You are viewing a plain text version of this content. The canonical link for it is here.
Posted to notifications@asterixdb.apache.org by AsterixDB Code Review <do...@asterix-gerrit.ics.uci.edu> on 2022/04/18 17:38:31 UTC

Change in asterixdb[master]: [NO ISSUE][REP] Increase replication ack timeout

From Dmitry Lychagin <dm...@couchbase.com>:

Hello Murtadha Hubail, Ali Alsuliman, Jenkins,

I'd like you to do a code review. Please visit

    https://asterix-gerrit.ics.uci.edu/c/asterixdb/+/16125

to review the following change.


Change subject: [NO ISSUE][REP] Increase replication ack timeout
......................................................................

[NO ISSUE][REP] Increase replication ack timeout

- user model changes: no
- storage format changes: no
- interface changes: no

Details:

- Increase replication ack timeout to 120 seconds.

Change-Id: I228620af371d651a84160231cdd832ca1087e7f9
Reviewed-on: https://asterix-gerrit.ics.uci.edu/c/asterixdb/+/15843
Reviewed-by: Ali Alsuliman <al...@gmail.com>
Integration-Tests: Jenkins <je...@fulliautomatix.ics.uci.edu>
Tested-by: Jenkins <je...@fulliautomatix.ics.uci.edu>
---
M asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1/cluster_state_1.1.regexadm
M asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_full/cluster_state_1_full.1.regexadm
M asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_less/cluster_state_1_less.1.regexadm
M asterixdb/asterix-common/src/main/java/org/apache/asterix/common/config/ReplicationProperties.java
M asterixdb/asterix-replication/src/main/java/org/apache/asterix/replication/messaging/MarkComponentValidTask.java
5 files changed, 10 insertions(+), 5 deletions(-)



  git pull ssh://asterix-gerrit.ics.uci.edu:29418/asterixdb refs/changes/25/16125/1

diff --git a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1/cluster_state_1.1.regexadm b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1/cluster_state_1.1.regexadm
index d99f2e9..54793dc 100644
--- a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1/cluster_state_1.1.regexadm
+++ b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1/cluster_state_1.1.regexadm
@@ -44,7 +44,7 @@
     "replication\.log\.buffer\.numpages" : 8,
     "replication\.log\.buffer\.pagesize" : 131072,
     "replication\.strategy" : "none",
-    "replication\.timeout" : 30,
+    "replication\.timeout" : 120,
     "ssl\.enabled" : false,
     "storage.compression.block" : "snappy",
     "storage.global.cleanup.timeout" : 600,
diff --git a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_full/cluster_state_1_full.1.regexadm b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_full/cluster_state_1_full.1.regexadm
index 479de3e..06da0ad 100644
--- a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_full/cluster_state_1_full.1.regexadm
+++ b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_full/cluster_state_1_full.1.regexadm
@@ -44,7 +44,7 @@
     "replication\.log\.buffer\.numpages" : 8,
     "replication\.log\.buffer\.pagesize" : 131072,
     "replication\.strategy" : "none",
-    "replication\.timeout" : 30,
+    "replication\.timeout" : 120,
     "ssl\.enabled" : false,
     "storage.compression.block" : "snappy",
     "storage.global.cleanup.timeout" : 600,
diff --git a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_less/cluster_state_1_less.1.regexadm b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_less/cluster_state_1_less.1.regexadm
index 3349f11..bef14c1 100644
--- a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_less/cluster_state_1_less.1.regexadm
+++ b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_less/cluster_state_1_less.1.regexadm
@@ -44,7 +44,7 @@
     "replication\.log\.buffer\.numpages" : 8,
     "replication\.log\.buffer\.pagesize" : 131072,
     "replication\.strategy" : "none",
-    "replication\.timeout" : 30,
+    "replication\.timeout" : 120,
     "ssl\.enabled" : false,
     "storage.compression.block" : "snappy",
     "storage.global.cleanup.timeout" : 600,
diff --git a/asterixdb/asterix-common/src/main/java/org/apache/asterix/common/config/ReplicationProperties.java b/asterixdb/asterix-common/src/main/java/org/apache/asterix/common/config/ReplicationProperties.java
index dd42936..ada3875 100644
--- a/asterixdb/asterix-common/src/main/java/org/apache/asterix/common/config/ReplicationProperties.java
+++ b/asterixdb/asterix-common/src/main/java/org/apache/asterix/common/config/ReplicationProperties.java
@@ -48,7 +48,7 @@
                 "The size in bytes to replicate in each batch"),
         REPLICATION_TIMEOUT(
                 LONG,
-                TimeUnit.SECONDS.toSeconds(30),
+                TimeUnit.SECONDS.toSeconds(120),
                 "The time in seconds to timeout waiting for master or replica to ack"),
         REPLICATION_ENABLED(BOOLEAN, false, "Whether or not data replication is enabled"),
         REPLICATION_FACTOR(NONNEGATIVE_INTEGER, 2, "Number of replicas (backups) to maintain per master replica"),
diff --git a/asterixdb/asterix-replication/src/main/java/org/apache/asterix/replication/messaging/MarkComponentValidTask.java b/asterixdb/asterix-replication/src/main/java/org/apache/asterix/replication/messaging/MarkComponentValidTask.java
index 1ea076d..172bd59 100644
--- a/asterixdb/asterix-replication/src/main/java/org/apache/asterix/replication/messaging/MarkComponentValidTask.java
+++ b/asterixdb/asterix-replication/src/main/java/org/apache/asterix/replication/messaging/MarkComponentValidTask.java
@@ -37,12 +37,15 @@
 import org.apache.asterix.replication.sync.IndexSynchronizer;
 import org.apache.hyracks.api.exceptions.HyracksDataException;
 import org.apache.hyracks.storage.am.lsm.common.impls.IndexComponentFileReference;
+import org.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
 
