Pass Interfaces instead of Implementations; e.g. TableDescriptor instead of HTableDescriptor and Region instead of HRegion ([HBASE-18241](https://issues.apache.org/jira/browse/HBASE-18241) Change client.Table and client.Admin to not use HTableDescriptor).
+2. Design refactor so implementers need to fill out less boilerplate and so we can do more compile-time checking ([HBASE-17732](https://issues.apache.org/jira/browse/HBASE-17732))
+3. Purge Protocol Buffers from Coprocessor API ([HBASE-18859](https://issues.apache.org/jira/browse/HBASE-18859), [HBASE-16769](https://issues.apache.org/jira/browse/HBASE-16769), etc)
+4. Cut back on what we expose to Coprocessors removing hooks on internals that were too private to expose (for eg. [HBASE-18453](https://issues.apache.org/jira/browse/HBASE-18453) CompactionRequest should not be exposed to user directly; [HBASE-18298](https://issues.apache.org/jira/browse/HBASE-18298) RegionServerServices Interface cleanup for CP expose; etc)
+
+To use coprocessors in 2.0, they should be rebuilt against new API otherwise they will fail to load and HBase processes will die.
+
+Suggested order of changes to upgrade the coprocessors:
+
+1. Directly implement observer interfaces instead of extending Base\\*Observer classes. Change \`Foo extends BaseXXXObserver\` to \`Foo implements XXXObserver\`. ([HBASE-17312](https://issues.apache.org/jira/browse/HBASE-17312)).
+2. Adapt to design change from Inheritence to Composition ([HBASE-17732](https://issues.apache.org/jira/browse/HBASE-17732)) by following [this example](https://github.com/apache/hbase/blob/master/dev-support/design-docs/Coprocessor_Design_Improvements-Use_composition_instead_of_inheritance-HBASE-17732.adoc#migrating-existing-cps-to-new-design).
+3. getTable() has been removed from the CoprocessorEnvrionment, coprocessors should self-manage Table instances.
+
+Some examples of writing coprocessors with new API can be found in hbase-example module [here](https://github.com/apache/hbase/tree/branch-2.0/hbase-examples/src/main/java/org/apache/hadoop/hbase/coprocessor/example).
+
+Lastly, if an api has been changed/removed that breaks you in an irreparable way, and if there's a good justification to add it back, bring it our notice [dev@hbase.apache.org](mailto:dev@hbase.apache.org).
+
+### Rolling Upgrade from 1.x to 2.x
+
+Rolling upgrades are currently an experimental feature. They have had limited testing. There are likely corner cases as yet uncovered in our limited experience so you should be careful if you go this route. The stop/upgrade/start described in the next section, [Upgrade process from 1.x to 2.x](/docs/upgrading/paths#upgrade-process-from-1x-to-2x), is the safest route.
+
+That said, the below is a prescription for a rolling upgrade of a 1.4 cluster.
+
+#### Pre-Requirements
+
+* Upgrade to the latest 1.4.x release. Pre 1.4 releases may also work but are not tested, so please upgrade to 1.4.3+ before upgrading to 2.x, unless you are an expert and familiar with the region assignment and crash processing. See the section [Upgrading from pre-1.4 to 1.4+](/docs/upgrading/paths#upgrading-from-pre-14-to-14) on how to upgrade to 1.4.x.
+* Make sure that the zk-less assignment is enabled, i.e, set \`hbase.assignment.usezk\` to \`false\`. This is the most important thing. It allows the 1.x master to assign/unassign regions to/from 2.x region servers. See the release note section of [HBASE-11059](https://issues.apache.org/jira/browse/HBASE-11059) on how to migrate from zk based assignment to zk less assignment.
+* Before you upgrade, ensure that *hbck1* reports no \`INCONSISTENCIES\`. Fixing hbase1-type inconsistencies post-upgrade is an involved process.
+* We have tested rolling upgrading from 1.4.3 to 2.1.0, but it should also work if you want to upgrade to 2.0.x.
+
+#### Instructions
+
+1. Unload a region server and upgrade it to 2.1.0. With [HBASE-17931](https://issues.apache.org/jira/browse/HBASE-17931) in place, the meta region and regions for other system tables will be moved to this region server immediately. If not, please move them manually to the new region server. This is very important because
+ * The schema of meta region is hard coded, if meta is on an old region server, then the new region servers can not access it as it does not have some families, for example, table state.
+ * Client with lower version can communicate with server with higher version, but not vice versa. If the meta region is on an old region server, the new region server will use a client with higher version to communicate with a server with lower version, this may introduce strange problems.
+2. Rolling upgrade all other region servers.
+3. Upgrading masters.
+
+It is OK that during the rolling upgrading there are region server crashes. The 1.x master can assign regions to both 1.x and 2.x region servers, and [HBASE-19166](https://issues.apache.org/jira/browse/HBASE-19166) fixed a problem so that 1.x region server can also read the WALs written by 2.x region server and split them.
+
+<Callout type="info">
+ Please read the [Changes of Note!](/docs/upgrading/paths#changes-of-note) section carefully before
+ rolling upgrading. Make sure that you do not use the removed features in 2.0, for example, the
+ prefix-tree encoding, the old hfile format, etc. They could both fail the upgrading and leave the
+ cluster in an intermediate state and hard to recover.
+</Callout>
+
+<Callout type="info">
+ If you have success running this prescription, please notify the dev list with a note on your
+ experience and/or update the above with any deviations you may have taken so others going this
+ route can benefit from your efforts.
+</Callout>
+
+### Upgrade process from 1.x to 2.x
+
+To upgrade an existing HBase 1.x cluster, you should:
+
+* Ensure that *hbck1* reports no \`INCONSISTENCIES\`. Fixing hbase1-type inconsistencies post-upgrade is an involved process. Fix all *hbck1* complaints before proceeding.
+* Clean shutdown of existing 1.x cluster
+* Update coprocessors
+* Upgrade Master roles first
+* Upgrade RegionServers
+* (Eventually) Upgrade Clients
+
+## Upgrading to 1.7.1+
+
+HBase release 1.7.0 introduced an incompatible table metadata serialization format that broke the minor release compatibility guarantees. The issue was reported in [HBASE-26021](https://issues.apache.org/jira/browse/HBASE-26021) and the problematic serialization patch was reverted in HBase 1.7.1. Some important notes about 1.7.x upgrades below.
+
+* If you are considering an upgrade to 1.7.x version, skip 1.7.0 completely and upgrade to 1.7.1+ version. 1.7.0 was withdrawn and removed from the Apache sites.
+* If you already installed a 1.7.0 cluster from scratch and are looking to migrate to 1.7.1+, you cannot follow the regular rolling upgrade procedures due to broken compatibility contracts. Instead shutdown the cluster and reboot with 1.7.1+ binaries. Newer versions detect any existing tables with incompatible serialization and rewrite them using the correct format at bootstrap.
+* If you are already on 1.7.1+ version, everything is good and no additional steps need to be performed.
+
+## Upgrading from pre-1.4 to 1.4+
+
+### Region Server memory consumption changes.
+
+Users upgrading from versions prior to HBase 1.4 should be aware that the estimates of heap usage by the memstore objects (KeyValue, object and array header sizes, etc) have been made more accurate for heap sizes up to 32G (using CompressedOops), resulting in them dropping by 10-50% in practice. This also results in less number of flushes and compactions due to "fatter" flushes. YMMV. As a result, the actual heap usage of the memstore before being flushed may increase by up to 100%. If c [...]
+
+### Replication peer's TableCFs config
+
+Before 1.4, the table name can't include namespace for replication peer's TableCFs config. It was fixed by add TableCFs to ReplicationPeerConfig which was stored on Zookeeper. So when upgrade to 1.4, you have to update the original ReplicationPeerConfig data on Zookeeper firstly. There are four steps to upgrade when your cluster have a replication peer with TableCFs config.
+
+* Disable the replication peer.
+* If master has permission to write replication peer znode, then rolling update master directly. If not, use TableCFsUpdater tool to update the replication peer's config.
+ \`\`\`bash
+ $ bin/hbase org.apache.hadoop.hbase.replication.master.TableCFsUpdater update
+ \`\`\`
+* Rolling update regionservers.
+* Enable the replication peer.
+
+Notes:
+
+* Can't use the old client(before 1.4) to change the replication peer's config. Because the client will write config to Zookeeper directly, the old client will miss TableCFs config. And the old client write TableCFs config to the old tablecfs znode, it will not work for new version regionserver.
+
+### Raw scan now ignores TTL
+
+Doing a raw scan will now return results that have expired according to TTL settings.
+
+## Upgrading from pre-1.3 to 1.3+
+
+If running Integration Tests under Kerberos, see [upgrade2.0.it.kerberos](/docs/upgrading/paths#integration-tests-and-kerberos-toc).
+
+## Upgrading to 1.x
+
+Please consult the documentation published specifically for the version of HBase that you are upgrading to for details on the upgrade process.
+
+***
+
+# The Apache HBase Shell
+
+The Apache HBase Shell is [(J)Ruby](http://jruby.org)'s IRB with some HBase particular commands added.
+Anything you can do in IRB, you should be able to do in the HBase Shell.
+
+To run the HBase shell, do as follows:
+
+\`\`\`bash
+$ ./bin/hbase shell
+\`\`\`
+
+Type \`help\` and then \`<RETURN>\` to see a listing of shell commands and options.
+Browse at least the paragraphs at the end of the help output for the gist of how variables and command arguments are entered into the HBase shell; in particular note how table names, rows, and columns, etc., must be quoted.
+
+See [shell exercises](/docs/getting-started#procedure-use-hbase-for-the-first-time) for example basic shell operation.
+
+Here is a nicely formatted listing of [all shell commands](http://learnhbase.wordpress.com/2013/03/02/hbase-shell-commands/) by Rajeshbabu Chintaguntla.
+
+## Scripting with Ruby
+
+For examples scripting Apache HBase, look in the HBase *bin* directory.
+Look at the files that end in *\\*.rb*.
+To run one of these files, do as follows:
+
+\`\`\`bash
+$ ./bin/hbase org.jruby.Main PATH_TO_SCRIPT
+\`\`\`
+
+## Running the Shell in Non-Interactive Mode
+
+A new non-interactive mode has been added to the HBase Shell ([HBASE-11658](https://issues.apache.org/jira/browse/HBASE-11658)).
+Non-interactive mode captures the exit status (success or failure) of HBase Shell commands and passes that status back to the command interpreter.
+If you use the normal interactive mode, the HBase Shell will only ever return its own exit status, which will nearly always be \`0\` for success.
+
+To invoke non-interactive mode, pass the \`-n\` or \`--non-interactive\` option to HBase Shell.
+
+## HBase Shell in OS Scripts
+
+You can use the HBase shell from within operating system script interpreters like the Bash shell which is the default command interpreter for most Linux and UNIX distributions.
+The following guidelines use Bash syntax, but could be adjusted to work with C-style shells such as csh or tcsh, and could probably be modified to work with the Microsoft Windows script interpreter as well. Submissions are welcome.
+
+<Callout type="info">
+ Spawning HBase Shell commands in this way is slow, so keep that in mind when you are deciding when
+ combining HBase operations with the operating system command line is appropriate.
+</Callout>
+
+### Passing Commands to the HBase Shell
+
+You can pass commands to the HBase Shell in non-interactive mode (see [hbase.shell.noninteractive](/docs/shell#hbase-shell-in-os-scripts)) using the \`echo\` command and the \`|\` (pipe) operator.
+Be sure to escape characters in the HBase commands which would otherwise be interpreted by the shell.
+Some debug-level output has been truncated from the example below.
+
+\`\`\`bash
+$ echo "describe 'test1'" | ./hbase shell -n
+
+Version 0.98.3-hadoop2, rd5e65a9144e315bb0a964e7730871af32f5018d5, Sat May 31 19:56:09 PDT 2014
+
+describe 'test1'
+
+DESCRIPTION ENABLED
+ 'test1', {NAME => 'cf', DATA_BLOCK_ENCODING => 'NON true
+ E', BLOOMFILTER => 'ROW', REPLICATION_SCOPE => '0',
+ VERSIONS => '1', COMPRESSION => 'NONE', MIN_VERSIO
+ NS => '0', TTL => 'FOREVER', KEEP_DELETED_CELLS =>
+ 'false', BLOCKSIZE => '65536', IN_MEMORY => 'false'
+ , BLOCKCACHE => 'true'}
+1 row(s) in 3.2410 seconds
+\`\`\`
+
+To suppress all output, echo it to */dev/null:*
+
+\`\`\`bash
+$ echo "describe 'test'" | ./hbase shell -n > /dev/null 2>&1
+\`\`\`
+
+### Checking the Result of a Scripted Command
+
+Since scripts are not designed to be run interactively, you need a way to check whether your command failed or succeeded.
+The HBase shell uses the standard convention of returning a value of \`0\` for successful commands, and some non-zero value for failed commands.
+Bash stores a command's return value in a special environment variable called \`$?\`.
+Because that variable is overwritten each time the shell runs any command, you should store the result in a different, script-defined variable.
+
+This is a naive script that shows one way to store the return value and make a decision based upon it.
+
+\`\`\`bash
+#!/bin/bash
+
+echo "describe 'test'" | ./hbase shell -n > /dev/null 2>&1
+status=$?
+echo "The status was " $status
+if ($status == 0); then
+ echo "The command succeeded"
+else
+ echo "The command may have failed."
+fi
+return $status
+\`\`\`
+
+### Checking for Success or Failure In Scripts
+
+Getting an exit code of \`0\` means that the command you scripted definitely succeeded.
+However, getting a non-zero exit code does not necessarily mean the command failed.
+The command could have succeeded, but the client lost connectivity, or some other event obscured its success.
+This is because RPC commands are stateless.
+The only way to be sure of the status of an operation is to check.
+For instance, if your script creates a table, but returns a non-zero exit value, you should check whether the table was actually created before trying again to create it.
+
+## Read HBase Shell Commands from a Command File
+
+You can enter HBase Shell commands into a text file, one command per line, and pass that file to the HBase Shell.
+
+### Example Command File
+
+\`\`\`ruby
+create 'test', 'cf'
+list 'test'
+put 'test', 'row1', 'cf:a', 'value1'
+put 'test', 'row2', 'cf:b', 'value2'
+put 'test', 'row3', 'cf:c', 'value3'
+put 'test', 'row4', 'cf:d', 'value4'
+scan 'test'
+get 'test', 'row1'
+disable 'test'
+enable 'test'
+\`\`\`
+
+### Directing HBase Shell to Execute the Commands
+
+Pass the path to the command file as the only argument to the \`hbase shell\` command.
+Each command is executed and its output is shown.
+If you do not include the \`exit\` command in your script, you are returned to the HBase shell prompt.
+There is no way to programmatically check each individual command for success or failure.
+Also, though you see the output for each command, the commands themselves are not echoed to the screen so it can be difficult to line up the command with its output.
+
+\`\`\`bash
+$ ./hbase shell ./sample_commands.txt
+0 row(s) in 3.4170 seconds
+
+TABLE
+test
+1 row(s) in 0.0590 seconds
+
+0 row(s) in 0.1540 seconds
+
+0 row(s) in 0.0080 seconds
+
+0 row(s) in 0.0060 seconds
+
+0 row(s) in 0.0060 seconds
+
+ROW COLUMN+CELL
+ row1 column=cf:a, timestamp=1407130286968, value=value1
+ row2 column=cf:b, timestamp=1407130286997, value=value2
+ row3 column=cf:c, timestamp=1407130287007, value=value3
+ row4 column=cf:d, timestamp=1407130287015, value=value4
+4 row(s) in 0.0420 seconds
+
+COLUMN CELL
+ cf:a timestamp=1407130286968, value=value1
+1 row(s) in 0.0110 seconds
+
+0 row(s) in 1.5630 seconds
+
+0 row(s) in 0.4360 seconds
+\`\`\`
+
+## Passing VM Options to the Shell
+
+You can pass VM options to the HBase Shell using the \`HBASE_SHELL_OPTS\` environment variable.
+You can set this in your environment, for instance by editing *\\~/.bashrc*, or set it as part of the command to launch HBase Shell.
+The following example sets several garbage-collection-related variables, just for the lifetime of the VM running the HBase Shell.
+The command should be run all on a single line, but is broken by the \`\\\` character, for readability.
+
+\`\`\`bash
+$ HBASE_SHELL_OPTS="-verbose:gc -XX:+PrintGCApplicationStoppedTime -XX:+PrintGCDateStamps \\
+ -XX:+PrintGCDetails -Xloggc:$HBASE_HOME/logs/gc-hbase.log" ./bin/hbase shell
+\`\`\`
+
+## Overriding configuration starting the HBase Shell
+
+As of hbase-2.0.5/hbase-2.1.3/hbase-2.2.0/hbase-1.4.10/hbase-1.5.0, you can
+pass or override hbase configuration as specified in \`hbase-*.xml\` by passing
+your key/values prefixed with \`-D\` on the command-line as follows:
+
+\`\`\`bash
+$ ./bin/hbase shell -Dhbase.zookeeper.quorum=ZK0.remote.cluster.example.org,ZK1.remote.cluster.example.org,ZK2.remote.cluster.example.org -Draining=false
+...
+hbase(main):001:0> @shell.hbase.configuration.get("hbase.zookeeper.quorum")
+=> "ZK0.remote.cluster.example.org,ZK1.remote.cluster.example.org,ZK2.remote.cluster.example.org"
+hbase(main):002:0> @shell.hbase.configuration.get("raining")
+=> "false"
+\`\`\`
+
+## Shell Tricks
+
+### Table variables
+
+HBase 0.95 adds shell commands that provides jruby-style object-oriented references for tables.
+Previously all of the shell commands that act upon a table have a procedural style that always took the name of the table as an argument.
+HBase 0.95 introduces the ability to assign a table to a jruby variable.
+The table reference can be used to perform data read write operations such as puts, scans, and gets well as admin functionality such as disabling, dropping, describing tables.
+
+For example, previously you would always specify a table name:
+
+\`\`\`ruby
+hbase(main):000:0> create 't', 'f'
+0 row(s) in 1.0970 seconds
+hbase(main):001:0> put 't', 'rold', 'f', 'v'
+0 row(s) in 0.0080 seconds
+
+hbase(main):002:0> scan 't'
+ROW COLUMN+CELL
+ rold column=f:, timestamp=1378473207660, value=v
+1 row(s) in 0.0130 seconds
+
+hbase(main):003:0> describe 't'
+DESCRIPTION ENABLED
+ 't', {NAME => 'f', DATA_BLOCK_ENCODING => 'NONE', BLOOMFILTER => 'ROW', REPLICATION_ true
+ SCOPE => '0', VERSIONS => '1', COMPRESSION => 'NONE', MIN_VERSIONS => '0', TTL => '2
+ 147483647', KEEP_DELETED_CELLS => 'false', BLOCKSIZE => '65536', IN_MEMORY => 'false
+ ', BLOCKCACHE => 'true'}
+1 row(s) in 1.4430 seconds
+
+hbase(main):004:0> disable 't'
+0 row(s) in 14.8700 seconds
+
+hbase(main):005:0> drop 't'
+0 row(s) in 23.1670 seconds
+
+hbase(main):006:0>
+\`\`\`
+
+Now you can assign the table to a variable and use the results in jruby shell code.
+
+\`\`\`ruby
+hbase(main):007 > t = create 't', 'f'
+0 row(s) in 1.0970 seconds
+
+=> Hbase::Table - t
+hbase(main):008 > t.put 'r', 'f', 'v'
+0 row(s) in 0.0640 seconds
+hbase(main):009 > t.scan
+ROW COLUMN+CELL
+ r column=f:, timestamp=1331865816290, value=v
+1 row(s) in 0.0110 seconds
+hbase(main):010:0> t.describe
+DESCRIPTION ENABLED
+ 't', {NAME => 'f', DATA_BLOCK_ENCODING => 'NONE', BLOOMFILTER => 'ROW', REPLICATION_ true
+ SCOPE => '0', VERSIONS => '1', COMPRESSION => 'NONE', MIN_VERSIONS => '0', TTL => '2
+ 147483647', KEEP_DELETED_CELLS => 'false', BLOCKSIZE => '65536', IN_MEMORY => 'false
+ ', BLOCKCACHE => 'true'}
+1 row(s) in 0.0210 seconds
+hbase(main):038:0> t.disable
+0 row(s) in 6.2350 seconds
+hbase(main):039:0> t.drop
+0 row(s) in 0.2340 seconds
+\`\`\`
+
+If the table has already been created, you can assign a Table to a variable by using the get\\_table method:
+
+\`\`\`ruby
+hbase(main):011 > create 't','f'
+0 row(s) in 1.2500 seconds
+
+=> Hbase::Table - t
+hbase(main):012:0> tab = get_table 't'
+0 row(s) in 0.0010 seconds
+
+=> Hbase::Table - t
+hbase(main):013:0> tab.put 'r1' ,'f', 'v'
+0 row(s) in 0.0100 seconds
+hbase(main):014:0> tab.scan
+ROW COLUMN+CELL
+ r1 column=f:, timestamp=1378473876949, value=v
+1 row(s) in 0.0240 seconds
+hbase(main):015:0>
+\`\`\`
+
+The list functionality has also been extended so that it returns a list of table names as strings.
+You can then use jruby to script table operations based on these names.
+The list\\_snapshots command also acts similarly.
+
+\`\`\`ruby
+hbase(main):016 > tables = list('t.*')
+TABLE
+t
+1 row(s) in 0.1040 seconds
+
+=> ["t"]
+hbase(main):017:0> tables.map { |t| disable t ; drop t}
+0 row(s) in 2.2510 seconds
+
+=> [nil]
+hbase(main):018:0>
+\`\`\`
+
+### *irbrc*
+
+Create an *.irbrc* file for yourself in your home directory.
+Add customizations.
+A useful one is command history so commands are save across Shell invocations:
+
+\`\`\`bash
+$ more .irbrc
+require 'irb/ext/save-history'
+IRB.conf[:SAVE_HISTORY] = 100
+IRB.conf[:HISTORY_FILE] = "#{ENV['HOME']}/.irb-save-history"
+\`\`\`
+
+If you'd like to avoid printing the result of evaluting each expression to stderr, for example the array of tables returned from the "list" command:
+
+\`\`\`bash
+$ echo "IRB.conf[:ECHO] = false" >>~/.irbrc
+\`\`\`
+
+See the \`ruby\` documentation of *.irbrc* to learn about other possible configurations.