 /**
  * A task to mark a replicated LSM component as valid
  */
 public class MarkComponentValidTask implements IReplicaTask {
 
+    private static final Logger LOGGER = LogManager.getLogger();
     private final long masterLsn;
     private final long lastComponentId;
     private final String file;
@@ -90,7 +93,9 @@
             // wait until the lsn mapping is flushed to disk
             while (!indexCheckpointManager.isFlushed(masterLsn)) {
                 if (replicationTimeOut <= 0) {
-                    throw new ReplicationException(new TimeoutException("Couldn't receive flush lsn from master"));
+                    LOGGER.warn("{} seconds passed without receiving flush lsn {} from master for component {}",
+                            appCtx.getReplicationProperties().getReplicationTimeOut(), masterLsn, file);
+                    throw new ReplicationException(new TimeoutException("couldn't receive flush lsn from master"));
                 }
                 final long startTime = System.nanoTime();
                 indexCheckpointManager.wait(replicationTimeOut);

-- 
To view, visit https://asterix-gerrit.ics.uci.edu/c/asterixdb/+/16125
To unsubscribe, or for help writing mail filters, visit https://asterix-gerrit.ics.uci.edu/settings

Gerrit-Project: asterixdb
Gerrit-Branch: master
Gerrit-Change-Id: I228620af371d651a84160231cdd832ca1087e7f9
Gerrit-Change-Number: 16125
Gerrit-PatchSet: 1
Gerrit-Owner: Dmitry Lychagin <dm...@couchbase.com>
Gerrit-Reviewer: Ali Alsuliman <al...@gmail.com>
Gerrit-Reviewer: Jenkins <je...@fulliautomatix.ics.uci.edu>
Gerrit-Reviewer: Murtadha Hubail <mh...@apache.org>
Gerrit-MessageType: newchange

Change in asterixdb[master]: [NO ISSUE][REP] Increase replication ack timeout

Posted by AsterixDB Code Review <do...@asterix-gerrit.ics.uci.edu>.
From Dmitry Lychagin <dm...@couchbase.com>:

Dmitry Lychagin has abandoned this change. ( https://asterix-gerrit.ics.uci.edu/c/asterixdb/+/16125 )

Change subject: [NO ISSUE][REP] Increase replication ack timeout
......................................................................