+
+### LOG data to timestamp
+
+To convert the date '08/08/16 20:56:29' from an hbase log into a timestamp, do:
+
+\`\`\`ruby
+hbase(main):021:0> import java.text.SimpleDateFormat
+hbase(main):022:0> import java.text.ParsePosition
+hbase(main):023:0> SimpleDateFormat.new("yy/MM/dd HH:mm:ss").parse("08/08/16 20:56:29", ParsePosition.new(0)).getTime() => 1218920189000
+\`\`\`
+
+To go the other direction:
+
+\`\`\`ruby
+hbase(main):021:0> import java.util.Date
+hbase(main):022:0> Date.new(1218920189000).toString() => "Sat Aug 16 20:56:29 UTC 2008"
+\`\`\`
+
+To output in a format that is exactly like that of the HBase log format will take a little messing with [SimpleDateFormat](http://download.oracle.com/javase/6/docs/api/java/text/SimpleDateFormat.html).
+
+### Query Shell Configuration
+
+\`\`\`ruby
+hbase(main):001:0> @shell.hbase.configuration.get("hbase.rpc.timeout")
+=> "60000"
+\`\`\`
+
+To set a config in the shell:
+
+\`\`\`ruby
+hbase(main):005:0> @shell.hbase.configuration.setInt("hbase.rpc.timeout", 61010)
+hbase(main):006:0> @shell.hbase.configuration.get("hbase.rpc.timeout")
+=> "61010"
+\`\`\`
+
+### Pre-splitting tables with the HBase Shell
+
+You can use a variety of options to pre-split tables when creating them via the HBase Shell \`create\` command.
+
+The simplest approach is to specify an array of split points when creating the table. Note that when specifying string literals as split points, these will create split points based on the underlying byte representation of the string. So when specifying a split point of '10', we are actually specifying the byte split point '\\x31\\30'.
+
+The split points will define \`n+1\` regions where \`n\` is the number of split points. The lowest region will contain all keys from the lowest possible key up to but not including the first split point key.
+The next region will contain keys from the first split point up to, but not including the next split point key.
+This will continue for all split points up to the last. The last region will be defined from the last split point up to the maximum possible key.
+
+\`\`\`ruby
+hbase>create 't1','f',SPLITS => ['10','20','30']
+\`\`\`
+
+In the above example, the table 't1' will be created with column family 'f', pre-split to four regions. Note the first region will contain all keys from '\\x00' up to '\\x30' (as '\\x31' is the ASCII code for '1').
+
+You can pass the split points in a file using following variation. In this example, the splits are read from a file corresponding to the local path on the local filesystem. Each line in the file specifies a split point key.
+
+\`\`\`ruby
+hbase>create 't14','f',SPLITS_FILE=>'splits.txt'
+\`\`\`
+
+The other options are to automatically compute splits based on a desired number of regions and a splitting algorithm.
+HBase supplies algorithms for splitting the key range based on uniform splits or based on hexadecimal keys, but you can provide your own splitting algorithm to subdivide the key range.
+
+\`\`\`ruby
+# create table with four regions based on random bytes keys
+hbase>create 't2','f1', { NUMREGIONS => 4 , SPLITALGO => 'UniformSplit' }
+
+# create table with five regions based on hex keys
+hbase>create 't3','f1', { NUMREGIONS => 5, SPLITALGO => 'HexStringSplit' }
+\`\`\`
+
+As the HBase Shell is effectively a Ruby environment, you can use simple Ruby scripts to compute splits algorithmically.
+
+\`\`\`ruby
+# generate splits for long (Ruby fixnum) key range from start to end key
+hbase(main):070:0> def gen_splits(start_key,end_key,num_regions)
+hbase(main):071:1> results=[]
+hbase(main):072:1> range=end_key-start_key
+hbase(main):073:1> incr=(range/num_regions).floor
+hbase(main):074:1> for i in 1 .. num_regions-1
+hbase(main):075:2> results.push([i*incr+start_key].pack("N"))
+hbase(main):076:2> end
+hbase(main):077:1> return results
+hbase(main):078:1> end
+hbase(main):079:0>
+hbase(main):080:0> splits=gen_splits(1,2000000,10)
+=> ["\\000\\003\\r@", "\\000\\006\\032\\177", "\\000\\t'\\276", "\\000\\f4\\375", "\\000\\017B<", "\\000\\022O{", "\\000\\025\\\\\\272", "\\000\\030i\\371", "\\000\\ew8"]
+hbase(main):081:0> create 'test_splits','f',SPLITS=>splits
+0 row(s) in 0.2670 seconds
+
+=> Hbase::Table - test_splits
+\`\`\`
+
+Note that the HBase Shell command \`truncate\` effectively drops and recreates the table with default options which will discard any pre-splitting.
+If you need to truncate a pre-split table, you must drop and recreate the table explicitly to re-specify custom split options.
+
+### Debug
+
+#### Shell debug switch
+
+You can set a debug switch in the shell to see more output — e.g.
+more of the stack trace on exception — when you run a command:
+
+\`\`\`
+hbase> debug <RETURN>
+\`\`\`
+
+#### DEBUG log level
+
+To enable DEBUG level logging in the shell, launch it with the \`-d\` option.
+
+\`\`\`bash
+$ ./bin/hbase shell -d
+\`\`\`
+
+### Commands
+
+#### count
+
+Count command returns the number of rows in a table.
+It's quite fast when configured with the right CACHE
+
+\`\`\`ruby
+hbase> count '<tablename>', CACHE => 1000
+\`\`\`
+
+The above count fetches 1000 rows at a time.
+Set CACHE lower if your rows are big.
+Default is to fetch one row at a time.
+
+***
+
+# Data Model
+
+## HBase Data Model Terminology
+
+#### Table \\[!toc]
+
+An HBase table consists of multiple rows.
+
+#### Row \\[!toc]
+
+A row in HBase consists of a row key and one or more columns with values associated with them.
+Rows are sorted alphabetically by the row key as they are stored.
+For this reason, the design of the row key is very important.
+The goal is to store data in such a way that related rows are near each other.
+A common row key pattern is a website domain.
+If your row keys are domains, you should probably store them in reverse (org.apache.www, org.apache.mail, org.apache.jira). This way, all of the Apache domains are near each other in the table, rather than being spread out based on the first letter of the subdomain.
+
+#### Column \\[!toc]
+
+A column in HBase consists of a column family and a column qualifier, which are delimited by a \`:\` (colon) character.
+
+#### Column Family \\[!toc]
+
+Column families physically colocate a set of columns and their values, often for performance reasons.
+Each column family has a set of storage properties, such as whether its values should be cached in memory, how its data is compressed or its row keys are encoded, and others.
+Each row in a table has the same column families, though a given row might not store anything in a given column family.
+
+#### Column Qualifier \\[!toc]
+
+A column qualifier is added to a column family to provide the index for a given piece of data.
+Given a column family \`content\`, a column qualifier might be \`content:html\`, and another might be \`content:pdf\`.
+Though column families are fixed at table creation, column qualifiers are mutable and may differ greatly between rows.
+
+#### Cell \\[!toc]
+
+A cell is a combination of row, column family, and column qualifier, and contains a value and a timestamp, which represents the value's version.
+
+#### Timestamp \\[!toc]
+
+A timestamp is written alongside each value, and is the identifier for a given version of a value.
+By default, the timestamp represents the time on the RegionServer when the data was written, but you can specify a different timestamp value when you put data into the cell.
+
+## Conceptual View
+
+You can read a very understandable explanation of the HBase data model in the blog post [Understanding HBase and BigTable](https://dzone.com/articles/understanding-hbase-and-bigtab) by Jim R. Wilson.
+Another good explanation is available in the PDF [Introduction to Basic Schema Design](http://0b4af6cdc2f0c5998459-c0245c5c937c5dedcca3f1764ecc9b2f.r43.cf2.rackcdn.com/9353-login1210_khurana.pdf) by Amandeep Khurana.
+
+It may help to read different perspectives to get a solid understanding of HBase schema design.
+The linked articles cover the same ground as the information in this section.
+
+The following example is a slightly modified form of the one on page 2 of the [BigTable](http://research.google.com/archive/bigtable.html) paper.
+There is a table called \`webtable\` that contains two rows (\`com.cnn.www\` and \`com.example.www\`) and three column families named \`contents\`, \`anchor\`, and \`people\`.
+In this example, for the first row (\`com.cnn.www\`), \`anchor\` contains two columns (\`anchor:cssnsi.com\`, \`anchor:my.look.ca\`) and \`contents\` contains one column (\`contents:html\`). This example contains 5 versions of the row with the row key \`com.cnn.www\`, and one version of the row with the row key \`com.example.www\`.
+The \`contents:html\` column qualifier contains the entire HTML of a given website.
+Qualifiers of the \`anchor\` column family each contain the external site which links to the site represented by the row, along with the text it used in the anchor of its link.
+The \`people\` column family represents people associated with the site.
+
+<Callout type="info" title="Column Names">
+ By convention, a column name is made of its column family prefix and a *qualifier*. For example,
+ the column *contents:html* is made up of the column family \`contents\` and the \`html\` qualifier.
+ The colon character (\`:\`) delimits the column family from the column family *qualifier*.
+</Callout>
+
+#### Table \`webtable\` \\[!toc]
+
+| Row Key | Time Stamp | ColumnFamily \`contents\` | ColumnFamily \`anchor\` | ColumnFamily \`people\` |
+| ----------------- | ---------- | ---------------------------- | ----------------------------- | -------------------------- |
+| "com.cnn.www" | t9 | | anchor:cnnsi.com = "CNN" | |
+| "com.cnn.www" | t8 | | anchor:my.look.ca = "CNN.com" | |
+| "com.cnn.www" | t6 | contents:html = "\\<html>..." | | |
+| "com.cnn.www" | t5 | contents:html = "\\<html>..." | | |
+| "com.cnn.www" | t3 | contents:html = "\\<html>..." | | |
+| "com.example.www" | t5 | contents:html = "\\<html>..." | | people:author = "John Doe" |
+
+Cells in this table that appear to be empty do not take space, or in fact exist, in HBase.
+This is what makes HBase "sparse." A tabular view is not the only possible way to look at data in HBase, or even the most accurate.
+The following represents the same information as a multi-dimensional map.
+This is only a mock-up for illustrative purposes and may not be strictly accurate.
+
+\`\`\`json
+{
+ "com.cnn.www": {
+ contents: {
+ t6: contents:html: "<html>..."
+ t5: contents:html: "<html>..."
+ t3: contents:html: "<html>..."
+ }
+ anchor: {
+ t9: anchor:cnnsi.com = "CNN"
+ t8: anchor:my.look.ca = "CNN.com"
+ }
+ people: {}
+ }
+ "com.example.www": {
+ contents: {
+ t5: contents:html: "<html>..."
+ }
+ anchor: {}
+ people: {
+ t5: people:author: "John Doe"
+ }
+ }
+}
+\`\`\`
+
+## Physical View
+
+Although at a conceptual level tables may be viewed as a sparse set of rows, they are physically stored by column family.
+A new column qualifier (column\\_family:column\\_qualifier) can be added to an existing column family at any time.
+
+#### ColumnFamily \`anchor\` \\[!toc]
+
+| Row Key | Time Stamp | Column Family \`anchor\` |
+| ------------- | ---------- | ------------------------------- |
+| "com.cnn.www" | t9 | \`anchor:cnnsi.com = "CNN"\` |
+| "com.cnn.www" | t8 | \`anchor:my.look.ca = "CNN.com"\` |
+
+#### ColumnFamily \`contents\` \\[!toc]
+
+| Row Key | Time Stamp | ColumnFamily \`contents:\` |
+| ------------- | ---------- | ---------------------------- |
+| "com.cnn.www" | t6 | contents:html = "\\<html>..." |
+| "com.cnn.www" | t5 | contents:html = "\\<html>..." |
+| "com.cnn.www" | t3 | contents:html = "\\<html>..." |
+
+The empty cells shown in the conceptual view are not stored at all.
+Thus a request for the value of the \`contents:html\` column at time stamp \`t8\` would return no value.
+Similarly, a request for an \`anchor:my.look.ca\` value at time stamp \`t9\` would return no value.
+However, if no timestamp is supplied, the most recent value for a particular column would be returned.
+Given multiple versions, the most recent is also the first one found, since timestamps are stored in descending order.
+Thus a request for the values of all columns in the row \`com.cnn.www\` if no timestamp is specified would be: the value of \`contents:html\` from timestamp \`t6\`, the value of \`anchor:cnnsi.com\` from timestamp \`t9\`, the value of \`anchor:my.look.ca\` from timestamp \`t8\`.
+
+For more information about the internals of how Apache HBase stores data, see [regions.arch](/docs/architecture/regions).
+
+## Namespace
+
+A namespace is a logical grouping of tables analogous to a database in relation database systems.
+This abstraction lays the groundwork for upcoming multi-tenancy related features:
+
+* Quota Management ([HBASE-8410](https://issues.apache.org/jira/browse/HBASE-8410)) - Restrict the amount of resources (i.e. regions, tables) a namespace can consume.
+* Namespace Security Administration ([HBASE-9206](https://issues.apache.org/jira/browse/HBASE-9206)) - Provide another level of security administration for tenants.
+* Region server groups ([HBASE-6721](https://issues.apache.org/jira/browse/HBASE-6721)) - A namespace/table can be pinned onto a subset of RegionServers thus guaranteeing a coarse level of isolation.
+
+### Namespace management
+
+A namespace can be created, removed or altered.
+Namespace membership is determined during table creation by specifying a fully-qualified table name of the form:
+
+\`\`\`xml
+<table namespace>:<table qualifier>
+\`\`\`
+
+#### Examples
+
+\`\`\`bash
+#Create a namespace
+create_namespace 'my_ns'
+\`\`\`
+
+\`\`\`bash
+#create my_table in my_ns namespace
+create 'my_ns:my_table', 'fam'
+\`\`\`
+
+\`\`\`bash
+#drop namespace
+drop_namespace 'my_ns'
+\`\`\`
+
+\`\`\`bash
+#alter namespace
+alter_namespace 'my_ns', {METHOD => 'set', 'PROPERTY_NAME' => 'PROPERTY_VALUE'}
+\`\`\`
+
+### Predefined namespaces
+
+There are two predefined special namespaces:
+
+* hbase - system namespace, used to contain HBase internal tables
+* default - tables with no explicit specified namespace will automatically fall into this namespace
+
+#### Examples #datamodel-predefined-namespaces-examples
+
+\`\`\`bash
+#namespace=foo and table qualifier=bar
+create 'foo:bar', 'fam'
+
+#namespace=default and table qualifier=bar
+create 'bar', 'fam'
+\`\`\`
+
+### About hbase:namespace table
+
+We used to have a system table called \`hbase:namespace\` for storing the namespace information.
+
+It introduced some painful bugs in the past, especially that it may hang the master startup thus
+hang the whole cluster. This is because meta table also has a namespace, so it depends on namespace
+table. But namespace table also depends on meta table as meta table stores the location of all
+regions. This is a cyclic dependency so sometimes namespace and meta table will wait for each other
+to online and hang the master start up.
+
+It is not easy to fix so in 3.0.0, we decided to completely remove the \`hbase:namespace\` table and
+fold its content into the \`ns\` family in \`hbase:meta\` table. When upgrading from 2.x to 3.x, the
+migration will be done automatically and the \`hbase:namespace\` table will be disabled after the
+migration is done. You are free to leave it there for sometime and finally drop it.
+
+For more tails, please see [https://issues.apache.org/jira/browse/HBASE-21154](https://issues.apache.org/jira/browse/HBASE-21154).
+
+## Table
+
+Tables are declared up front at schema definition time.
+
+## Row
+
+Row keys are uninterpreted bytes.
+Rows are lexicographically sorted with the lowest order appearing first in a table.
+The empty byte array is used to denote both the start and end of a tables' namespace.
+
+## Column Family
+
+Columns in Apache HBase are grouped into *column families*.
+All column members of a column family have the same prefix.
+For example, the columns *courses:history* and *courses:math* are both members of the *courses* column family.
+The colon character (\`:\`) delimits the column family from the column family qualifier.
+The column family prefix must be composed of *printable* characters.
+The qualifying tail, the column family *qualifier*, can be made of any arbitrary bytes.
+Column families must be declared up front at schema definition time whereas columns do not need to be defined at schema time but can be conjured on the fly while the table is up and running.
+
+Physically, all column family members are stored together on the filesystem.
+Because tunings and storage specifications are done at the column family level, it is advised that all column family members have the same general access pattern and size characteristics.
+
+## Cells
+
+A *\\{row, column, version}* tuple exactly specifies a \`cell\` in HBase.
+Cell content is uninterpreted bytes
+
+## Data Model Operations
+
+The four primary data model operations are Get, Put, Scan, and Delete.
+Operations are applied via [Table](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Table.html) instances.
+
+### Get
+
+[Get](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Get.html) returns attributes for a specified row.
+Gets are executed via [Table.get](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Table.html#get\\(org.apache.hadoop.hbase.client.Get\\))
+
+### Put
+
+[Put](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Put.html) either adds new rows to a table (if the key is new) or can update existing rows (if the key already exists). Puts are executed via [Table.put](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Table.html#put\\(org.apache.hadoop.hbase.client.Put\\)) (non-writeBuffer) or [Table.batch](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Table.html#batch\\(java.util.List,java.la [...]
+
+### Scans
+
+[Scan](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Scan.html) allow iteration over multiple rows for specified attributes.
+
+The following is an example of a Scan on a Table instance.
+Assume that a table is populated with rows with keys "row1", "row2", "row3", and then another set of rows with the keys "abc1", "abc2", and "abc3". The following example shows how to set a Scan instance to return the rows beginning with "row".
+
+\`\`\`java
+public static final byte[] CF = "cf".getBytes();
+public static final byte[] ATTR = "attr".getBytes();
+...
+
+Table table = ... // instantiate a Table instance
+
+Scan scan = new Scan();
+scan.addColumn(CF, ATTR);
+scan.setStartStopRowForPrefixScan(Bytes.toBytes("row"));
+ResultScanner rs = table.getScanner(scan);
+try {
+ for (Result r = rs.next(); r != null; r = rs.next()) {
+ // process result...
+ }
+} finally {
+ rs.close(); // always close the ResultScanner!
+}
+\`\`\`
+
+Note that generally the easiest way to specify a specific stop point for a scan is by using the [InclusiveStopFilter](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/filter/InclusiveStopFilter.html) class.
+
+### Delete
+
+[Delete](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Delete.html) removes a row from a table.
+Deletes are executed via [Table.delete](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Table.html#delete\\(org.apache.hadoop.hbase.client.Delete\\)).
+
+HBase does not modify data in place, and so deletes are handled by creating new markers called *tombstones*.
+These tombstones, along with the dead values, are cleaned up on major compactions.
+
+See [version.delete](/docs/datamodel#delete-toc) for more information on deleting versions of columns, and see [compaction](/docs/architecture/regions#compaction) for more information on compactions.
+
+## Versions
+
+A *\\{row, column, version}* tuple exactly specifies a \`cell\` in HBase.
+It's possible to have an unbounded number of cells where the row and column are the same but the cell address differs only in its version dimension.
+
+While rows and column keys are expressed as bytes, the version is specified using a long integer.
+Typically this long contains time instances such as those returned by \`java.util.Date.getTime()\` or \`System.currentTimeMillis()\`, that is: *the difference, measured in milliseconds, between the current time and midnight, January 1, 1970 UTC*.
+
+The HBase version dimension is stored in decreasing order, so that when reading from a store file, the most recent values are found first.
+
+There is a lot of confusion over the semantics of \`cell\` versions, in HBase.
+In particular:
+
+* If multiple writes to a cell have the same version, only the last written is fetchable.
+* It is OK to write cells in a non-increasing version order.
+
+Below we describe how the version dimension in HBase currently works.
+See [HBASE-2406](https://issues.apache.org/jira/browse/HBASE-2406) for discussion of HBase versions. [Bending time in HBase](https://web.archive.org/web/20160909085951/https://www.ngdata.com/bending-time-in-hbase/) makes for a good read on the version, or time, dimension in HBase.
+It has more detail on versioning than is provided here.
+
+As of this writing, the limitation *Overwriting values at existing timestamps* mentioned in the article no longer holds in HBase.
+This section is basically a synopsis of this article by Bruno Dumon.
+
+### Specifying the Number of Versions to Store
+
+The maximum number of versions to store for a given column is part of the column schema and is specified at table creation, or via an \`alter\` command, via \`HColumnDescriptor.DEFAULT_VERSIONS\`.
+Prior to HBase 0.96, the default number of versions kept was \`3\`, but in 0.96 and newer has been changed to \`1\`.
+
+#### Example: Modify the Maximum Number of Versions for a Column Family \\[!toc]
+
+This example uses HBase Shell to keep a maximum of 5 versions of all columns in column family \`f1\`.
+You could also use [ColumnFamilyDescriptorBuilder](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/ColumnFamilyDescriptorBuilder.html).
+
+\`\`\`bash
+hbase> alter 't1', NAME => 'f1', VERSIONS => 5
+\`\`\`
+
+#### Example: Modify the Minimum Number of Versions for a Column Family \\[!toc]
+
+You can also specify the minimum number of versions to store per column family.
+By default, this is set to 0, which means the feature is disabled.
+The following example sets the minimum number of versions on all columns in column family \`f1\` to \`2\`, via HBase Shell.
+You could also use [ColumnFamilyDescriptorBuilder](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/ColumnFamilyDescriptorBuilder.html).
+
+\`\`\`bash
+hbase> alter 't1', NAME => 'f1', MIN_VERSIONS => 2
+\`\`\`
+
+Starting with HBase 0.98.2, you can specify a global default for the maximum number of versions kept for all newly-created columns, by setting \`hbase.column.max.version\` in *hbase-site.xml*.
+See [hbase.column.max.version](/docs/configuration/default#hbasecolumnmaxversion-toc).
+
+### Versions and HBase Operations
+
+In this section we look at the behavior of the version dimension for each of the core HBase operations.
+
+#### Get/Scan
+
+Gets are implemented on top of Scans.
+The below discussion of [Get](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Get.html) applies equally to [Scans](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Scan.html).
+
+By default, i.e. if you specify no explicit version, when doing a \`get\`, the cell whose version has the largest value is returned (which may or may not be the latest one written, see later). The default behavior can be modified in the following ways:
+
+* to return more than one version, see [Get.readVersions(int)](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Get.html#readVersions\\(int\\))
+* to return versions other than the latest, see [Get.setTimeRange(long,long)](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Get.html#setTimeRange\\(long,long\\))
+
+To retrieve the latest version that is less than or equal to a given value, thus giving the 'latest' state of the record at a certain point in time, just use a range from 0 to the desired version and set the max versions to 1.
+
+#### Default Get Example
+
+The following Get will only retrieve the current version of the row
+
+\`\`\`java
+public static final byte[] CF = "cf".getBytes();
+public static final byte[] ATTR = "attr".getBytes();
+...
+Get get = new Get(Bytes.toBytes("row1"));
+Result r = table.get(get);
+byte[] b = r.getValue(CF, ATTR); // returns current version of value
+\`\`\`
+
+#### Versioned Get Example
+
+The following Get will return the last 3 versions of the row.
+
+\`\`\`java
+public static final byte[] CF = "cf".getBytes();
+public static final byte[] ATTR = "attr".getBytes();
+...
+Get get = new Get(Bytes.toBytes("row1"));
+get.setMaxVersions(3); // will return last 3 versions of row
+Result r = table.get(get);
+byte[] b = r.getValue(CF, ATTR); // returns current version of value
+List<Cell> cells = r.getColumnCells(CF, ATTR); // returns all versions of this column
+\`\`\`
+
+#### Put
+
+Doing a put always creates a new version of a \`cell\`, at a certain timestamp.
+By default the system uses the server's \`currentTimeMillis\`, but you can specify the version (= the long integer) yourself, on a per-column level.
+This means you could assign a time in the past or the future, or use the long value for non-time purposes.
+
+To overwrite an existing value, do a put at exactly the same row, column, and version as that of the cell you want to overwrite.
+
+#### Implicit Version Example \\[!toc]
+
+The following Put will be implicitly versioned by HBase with the current time.
+
+\`\`\`java
+public static final byte[] CF = "cf".getBytes();
+public static final byte[] ATTR = "attr".getBytes();
+...
+Put put = new Put(Bytes.toBytes(row));
+put.add(CF, ATTR, Bytes.toBytes( data));
+table.put(put);
+\`\`\`
+
+#### Explicit Version Example
+
+The following Put has the version timestamp explicitly set.
+
+\`\`\`java
+public static final byte[] CF = "cf".getBytes();
+public static final byte[] ATTR = "attr".getBytes();
+...
+Put put = new Put( Bytes.toBytes(row));
+long explicitTimeInMs = 555; // just an example
+put.add(CF, ATTR, explicitTimeInMs, Bytes.toBytes(data));
+table.put(put);
+\`\`\`
+
+Caution: the version timestamp is used internally by HBase for things like time-to-live calculations.
+It's usually best to avoid setting this timestamp yourself.
+Prefer using a separate timestamp attribute of the row, or have the timestamp as a part of the row key, or both.
+
+#### Cell Version Example \\[!toc]
+
+The following Put uses a method getCellBuilder() to get a CellBuilder instance
+that already has relevant Type and Row set.
+
+\`\`\`java
+public static final byte[] CF = "cf".getBytes();
+public static final byte[] ATTR = "attr".getBytes();
+...
+
+Put put = new Put(Bytes.toBytes(row));
+put.add(put.getCellBuilder().setQualifier(ATTR)
+ .setFamily(CF)
+ .setValue(Bytes.toBytes(data))
+ .build());
+table.put(put);
+\`\`\`
+
+#### Delete \\[!toc]
+
+There are three different types of internal delete markers.
+See Lars Hofhansl's blog for discussion of his attempt adding another, [Scanning in HBase: Prefix Delete Marker](http://hadoop-hbase.blogspot.com/2012/01/scanning-in-hbase.html).
+
+* Delete: for a specific version of a column.
+* Delete column: for all versions of a column.
+* Delete family: for all columns of a particular ColumnFamily
+
+When deleting an entire row, HBase will internally create a tombstone for each ColumnFamily (i.e., not each individual column).
+
+Deletes work by creating *tombstone* markers.
+For example, let's suppose we want to delete a row.
+For this you can specify a version, or else by default the \`currentTimeMillis\` is used.
+What this means is *delete all cells where the version is less than or equal to this version*.
+HBase never modifies data in place, so for example a delete will not immediately delete (or mark as deleted) the entries in the storage file that correspond to the delete condition.
+Rather, a so-called *tombstone* is written, which will mask the deleted values.
+When HBase does a major compaction, the tombstones are processed to actually remove the dead values, together with the tombstones themselves.
+If the version you specified when deleting a row is larger than the version of any value in the row, then you can consider the complete row to be deleted.
+
+For an informative discussion on how deletes and versioning interact, see the thread [Put w/timestamp -> Deleteall -> Put w/ timestamp fails](https://lists.apache.org/thread/g6s0fkx74hbmc0pplnf5r3gq5xn4vkyt) up on the user mailing list.
+
+Also see [keyvalue](/docs/architecture/regions#keyvalue) for more information on the internal KeyValue format.
+
+Delete markers are purged during the next major compaction of the store, unless the \`KEEP_DELETED_CELLS\` option is set in the column family (See [Keeping Deleted Cells](/docs/regionserver-sizing#keeping-deleted-cells)).
+To keep the deletes for a configurable amount of time, you can set the delete TTL via the \`hbase.hstore.time.to.purge.deletes\` property in *hbase-site.xml*.
+If \`hbase.hstore.time.to.purge.deletes\` is not set, or set to 0, all delete markers, including those with timestamps in the future, are purged during the next major compaction.
+Otherwise, a delete marker with a timestamp in the future is kept until the major compaction which occurs after the time represented by the marker's timestamp plus the value of \`hbase.hstore.time.to.purge.deletes\`, in milliseconds.
+
+<Callout type="info">
+ This behavior represents a fix for an unexpected change that was introduced in HBase 0.94, and was
+ fixed in [HBASE-10118](https://issues.apache.org/jira/browse/HBASE-10118). The change has been
+ backported to HBase 0.94 and newer branches.
+</Callout>
+
+### Optional New Version and Delete behavior in HBase-2.0.0
+
+In \`hbase-2.0.0\`, the operator can specify an alternate version and
+delete treatment by setting the column descriptor property
+\`NEW_VERSION_BEHAVIOR\` to true (To set a property on a column family
+descriptor, you must first disable the table and then alter the
+column family descriptor; see [Keeping Deleted Cells](/docs/regionserver-sizing#keeping-deleted-cells) for an example
+of editing an attribute on a column family descriptor).
+
+The 'new version behavior', undoes the limitations listed below
+whereby a \`Delete\` ALWAYS overshadows a \`Put\` if at the same
+location — i.e. same row, column family, qualifier and timestamp
+\\-- regardless of which arrived first. Version accounting is also
+changed as deleted versions are considered toward total version count.
+This is done to ensure results are not changed should a major
+compaction intercede. See \`HBASE-15968\` and linked issues for
+discussion.
+
+Running with this new configuration currently costs; we factor
+the Cell MVCC on every compare so we burn more CPU. The slow
+down will depend. In testing we've seen between 0% and 25%
+degradation.
+
+If replicating, it is advised that you run with the new
+serial replication feature (See \`HBASE-9465\`; the serial
+replication feature did NOT make it into \`hbase-2.0.0\` but
+should arrive in a subsequent hbase-2.x release) as now
+the order in which Mutations arrive is a factor.
+
+### Current Limitations
+
+The below limitations are addressed in hbase-2.0.0. See
+the section above, [Optional New Version and Delete behavior in HBase-2.0.0](/docs/datamodel#optional-new-version-and-delete-behavior-in-hbase-200).
+
+#### Deletes mask Puts
+
+Deletes mask puts, even puts that happened after the delete was entered.
+See [HBASE-2256](https://issues.apache.org/jira/browse/HBASE-2256).
+Remember that a delete writes a tombstone, which only disappears after then next major compaction has run.
+Suppose you do a delete of everything \`<= T\`.
+After this you do a new put with a timestamp \`<= T\`.
+This put, even if it happened after the delete, will be masked by the delete tombstone.
+Performing the put will not fail, but when you do a get you will notice the put did have no effect.
+It will start working again after the major compaction has run.
+These issues should not be a problem if you use always-increasing versions for new puts to a row.
+But they can occur even if you do not care about time: just do delete and put immediately after each other, and there is some chance they happen within the same millisecond.
+
+#### Major compactions change query results
+
+*...create three cell versions at t1, t2 and t3, with a maximum-versions
+setting of 2. So when getting all versions, only the values at t2 and t3 will be
+returned. But if you delete the version at t2 or t3, the one at t1 will appear again.
+Obviously, once a major compaction has run, such behavior will not be the case
+anymore...* (See *Garbage Collection* in [Bending time in HBase](https://web.archive.org/web/20160909085951/https://www.ngdata.com/bending-time-in-hbase/).)
+
+## Sort Order
+
+All data model operations HBase return data in sorted order.
+First by row, then by ColumnFamily, followed by column qualifier, and finally timestamp (sorted in reverse, so newest records are returned first).
+
+## Column Metadata
+
+There is no store of column metadata outside of the internal KeyValue instances for a ColumnFamily.
+Thus, while HBase can support not only a wide number of columns per row, but a heterogeneous set of columns between rows as well, it is your responsibility to keep track of the column names.
+
+The only way to get a complete set of columns that exist for a ColumnFamily is to process all the rows.
+For more information about how HBase stores data internally, see [keyvalue](/docs/architecture/regions#keyvalue).
+
+## Joins
+
+Whether HBase supports joins is a common question on the dist-list, and there is a simple answer: it doesn't, at not least in the way that RDBMS' support them (e.g., with equi-joins or outer-joins in SQL). As has been illustrated in this chapter, the read data model operations in HBase are Get and Scan.
+
+However, that doesn't mean that equivalent join functionality can't be supported in your application, but you have to do it yourself.
+The two primary strategies are either denormalizing the data upon writing to HBase, or to have lookup tables and do the join between HBase tables in your application or MapReduce code (and as RDBMS' demonstrate, there are several strategies for this depending on the size of the tables, e.g., nested loops vs.
+hash-joins). So which is the best approach? It depends on what you are trying to do, and as such there isn't a single answer that works for every use case.
+
+## ACID
+
+See [ACID Semantics](/acid-semantics).
+Lars Hofhansl has also written a note on [ACID in HBase](http://hadoop-hbase.blogspot.com/2012/03/acid-in-hbase.html).
+
+***
+
+# HBase and Schema Design
+
+A good introduction on the strength and weaknesses modelling on the various non-rdbms datastores is to be found in Ian Varley's Master thesis, [No Relation: The Mixed Blessings of Non-Relational Databases](http://ianvarley.com/UT/MR/Varley_MastersReport_Full_2009-08-07.pdf). It is a little dated now but a good background read if you have a moment on how HBase schema modeling differs from how it is done in an RDBMS. Also, read [keyvalue](/docs/architecture/regions#keyvalue) for how HBase [...]
+
+The documentation on the Cloud Bigtable website, [Designing Your Schema](https://cloud.google.com/bigtable/docs/schema-design), is pertinent and nicely done and lessons learned there equally apply here in HBase land; just divide any quoted values by \\~10 to get what works for HBase: e.g. where it says individual values can be \\~10MBs in size, HBase can do similar — perhaps best to go smaller if you can — and where it says a maximum of 100 column families in Cloud Bigtable, think \\~10 [...]
+
+See also Robert Yokota's [HBase Application Archetypes](https://blogs.apache.org/hbase/entry/hbase-application-archetypes-redux) (an update on work done by other HBasers), for a helpful categorization of use cases that do well on top of the HBase model.
+
+## Schema Creation
+
+HBase schemas can be created or updated using the [Apache HBase Shell](/docs/shell) or by using [Admin](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Admin.html) in the Java API.
+
+Tables must be disabled when making ColumnFamily modifications, for example:
+
+\`\`\`java
+Configuration config = HBaseConfiguration.create();
+Admin admin = new Admin(conf);
+TableName table = TableName.valueOf("myTable");
+
+admin.disableTable(table);
+
+HColumnDescriptor cf1 = ...;
+admin.addColumn(table, cf1); // adding new ColumnFamily
+HColumnDescriptor cf2 = ...;
+admin.modifyColumn(table, cf2); // modifying existing ColumnFamily
+
+admin.enableTable(table);
+\`\`\`
+
+See [client dependencies](/docs/configuration/default#client-configuration-and-dependencies-connecting-to-an-hbase-cluster) for more information about configuring client connections.
+
+<Callout type="info">
+ Online schema changes are supported in the 0.92.x codebase, but the 0.90.x codebase requires the
+ table to be disabled.
+</Callout>
+
+### Schema Updates
+
+When changes are made to either Tables or ColumnFamilies (e.g. region size, block size), these changes take effect the next time there is a major compaction and the StoreFiles get re-written.
+
+See [store](/docs/architecture/regions#store) for more information on StoreFiles.
+
+## Table Schema Rules Of Thumb
+
+There are many different data sets, with different access patterns and service-level expectations. Therefore, these rules of thumb are only an overview. Read the rest of this chapter to get more details after you have gone through this list.
+
+* Aim to have regions sized between 10 and 50 GB.
+* Aim to have cells no larger than 10 MB, or 50 MB if you use [mob](/docs/architecture/hbase-mob). Otherwise, consider storing your cell data in HDFS and store a pointer to the data in HBase.
+* A typical schema has between 1 and 3 column families per table. HBase tables should not be designed to mimic RDBMS tables.
+* Around 50-100 regions is a good number for a table with 1 or 2 column families. Remember that a region is a contiguous segment of a column family.
+* Keep your column family names as short as possible. The column family names are stored for every value (ignoring prefix encoding). They should not be self-documenting and descriptive like in a typical RDBMS.
+* If you are storing time-based machine data or logging information, and the row key is based on device ID or service ID plus time, you can end up with a pattern where older data regions never have additional writes beyond a certain age. In this type of situation, you end up with a small number of active regions and a large number of older regions which have no new writes. For these situations, you can tolerate a larger number of regions because your resource consumption is driven by the [...]
+* If only one column family is busy with writes, only that column family accomulates memory. Be aware of write patterns when allocating resources.
+
+***
+
+# RegionServer Sizing Rules of Thumb
+
+Lars Hofhansl wrote a great [blog post](http://hadoop-hbase.blogspot.com/2013/01/hbase-region-server-memory-sizing.html) about RegionServer memory sizing. The upshot is that you probably need more memory than you think you need. He goes into the impact of region size, memstore size, HDFS replication factor, and other things to check.
+
+> Personally I would place the maximum disk space per machine that can be served exclusively with HBase around 6T, unless you have a very read-heavy workload. In that case the Java heap should be 32GB (20G regions, 128M memstores, the rest defaults).
+>
+> — Lars Hofhansl [http://hadoop-hbase.blogspot.com/2013/01/hbase-region-server-memory-sizing.html](http://hadoop-hbase.blogspot.com/2013/01/hbase-region-server-memory-sizing.html)
+
+## On the number of column families
+
+HBase currently does not do well with anything above two or three column families so keep the number of column families in your schema low. Currently, flushing is done on a per Region basis so if one column family is carrying the bulk of the data bringing on flushes, the adjacent families will also be flushed even though the amount of data they carry is small. When many column families exist the flushing interaction can make for a bunch of needless i/o (To be addressed by changing flushi [...]
+
+Try to make do with one column family if you can in your schemas. Only introduce a second and third column family in the case where data access is usually column scoped; i.e. you query one column family or the other but usually not both at the one time.
+
+### Cardinality of ColumnFamilies
+
+Where multiple ColumnFamilies exist in a single table, be aware of the cardinality (i.e., number of rows). If ColumnFamilyA has 1 million rows and ColumnFamilyB has 1 billion rows, ColumnFamilyA's data will likely be spread across many, many regions (and RegionServers). This makes mass scans for ColumnFamilyA less efficient.
+
+## Rowkey Design
+
+### Hotspotting
+
+Rows in HBase are sorted lexicographically by row key. This design optimizes for scans, allowing you to store related rows, or rows that will be read together, near each other. However, poorly designed row keys are a common source of **hotspotting**. Hotspotting occurs when a large amount of client traffic is directed at one node, or only a few nodes, of a cluster. This traffic may represent reads, writes, or other operations. The traffic overwhelms the single machine responsible for hos [...]
+
+To prevent hotspotting on writes, design your row keys such that rows that truly do need to be in the same region are, but in the bigger picture, data is being written to multiple regions across the cluster, rather than one at a time. Some common techniques for avoiding hotspotting are described below, along with some of their advantages and drawbacks.
+
+#### Salting \\[!toc]
+
+Salting in this sense has nothing to do with cryptography, but refers to adding random data to the start of a row key. In this case, salting refers to adding a randomly-assigned prefix to the row key to cause it to sort differently than it otherwise would. The number of possible prefixes correspond to the number of regions you want to spread the data across. Salting can be helpful if you have a few "hot" row key patterns which come up over and over amongst other more evenly-distributed r [...]
+
+#### Salting Example: \\[!toc]
+
+Suppose you have the following list of row keys, and your table is split such that there is one region for each letter of the alphabet. Prefix 'a' is one region, prefix 'b' is another. In this table, all rows starting with 'f' are in the same region. This example focuses on rows with keys like the following:
+
+\`\`\`text
+foo0001
+foo0002
+foo0003
+foo0004
+\`\`\`
+
+Now, imagine that you would like to spread these across four different regions. You decide to use four different salts: \`a\`, \`b\`, \`c\`, and \`d\`. In this scenario, each of these letter prefixes will be on a different region. After applying the salts, you have the following rowkeys instead. Since you can now write to four separate regions, you theoretically have four times the throughput when writing that you would have if all the writes were going to the same region.
+
+\`\`\`text
+a-foo0003
+b-foo0001
+c-foo0004
+d-foo0002
+\`\`\`
+
+Then, if you add another row, it will randomly be assigned one of the four possible salt values and end up near one of the existing rows.
+
+\`\`\`text
+a-foo0003
+b-foo0001
+c-foo0003
+c-foo0004
+d-foo0002
+\`\`\`
+
+Since this assignment will be random, you will need to do more work if you want to retrieve the rows in lexicographic order. In this way, salting attempts to increase throughput on writes, but has a cost during reads.
+
+#### Hashing \\[!toc]
+
+Instead of a random assignment, you could use a one-way **hash** that would cause a given row to always be "salted" with the same prefix, in a way that would spread the load across the RegionServers, but allow for predictability during reads. Using a deterministic hash allows the client to reconstruct the complete rowkey and use a Get operation to retrieve that row as normal.
+
+#### Hashing Example: \\[!toc]
+
+Given the same situation in the salting example above, you could instead apply a one-way hash that would cause the row with key \`foo0003\` to always, and predictably, receive the \`a\` prefix. Then, to retrieve that row, you would already know the key. You could also optimize things so that certain pairs of keys were always in the same region, for instance.
+
+#### Reversing the Key \\[!toc]
+
+A third common trick for preventing hotspotting is to reverse a fixed-width or numeric row key so that the part that changes the most often (the least significant digit) is first. This effectively randomizes row keys, but sacrifices row ordering properties.
+
+See [https://communities.intel.com/community/itpeernetwork/datastack/blog/2013/11/10/discussion-on-designing-hbase-tables](https://communities.intel.com/community/itpeernetwork/datastack/blog/2013/11/10/discussion-on-designing-hbase-tables), and [article on Salted Tables](https://phoenix.apache.org/salted.html) from the Phoenix project, and the discussion in the comments of [HBASE-11682](https://issues.apache.org/jira/browse/HBASE-11682) for more information about avoiding hotspotting.
+
+### Monotonically Increasing Row Keys/Timeseries Data
+
+In the HBase chapter of Tom White's book [Hadoop: The Definitive Guide](http://oreilly.com/catalog/9780596521981) (O'Reilly) there is a an optimization note on watching out for a phenomenon where an import process walks in lock-step with all clients in concert pounding one of the table's regions (and thus, a single node), then moving onto the next region, etc. With monotonically increasing row-keys (i.e., using a timestamp), this will happen. See this comic by IKai Lan on why monotonical [...]
+
+If you do need to upload time series data into HBase, you should study [OpenTSDB](http://opentsdb.net/) as a successful example. It has a page describing the [schema](http://opentsdb.net/schema.html) it uses in HBase. The key format in OpenTSDB is effectively \\[metric\\_type]\\[event\\_timestamp], which would appear at first glance to contradict the previous advice about not using a timestamp as the key. However, the difference is that the timestamp is not in the *lead* position of the [...]
+
+See [schema.casestudies](/docs/regionserver-sizing#schema-design-case-studies) for some rowkey design examples.
+
+### Try to minimize row and column sizes
+
+In HBase, values are always freighted with their coordinates; as a cell value passes through the system, it'll be accompanied by its row, column name, and timestamp - always. If your rows and column names are large, especially compared to the size of the cell value, then you may run up against some interesting scenarios. One such is the case described by Marc Limotte at the tail of [HBASE-3551](https://issues.apache.org/jira/browse/HBASE-3551?page=com.atlassian.jira.plugin.system.issueta [...]
+
+Most of the time small inefficiencies don't matter all that much. Unfortunately, this is a case where they do. Whatever patterns are selected for ColumnFamilies, attributes, and rowkeys they could be repeated several billion times in your data.
+
+See [keyvalue](/docs/architecture/regions#keyvalue) for more information on HBase stores data internally to see why this is important.
+
+#### Column Families
+
+Try to keep the ColumnFamily names as small as possible, preferably one character (e.g. "d" for data/default).
+
+See [KeyValue](/docs/architecture/regions#keyvalue) for more information on how HBase stores data internally.
+
+#### Attributes
+
+Although verbose attribute names (e.g., "myVeryImportantAttribute") are easier to read, prefer shorter attribute names (e.g., "via") to store in HBase.
+
+See [keyvalue](/docs/architecture/regions#keyvalue) for more information on HBase stores data internally to see why this is important.
+
+#### Rowkey Length
+
+Keep them as short as is reasonable such that they can still be useful for required data access (e.g. Get vs. Scan). A short key that is useless for data access is not better than a longer key with better get/scan properties. Expect tradeoffs when designing rowkeys.
+
+#### Byte Patterns
+
+A long is 8 bytes. You can store an unsigned number up to 18,446,744,073,709,551,615 in those eight bytes. If you stored this number as a String — presuming a byte per character — you need nearly 3x the bytes.
+
+Not convinced? Below is some sample code that you can run on your own.
+
+\`\`\`java
+// long
+//
+long l = 1234567890L;
+byte[] lb = Bytes.toBytes(l);
+System.out.println("long bytes length: " + lb.length); // returns 8
+
+String s = String.valueOf(l);
+byte[] sb = Bytes.toBytes(s);
+System.out.println("long as string length: " + sb.length); // returns 10
+
+// hash
+//
+MessageDigest md = MessageDigest.getInstance("MD5");
+byte[] digest = md.digest(Bytes.toBytes(s));
+System.out.println("md5 digest bytes length: " + digest.length); // returns 16
+
+String sDigest = new String(digest);
+byte[] sbDigest = Bytes.toBytes(sDigest);
+System.out.println("md5 digest as string length: " + sbDigest.length); // returns 26
+\`\`\`
+
+Unfortunately, using a binary representation of a type will make your data harder to read outside of your code. For example, this is what you will see in the shell when you increment a value:
+
+\`\`\`bash
+hbase(main):001:0> incr 't', 'r', 'f:q', 1
+COUNTER VALUE = 1
+
+hbase(main):002:0> get 't', 'r'
+COLUMN CELL
+ f:q timestamp=1369163040570, value=\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x01
+1 row(s) in 0.0310 seconds
+\`\`\`
+
+The shell makes a best effort to print a string, and it this case it decided to just print the hex. The same will happen to your row keys inside the region names. It can be okay if you know what's being stored, but it might also be unreadable if arbitrary data can be put in the same cells. This is the main trade-off.
+
+### Reverse Timestamps
+
+<Callout type="info">
+ [HBASE-4811](https://issues.apache.org/jira/browse/HBASE-4811) implements an API to scan a table
+ or a range within a table in reverse, reducing the need to optimize your schema for forward or
+ reverse scanning. This feature is available in HBase 0.98 and later. See
+ [Scan.setReversed()](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Scan.html#setReversed\\(boolean\\))
+ for more information.
+</Callout>
+
+A common problem in database processing is quickly finding the most recent version of a value. A technique using reverse timestamps as a part of the key can help greatly with a special case of this problem. Also found in the HBase chapter of Tom White's book Hadoop: The Definitive Guide (O'Reilly), the technique involves appending (\`Long.MAX_VALUE - timestamp\`) to the end of any key, e.g. \\[key]\\[reverse\\_timestamp].
+
+The most recent value for \\[key] in a table can be found by performing a Scan for \\[key] and obtaining the first record. Since HBase keys are in sorted order, this key sorts before any older row-keys for \\[key] and thus is first.
+
+This technique would be used instead of using [Number of Versions](/docs/regionserver-sizing#number-of-versions) where the intent is to hold onto all versions "forever" (or a very long time) and at the same time quickly obtain access to any other version by using the same Scan technique.
+
+### Rowkeys and ColumnFamilies
+
+Rowkeys are scoped to ColumnFamilies. Thus, the same rowkey could exist in each ColumnFamily that exists in a table without collision.
+
+### Immutability of Rowkeys
+
+Rowkeys cannot be changed. The only way they can be "changed" in a table is if the row is deleted and then re-inserted. This is a fairly common question on the HBase dist-list so it pays to get the rowkeys right the first time (and/or before you've inserted a lot of data).
+
+### Relationship Between RowKeys and Region Splits
+
+If you pre-split your table, it is *critical* to understand how your rowkey will be distributed across the region boundaries. As an example of why this is important, consider the example of using displayable hex characters as the lead position of the key (e.g., "0000000000000000" to "ffffffffffffffff"). Running those key ranges through \`Bytes.split\` (which is the split strategy used when creating regions in \`Admin.createTable(byte[] startKey, byte[] endKey, numRegions)\` for 10 region [...]
+
+\`\`\`text
+48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 // 0
+54 -10 -10 -10 -10 -10 -10 -10 -10 -10 -10 -10 -10 -10 -10 -10 // 6
+61 -67 -67 -67 -67 -67 -67 -67 -67 -67 -67 -67 -67 -67 -67 -68 // =
+68 -124 -124 -124 -124 -124 -124 -124 -124 -124 -124 -124 -124 -124 -124 -126 // D
+75 75 75 75 75 75 75 75 75 75 75 75 75 75 75 72 // K
+82 18 18 18 18 18 18 18 18 18 18 18 18 18 18 14 // R
+88 -40 -40 -40 -40 -40 -40 -40 -40 -40 -40 -40 -40 -40 -40 -44 // X
+95 -97 -97 -97 -97 -97 -97 -97 -97 -97 -97 -97 -97 -97 -97 -102 // _
+102 102 102 102 102 102 102 102 102 102 102 102 102 102 102 102 // f
+\`\`\`
+
+(note: the lead byte is listed to the right as a comment.) Given that the first split is a '0' and the last split is an 'f', everything is great, right? Not so fast.
+
+The problem is that all the data is going to pile up in the first 2 regions and the last region thus creating a "lumpy" (and possibly "hot") region problem. To understand why, refer to an [ASCII Table](http://www.asciitable.com). '0' is byte 48, and 'f' is byte 102, but there is a huge gap in byte values (bytes 58 to 96) that will *never appear in this keyspace* because the only values are \\[0-9] and \\[a-f]. Thus, the middle regions will never be used. To make pre-splitting work with t [...]
+
+Lesson #1: Pre-splitting tables is generally a best practice, but you need to pre-split them in such a way that all the regions are accessible in the keyspace. While this example demonstrated the problem with a hex-key keyspace, the same problem can happen with *any* keyspace. Know your data.
+
+Lesson #2: While generally not advisable, using hex-keys (and more generally, displayable data) can still work with pre-split tables as long as all the created regions are accessible in the keyspace.
+
+To conclude this example, the following is an example of how appropriate splits can be pre-created for hex-keys:
+
+\`\`\`java
+public static boolean createTable(Admin admin, HTableDescriptor table, byte[][] splits)
+throws IOException {
+ try {
+ admin.createTable( table, splits );
+ return true;
+ } catch (TableExistsException e) {
+ logger.info("table " + table.getNameAsString() + " already exists");
+ // the table already exists...
+ return false;
+ }
+}
+
+public static byte[][] getHexSplits(String startKey, String endKey, int numRegions) {
+ byte[][] splits = new byte[numRegions-1][];
+ BigInteger lowestKey = new BigInteger(startKey, 16);
+ BigInteger highestKey = new BigInteger(endKey, 16);
+ BigInteger range = highestKey.subtract(lowestKey);
+ BigInteger regionIncrement = range.divide(BigInteger.valueOf(numRegions));
+ lowestKey = lowestKey.add(regionIncrement);
+ for(int i=0; i < numRegions-1;i++) {
+ BigInteger key = lowestKey.add(regionIncrement.multiply(BigInteger.valueOf(i)));
+ byte[] b = String.format("%016x", key).getBytes();
+ splits[i] = b;
+ }
+ return splits;
+}
+\`\`\`
+
+## Number of Versions
+
+### Maximum Number of Versions
+
+The maximum number of row versions to store is configured per column family via [HColumnDescriptor](https://hbase.apache.org/apidocs/org/apache/hadoop/hbase/HColumnDescriptor.html). The default for max versions is 1. This is an important parameter because as described in [Data Model](/docs/datamodel) section HBase does *not* overwrite row values, but rather stores different values per row by time (and qualifier). Excess versions are removed during major compactions. The number of max ver [...]
+
+It is not recommended setting the number of max versions to an exceedingly high level (e.g., hundreds or more) unless those old values are very dear to you because this will greatly increase StoreFile size.
+
+### Minimum Number of Versions
+
+Like maximum number of row versions, the minimum number of row versions to keep is configured per column family via [ColumnFamilyDescriptorBuilder](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/ColumnFamilyDescriptorBuilder.html). The default for min versions is 0, which means the feature is disabled. The minimum number of row versions parameter is used together with the time-to-live parameter and can be combined with the number of row versions parameter to allow con [...]
+
+## Supported Datatypes
+
+HBase supports a "bytes-in/bytes-out" interface via [Put](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Put.html) and [Result](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Result.html), so anything that can be converted to an array of bytes can be stored as a value. Input could be strings, numbers, complex objects, or even images as long as they can rendered as bytes.
+
+There are practical limits to the size of values (e.g., storing 10-50MB objects in HBase would probably be too much to ask); search the mailing list for conversations on this topic. All rows in HBase conform to the [Data Model](/docs/datamodel), and that includes versioning. Take that into consideration when making your design, as well as block size for the ColumnFamily.
+
+### Counters
+
+One supported datatype that deserves special mention are "counters" (i.e., the ability to do atomic increments of numbers). See [Increment](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Table.html#increment\\(org.apache.hadoop.hbase.client.Increment\\)) in \`Table\`.
+
+Synchronization on counters are done on the RegionServer, not in the client.
+
+## Joins
+
+If you have multiple tables, don't forget to factor in the potential for [Joins](/docs/datamodel#datamodel-joins) into the schema design.
+
+## Time To Live (TTL)
+
+ColumnFamilies can set a TTL length in seconds, and HBase will automatically delete rows once the expiration time is reached. This applies to *all* versions of a row - even the current one. The TTL time encoded in the HBase for the row is specified in UTC.
+
+Store files which contains only expired rows are deleted on minor compaction. Setting \`hbase.store.delete.expired.storefile\` to \`false\` disables this feature. Setting minimum number of versions to other than 0 also disables this.
+
+See [HColumnDescriptor](https://hbase.apache.org/apidocs/org/apache/hadoop/hbase/HColumnDescriptor.html) for more information.
+
+Recent versions of HBase also support setting time to live on a per cell basis. See [HBASE-10560](https://issues.apache.org/jira/browse/HBASE-10560) for more information. Cell TTLs are submitted as an attribute on mutation requests (Appends, Increments, Puts, etc.) using Mutation#setTTL. If the TTL attribute is set, it will be applied to all cells updated on the server by the operation. There are two notable differences between cell TTL handling and ColumnFamily TTLs:
+
+* Cell TTLs are expressed in units of milliseconds instead of seconds.
+
+* A cell TTLs cannot extend the effective lifetime of a cell beyond a ColumnFamily level TTL setting.
+
+## Keeping Deleted Cells
+
+By default, delete markers extend back to the beginning of time. Therefore, [Get](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Get.html) or [Scan](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Scan.html) operations will not see a deleted cell (row or column), even when the Get or Scan operation indicates a time range before the delete marker was placed.
+
+ColumnFamilies can optionally keep deleted cells. In this case, deleted cells can still be retrieved, as long as these operations specify a time range that ends before the timestamp of any delete that would affect the cells. This allows for point-in-time queries even in the presence of deletes.
+
+Deleted cells are still subject to TTL and there will never be more than "maximum number of versions" deleted cells. A new "raw" scan options returns all deleted rows and the delete markers.
+
+#### Change the Value of \`KEEP_DELETED_CELLS\` Using HBase Shell: \\[!toc]
+
+\`\`\`bash
+hbase> hbase> alter 't1', NAME => 'f1', KEEP_DELETED_CELLS => true
+\`\`\`
+
+#### Change the Value of \`KEEP_DELETED_CELLS\` Using the API: \\[!toc]
+
+\`\`\`java
+...
+HColumnDescriptor.setKeepDeletedCells(true);
+...
+\`\`\`
+
+Let us illustrate the basic effect of setting the \`KEEP_DELETED_CELLS\` attribute on a table.
+
+First, without:
+
+\`\`\`bash
+create 'test', {NAME=>'e', VERSIONS=>2147483647}
+put 'test', 'r1', 'e:c1', 'value', 10
+put 'test', 'r1', 'e:c1', 'value', 12
+put 'test', 'r1', 'e:c1', 'value', 14
+delete 'test', 'r1', 'e:c1', 11
+
+hbase(main):017:0> scan 'test', {RAW=>true, VERSIONS=>1000}
+ROW COLUMN+CELL
+ r1 column=e:c1, timestamp=14, value=value
+ r1 column=e:c1, timestamp=12, value=value
+ r1 column=e:c1, timestamp=11, type=DeleteColumn
+ r1 column=e:c1, timestamp=10, value=value
+1 row(s) in 0.0120 seconds
+
+hbase(main):018:0> flush 'test'
+0 row(s) in 0.0350 seconds
+
+hbase(main):019:0> scan 'test', {RAW=>true, VERSIONS=>1000}
+ROW COLUMN+CELL
+ r1 column=e:c1, timestamp=14, value=value
+ r1 column=e:c1, timestamp=12, value=value
+ r1 column=e:c1, timestamp=11, type=DeleteColumn
+1 row(s) in 0.0120 seconds
+
+hbase(main):020:0> major_compact 'test'
+0 row(s) in 0.0260 seconds
+
+hbase(main):021:0> scan 'test', {RAW=>true, VERSIONS=>1000}
+ROW COLUMN+CELL
+ r1 column=e:c1, timestamp=14, value=value
+ r1 column=e:c1, timestamp=12, value=value
+1 row(s) in 0.0120 seconds
+\`\`\`
+
+Notice how delete cells are let go.
+
+Now let's run the same test only with \`KEEP_DELETED_CELLS\` set on the table (you can do table or per-column-family):
+
+\`\`\`bash
+hbase(main):005:0> create 'test', {NAME=>'e', VERSIONS=>2147483647, KEEP_DELETED_CELLS => true}
+0 row(s) in 0.2160 seconds
+
+=> Hbase::Table - test
+hbase(main):006:0> put 'test', 'r1', 'e:c1', 'value', 10
+0 row(s) in 0.1070 seconds
+
+hbase(main):007:0> put 'test', 'r1', 'e:c1', 'value', 12
+0 row(s) in 0.0140 seconds
+
+hbase(main):008:0> put 'test', 'r1', 'e:c1', 'value', 14
+0 row(s) in 0.0160 seconds
+
+hbase(main):009:0> delete 'test', 'r1', 'e:c1', 11
+0 row(s) in 0.0290 seconds
+
+hbase(main):010:0> scan 'test', {RAW=>true, VERSIONS=>1000}
+ROW COLUMN+CELL
+ r1 column=e:c1, timestamp=14, value=value
+ r1 column=e:c1, timestamp=12, value=value
+ r1 column=e:c1, timestamp=11, type=DeleteColumn
+ r1 column=e:c1, timestamp=10, value=value
+1 row(s) in 0.0550 seconds
+
+hbase(main):011:0> flush 'test'
+0 row(s) in 0.2780 seconds
+
+hbase(main):012:0> scan 'test', {RAW=>true, VERSIONS=>1000}
+ROW COLUMN+CELL
+ r1 column=e:c1, timestamp=14, value=value
+ r1 column=e:c1, timestamp=12, value=value
+ r1 column=e:c1, timestamp=11, type=DeleteColumn
+ r1 column=e:c1, timestamp=10, value=value
+1 row(s) in 0.0620 seconds
+
+hbase(main):013:0> major_compact 'test'
+0 row(s) in 0.0530 seconds
+
+hbase(main):014:0> scan 'test', {RAW=>true, VERSIONS=>1000}
+ROW COLUMN+CELL
+ r1 column=e:c1, timestamp=14, value=value
+ r1 column=e:c1, timestamp=12, value=value
+ r1 column=e:c1, timestamp=11, type=DeleteColumn
+ r1 column=e:c1, timestamp=10, value=value
+1 row(s) in 0.0650 seconds
+\`\`\`
+
+KEEP*DELETED\\_CELLS is to avoid removing Cells from HBase when the \\_only* reason to remove them is the delete marker. So with KEEP\\_DELETED\\_CELLS enabled deleted cells would get removed if either you write more versions than the configured max, or you have a TTL and Cells are in excess of the configured timeout, etc.
+
+## Secondary Indexes and Alternate Query Paths
+
+This section could also be titled "what if my table rowkey looks like *this* but I also want to query my table like *that*." A common example on the dist-list is where a row-key is of the format "user-timestamp" but there are reporting requirements on activity across users for certain time ranges. Thus, selecting by user is easy because it is in the lead position of the key, but time is not.
+
+There is no single answer on the best way to handle this because it depends on...
+
+* Number of users
+* Data size and data arrival rate
+* Flexibility of reporting requirements (e.g., completely ad-hoc date selection vs. pre-configured ranges)
+* Desired execution speed of query (e.g., 90 seconds may be reasonable to some for an ad-hoc report, whereas it may be too long for others)
+
+and solutions are also influenced by the size of the cluster and how much processing power you have to throw at the solution. Common techniques are in sub-sections below. This is a comprehensive, but not exhaustive, list of approaches.
+
+It should not be a surprise that secondary indexes require additional cluster space and processing. This is precisely what happens in an RDBMS because the act of creating an alternate index requires both space and processing cycles to update. RDBMS products are more advanced in this regard to handle alternative index management out of the box. However, HBase scales better at larger data volumes, so this is a feature trade-off.
+
+Pay attention to [Apache HBase Performance Tuning](/docs/performance) when implementing any of these approaches.
+
+Additionally, see the David Butler response in this dist-list thread [HBase, mail # user - Stargate+hbase](https://lists.apache.org/thread.html/b0ca33407f010d5b1be67a20d1708e8d8bb1e147770f2cb7182a2e37%401300972712%40%3Cuser.hbase.apache.org%3E)
+
+### Filter Query
+
+Depending on the case, it may be appropriate to use [Client Request Filters](/docs/architecture/client-request-filters). In this case, no secondary index is created. However, don't try a full-scan on a large table like this from an application (i.e., single-threaded client).
+
+### Periodic-Update Secondary Index
+
+A secondary index could be created in another table which is periodically updated via a MapReduce job. The job could be executed intra-day, but depending on load-strategy it could still potentially be out of sync with the main data table.
+
+See [mapreduce.example.readwrite](/docs/mapreduce#hbase-mapreduce-read-example) for more information.
+
+### Dual-Write Secondary Index
+
+Another strategy is to build the secondary index while publishing data to the cluster (e.g., write to data table, write to index table). If this is approach is taken after a data table already exists, then bootstrapping will be needed for the secondary index with a MapReduce job (see [secondary.indexes.periodic](/docs/regionserver-sizing#periodic-update-secondary-index)).
+
+### Summary Tables
+
+Where time-ranges are very wide (e.g., year-long report) and where the data is voluminous, summary tables are a common approach. These would be generated with MapReduce jobs into another table.
+
+See [mapreduce.example.summary](/docs/mapreduce#hbase-mapreduce-summary-to-hbase-example) for more information.
+
+### Coprocessor Secondary Index
+
+Coprocessors act like RDBMS triggers. These were added in 0.92. For more information, see [coprocessors](/docs/cp)
+
+## Constraints
+
+HBase currently supports 'constraints' in traditional (SQL) database parlance. The advised usage for Constraints is in enforcing business rules for attributes in the table (e.g. make sure values are in the range 1-10). Constraints could also be used to enforce referential integrity, but this is strongly discouraged as it will dramatically decrease the write throughput of the tables where integrity checking is enabled. Extensive documentation on using Constraints can be found at [Constrai [...]
+
+## Schema Design Case Studies
+
+The following will describe some typical data ingestion use-cases with HBase, and how the rowkey design and construction can be approached. Note: this is just an illustration of potential approaches, not an exhaustive list. Know your data, and know your processing requirements.
+
+It is highly recommended that you read the rest of the [HBase and Schema Design](/docs/schema-design) first, before reading these case studies.
+
+The following case studies are described:
+
+* Log Data / Timeseries Data
+* Log Data / Timeseries on Steroids
+* Customer/Order
+* Tall/Wide/Middle Schema Design
+* List Data
+
+### Case Study - Log Data and Timeseries Data
+
+Assume that the following data elements are being collected.
+
+* Hostname
+* Timestamp
+* Log event
+* Value/message
+
+We can store them in an HBase table called LOG\\_DATA, but what will the rowkey be? From these attributes the rowkey will be some combination of hostname, timestamp, and log-event - but what specifically?
+
+#### Timestamp In The Rowkey Lead Position
+
+The rowkey \`[timestamp][hostname][log-event]\` suffers from the monotonically increasing rowkey problem described in [Monotonically Increasing Row Keys/Timeseries Data](/docs/regionserver-sizing#monotonically-increasing-row-keystimeseries-data).
+
+There is another pattern frequently mentioned in the dist-lists about "bucketing" timestamps, by performing a mod operation on the timestamp. If time-oriented scans are important, this could be a useful approach. Attention must be paid to the number of buckets, because this will require the same number of scans to return results.
+
+\`\`\`java
+long bucket = timestamp % numBuckets;
+\`\`\`
+
+to construct:
+
+\`\`\`text
+[bucket][timestamp][hostname][log-event]
+\`\`\`
+
+As stated above, to select data for a particular timerange, a Scan will need to be performed for each bucket. 100 buckets, for example, will provide a wide distribution in the keyspace but it will require 100 Scans to obtain data for a single timestamp, so there are trade-offs.
+
+#### Host In The Rowkey Lead Position
+
+The rowkey \`[hostname][log-event][timestamp]\` is a candidate if there is a large-ish number of hosts to spread the writes and reads across the keyspace. This approach would be useful if scanning by hostname was a priority.
+
+#### Timestamp, or Reverse Timestamp?
+
+If the most important access path is to pull most recent events, then storing the timestamps as reverse-timestamps (e.g., \`timestamp = Long.MAX_VALUE – timestamp\`) will create the property of being able to do a Scan on \`[hostname][log-event]\` to obtain the most recently captured events.
+
+Neither approach is wrong, it just depends on what is most appropriate for the situation.
+
+<Callout type="info">
+ [HBASE-4811](https://issues.apache.org/jira/browse/HBASE-4811) implements an API to scan a table
+ or a range within a table in reverse, reducing the need to optimize your schema for forward or
+ reverse scanning. This feature is available in HBase 0.98 and later. See
+ [Scan.setReversed()](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Scan.html#setReversed\\(boolean\\))
+ for more information.
+</Callout>
+
+#### Variable Length or Fixed Length Rowkeys?
+
+It is critical to remember that rowkeys are stamped on every column in HBase. If the hostname is \`a\` and the event type is \`e1\` then the resulting rowkey would be quite small. However, what if the ingested hostname is \`myserver1.mycompany.com\` and the event type is \`com.package1.subpackage2.subsubpackage3.ImportantService\`?
+
+It might make sense to use some substitution in the rowkey. There are at least two approaches: hashed and numeric. In the Hostname In The Rowkey Lead Position example, it might look like this:
+
+Composite Rowkey With Hashes:
+
+* \\[MD5 hash of hostname] = 16 bytes
+* \\[MD5 hash of event-type] = 16 bytes
+* \\[timestamp] = 8 bytes
+
+Composite Rowkey With Numeric Substitution:
+
+For this approach another lookup table would be needed in addition to LOG\\_DATA, called LOG\\_TYPES. The rowkey of LOG\\_TYPES would be:
+
+* \`[type]\` (e.g., byte indicating hostname vs. event-type)
+* \`[bytes]\` variable length bytes for raw hostname or event-type.
+
+A column for this rowkey could be a long with an assigned number, which could be obtained by using an [HBase counter](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Table.html#incrementColumnValue\\(byte%5B%5D,byte%5B%5D,byte%5B%5D,long\\))
+
+So the resulting composite rowkey would be:
+
+* \\[substituted long for hostname] = 8 bytes
+* \\[substituted long for event type] = 8 bytes
+* \\[timestamp] = 8 bytes
+
+In either the Hash or Numeric substitution approach, the raw values for hostname and event-type can be stored as columns.
+
+### Case Study - Log Data and Timeseries Data on Steroids
+
+This effectively is the OpenTSDB approach. What OpenTSDB does is re-write data and pack rows into columns for certain time-periods. For a detailed explanation, see: [http://opentsdb.net/schema.html](http://opentsdb.net/schema.html), and [Lessons Learned from OpenTSDB](https://www.slideshare.net/cloudera/4-opentsdb-hbasecon) from HBaseCon2012.
+
+But this is how the general concept works: data is ingested, for example, in this manner...
+
+\`\`\`text
+[hostname][log-event][timestamp1]
+[hostname][log-event][timestamp2]
+[hostname][log-event][timestamp3]
+\`\`\`
+
+with separate rowkeys for each detailed event, but is re-written like this...
+
+\`\`\`text
+[hostname][log-event][timerange]
+\`\`\`
+
+and each of the above events are converted into columns stored with a time-offset relative to the beginning timerange (e.g., every 5 minutes). This is obviously a very advanced processing technique, but HBase makes this possible.
+
+### Case Study - Customer/Order
+
+Assume that HBase is used to store customer and order information. There are two core record-types being ingested: a Customer record type, and Order record type.
+
+The Customer record type would include all the things that you'd typically expect:
+
+* Customer number
+* Customer name
+* Address (e.g., city, state, zip)
+* Phone numbers, etc.
+
+The Order record type would include things like:
+
+* Customer number
+* Order number
+* Sales date
+* A series of nested objects for shipping locations and line-items (see [Order Object Design](/docs/regionserver-sizing#order-object-design) for details)
+
+Assuming that the combination of customer number and sales order uniquely identify an order, these two attributes will compose the rowkey, and specifically a composite key such as:
+
+\`\`\`text
+[customer number][order number]
+\`\`\`
+
+for an ORDER table. However, there are more design decisions to make: are the *raw* values the best choices for rowkeys?
+
+The same design questions in the Log Data use-case confront us here. What is the keyspace of the customer number, and what is the format (e.g., numeric? alphanumeric?) As it is advantageous to use fixed-length keys in HBase, as well as keys that can support a reasonable spread in the keyspace, similar options appear:
+
+Composite Rowkey With Hashes:
+
+* \\[MD5 of customer number] = 16 bytes
+* \\[MD5 of order number] = 16 bytes
+
+Composite Numeric/Hash Combo Rowkey:
+
+* \\[substituted long for customer number] = 8 bytes
+* \\[MD5 of order number] = 16 bytes
+
+#### Single Table? Multiple Tables?
+
+A traditional design approach would have separate tables for CUSTOMER and SALES. Another option is to pack multiple record types into a single table (e.g., CUSTOMER++).
+
+Customer Record Type Rowkey:
+
+* \\[customer-id]
+* \\[type] = type indicating \`1\` for customer record type
+
+Order Record Type Rowkey:
+
+* \\[customer-id]
+* \\[type] = type indicating \`2\` for order record type
+* \\[order]
+
+The advantage of this particular CUSTOMER++ approach is that organizes many different record-types by customer-id (e.g., a single scan could get you everything about that customer). The disadvantage is that it's not as easy to scan for a particular record-type.
+
+#### Order Object Design
+
+Now we need to address how to model the Order object. Assume that the class structure is as follows:
+
+#### Order \\[!toc]
+
+an Order can have multiple ShippingLocations
+
+#### LineItem \\[!toc]
+
+a ShippingLocation can have multiple LineItems
+
+there are multiple options on storing this data.
+
+##### Completely Normalized
+
+With this approach, there would be separate tables for ORDER, SHIPPING\\_LOCATION, and LINE\\_ITEM.
+
+The ORDER table's rowkey was described above: [schema.casestudies.custorder](/docs/regionserver-sizing#case-study---customerorder)
+
+The SHIPPING\\_LOCATION's composite rowkey would be something like this:
+
+* \`[order-rowkey]\`
+* \`[shipping location number]\` (e.g., 1st location, 2nd, etc.)
+
+The LINE\\_ITEM table's composite rowkey would be something like this:
+
+* \`[order-rowkey]\`
+* \`[shipping location number]\` (e.g., 1st location, 2nd, etc.)
+* \`[line item number]\` (e.g., 1st lineitem, 2nd, etc.)
+
+Such a normalized model is likely to be the approach with an RDBMS, but that's not your only option with HBase. The cons of such an approach is that to retrieve information about any Order, you will need:
+
+* Get on the ORDER table for the Order
+* Scan on the SHIPPING\\_LOCATION table for that order to get the ShippingLocation instances
+* Scan on the LINE\\_ITEM for each ShippingLocation
+
+granted, this is what an RDBMS would do under the covers anyway, but since there are no joins in HBase you're just more aware of this fact.
+
+#### Single Table With Record Types
+
+With this approach, there would exist a single table ORDER that would contain
+
+The Order rowkey was described above: [schema.casestudies.custorder](/docs/regionserver-sizing#case-study---customerorder)
+
+* \`[order-rowkey]\`
+* \`[ORDER record type]\`
+
+The ShippingLocation composite rowkey would be something like this:
+
+* \`[order-rowkey]\`
+* \`[SHIPPING record type]\`
+* \`[shipping location number]\` (e.g., 1st location, 2nd, etc.)
+
+The LineItem composite rowkey would be something like this:
+
+* \`[order-rowkey]\`
+* \`[LINE record type]\`
+* \`[shipping location number]\` (e.g., 1st location, 2nd, etc.)
+* \`[line item number]\` (e.g., 1st lineitem, 2nd, etc.)
+
+#### Denormalized
+
+A variant of the Single Table With Record Types approach is to denormalize and flatten some of the object hierarchy, such as collapsing the ShippingLocation attributes onto each LineItem instance.
+
+The LineItem composite rowkey would be something like this:
+
+* \`[order-rowkey]\`
+* \`[LINE record type]\`
+* \`[line item number]\` (e.g., 1st lineitem, 2nd, etc., care must be taken that there are unique across the entire order)
+
+and the LineItem columns would be something like this:
+
+* itemNumber
+* quantity
+* price
+* shipToLine1 (denormalized from ShippingLocation)
+* shipToLine2 (denormalized from ShippingLocation)
+* shipToCity (denormalized from ShippingLocation)
+* shipToState (denormalized from ShippingLocation)
+* shipToZip (denormalized from ShippingLocation)
+
+The pros of this approach include a less complex object hierarchy, but one of the cons is that updating gets more complicated in case any of this information changes.
+
+#### Object BLOB
+
+With this approach, the entire Order object graph is treated, in one way or another, as a BLOB. For example, the ORDER table's rowkey was described above: [schema.casestudies.custorder](/docs/regionserver-sizing#case-study---customerorder), and a single column called "order" would contain an object that could be deserialized that contained a container Order, ShippingLocations, and LineItems.
+
+There are many options here: JSON, XML, Java Serialization, Avro, Hadoop Writables, etc. All of them are variants of the same approach: encode the object graph to a byte-array. Care should be taken with this approach to ensure backward compatibility in case the object model changes such that older persisted structures can still be read back out of HBase.
+
+Pros are being able to manage complex object graphs with minimal I/O (e.g., a single HBase Get per Order in this example), but the cons include the aforementioned warning about backward compatibility of serialization, language dependencies of serialization (e.g., Java Serialization only works with Java clients), the fact that you have to deserialize the entire object to get any piece of information inside the BLOB, and the difficulty in getting frameworks like Hive to work with custom ob [...]
+
+### Case Study - "Tall/Wide/Middle" Schema Design Smackdown
+
+This section will describe additional schema design questions that appear on the dist-list, specifically about tall and wide tables. These are general guidelines and not laws - each application must consider its own needs.
+
+#### Rows vs. Versions
+
+A common question is whether one should prefer rows or HBase's built-in-versioning. The context is typically where there are "a lot" of versions of a row to be retained (e.g., where it is significantly above the HBase default of 1 max versions). The rows-approach would require storing a timestamp in some portion of the rowkey so that they would not overwrite with each successive update.
+
+Preference: Rows (generally speaking).
+
+#### Rows vs. Columns
+
+Another common question is whether one should prefer rows or columns. The context is typically in extreme cases of wide tables, such as having 1 row with 1 million attributes, or 1 million rows with 1 columns apiece.
+
+Preference: Rows (generally speaking). To be clear, this guideline is in the context is in extremely wide cases, not in the standard use-case where one needs to store a few dozen or hundred columns. But there is also a middle path between these two options, and that is "Rows as Columns."
+
+#### Rows as Columns
+
+The middle path between Rows vs. Columns is packing data that would be a separate row into columns, for certain rows. OpenTSDB is the best example of this case where a single row represents a defined time-range, and then discrete events are treated as columns. This approach is often more complex, and may require the additional complexity of re-writing your data, but has the advantage of being I/O efficient. For an overview of this approach, see [schema.casestudies.log-steroids](#schema.c [...]
+
+### Case Study - List Data
+
+The following is an exchange from the user dist-list regarding a fairly common question: how to handle per-user list data in Apache HBase.
+
+* QUESTION \\*
+
+We're looking at how to store a large amount of (per-user) list data in HBase, and we were trying to figure out what kind of access pattern made the most sense. One option is store the majority of the data in a key, so we could have something like:
+
+\`\`\`text
+<FixedWidthUserName><FixedWidthValueId1>:"" (no value)
+<FixedWidthUserName><FixedWidthValueId2>:"" (no value)
+<FixedWidthUserName><FixedWidthValueId3>:"" (no value)
+\`\`\`
+
+The other option we had was to do this entirely using:
+
+\`\`\`text
+<FixedWidthUserName><FixedWidthPageNum0>:<FixedWidthLength><FixedIdNextPageNum><ValueId1><ValueId2><ValueId3>...
+<FixedWidthUserName><FixedWidthPageNum1>:<FixedWidthLength><FixedIdNextPageNum><ValueId1><ValueId2><ValueId3>...
+\`\`\`
+
+where each row would contain multiple values. So in one case reading the first thirty values would be:
+
+\`\`\`bash
+scan { STARTROW => 'FixedWidthUsername' LIMIT => 30}
+\`\`\`
+
+And in the second case it would be
+
+\`\`\`bash
+get 'FixedWidthUserName\\x00\\x00\\x00\\x00'
+\`\`\`
+
+The general usage pattern would be to read only the first 30 values of these lists, with infrequent access reading deeper into the lists. Some users would have ⇐ 30 total values in these lists, and some users would have millions (i.e. power-law distribution)
+
+The single-value format seems like it would take up more space on HBase, but would offer some improved retrieval / pagination flexibility. Would there be any significant performance advantages to be able to paginate via gets vs paginating with scans?
+
+My initial understanding was that doing a scan should be faster if our paging size is unknown (and caching is set appropriately), but that gets should be faster if we'll always need the same page size. I've ended up hearing different people tell me opposite things about performance. I assume the page sizes would be relatively consistent, so for most use cases we could guarantee that we only wanted one page of data in the fixed-page-length case. I would also assume that we would have infr [...]
+
+Thanks for help / suggestions / follow-up questions.
+
+* ANSWER \\*
+
+If I understand you correctly, you're ultimately trying to store triples in the form "user, valueid, value", right? E.g., something like:
+
+\`\`\`text
+"user123, firstname, Paul",
+"user234, lastname, Smith"
+\`\`\`
+
+(But the usernames are fixed width, and the valueids are fixed width).
+
+And, your access pattern is along the lines of: "for user X, list the next 30 values, starting with valueid Y". Is that right? And these values should be returned sorted by valueid?
+
+The tl;dr version is that you should probably go with one row per user+value, and not build a complicated intra-row pagination scheme on your own unless you're really sure it is needed.
+
+Your two options mirror a common question people have when designing HBase schemas: should I go "tall" or "wide"? Your first schema is "tall": each row represents one value for one user, and so there are many rows in the table for each user; the row key is user + valueid, and there would be (presumably) a single column qualifier that means "the value". This is great if you want to scan over rows in sorted order by row key (thus my question above, about whether these ids are sorted correc [...]
+
+Your second option is "wide": you store a bunch of values in one row, using different qualifiers (where the qualifier is the valueid). The simple way to do that would be to just store ALL values for one user in a single row. I'm guessing you jumped to the "paginated" version because you're assuming that storing millions of columns in a single row would be bad for performance, which may or may not be true; as long as you're not trying to do too much in a single request, or do things like [...]
+
+Note that neither case fundamentally uses more disk space than the other; you're just "shifting" part of the identifying information for a value either to the left (into the row key, in option one) or to the right (into the column qualifiers in option 2). Under the covers, every key/value still stores the whole row key, and column family name. (If this is a bit confusing, take an hour and watch Lars George's excellent video about understanding HBase schema design: [http://www.youtube.com [...]
+
+A manually paginated version has lots more complexities, as you note, like having to keep track of how many things are in each page, re-shuffling if new values are inserted, etc. That seems significantly more complex. It might have some slight speed advantages (or disadvantages!) at extremely high throughput, and the only way to really know that would be to try it out. If you don't have time to build it both ways and compare, my advice would be to start with the simplest option (one row [...]
+
+## Operational and Performance Configuration Options
+
+### Tune HBase Server RPC Handling
+
+* Set \`hbase.regionserver.handler.count\` (in \`hbase-site.xml\`) to cores x spindles for concurrency.
+* Optionally, split the call queues into separate read and write queues for differentiated service. The parameter \`hbase.ipc.server.callqueue.handler.factor\` specifies the number of call queues:
+ * \`0\` means a single shared queue
+ * \`1\` means one queue for each handler.
+ * A value between \`0\` and \`1\` allocates the number of queues proportionally to the number of handlers. For instance, a value of \`.5\` shares one queue between each two handlers.
+* Use \`hbase.ipc.server.callqueue.read.ratio\` (\`hbase.ipc.server.callqueue.read.share\` in 0.98) to split the call queues into read and write queues:
+ * \`0.5\` means there will be the same number of read and write queues
+ * \`< 0.5\` for more write than read
+ * \`> 0.5\` for more read than write
+* Set \`hbase.ipc.server.callqueue.scan.ratio\` (HBase 1.0+) to split read call queues into small-read and long-read queues:
+ * 0.5 means that there will be the same number of short-read and long-read queues
+ * \`< 0.5\` for more short-read
+ * \`> 0.5\` for more long-read
+
+### Disable Nagle for RPC
+
+Disable Nagle's algorithm. Delayed ACKs can add up to \\~200ms to RPC round trip time. Set the following parameters:
+
+* In Hadoop's \`core-site.xml\`:
+ * \`ipc.server.tcpnodelay = true\`
+ * \`ipc.client.tcpnodelay = true\`
+* In HBase's \`hbase-site.xml\`:
+ * \`hbase.ipc.client.tcpnodelay = true\`
+ * \`hbase.ipc.server.tcpnodelay = true\`
+
+### Limit Server Failure Impact
+
+Detect regionserver failure as fast as reasonable. Set the following parameters:
+
+* In \`hbase-site.xml\`, set \`zookeeper.session.timeout\` to 30 seconds or less to bound failure detection (20-30 seconds is a good start).
+ * Note: Zookeeper clients negotiate a session timeout with the server during client init. Server enforces this timeout to be in the range \\[\`minSessionTimeout\`, \`maxSessionTimeout\`] and both these timeouts (measured in milliseconds) are configurable in Zookeeper service configuration. If not configured, these default to 2 \\* \`tickTime\` and 20 \\* \`tickTime\` respectively (\`tickTime\` is the basic time unit used by ZooKeeper, as measured in milliseconds. It is used to regulate [...]
+* Detect and avoid unhealthy or failed HDFS DataNodes: in \`hdfs-site.xml\` and \`hbase-site.xml\`, set the following parameters:
+ * \`dfs.namenode.avoid.read.stale.datanode = true\`
+ * \`dfs.namenode.avoid.write.stale.datanode = true\`
+
+### Optimize on the Server Side for Low Latency
+
+Skip the network for local blocks when the RegionServer goes to read from HDFS by exploiting HDFS's [Short-Circuit Local Reads](https://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-hdfs/ShortCircuitLocalReads.html) facility. Note how setup must be done both at the datanode and on the dfsclient ends of the conneciton — i.e. at the RegionServer and how both ends need to have loaded the hadoop native \`.so\` library. After configuring your hadoop setting *dfs.client.read.shortci [...]
+
+* In \`hbase-site.xml\`, set the following parameters:
+ * \`dfs.client.read.shortcircuit = true\`
+ * \`dfs.client.read.shortcircuit.skip.checksum = true\` so we don't double checksum (HBase does its own checksumming to save on i/os).
+ * \`dfs.domain.socket.path\` to match what was set for the datanodes.
+ * \`dfs.client.read.shortcircuit.buffer.size = 131072\` Important to avoid OOME — hbase has a default it uses if unset, see \`hbase.dfs.client.read.shortcircuit.buffer.size\`; its default is 131072.
+* Ensure data locality. In \`hbase-site.xml\`, set \`hbase.hstore.min.locality.to.skip.major.compact = 0.7\` (Meaning that 0.7 \\<= n \\<= 1)
+* Make sure DataNodes have enough handlers for block transfers. In \`hdfs-site.xml\`, set the following parameters:
+ * \`dfs.datanode.max.xcievers >= 8192\`
+ * \`dfs.datanode.handler.count =\` number of spindles
+
+Check the RegionServer logs after restart. You should only see complaint if misconfiguration. Otherwise, shortcircuit read operates quietly in background. It does not provide metrics so no optics on how effective it is but read latencies should show a marked improvement, especially if good data locality, lots of random reads, and dataset is larger than available cache.
+
+Other advanced configurations that you might play with, especially if shortcircuit functionality is complaining in the logs, include \`dfs.client.read.shortcircuit.streams.cache.size\` and \`dfs.client.socketcache.capacity\`. Documentation is sparse on these options. You'll have to read source code.
+
+RegionServer metric system exposes HDFS short circuit read metrics \`shortCircuitBytesRead\`. Other HDFS read metrics, including \`totalBytesRead\` (The total number of bytes read from HDFS), \`localBytesRead\` (The number of bytes read from the local HDFS DataNode), \`zeroCopyBytesRead\` (The number of bytes read through HDFS zero copy) are available and can be used to troubleshoot short-circuit read issues.
+
+For more on short-circuit reads, see Colin's old blog on rollout, [How Improved Short-Circuit Local Reads Bring Better Performance and Security to Hadoop](http://blog.cloudera.com/blog/2013/08/how-improved-short-circuit-local-reads-bring-better-performance-and-security-to-hadoop/). The [HDFS-347](https://issues.apache.org/jira/browse/HDFS-347) issue also makes for an interesting read showing the HDFS community at its best (caveat a few comments).
+
+### JVM Tuning
+
+#### Tune JVM GC for low collection latencies
+
+* Use the CMS collector: \`-XX:+UseConcMarkSweepGC\`
+* Keep eden space as small as possible to minimize average collection time. Example:
+ \`\`\`text
+ -XX:CMSInitiatingOccupancyFraction=70
+ \`\`\`
+* Optimize for low collection latency rather than throughput: \`-Xmn512m\`
+* Collect eden in parallel: \`-XX:+UseParNewGC\`
+* Avoid collection under pressure: \`-XX:+UseCMSInitiatingOccupancyOnly\`
+* Limit per request scanner result sizing so everything fits into survivor space but doesn't tenure. In \`hbase-site.xml\`, set \`hbase.client.scanner.max.result.size\` to 1/8th of eden space (with -\`Xmn512m\` this is \\~51MB )
+* Set \`max.result.size\` x \`handler.count\` less than survivor space
+
+#### OS-Level Tuning
+
+* Turn transparent huge pages (THP) off:
+ \`\`\`bash
+ echo never > /sys/kernel/mm/transparent_hugepage/enabled
+ echo never > /sys/kernel/mm/transparent_hugepage/defrag
+ \`\`\`
+* Set \`vm.swappiness = 0\`
+* Set \`vm.min_free_kbytes\` to at least 1GB (8GB on larger memory systems)
+* Disable NUMA zone reclaim with \`vm.zone_reclaim_mode = 0\`
+
+## Special Cases
+
+### For applications where failing quickly is better than waiting
+
+* In \`hbase-site.xml\` on the client side, set the following parameters:
+ * Set \`hbase.client.pause = 1000\`
+ * Set \`hbase.client.retries.number = 3\`
+ * If you want to ride over splits and region moves, increase \`hbase.client.retries.number\` substantially (>= 20)
+ * Set the RecoverableZookeeper retry count: \`zookeeper.recovery.retry = 1\` (no retry)
+* In \`hbase-site.xml\` on the server side, set the Zookeeper session timeout for detecting server failures: \`zookeeper.session.timeout\` ⇐ 30 seconds (20-30 is good).
+
+### For applications that can tolerate slightly out of date information
+
+**HBase timeline consistency (HBASE-10070)** With read replicas enabled, read-only copies of regions (replicas) are distributed over the cluster. One RegionServer services the default or primary replica, which is the only replica that can service writes. Other RegionServers serve the secondary replicas, follow the primary RegionServer, and only see committed updates. The secondary replicas are read-only, but can serve reads immediately while the primary is failing over, cutting read avai [...]
+
+* Deploy HBase 1.0.0 or later.
+* Enable timeline consistent replicas on the server side.
+* Use one of the following methods to set timeline consistency:
+ * Use \`ALTER SESSION SET CONSISTENCY = 'TIMELINE'\`
+ * Set the connection property \`Consistency\` to \`timeline\` in the JDBC connect string
+
+### More Information
+
+See the Performance section [perf.schema](/docs/case-studies#case-studies-schema-design) for more information about operational and performance schema design options, such as Bloom Filters, Table-configured regionsizes, compression, and blocksizes.
+
+***
+
+# HBase and MapReduce
+
+Apache MapReduce is a software framework used to analyze large amounts of data. It is provided by [Apache Hadoop](https://hadoop.apache.org/).
+MapReduce itself is out of the scope of this document.
+A good place to get started with MapReduce is [https://hadoop.apache.org/docs/r2.6.0/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html](https://hadoop.apache.org/docs/r2.6.0/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html).
+MapReduce version 2 (MR2)is now part of [YARN](https://hadoop.apache.org/docs/r2.6.0/hadoop-yarn/hadoop-yarn-site/).
+
+This chapter discusses specific configuration steps you need to take to use MapReduce on data within HBase.
+In addition, it discusses other interactions and issues between HBase and MapReduce jobs.
+
+<Callout type="info" title="mapred and mapreduce">
+ There are two mapreduce packages in HBase as in MapReduce itself: *org.apache.hadoop.hbase.mapred*
+ and *org.apache.hadoop.hbase.mapreduce*. The former does old-style API and the latter the new
+ mode. The latter has more facility though you can usually find an equivalent in the older package.
+ Pick the package that goes with your MapReduce deploy. When in doubt or starting over, pick
+ *org.apache.hadoop.hbase.mapreduce*. In the notes below, we refer to *o.a.h.h.mapreduce* but
+ replace with *o.a.h.h.mapred* if that is what you are using.
+</Callout>
+
+## HBase, MapReduce, and the CLASSPATH
+
+By default, MapReduce jobs deployed to a MapReduce cluster do not have access to
+either the HBase configuration under \`$HBASE_CONF_DIR\` or the HBase classes.
+
+To give the MapReduce jobs the access they need, you could add \\_hbase-site.xml\\_to \\_\\$HADOOP*HOME/conf* and add HBase jars to the *\\$HADOOP\\_HOME/lib* directory.
+You would then need to copy these changes across your cluster. Or you could edit *\\$HADOOP\\_HOME/conf/hadoop-env.sh* and add hbase dependencies to the \`HADOOP_CLASSPATH\` variable.
+Neither of these approaches is recommended because it will pollute your Hadoop install with HBase references.
+It also requires you restart the Hadoop cluster before Hadoop can use the HBase data.
+
+The recommended approach is to let HBase add its dependency jars and use \`HADOOP_CLASSPATH\` or \`-libjars\`.
+
+Since HBase \`0.90.x\`, HBase adds its dependency JARs to the job configuration itself.
+The dependencies only need to be available on the local \`CLASSPATH\` and from here they'll be picked
+up and bundled into the fat job jar deployed to the MapReduce cluster. A basic trick just passes
+the full hbase classpath — all hbase and dependent jars as well as configurations — to the mapreduce
+job runner letting hbase utility pick out from the full-on classpath what it needs adding them to the
+MapReduce job configuration (See the source at \`TableMapReduceUtil#addDependencyJars(org.apache.hadoop.mapreduce.Job)\` for how this is done).
+
+The following example runs the bundled HBase [RowCounter](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/RowCounter.html) MapReduce job against a table named \`usertable\`.
+It sets into \`HADOOP_CLASSPATH\` the jars hbase needs to run in an MapReduce context (including configuration files such as hbase-site.xml).
+Be sure to use the correct version of the HBase JAR for your system; replace the VERSION string in the below command line w/ the version of
+your local hbase install. The backticks (\\\`\\\`\\\`) cause the shell to execute the sub-commands, setting the output of \`hbase classpath\` into \`HADOOP_CLASSPATH\`.
+This example assumes you use a BASH-compatible shell.
+
+\`\`\`bash
+$ HADOOP_CLASSPATH=\`\${HBASE_HOME}/bin/hbase classpath\` \\
+ \${HADOOP_HOME}/bin/hadoop jar \${HBASE_HOME}/lib/hbase-mapreduce-VERSION.jar \\
+ org.apache.hadoop.hbase.mapreduce.RowCounter usertable
+\`\`\`
+
+The above command will launch a row counting mapreduce job against the hbase cluster that is pointed to by your local configuration on a cluster that the hadoop configs are pointing to.
+
+The main for the \`hbase-mapreduce.jar\` is a Driver that lists a few basic mapreduce tasks that ship with hbase.
+For example, presuming your install is hbase \`2.0.0-SNAPSHOT\`:
+
+\`\`\`bash
+$ HADOOP_CLASSPATH=\`\${HBASE_HOME}/bin/hbase classpath\` \\
+ \${HADOOP_HOME}/bin/hadoop jar \${HBASE_HOME}/lib/hbase-mapreduce-2.0.0-SNAPSHOT.jar
+An example program must be given as the first argument.
+Valid program names are:
+ CellCounter: Count cells in HBase table.
+ WALPlayer: Replay WAL files.
+ completebulkload: Complete a bulk data load.
+ copytable: Export a table from local cluster to peer cluster.
+ export: Write table data to HDFS.
+ exportsnapshot: Export the specific snapshot to a given FileSystem.
+ import: Import data written by Export.
+ importtsv: Import data in TSV format.
+ rowcounter: Count rows in HBase table.
+ verifyrep: Compare the data from tables in two different clusters. WARNING: It doesn't work for incrementColumnValues'd cells since the timestamp is changed after being appended to the log.
+\`\`\`
+
+You can use the above listed shortnames for mapreduce jobs as in the below re-run of the row counter job (again, presuming your install is hbase \`2.0.0-SNAPSHOT\`):
+
+\`\`\`bash
+$ HADOOP_CLASSPATH=\`\${HBASE_HOME}/bin/hbase classpath\` \\
+ \${HADOOP_HOME}/bin/hadoop jar \${HBASE_HOME}/lib/hbase-mapreduce-2.0.0-SNAPSHOT.jar \\
+ rowcounter usertable
+\`\`\`
+
+You might find the more selective \`hbase mapredcp\` tool output of interest; it lists the minimum set of jars needed
+to run a basic mapreduce job against an hbase install. It does not include configuration. You'll probably need to add
+these if you want your MapReduce job to find the target cluster. You'll probably have to also add pointers to extra jars
+once you start to do anything of substance. Just specify the extras by passing the system propery \`-Dtmpjars\` when
+you run \`hbase mapredcp\`.
+
+For jobs that do not package their dependencies or call \`TableMapReduceUtil#addDependencyJars\`, the following command structure is necessary:
+
+\`\`\`bash
+$ HADOOP_CLASSPATH=\`\${HBASE_HOME}/bin/hbase mapredcp\`:\${HBASE_HOME}/conf hadoop jar MyApp.jar MyJobMainClass -libjars $(\${HBASE_HOME}/bin/hbase mapredcp | tr ':' ',') ...
+\`\`\`
+
+<Callout type="info">
+ The example may not work if you are running HBase from its build directory rather than an installed location.
+ You may see an error like the following:
+
+ \`\`\`text
+ java.lang.RuntimeException: java.lang.ClassNotFoundException: org.apache.hadoop.hbase.mapreduce.RowCounter$RowCounterMapper
+ \`\`\`
+
+ If this occurs, try modifying the command as follows, so that it uses the HBase JARs from the *target/* directory within the build environment.
+
+ \`\`\`bash
+ $ HADOOP_CLASSPATH=\${HBASE_BUILD_HOME}/hbase-mapreduce/target/hbase-mapreduce-VERSION-SNAPSHOT.jar:\`\${HBASE_BUILD_HOME}/bin/hbase classpath\` \${HADOOP_HOME}/bin/hadoop jar \${HBASE_BUILD_HOME}/hbase-mapreduce/target/hbase-mapreduce-VERSION-SNAPSHOT.jar rowcounter usertable
+ \`\`\`
+</Callout>
+
+<Callout type="warn" title="Notice to MapReduce users of HBase between 0.96.1 and 0.98.4">
+ Some MapReduce jobs that use HBase fail to launch.
+ The symptom is an exception similar to the following:
+
+ \`\`\`text
+ Exception in thread "main" java.lang.IllegalAccessError: class
+ com.google.protobuf.ZeroCopyLiteralByteString cannot access its superclass
+ com.google.protobuf.LiteralByteString
+ at java.lang.ClassLoader.defineClass1(Native Method)
+ at java.lang.ClassLoader.defineClass(ClassLoader.java:792)
+ at java.security.SecureClassLoader.defineClass(SecureClassLoader.java:142)
+ at java.net.URLClassLoader.defineClass(URLClassLoader.java:449)
+ at java.net.URLClassLoader.access$100(URLClassLoader.java:71)
+ at java.net.URLClassLoader$1.run(URLClassLoader.java:361)
+ at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
+ at java.security.AccessController.doPrivileged(Native Method)
+ at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
+ at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
+ at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
+ at
+ org.apache.hadoop.hbase.protobuf.ProtobufUtil.toScan(ProtobufUtil.java:818)
+ at
+ org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil.convertScanToString(TableMapReduceUtil.java:433)
+ at
+ org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil.initTableMapperJob(TableMapReduceUtil.java:186)
+ at
+ org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil.initTableMapperJob(TableMapReduceUtil.java:147)
+ at
+ org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil.initTableMapperJob(TableMapReduceUtil.java:270)
+ at
+ org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil.initTableMapperJob(TableMapReduceUtil.java:100)
+ ...
+ \`\`\`
+
+ This is caused by an optimization introduced in [HBASE-9867](https://issues.apache.org/jira/browse/HBASE-9867) that inadvertently introduced a classloader dependency.
+
+ This affects both jobs using the \`-libjars\` option and "fat jar," those which package their runtime dependencies in a nested \`lib\` folder.
+
+ In order to satisfy the new classloader requirements, \`hbase-protocol.jar\` must be included in Hadoop's classpath.
+ See [HBase, MapReduce, and the CLASSPATH](/docs/mapreduce#hbase-mapreduce-and-the-classpath) for current recommendations for resolving classpath errors.
+ The following is included for historical purposes.
+
+ This can be resolved system-wide by including a reference to the \`hbase-protocol.jar\` in Hadoop's lib directory, via a symlink or by copying the jar into the new location.
+
+ This can also be achieved on a per-job launch basis by including it in the \`HADOOP_CLASSPATH\` environment variable at job submission time.
+ When launching jobs that package their dependencies, all three of the following job launching commands satisfy this requirement:
+
+ \`\`\`bash
+ $ HADOOP_CLASSPATH=/path/to/hbase-protocol.jar:/path/to/hbase/conf hadoop jar MyJob.jar MyJobMainClass
+ $ HADOOP_CLASSPATH=$(hbase mapredcp):/path/to/hbase/conf hadoop jar MyJob.jar MyJobMainClass
+ $ HADOOP_CLASSPATH=$(hbase classpath) hadoop jar MyJob.jar MyJobMainClass
+ \`\`\`
+
+ For jars that do not package their dependencies, the following command structure is necessary:
+
+ \`\`\`bash
+ $ HADOOP_CLASSPATH=$(hbase mapredcp):/etc/hbase/conf hadoop jar MyApp.jar MyJobMainClass -libjars $(hbase mapredcp | tr ':' ',') ...
+ \`\`\`
+
+ See also [HBASE-10304](https://issues.apache.org/jira/browse/HBASE-10304) for further discussion of this issue.
+</Callout>
+
+## MapReduce Scan Caching
+
+TableMapReduceUtil now restores the option to set scanner caching (the number of rows which are cached before returning the result to the client) on the Scan object that is passed in.
+This functionality was lost due to a bug in HBase 0.95 ([HBASE-11558](https://issues.apache.org/jira/browse/HBASE-11558)), which is fixed for HBase 0.98.5 and 0.96.3.
+The priority order for choosing the scanner caching is as follows:
+
+1. Caching settings which are set on the scan object.
+2. Caching settings which are specified via the configuration option \`hbase.client.scanner.caching\`, which can either be set manually in *hbase-site.xml* or via the helper method \`TableMapReduceUtil.setScannerCaching()\`.
+3. The default value \`HConstants.DEFAULT_HBASE_CLIENT_SCANNER_CACHING\`, which is set to \`100\`.
+
+Optimizing the caching settings is a balance between the time the client waits for a result and the number of sets of results the client needs to receive.
+If the caching setting is too large, the client could end up waiting for a long time or the request could even time out.
+If the setting is too small, the scan needs to return results in several pieces.
+If you think of the scan as a shovel, a bigger cache setting is analogous to a bigger shovel, and a smaller cache setting is equivalent to more shoveling in order to fill the bucket.
+
+The list of priorities mentioned above allows you to set a reasonable default, and override it for specific operations.
+
+See the API documentation for [Scan](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/client/Scan.html) for more details.
+
+## Bundled HBase MapReduce Jobs
+
+The HBase JAR also serves as a Driver for some bundled MapReduce jobs.
+To learn about the bundled MapReduce jobs, run the following command.
+
+\`\`\`bash
+$ \${HADOOP_HOME}/bin/hadoop jar \${HBASE_HOME}/hbase-mapreduce-VERSION.jar
+An example program must be given as the first argument.
+Valid program names are:
+ copytable: Export a table from local cluster to peer cluster
+ completebulkload: Complete a bulk data load.
+ export: Write table data to HDFS.
+ import: Import data written by Export.
+ importtsv: Import data in TSV format.
+ rowcounter: Count rows in HBase table
+\`\`\`
+
+Each of the valid program names are bundled MapReduce jobs.
+To run one of the jobs, model your command after the following example.
+
+\`\`\`bash
+$ \${HADOOP_HOME}/bin/hadoop jar \${HBASE_HOME}/hbase-mapreduce-VERSION.jar rowcounter myTable
+\`\`\`
+
+## HBase as a MapReduce Job Data Source and Data Sink
+
+HBase can be used as a data source, [TableInputFormat](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/TableInputFormat.html), and data sink, [TableOutputFormat](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/TableOutputFormat.html) or [MultiTableOutputFormat](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/MultiTableOutputFormat.html), for MapReduce jobs.
+Writing MapReduce jobs that read or write HBase, it is advisable to subclass [TableMapper](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/TableMapper.html) and/or [TableReducer](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/TableReducer.html).
+See the do-nothing pass-through classes [IdentityTableMapper](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/IdentityTableMapper.html) and [IdentityTableReducer](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/IdentityTableReducer.html) for basic usage.
+For a more involved example, see [RowCounter](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/RowCounter.html) or review the \`org.apache.hadoop.hbase.mapreduce.TestTableMapReduce\` unit test.
+
+If you run MapReduce jobs that use HBase as source or sink, need to specify source and sink table and column names in your configuration.
+
+When you read from HBase, the \`TableInputFormat\` requests the list of regions from HBase and makes a map, which is either a \`map-per-region\` or \`mapreduce.job.maps\` map, whichever is smaller.
+If your job only has two maps, raise \`mapreduce.job.maps\` to a number greater than the number of regions.
+Maps will run on the adjacent TaskTracker/NodeManager if you are running a TaskTracer/NodeManager and RegionServer per node.
+When writing to HBase, it may make sense to avoid the Reduce step and write back into HBase from within your map.
+This approach works when your job does not need the sort and collation that MapReduce does on the map-emitted data.
+On insert, HBase 'sorts' so there is no point double-sorting (and shuffling data around your MapReduce cluster) unless you need to.
+If you do not need the Reduce, your map might emit counts of records processed for reporting at the end of the job, or set the number of Reduces to zero and use TableOutputFormat.
+If running the Reduce step makes sense in your case, you should typically use multiple reducers so that load is spread across the HBase cluster.
+
+A new HBase partitioner, the [HRegionPartitioner](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/HRegionPartitioner.html), can run as many reducers the number of existing regions.
+The HRegionPartitioner is suitable when your table is large and your upload will not greatly alter the number of existing regions upon completion.
+Otherwise use the default partitioner.
+
+## Writing HFiles Directly During Bulk Import
+
+If you are importing into a new table, you can bypass the HBase API and write your content directly to the filesystem, formatted into HBase data files (HFiles). Your import will run faster, perhaps an order of magnitude faster.
+For more on how this mechanism works, see [Bulk Load](/docs/architecture/bulk-loading).
+
+## RowCounter Example
+
+The included [RowCounter](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/RowCounter.html) MapReduce job uses \`TableInputFormat\` and does a count of all rows in the specified table.
+To run it, use the following command:
+
+\`\`\`bash
+$ ./bin/hadoop jar hbase-X.X.X.jar
+\`\`\`
+
+This will invoke the HBase MapReduce Driver class.
+Select \`rowcounter\` from the choice of jobs offered.
+This will print rowcounter usage advice to standard output.
+Specify the tablename, column to count, and output directory.
+If you have classpath errors, see [HBase, MapReduce, and the CLASSPATH](/docs/mapreduce#hbase-mapreduce-and-the-classpath).
+
+## Map-Task Splitting
+
+### The Default HBase MapReduce Splitter
+
+When [TableInputFormat](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/TableInputFormat.html) is used to source an HBase table in a MapReduce job, its splitter will make a map task for each region of the table.
+Thus, if there are 100 regions in the table, there will be 100 map-tasks for the job - regardless of how many column families are selected in the Scan.
+
+### Custom Splitters
+
+For those interested in implementing custom splitters, see the method \`getSplits\` in [TableInputFormatBase](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/TableInputFormatBase.html).
+That is where the logic for map-task assignment resides.
+
+## HBase MapReduce Examples
+
+### HBase MapReduce Read Example
+
+The following is an example of using HBase as a MapReduce source in read-only manner.
+Specifically, there is a Mapper instance but no Reducer, and nothing is being emitted from the Mapper.
+The job would be defined as follows...
+
+\`\`\`java
+Configuration config = HBaseConfiguration.create();
+Job job = new Job(config, "ExampleRead");
+job.setJarByClass(MyReadJob.class); // class that contains mapper
+
+Scan scan = new Scan();
+scan.setCaching(500); // 1 is the default in Scan, which will be bad for MapReduce jobs
+scan.setCacheBlocks(false); // don't set to true for MR jobs
+// set other scan attrs
+...
+
+TableMapReduceUtil.initTableMapperJob(
+ tableName, // input HBase table name
+ scan, // Scan instance to control CF and attribute selection
+ MyMapper.class, // mapper
+ null, // mapper output key
+ null, // mapper output value
+ job);
+job.setOutputFormatClass(NullOutputFormat.class); // because we aren't emitting anything from mapper
+
+boolean b = job.waitForCompletion(true);
+if (!b) {
+ throw new IOException("error with job!");
+}
+\`\`\`
+
+...and the mapper instance would extend [TableMapper](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/TableMapper.html)...
+
+\`\`\`java
+public static class MyMapper extends TableMapper<Text, Text> {
+
+ public void map(ImmutableBytesWritable row, Result value, Context context) throws InterruptedException, IOException {
+ // process data for the row from the Result instance.
+ }
+}
+\`\`\`
+
+### HBase MapReduce Read/Write Example
+
+The following is an example of using HBase both as a source and as a sink with MapReduce.
+This example will simply copy data from one table to another.
+
+\`\`\`java
+Configuration config = HBaseConfiguration.create();
+Job job = new Job(config,"ExampleReadWrite");
+job.setJarByClass(MyReadWriteJob.class); // class that contains mapper
+
+Scan scan = new Scan();
+scan.setCaching(500); // 1 is the default in Scan, which will be bad for MapReduce jobs
+scan.setCacheBlocks(false); // don't set to true for MR jobs
+// set other scan attrs
+
+TableMapReduceUtil.initTableMapperJob(
+ sourceTable, // input table
+ scan, // Scan instance to control CF and attribute selection
+ MyMapper.class, // mapper class
+ null, // mapper output key
+ null, // mapper output value
+ job);
+TableMapReduceUtil.initTableReducerJob(
+ targetTable, // output table
+ null, // reducer class
+ job);
+job.setNumReduceTasks(0);
+
+boolean b = job.waitForCompletion(true);
+if (!b) {
+ throw new IOException("error with job!");
+}
+\`\`\`
+
+An explanation is required of what \`TableMapReduceUtil\` is doing, especially with the reducer. [TableOutputFormat](https://hbase.apache.org/devapidocs/org/apache/hadoop/hbase/mapreduce/TableOutputFormat.html) is being used as the outputFormat class, and several parameters are being set on the config (e.g., \`TableOutputFormat.OUTPUT_TABLE\`), as well as setting the reducer output key to \`ImmutableBytesWritable\` and reducer value to \`Writable\`.
+These could be set by the programmer on the job and conf, but \`TableMapReduceUtil\` tries to make things easier.
+
+The following is the example mapper, which will create a \`Put\` and matching the input \`Result\` and emit it.
+Note: this is what the CopyTable utility does.
+
+\`\`\`java
+public static class MyMapper extends TableMapper<ImmutableBytesWritable, Put> {
+
+ public void map(ImmutableBytesWritable row, Result value, Context context) throws IOException, InterruptedException {
+ // this example is just copying the data from the source table...
+ context.write(row, resultToPut(row,value));
+ }
+
+ private static Put resultToPut(ImmutableBytesWritable key, Result result) throws IOException {
+ Put put = new Put(key.get());
+ for (Cell cell : result.listCells()) {
+ put.add(cell);
+ }
+ return put;
+ }
+}
+\`\`\`
+
+There isn't actually a reducer step, so \`TableOutputFormat\` takes care of sending the \`Put\` to the target table.
+
+This is just an example, developers could choose not to use \`TableOutputFormat\` and connect to the target table themselves.
+
+### HBase MapReduce Read/Write Example With Multi-Table Output
+
+TODO: example for \`MultiTableOutputFormat\`.
+
+### HBase MapReduce Summary to HBase Example
+
+The following example uses HBase as a MapReduce source and sink with a summarization step.
+This example will count the number of distinct instances of a value in a table and write those summarized counts in another table.
+
+\`\`\`java
+Configuration config = HBaseConfiguration.create();
+Job job = new Job(config,"ExampleSummary");
+job.setJarByClass(MySummaryJob.class); // class that contains mapper and reducer
+
+Scan scan = new Scan();
+scan.setCaching(500); // 1 is the default in Scan, which will be bad for MapReduce jobs
+scan.setCacheBlocks(false); // don't set to true for MR jobs
+// set other scan attrs
+
+TableMapReduceUtil.initTableMapperJob(
+ sourceTable, // input table
+ scan, // Scan instance to control CF and attribute selection
+ MyMapper.class, // mapper class
+ Text.class, // mapper output key
+ IntWritable.class, // mapper output value
+ job);
+TableMapReduceUtil.initTableReducerJob(
+ targetTable, // output table
+ MyTableReducer.class, // reducer class
+ job);
+job.setNumReduceTasks(1); // at least one, adjust as required
+
+boolean b = job.waitForCompletion(true);
+if (!b) {
+ throw new IOException("error with job!");
+}
+\`\`\`
+
+In this example mapper a column with a String-value is chosen as the value to summarize upon.
+This value is used as the key to emit from the mapper, and an \`IntWritable\` represents an instance counter.
+
+\`\`\`java
+public static class MyMapper extends TableMapper<Text, IntWritable> {
+ public static final byte[] CF = "cf".getBytes();
+ public static final byte[] ATTR1 = "attr1".getBytes();
+
+ private final IntWritable ONE = new IntWritable(1);
+ private Text text = new Text();
+
+ public void map(ImmutableBytesWritable row, Result value, Context context) throws IOException, InterruptedException {
+ String val = new String(value.getValue(CF, ATTR1));
+ text.set(val); // we can only emit Writables...
+ context.write(text, ONE);
+ }
+}
+\`\`\`
+
+In the reducer, the "ones" are counted (just like any other MR example that does this), and then emits a \`Put\`.
+
+\`\`\`java
+public static class MyTableReducer extends TableReducer<Text, IntWritable, ImmutableBytesWritable> {
+ public static final byte[] CF = "cf".getBytes();
+ public static final byte[] COUNT = "count".getBytes();
+
+ public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
+ int i = 0;
+ for (IntWritable val : values) {
+ i += val.get();
+ }
+ Put put = new Put(Bytes.toBytes(key.toString()));
+ put.add(CF, COUNT, Bytes.toBytes(i));
+
+ context.write(null, put);
+ }
+}
+\`\`\`
+
+### HBase MapReduce Summary to File Example
+
+This very similar to the summary example above, with exception that this is using HBase as a MapReduce source but HDFS as the sink.
+The differences are in the job setup and in the reducer.
+The mapper remains the same.
+
+\`\`\`java
+Configuration config = HBaseConfiguration.create();
+Job job = new Job(config,"ExampleSummaryToFile");
+job.setJarByClass(MySummaryFileJob.class); // class that contains mapper and reducer
+
+Scan scan = new Scan();
+scan.setCaching(500); // 1 is the default in Scan, which will be bad for MapReduce jobs
+scan.setCacheBlocks(false); // don't set to true for MR jobs
+// set other scan attrs
+
+TableMapReduceUtil.initTableMapperJob(
+ sourceTable, // input table
+ scan, // Scan instance to control CF and attribute selection
+ MyMapper.class, // mapper class
+ Text.class, // mapper output key
+ IntWritable.class, // mapper output value
+ job);
+job.setReducerClass(MyReducer.class); // reducer class
+job.setNumReduceTasks(1); // at least one, adjust as required
+FileOutputFormat.setOutputPath(job, new Path("/tmp/mr/mySummaryFile")); // adjust directories as required
+
+boolean b = job.waitForCompletion(true);
+if (!b) {
+ throw new IOException("error with job!");
+}
+\`\`\`
+
+As stated above, the previous Mapper can run unchanged with this example.
+As for the Reducer, it is a "generic" Reducer instead of extending TableMapper and emitting Puts.
+
+\`\`\`java
+public static class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
+
+ public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
+ int i = 0;
+ for (IntWritable val : values) {
+ i += val.get();
+ }
+ context.write(key, new IntWritable(i));
+ }
+}
+\`\`\`
+
+### HBase MapReduce Summary to HBase Without Reducer
+
+It is also possible to perform summaries without a reducer - if you use HBase as the reducer.
+
+An HBase target table would need to exist for the job summary.
+The Table method \`incrementColumnValue\` would be used to atomically increment values.
+From a performance perspective, it might make sense to keep a Map of values with their values to be incremented for each map-task, and make one update per key at during the \`cleanup\` method of the mapper.
+However, your mileage may vary depending on the number of rows to be processed and unique keys.
+
+In the end, the summary results are in HBase.
+
+### HBase MapReduce Summary to RDBMS
+
+Sometimes it is more appropriate to generate summaries to an RDBMS.
+For these cases, it is possible to generate summaries directly to an RDBMS via a custom reducer.
+The \`setup\` method can connect to an RDBMS (the connection information can be passed via custom parameters in the context) and the cleanup method can close the connection.
+
+It is critical to understand that number of reducers for the job affects the summarization implementation, and you'll have to design this into your reducer.
+Specifically, whether it is designed to run as a singleton (one reducer) or multiple reducers.
+Neither is right or wrong, it depends on your use-case.
+Recognize that the more reducers that are assigned to the job, the more simultaneous connections to the RDBMS will be created - this will scale, but only to a point.
+
+\`\`\`java
+public static class MyRdbmsReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
+
+ private Connection c = null;
+
+ public void setup(Context context) {
+ // create DB connection...
+ }
+
+ public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
+ // do summarization
+ // in this example the keys are Text, but this is just an example
+ }
+
+ public void cleanup(Context context) {
+ // close db connection
+ }
+
+}
+\`\`\`
+
+In the end, the summary results are written to your RDBMS table/s.
+
+## Accessing Other HBase Tables in a MapReduce Job
+
+Although the framework currently allows one HBase table as input to a MapReduce job, other HBase tables can be accessed as lookup tables, etc., in a MapReduce job via creating an Table instance in the setup method of the Mapper.
+
+\`\`\`java
+public class MyMapper extends TableMapper<Text, LongWritable> {
+ private Table myOtherTable;
+
+ public void setup(Context context) {
+ // In here create a Connection to the cluster and save it or use the Connection
+ // from the existing table
+ myOtherTable = connection.getTable("myOtherTable");
+ }
+
+ public void map(ImmutableBytesWritable row, Result value, Context context) throws IOException, InterruptedException {
+ // process Result...
+ // use 'myOtherTable' for lookups
+ }
+\`\`\`
+
+## Speculative Execution
+
+It is generally advisable to turn off speculative execution for MapReduce jobs that use HBase as a source.
+This can either be done on a per-Job basis through properties, or on the entire cluster.
+Especially for longer running jobs, speculative execution will create duplicate map-tasks which will double-write your data to HBase; this is probably not what you want.
+
+See [Speculative Execution](/docs/configuration/important#configuration-important-recommended-configurations-speculative-execution) for more information.
+
+***
+
+# Security
+
+<Callout type="error">
+ **Reporting Security Bugs**
+
+ HBase adheres to the Apache Software Foundation's policy on reported vulnerabilities, available at [http://apache.org/security/](http://apache.org/security/).
+
+ If you wish to send an encrypted report, you can use the GPG details provided for the general ASF security list. This will likely increase the response time to your report.
+</Callout>
+
+<Callout type="info">
+ To protect existing HBase installations from exploitation, please **do not** use JIRA to report
+ security-related bugs. Instead, send your report to the mailing list \`private@hbase.apache.org\`,
+ which allows anyone to send messages, but restricts who can read them. Someone on that list will
+ contact you to follow up on your report.
+</Callout>
+
+<Callout type="info">
+ **Security Model**
+
+ Before reporting a security issue, please review the [Apache HBase Security Model](/security-model) page, which describes the project's security assumptions, trust boundaries, and what constitutes a valid vulnerability report.
+</Callout>
+
+## Web UI Security
+
+## Using Secure HTTP (HTTPS) for the Web UI
+
+A default HBase install uses insecure HTTP connections for Web UIs for the master and region servers. To enable secure HTTP (HTTPS) connections instead, set \`hbase.ssl.enabled\` to \`true\` in *hbase-site.xml*(Please prepare SSL certificate and ssl configuration file in advance). This does not change the port used by the Web UI. To change the port for the web UI for a given HBase component, configure that port's setting in hbase-site.xml. These settings are:
+
+* \`hbase.master.info.port\`
+* \`hbase.regionserver.info.port\`
+
+<Callout type="info">
+ If you enable secure HTTP, clients should connect to HBase using the \`https://\` URL. Clients using the \`http://\` URL will receive an HTTP response of \`200\`, but will not receive any data. The following exception is logged:
+
+ \`\`\`text
+ javax.net.ssl.SSLException: Unrecognized SSL message, plaintext connection?
+ \`\`\`
+
+ This is because the same port is used for HTTP and HTTPS.
+
+ HBase uses Jetty for the Web UI. Without modifying Jetty itself, it does not seem possible to configure Jetty to redirect one port to another on the same host. See Nick Dimiduk's contribution on this [Stack Overflow](http://stackoverflow.com/questions/20611815/redirect-from-http-to-https-in-jetty) thread for more information. If you know how to fix this without opening a second port for HTTPS, patches are appreciated.
+</Callout>
+
+## Disable cache in HBase UI
+
+Set the following configuration in hbase-site to set max age to zero and disable cache for the web UI:
+
+\`\`\`xml
+<property>
+ <name>hbase.http.filter.no-store.enable</name>
+ <value>true</value>
+</property>
+\`\`\`
+
+## Using SPNEGO for Kerberos authentication with Web UIs
+
+Kerberos-authentication to HBase Web UIs can be enabled via configuring SPNEGO with the \`hbase.security.authentication.ui\` property in *hbase-site.xml*. Enabling this authentication requires that HBase is also configured to use Kerberos authentication for RPCs (e.g \`hbase.security.authentication\` = \`kerberos\`).
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication.ui</name>
+ <value>kerberos</value>
+ <description>Controls what kind of authentication should be used for the HBase web UIs.</description>
+</property>
+<property>
+ <name>hbase.security.authentication</name>
+ <value>kerberos</value>
+ <description>The Kerberos keytab file to use for SPNEGO authentication by the web server.</description>
+</property>
+\`\`\`
+
+A number of properties exist to configure SPNEGO authentication for the web server:
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication.spnego.kerberos.principal</name>
+ <value>HTTP/_HOST@EXAMPLE.COM</value>
+ <description>Required for SPNEGO, the Kerberos principal to use for SPNEGO authentication by the
+ web server. The _HOST keyword will be automatically substituted with the node's
+ hostname.</description>
+</property>
+<property>
+ <name>hbase.security.authentication.spnego.kerberos.keytab</name>
+ <value>/etc/security/keytabs/spnego.service.keytab</value>
+ <description>Required for SPNEGO, the Kerberos keytab file to use for SPNEGO authentication by the
+ web server.</description>
+</property>
+<property>
+ <name>hbase.security.authentication.spnego.kerberos.name.rules</name>
+ <value></value>
+ <description>Optional, Hadoop-style \`auth_to_local\` rules which will be parsed and used in the
+ handling of Kerberos principals</description>
+</property>
+<property>
+ <name>hbase.security.authentication.signature.secret.file</name>
+ <value></value>
+ <description>Optional, a file whose contents will be used as a secret to sign the HTTP cookies
+ as a part of the SPNEGO authentication handshake. If this is not provided, Java's \`Random\` library
+ will be used for the secret.</description>
+</property>
+\`\`\`
+
+## Defining administrators of the Web UI with SPNEGO
+
+In the previous section, we cover how to enable authentication for the Web UI via SPNEGO. However, some portions of the Web UI could be used to impact the availability and performance of an HBase cluster. As such, it is desirable to ensure that only those with proper authority can interact with these sensitive endpoints.
+
+HBase allows the adminstrators to be defined via a list of usernames or groups in hbase-site.xml
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication.spnego.admin.users</name>
+ <value></value>
+</property>
+<property>
+ <name>hbase.security.authentication.spnego.admin.groups</name>
+ <value></value>
+</property>
+\`\`\`
+
+The usernames are those which the Kerberos identity maps to, given the Hadoop \`auth_to_local\` rules in core-site.xml. The groups here are the Unix groups associated with the mapped usernames.
+
+Consider the following scenario to describe how the configuration properties operate. Consider three users which are defined in the Kerberos KDC:
+
+* \`alice@COMPANY.COM\`
+* \`bob@COMPANY.COM\`
+* \`charlie@COMPANY.COM\`
+
+The default Hadoop \`auth_to_local\` rules map these principals to the "shortname":
+
+* \`alice\`
+* \`bob\`
+* \`charlie\`
+
+Unix groups membership define that \`alice\` is a member of the group \`admins\`. \`bob\` and \`charlie\` are not members of the \`admins\` group.
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication.spnego.admin.users</name>
+ <value>charlie</value>
+</property>
+<property>
+ <name>hbase.security.authentication.spnego.admin.groups</name>
+ <value>admins</value>
+</property>
+\`\`\`
+
+Given the above configuration, \`alice\` is allowed to access sensitive endpoints in the Web UI as she is a member of the \`admins\` group. \`charlie\` is also allowed to access sensitive endpoints because he is explicitly listed as an admin in the configuration. \`bob\` is not allowed to access sensitive endpoints because he is not a member of the \`admins\` group nor is listed as an explicit admin user via \`hbase.security.authentication.spnego.admin.users\`, but can still use any non- [...]
+
+If it doesn't go without saying: non-authenticated users cannot access any part of the Web UI.
+
+## Using LDAP authentication with Web UIs
+
+LDAP authentication to HBase Web UIs can be enabled via configuring LDAP with the \`hbase.security.authentication.ui\` property in *hbase-site.xml*. The \`hbase.http.filter.initializers\` property also needs to have the \`AuthenticationFilterInitializer\` class.
+
+**IMPORTANT:** A LDAP server must be configured and running. When TLS is enabled for communication with LDAP server (either via ldaps scheme or ‘start TLS' extension), configure the public certificate of the LDAP server in the local truststore. The LDAP authentication mechanism uses HTTP Basic authentication scheme to verify user specified credentials against a configured LDAP (or Active Directory) server. The authentication filter must be configured with the following init parameters:
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication.ui</name>
+ <value>ldap</value>
+ <description>Controls what kind of authentication should be used for the HBase web UIs.</description>
+</property>
+<property>
+ <name>hbase.http.filter.initializers</name>
+ <value>org.apache.hadoop.hbase.http.lib.AuthenticationFilterInitializer</value>
+ <description>Comma separated class names corresponding to the Filters that will be initialized.
+ Then, the Filters will be applied to all user facing jsp and servlet web pages.</description>
+</property>
+<property>
+ <name>hadoop.http.authentication.type</name>
+ <value>ldap</value>
+ <description>Defines authentication used for the HTTP web-consoles in Hadoop ecosystem.</description>
+</property>
+\`\`\`
+
+A number of properties exist to configure LDAP authentication for the web server:
+
+\`\`\`xml
+<property>
+ <name>hadoop.http.authentication.ldap.binddomain</name>
+ <value>EXAMPLE.COM</value>
+ <description>The LDAP bind domain value to be used with the LDAP server. This property is optional
+ and useful only in case of Active Directory server (e.g. example.com).</description>
+</property>
+<property>
+ <name>hadoop.http.authentication.ldap.providerurl</name>
+ <value>ldap://ldap-server-host:8920</value>
+ <description>The url of the LDAP server.</description>
+</property>
+<property>
+ <name>hadoop.http.authentication.ldap.enablestarttls</name>
+ <value>false</value>
+ <description>A boolean value used to define if the LDAP server supports ‘StartTLS' extension.</description>
+</property>
+<property>
+ <name>hadoop.http.authentication.ldap.basedn</name>
+ <value>ou=users,dc=example,dc=com</value>
+ <description>The base distinguished name (DN) to be used with the LDAP server. This value is
+ appended to the provided user id for authentication purpose. This property is not useful in case
+ of Active Directory server.</description>
+</property>
+\`\`\`
+
+## Defining Administrators of the Web UI with LDAP
+
+In the previous section, we discussed enabling authentication for the Web UI via LDAP. Certain portions of the Web UI can impact the availability and performance of an HBase cluster. To safeguard these sensitive endpoints, it is essential to restrict access to authorized administrators only.
+
+HBase provides a mechanism to define administrators for the Web UI through a list of usernames in the \`hbase-site.xml\` configuration file.
+
+To specify the administrators, use the following property in \`hbase-site.xml\`:
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication.ldap.admin.users</name>
+ <value>admin1,admin2,admin3</value>
+</property>
+\`\`\`
+
+The usernames listed in the above property should correspond to the LDAP usernames of the administrators.
+
+### Notes
+
+* This feature is supported by only versions of HBase having [HBASE-29244](https://issues.apache.org/jira/browse/HBASE-29244)
+* Ensure that the LDAP server is properly configured and running. See the previous section for details.
+* Only users explicitly listed in the \`hbase.security.authentication.ldap.admin.users\` property will have access to sensitive endpoints.
+* Non-administrative users can still access non-sensitive endpoints, provided they are authenticated.
+
+By defining administrators in this way, you can ensure that only authorized personnel can interact with critical Web UI functionalities, thereby enhancing the security and stability of your HBase cluster.
+
+## Other UI security-related configuration
+
+While it is a clear anti-pattern for HBase developers, the developers acknowledge that the HBase configuration (including Hadoop configuration files) may contain sensitive information. As such, a user may find that they do not want to expose the HBase service-level configuration to all authenticated users. They may configure HBase to require a user must be an admin to access the service-level configuration via the HBase UI. This configuration is **false** by default (any authenticated us [...]
+
+Users who wish to change this would set the following in their hbase-site.xml:
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication.ui.config.protected</name>
+ <value>true</value>
+</property>
+\`\`\`
+
+To disable showing stack traces in HBase UI for hiding sensitive information, set the following in hbase-site:
+
+\`\`\`xml
+<property>
+ <name>hbase.ui.show-stack-traces</name>
+ <value>false</value>
+</property>
+\`\`\`
+
+## Secure Client Access to Apache HBase
+
+Newer releases of Apache HBase (>= 0.92) support optional SASL authentication of clients. See also Matteo Bertozzi's article on [Understanding User Authentication and Authorization in Apache HBase](https://blog.cloudera.com/blog/2012/09/understanding-user-authentication-and-authorization-in-apache-hbase/).
+
+This describes how to set up Apache HBase and clients for connection to secure HBase resources.
+
+## Prerequisites
+
+#### Hadoop Authentication Configuration \\[!toc]
+
+To run HBase RPC with strong authentication, you must set \`hbase.security.authentication\` to \`kerberos\`. In this case, you must also set \`hadoop.security.authentication\` to \`kerberos\` in core-site.xml. Otherwise, you would be using strong authentication for HBase but not for the underlying HDFS, which would cancel out any benefit.
+
+#### Kerberos KDC \\[!toc]
+
+You need to have a working Kerberos KDC.
+
+## Server-side Configuration for Secure Operation
+
+First, refer to [security.prerequisites](/docs/security/client-access#security-client-access-prerequisites) and ensure that your underlying HDFS configuration is secure.
+
+Add the following to the \`hbase-site.xml\` file on every server machine in the cluster:
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication</name>
+ <value>kerberos</value>
+</property>
+<property>
+ <name>hbase.security.authorization</name>
+ <value>true</value>
+</property>
+<property>
+<name>hbase.coprocessor.region.classes</name>
+ <value>org.apache.hadoop.hbase.security.token.TokenProvider</value>
+</property>
+\`\`\`
+
+A full shutdown and restart of HBase service is required when deploying these configuration changes.
+
+## Client-side Configuration for Secure Operation
+
+First, refer to [Prerequisites](/docs/security/client-access#security-client-access-prerequisites) and ensure that your underlying HDFS configuration is secure.
+
+Add the following to the \`hbase-site.xml\` file on every client:
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication</name>
+ <value>kerberos</value>
+</property>
+\`\`\`
+
+Before 2.2.0 version, the client environment must be logged in to Kerberos from KDC or keytab via the \`kinit\` command before communication with the HBase cluster will be possible.
+
+Since 2.2.0, client can specify the following configurations in \`hbase-site.xml\`:
+
+\`\`\`xml
+<property>
+ <name>hbase.client.keytab.file</name>
+ <value>/local/path/to/client/keytab</value>
+</property>
+
+<property>
+ <name>hbase.client.keytab.principal</name>
+ <value>foo@EXAMPLE.COM</value>
+</property>
+\`\`\`
+
+Then application can automatically do the login and credential renewal jobs without client interference.
+
+It's optional feature, client, who upgrades to 2.2.0, can still keep their login and credential renewal logic already did in older version, as long as keeping \`hbase.client.keytab.file\` and \`hbase.client.keytab.principal\` are unset.
+
+Be advised that if the \`hbase.security.authentication\` in the client- and server-side site files do not match, the client will not be able to communicate with the cluster.
+
+Once HBase is configured for secure RPC it is possible to optionally configure encrypted communication. To do so, add the following to the \`hbase-site.xml\` file on every client:
+
+\`\`\`xml
+<property>
+ <name>hbase.rpc.protection</name>
+ <value>privacy</value>
+</property>
+\`\`\`
+
+This configuration property can also be set on a per-connection basis. Set it in the \`Configuration\` supplied to \`Table\`:
+
+\`\`\`java
+Configuration conf = HBaseConfiguration.create();
+Connection connection = ConnectionFactory.createConnection(conf);
+conf.set("hbase.rpc.protection", "privacy");
+try (Connection connection = ConnectionFactory.createConnection(conf);
+ Table table = connection.getTable(TableName.valueOf(tablename))) {
+ .... do your stuff
+}
+\`\`\`
+
+Expect a \\~10% performance penalty for encrypted communication.
+
+## Client-side Configuration for Secure Operation - Thrift Gateway
+
+Add the following to the \`hbase-site.xml\` file for every Thrift gateway:
+
+\`\`\`xml
+<property>
+ <name>hbase.thrift.keytab.file</name>
+ <value>/etc/hbase/conf/hbase.keytab</value>
+</property>
+<property>
+ <name>hbase.thrift.kerberos.principal</name>
+ <value>$USER/_HOST@HADOOP.LOCALDOMAIN</value>
+ <!-- TODO: This may need to be HTTP/_HOST@<REALM> and _HOST may not work.
+ You may have to put the concrete full hostname.
+ -->
+</property>
+<!-- Add these if you need to configure a different DNS interface from the default -->
+<property>
+ <name>hbase.thrift.dns.interface</name>
+ <value>default</value>
+</property>
+<property>
+ <name>hbase.thrift.dns.nameserver</name>
+ <value>default</value>
+</property>
+\`\`\`
+
+Substitute the appropriate credential and keytab for *\\$USER* and *\\$KEYTAB* respectively.
+
+In order to use the Thrift API principal to interact with HBase, it is also necessary to add the \`hbase.thrift.kerberos.principal\` to the \`acl\` table. For example, to give the Thrift API principal, \`thrift_server\`, administrative access, a command such as this one will suffice:
+
+\`\`\`sql
+grant 'thrift_server', 'RWCA'
+\`\`\`
+
+For more information about ACLs, please see the [Access Control Labels (ACLs)](/docs/security/data-access#access-control-labels-acls) section
+
+The Thrift gateway will authenticate with HBase using the supplied credential. No authentication will be performed by the Thrift gateway itself. All client access via the Thrift gateway will use the Thrift gateway's credential and have its privilege.
+
+## Configure the Thrift Gateway to Authenticate on Behalf of the Client
+
+[Client-side Configuration for Secure Operation - Thrift Gateway](/docs/security/client-access#client-side-configuration-for-secure-operation---thrift-gateway) describes how to authenticate a Thrift client to HBase using a fixed user. As an alternative, you can configure the Thrift gateway to authenticate to HBase on the client's behalf, and to access HBase using a proxy user. This was implemented in [HBASE-11349](https://issues.apache.org/jira/browse/HBASE-11349) for Thrift 1, and [HBAS [...]
+
+<Callout type="info">
+ If you use framed transport, you cannot yet take advantage of this feature, because SASL does not
+ work with Thrift framed transport at this time.
+</Callout>
+
+To enable it, do the following.
+
+1. Be sure Thrift is running in secure mode, by following the procedure described in [Client-side Configuration for Secure Operation - Thrift Gateway](/docs/security/client-access#client-side-configuration-for-secure-operation---thrift-gateway).
+2. Be sure that HBase is configured to allow proxy users, as described in [REST Gateway Impersonation Configuration](/docs/security/client-access#rest-gateway-impersonation-configuration).
+3. In *hbase-site.xml* for each cluster node running a Thrift gateway, set the property \`hbase.thrift.security.qop\` to one of the following three values:
+ * \`privacy\` - authentication, integrity, and confidentiality checking.
+ * \`integrity\` - authentication and integrity checking
+ * \`authentication\` - authentication checking only
+4. Restart the Thrift gateway processes for the changes to take effect. If a node is running Thrift, the output of the \`jps\` command will list a \`ThriftServer\` process. To stop Thrift on a node, run the command \`bin/hbase-daemon.sh stop thrift\`. To start Thrift on a node, run the command \`bin/hbase-daemon.sh start thrift\`.
+
+## Configure the Thrift Gateway to Use the \`doAs\` Feature
+
+[Configure the Thrift Gateway to Authenticate on Behalf of the Client](/docs/security/client-access#configure-the-thrift-gateway-to-authenticate-on-behalf-of-the-client) describes how to configure the Thrift gateway to authenticate to HBase on the client's behalf, and to access HBase using a proxy user. The limitation of this approach is that after the client is initialized with a particular set of credentials, it cannot change these credentials during the session. The \`doAs\` feature p [...]
+
+**To enable the \`doAs\` feature**, add the following to the *hbase-site.xml* file for every Thrift gateway:
+
+\`\`\`xml
+<property>
+ <name>hbase.regionserver.thrift.http</name>
+ <value>true</value>
+</property>
+<property>
+ <name>hbase.thrift.support.proxyuser</name>
+ <value>true</value>
+</property>
+\`\`\`
+
+**To allow proxy users** when using \`doAs\` impersonation, add the following to the *hbase-site.xml* file for every HBase node:
+
+\`\`\`xml
+<property>
+ <name>hadoop.security.authorization</name>
+ <value>true</value>
+</property>
+<property>
+ <name>hadoop.proxyuser.$USER.groups</name>
+ <value>$GROUPS</value>
+</property>
+<property>
+ <name>hadoop.proxyuser.$USER.hosts</name>
+ <value>$GROUPS</value>
+</property>
+\`\`\`
+
+Take a look at the [demo client](https://github.com/apache/hbase/blob/master/hbase-examples/src/main/java/org/apache/hadoop/hbase/thrift/HttpDoAsClient.java) to get an overall idea of how to use this feature in your client.
+
+## Client-side Configuration for Secure Operation - REST Gateway
+
+Add the following to the \`hbase-site.xml\` file for every REST gateway:
+
+\`\`\`xml
+<property>
+ <name>hbase.rest.keytab.file</name>
+ <value>$KEYTAB</value>
+</property>
+<property>
+ <name>hbase.rest.kerberos.principal</name>
+ <value>$USER/_HOST@HADOOP.LOCALDOMAIN</value>
+</property>
+\`\`\`
+
+Substitute the appropriate credential and keytab for *\\$USER* and *\\$KEYTAB* respectively.
+
+The REST gateway will authenticate with HBase using the supplied credential.
+
+In order to use the REST API principal to interact with HBase, it is also necessary to add the \`hbase.rest.kerberos.principal\` to the \`acl\` table. For example, to give the REST API principal, \`rest_server\`, administrative access, a command such as this one will suffice:
+
+\`\`\`sql
+grant 'rest_server', 'RWCA'
+\`\`\`
+
+For more information about ACLs, please see the [Access Control Labels (ACLs)](/docs/security/data-access#access-control-labels-acls) section
+
+HBase REST gateway supports [SPNEGO HTTP authentication](https://hadoop.apache.org/docs/stable/hadoop-auth/index.html) for client access to the gateway. To enable REST gateway Kerberos authentication for client access, add the following to the \`hbase-site.xml\` file for every REST gateway.
+
+\`\`\`xml
+<property>
+ <name>hbase.rest.support.proxyuser</name>
+ <value>true</value>
+</property>
+<property>
+ <name>hbase.rest.authentication.type</name>
+ <value>kerberos</value>
+</property>
+<property>
+ <name>hbase.rest.authentication.kerberos.principal</name>
+ <value>HTTP/_HOST@HADOOP.LOCALDOMAIN</value>
+</property>
+<property>
+ <name>hbase.rest.authentication.kerberos.keytab</name>
+ <value>$KEYTAB</value>
+</property>
+<!-- Add these if you need to configure a different DNS interface from the default -->
+<property>
+ <name>hbase.rest.dns.interface</name>
+ <value>default</value>
+</property>
+<property>
+ <name>hbase.rest.dns.nameserver</name>
+ <value>default</value>
+</property>
+\`\`\`
+
+Substitute the keytab for HTTP for *\\$KEYTAB*.
+
+HBase REST gateway supports different 'hbase.rest.authentication.type': simple, kerberos. You can also implement a custom authentication by implementing Hadoop AuthenticationHandler, then specify the full class name as 'hbase.rest.authentication.type' value. For more information, refer to [SPNEGO HTTP authentication](https://hadoop.apache.org/docs/stable/hadoop-auth/index.html).
+
+## REST Gateway Impersonation Configuration
+
+By default, the REST gateway doesn't support impersonation. It accesses the HBase on behalf of clients as the user configured as in the previous section. To the HBase server, all requests are from the REST gateway user. The actual users are unknown. You can turn on the impersonation support. With impersonation, the REST gateway user is a proxy user. The HBase server knows the actual/real user of each request. So it can apply proper authorizations.
+
+To turn on REST gateway impersonation, we need to configure HBase servers (masters and region servers) to allow proxy users; configure REST gateway to enable impersonation.
+
+To allow proxy users, add the following to the \`hbase-site.xml\` file for every HBase server:
+
+\`\`\`xml
+<property>
+ <name>hadoop.security.authorization</name>
+ <value>true</value>
+</property>
+<property>
+ <name>hadoop.proxyuser.$USER.groups</name>
+ <value>$GROUPS</value>
+</property>
+<property>
+ <name>hadoop.proxyuser.$USER.hosts</name>
+ <value>$GROUPS</value>
+</property>
+\`\`\`
+
+Substitute the REST gateway proxy user for *\\$USER*, and the allowed group list for *\\$GROUPS*.
+
+To enable REST gateway impersonation, add the following to the \`hbase-site.xml\` file for every REST gateway.
+
+\`\`\`xml
+<property>
+ <name>hbase.rest.authentication.type</name>
+ <value>kerberos</value>
+</property>
+<property>
+ <name>hbase.rest.authentication.kerberos.principal</name>
+ <value>HTTP/_HOST@HADOOP.LOCALDOMAIN</value>
+</property>
+<property>
+ <name>hbase.rest.authentication.kerberos.keytab</name>
+ <value>$KEYTAB</value>
+</property>
+\`\`\`
+
+Substitute the keytab for HTTP for *\\$KEYTAB*.
+
+## Simple User Access to Apache HBase
+
+Newer releases of Apache HBase (>= 0.92) support optional SASL authentication of clients. See also Matteo Bertozzi's article on [Understanding User Authentication and Authorization in Apache HBase](https://blog.cloudera.com/blog/2012/09/understanding-user-authentication-and-authorization-in-apache-hbase/).
+
+This describes how to set up Apache HBase and clients for simple user access to HBase resources.
+
+## Simple versus Secure Access
+
+The following section shows how to set up simple user access. Simple user access is not a secure method of operating HBase. This method is used to prevent users from making mistakes. It can be used to mimic the Access Control using on a development system without having to set up Kerberos.
+
+This method is not used to prevent malicious or hacking attempts. To make HBase secure against these types of attacks, you must configure HBase for secure operation. Refer to the section [Secure Client Access to Apache HBase](/docs/security/client-access) and complete all of the steps described there.
+
+## Prerequisites
+
+None
+
+## Server-side Configuration for Simple User Access Operation
+
+Add the following to the \`hbase-site.xml\` file on every server machine in the cluster:
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication</name>
+ <value>simple</value>
+</property>
+<property>
+ <name>hbase.security.authorization</name>
+ <value>true</value>
+</property>
+<property>
+ <name>hbase.coprocessor.master.classes</name>
+ <value>org.apache.hadoop.hbase.security.access.AccessController</value>
+</property>
+<property>
+ <name>hbase.coprocessor.region.classes</name>
+ <value>org.apache.hadoop.hbase.security.access.AccessController</value>
+</property>
+<property>
+ <name>hbase.coprocessor.regionserver.classes</name>
+ <value>org.apache.hadoop.hbase.security.access.AccessController</value>
+</property>
+\`\`\`
+
+For 0.94, add the following to the \`hbase-site.xml\` file on every server machine in the cluster:
+
+\`\`\`xml
+<property>
+ <name>hbase.rpc.engine</name>
+ <value>org.apache.hadoop.hbase.ipc.SecureRpcEngine</value>
+</property>
+<property>
+ <name>hbase.coprocessor.master.classes</name>
+ <value>org.apache.hadoop.hbase.security.access.AccessController</value>
+</property>
+<property>
+ <name>hbase.coprocessor.region.classes</name>
+ <value>org.apache.hadoop.hbase.security.access.AccessController</value>
+</property>
+\`\`\`
+
+A full shutdown and restart of HBase service is required when deploying these configuration changes.
+
+## Client-side Configuration for Simple User Access Operation
+
+Add the following to the \`hbase-site.xml\` file on every client:
+
+\`\`\`xml
+<property>
+ <name>hbase.security.authentication</name>
+ <value>simple</value>
+</property>
+\`\`\`
+
+For 0.94, add the following to the \`hbase-site.xml\` file on every server machine in the cluster:
+
+\`\`\`xml
+<property>
+ <name>hbase.rpc.engine</name>
+ <value>org.apache.hadoop.hbase.ipc.SecureRpcEngine</value>
+</property>
+\`\`\`
+
+Be advised that if the \`hbase.security.authentication\` in the client- and server-side site files do not match, the client will not be able to communicate with the cluster.
+
+### Client-side Configuration for Simple User Access Operation - Thrift Gateway
+
+The Thrift gateway user will need access. For example, to give the Thrift API user, \`thrift_server\`, administrative access, a command such as this one will suffice:
+
+\`\`\`sql
+grant 'thrift_server', 'RWCA'
+\`\`\`
+
+For more information about ACLs, please see the [Access Control Labels (ACLs)](/docs/security/data-access#access-control-labels-acls) section
+
+The Thrift gateway will authenticate with HBase using the supplied credential. No authentication will be performed by the Thrift gateway itself. All client access via the Thrift gateway will use the Thrift gateway's credential and have its privilege.
+
+### Client-side Configuration for Simple User Access Operation - REST Gateway
+
+The REST gateway will authenticate with HBase using the supplied credential. No authentication will be performed by the REST gateway itself. All client access via the REST gateway will use the REST gateway's credential and have its privilege.
+
+The REST gateway user will need access. For example, to give the REST API user, \`rest_server\`, administrative access, a command such as this one will suffice:
+
+\`\`\`sql
+grant 'rest_server', 'RWCA'
+\`\`\`
+
+For more information about ACLs, please see the [Access Control Labels (ACLs)](/docs/security/data-access#access-control-labels-acls) section
+
+It should be possible for clients to authenticate with the HBase cluster through the REST gateway in a pass-through manner via SPNEGO HTTP authentication. This is future work.
+
+## Transport Level Security (TLS) in HBase RPC communication
+
+Since version \`2.6.0\` HBase supports TLS encryption in server-client and Master-RegionServer communication. [Transport Layer Security (TLS)](https://en.wikipedia.org/wiki/Transport_Layer_Security) is a standard cryptographic protocol designed to provide communications security over a computer network. HBase TLS implementation works exactly how secure websites are accessed via **https** prefix in a web browser: once established all communication on the channel will be securely hidden fr [...]
+
+The encryption works at the transport level which means it's independent of the configured authentication method. Secure client access mentioned in the previous section requires Kerberos to be configured and used in HBase authentication, while TLS can be configured with any other SASL mechanism or even with simple client access methods, effectively preventing attackers from eavesdropping the communication. No Kerberos KDC or other complicated infrastructure required.
+
+HBase TLS is based on the Netty library therefore it only works with Netty client and server RPC implementations. Netty's powerful SSL implementation is a great foundation for highly secure and performant communication providing the latest and greatest cryptographic solution at all times.
+
+Since Region Servers effectively work as clients from Master's perspective, TLS supports encrypted communication between cluster members too.
+
+<Callout type="info">
+ From version 2.6.0 HBase supports the [Hadoop CredentialProvider API](https://hadoop.apache.org/docs/r3.3.4/hadoop-project-dist/hadoop-common/CredentialProviderAPI.html) to avoid storing sensitive information in HBase configuration files. The recommended way of storing keystore / truststore passwords is to use one of the supported credential providers e.g. the local jceks file provider. You can find more information about how to setup credential providers in the Hadoop documentation.
+
+ The CLI interface for accessing the Hadoop Credential Shell is also available in HBase CLI. Type \`hbase credential\` to get help.
+</Callout>
+
+## Server side configuration
+
+We need to set up Java key store for the server. Key store is the list of private keys that a server can use to configure TLS encryption. See [TLS wikipedia page](https://en.wikipedia.org/wiki/Transport_Layer_Security) for further details of the protocol. Add the following configuration to \`hbase-site.xml\` on Master, Region Servers and HBase clients:
+
+\`\`\`xml
+<property>
+ <name>hbase.server.netty.tls.enabled</name>
+ <value>true</value>
+</property>
+<property>
+ <name>hbase.rpc.tls.keystore.location</name>
+ <value>/path/to/keystore.jks</value>
+</property>
+\`\`\`
+
+Use \`hbase.rpc.tls.keystore.password\` alias to retrieve key store password from Hadoop credential provider.
+
+<Callout type="info">
+ The supported storefile formats are based on the registered security providers and the loader can
+ be autodetected from the file extension. If needed, the file format can be explicitly specified
+ with the \`hbase.rpc.tls.keystore.type\` property.
+</Callout>
+
+## Client side configuration
+
+We need to configure trust store for the client. Trust store contains the list of certificates that the client should trust when doing the handshake with the server. Add the following to \`hbase-site.xml\`.
+
+\`\`\`xml
+<property>
+ <name>hbase.client.netty.tls.enabled</name>
+ <value>true</value>
+</property>
+<property>
+ <name>hbase.rpc.tls.truststore.location</name>
+ <value>/path/to/truststore.jks</value>
+</property>
+\`\`\`
+
+Use \`hbase.rpc.tls.truststore.password\` alias to retrieve trust store password from Hadoop credential provider.
+
+<Callout type="info">
+ The supported storefile formats are based on the registered security providers and the loader can
+ be autodetected from the file extension. If needed, the file format can be explicitly specified
+ with the \`hbase.rpc.tls.truststore.type\` property.
+</Callout>
+
+However, specifying a trust store is not always required. Standard JDK implementations are shipped with a standard list of trusted certificates (the certificates of Certificate Authorities) and if your private key is provided by one of them, you don't need to configure your clients to trust it. Similarly to an internet browser, you don't need to set up the certificates of every single website you're planning to visit. Later in this documentation we'll walk through the steps of creating s [...]
+
+You can check the list of public certificate authorities shipped with your JDK implementation:
+
+\`\`\`bash
+keytool -keystore $JAVA_HOME/jre/lib/security/cacerts -list
+\`\`\`
+
+Password is empty by default.
+
+## Creating self-signed certificates
+
+While obtaining globally trusted certificates from Certificate Authorities is convenient, it's perfectly valid to generate your own private/public keypairs and set them up specifically for the HBase cluster. Especially if you don't want to enable public access to the cluster, paying money for a certificate doesn't make sense.
+
+Follow the following steps to generate self-signed certificates.
+
+1. Create SSL key store JKS to store local credentials
+
+ Please note that the alias (-alias) and the distinguished name (-dname) must match the hostname of the machine that is associated with, otherwise hostname verification won't work.
+
+ \`\`\`bash
+ keytool -genkeypair -alias $(hostname -f) -keyalg RSA -keysize 2048 -dname "cn=$(hostname -f)" -keypass password -keystore keystore.jks -storepass password
+ \`\`\`
+
+ At the end of this operation you'll have as many key store files as many servers you have in your cluster. Each cluster member will have its own key store.
+
+2. Extract the signed public key (certificate) from each key store
+
+ \`\`\`bash
+ keytool -exportcert -alias $(hostname -f) -keystore keystore.jks -file $(hostname -f).cer -rfc
+ \`\`\`
+
+3. Create SSL trust store JKS containing certificates for the clients
+
+ The same truststore (storing all accepted certs) should be shared on participants of the cluster. You need to use different aliases to store multiple certificates in the same truststore. Name of the aliases doesn't matter.
+
+ \`\`\`bash
+ keytool -importcert -alias [host1..3] -file [host1..3].cer -keystore truststore.jks -storepass password
+ \`\`\`
+
+## Upgrading existing non-TLS cluster with no downtime
+
+Here are the steps needed to upgrade an already running HBase cluster to TLS without downtime by taking advantage of port unification functionality. There's a property on server side called \`hbase.server.netty.tls.supportplaintext\` which makes possible to accept TLS and plaintext connections on the same socket port.
+
+<Steps>
+ <Step>
+ Create the necessary key stores and trust stores for all server participants as described in the previous section.
+ </Step>
+
+ <Step>
+ Enable secure communication on the Master node in *server-only* mode with plaintext support
+
+ \`\`\`xml
+ <property>
+ <name>hbase.client.netty.tls.enabled</name>
+ <value>false</value>
+ </property>
+ <property>
+ <name>hbase.server.netty.tls.enabled</name>
+ <value>true</value>
+ </property>
+ <property>
+ <name>hbase.server.netty.tls.supportplaintext</name>
+ <value>true</value>
+ </property>
+ ...keystore / truststore setup ...
+ \`\`\`
+
+ Restart the Master. Master now accepts both TLS/non-TLS connections and works with non-TLS in client mode.
+ </Step>
+
+ <Step>
+ Enable secure communication on the Region Servers in both *server and client* mode with plaintext support
+
+ Client mode here will ensure that RegionServer's communication to Master is encrypted.
+
+ <Callout type="warn">
+ **Replication**
+
+ If you have read replicas enabled in your cluster or replication between two different clusters, you have to break this into two steps. Secure communication has to be enabled on the *server side* first with plaintext support and once all Region Servers are upgraded you can repeat the upgrade by enabling *client side* as well.
+
+ You have to prepare all Region Servers for secure communication before upgrading the client side.
+ </Callout>
+
+ \`\`\`xml
+ <property>
+ <name>hbase.client.netty.tls.enabled</name>
+ <value>true</value>
+ </property>
+ <property>
+ <name>hbase.server.netty.tls.enabled</name>
+ <value>true</value>
+ </property>
+ <property>
+ <name>hbase.server.netty.tls.supportplaintext</name>
+ <value>true</value>
+ </property>
+ ...keystore / truststore setup ...
+ \`\`\`
+
+ Restart Region Servers in rolling restart fashion. They send requests with TLS and accept both TLS and non-TLS communication.
+ </Step>
+
+ <Step>
+ Enable secure communication on the clients
+
+ \`\`\`xml
+ <property>
+ <name>hbase.client.netty.tls.enabled</name>
+ <value>true</value>
+ </property>
+ ...truststore setup ...
+ \`\`\`
+ </Step>
+
+ <Step>
+ Enable client-mode TLS on master and disable plaintext mode
+
+ \`\`\`xml
+ <property>
+ <name>hbase.client.netty.tls.enabled</name>
+ <value>true</value>
+ </property>
+ <property>
+ <name>hbase.server.netty.tls.enabled</name>
+ <value>true</value>
+ </property>
+ <property>
+ <name>hbase.server.netty.tls.supportplaintext</name>
+ <value>false</value>
+ </property>
+ \`\`\`
+
+ Restart Master.
+ </Step>
+
+ <Step>
+ Disable plaintext communication on the Region Servers
+
+ Disable plaintext communication on the Region Servers by removing \`supportplaintext\` property. Restart RSs in rolling restart fashion.
+
+ <Callout type="warn">
+ Once \`hbase.client.netty.tls.enabled\` is enabled on the server side, the cluster will only be able
+ to communicate with other clusters which have TLS enabled. For example, this would impact
+ inter-cluster replication.
+ </Callout>
+ </Step>
+</Steps>
+
+## Enable automatic certificate reloading
+
+Certificates usually expire after some time to improve security. In this case we need to replace them by modifying Keystore / Truststore files and HBase processes have to be restarted. In order to avoid that you can enable automatic file change detection and certificate reloading with the following option. Default: false.
+
+\`\`\`xml
+<property>
+ <name>hbase.rpc.tls.certReload</name>
+ <value>true</value>
+</property>
+\`\`\`
+
+## Additional configuration
+
+### Enabled protocols
+
+Comma-separated list of TLS protocol versions to enable. Default is empty.
+
+\`\`\`xml
+<property>
+ <name>hbase.client.netty.tls.enabledProtocols</name>
+ <value>TLSv1.2,TLSv1.3</value>
+</property>
+\`\`\`
+
+### Default protocol
+
+Set the default TLS protocol version to use. Default is TLSv1.2. Use this protocol if enabled protocols is not defined.
+
+\`\`\`xml
+<property>
+ <name>hbase.client.netty.tls.protocol</name>
+ <value>TLSv1.2</value>
+</property>
+\`\`\`
+
+### Enabled cipher suites
+
+List of enabled cipher suites in TLS protocol. Useful when you want to disable certain cipher suites due to recent security concerns. Default value is a mix of CBC and GCM ciphers. Due to performance reasons we prefer CBC ciphers for Java 8 and GCM ciphers for Java 9+.
+
+\`\`\`xml
+<property>
+ <name>hbase.client.netty.tls.ciphersuites</name>
+ <value>TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256</value>
+</property>
+\`\`\`
+
+### Certificate Revocation Checking
+
+There's a built-in mechanism in JDK's TrustManager which automatically checks certificates for revocation. See [Managing Server Certificates](https://docs.oracle.com/cd/E19263-01/817-5215/ssl.html#wp19807). Disabled by default.
+
+\`\`\`xml
+<property>
+ <name>hbase.client.netty.tls.clr</name>
+ <value>false</value>
+</property>
+\`\`\`
+
+### Online Certificate Status Protocol
+
+Enables [OCSP](https://en.wikipedia.org/wiki/OCSP_stapling) stapling. Please note that not all \`SSLProvider\` implementations support OCSP stapling and an exception will be thrown upon. Disabled by default.
+
+\`\`\`xml
+<property>
+ <name>hbase.client.netty.tls.ocsp</name>
+ <value>false</value>
+</property>
... 67714 lines suppressed ...