Abandoned
-- 
To view, visit https://asterix-gerrit.ics.uci.edu/c/asterixdb/+/16125
To unsubscribe, or for help writing mail filters, visit https://asterix-gerrit.ics.uci.edu/settings

Gerrit-Project: asterixdb
Gerrit-Branch: master
Gerrit-Change-Id: I228620af371d651a84160231cdd832ca1087e7f9
Gerrit-Change-Number: 16125
Gerrit-PatchSet: 1
Gerrit-Owner: Dmitry Lychagin <dm...@couchbase.com>
Gerrit-Reviewer: Ali Alsuliman <al...@gmail.com>
Gerrit-Reviewer: Jenkins <je...@fulliautomatix.ics.uci.edu>
Gerrit-Reviewer: Murtadha Hubail <mh...@apache.org>
Gerrit-MessageType: abandon

Change in asterixdb[master]: [NO ISSUE][REP] Increase replication ack timeout

Posted by AsterixDB Code Review <do...@asterix-gerrit.ics.uci.edu>.
From Dmitry Lychagin <dm...@couchbase.com>:

Hello Murtadha Hubail, Ali Alsuliman, Jenkins,

I'd like you to do a code review. Please visit

    https://asterix-gerrit.ics.uci.edu/c/asterixdb/+/16125

to review the following change.


Change subject: [NO ISSUE][REP] Increase replication ack timeout
......................................................................

[NO ISSUE][REP] Increase replication ack timeout

- user model changes: no
- storage format changes: no
- interface changes: no

Details:

- Increase replication ack timeout to 120 seconds.

Change-Id: I228620af371d651a84160231cdd832ca1087e7f9
Reviewed-on: https://asterix-gerrit.ics.uci.edu/c/asterixdb/+/15843
Reviewed-by: Ali Alsuliman <al...@gmail.com>
Integration-Tests: Jenkins <je...@fulliautomatix.ics.uci.edu>
Tested-by: Jenkins <je...@fulliautomatix.ics.uci.edu>
---
M asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1/cluster_state_1.1.regexadm
M asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_full/cluster_state_1_full.1.regexadm
M asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_less/cluster_state_1_less.1.regexadm
M asterixdb/asterix-common/src/main/java/org/apache/asterix/common/config/ReplicationProperties.java
M asterixdb/asterix-replication/src/main/java/org/apache/asterix/replication/messaging/MarkComponentValidTask.java
5 files changed, 10 insertions(+), 5 deletions(-)



  git pull ssh://asterix-gerrit.ics.uci.edu:29418/asterixdb refs/changes/25/16125/1

diff --git a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1/cluster_state_1.1.regexadm b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1/cluster_state_1.1.regexadm
index d99f2e9..54793dc 100644
--- a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1/cluster_state_1.1.regexadm
+++ b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1/cluster_state_1.1.regexadm
@@ -44,7 +44,7 @@
     "replication\.log\.buffer\.numpages" : 8,
     "replication\.log\.buffer\.pagesize" : 131072,
     "replication\.strategy" : "none",
-    "replication\.timeout" : 30,
+    "replication\.timeout" : 120,
     "ssl\.enabled" : false,
     "storage.compression.block" : "snappy",
     "storage.global.cleanup.timeout" : 600,
diff --git a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_full/cluster_state_1_full.1.regexadm b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_full/cluster_state_1_full.1.regexadm
index 479de3e..06da0ad 100644
--- a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_full/cluster_state_1_full.1.regexadm
+++ b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_full/cluster_state_1_full.1.regexadm
@@ -44,7 +44,7 @@
     "replication\.log\.buffer\.numpages" : 8,
     "replication\.log\.buffer\.pagesize" : 131072,
     "replication\.strategy" : "none",
-    "replication\.timeout" : 30,
+    "replication\.timeout" : 120,
     "ssl\.enabled" : false,
     "storage.compression.block" : "snappy",
     "storage.global.cleanup.timeout" : 600,
diff --git a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_less/cluster_state_1_less.1.regexadm b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_less/cluster_state_1_less.1.regexadm
index 3349f11..bef14c1 100644
--- a/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_less/cluster_state_1_less.1.regexadm
+++ b/asterixdb/asterix-app/src/test/resources/runtimets/results/api/cluster_state_1_less/cluster_state_1_less.1.regexadm
@@ -44,7 +44,7 @@
     "replication\.log\.buffer\.numpages" : 8,
     "replication\.log\.buffer\.pagesize" : 131072,
     "replication\.strategy" : "none",
-    "replication\.timeout" : 30,
+    "replication\.timeout" : 120,
     "ssl\.enabled" : false,
     "storage.compression.block" : "snappy",
     "storage.global.cleanup.timeout" : 600,
diff --git a/asterixdb/asterix-common/src/main/java/org/apache/asterix/common/config/ReplicationProperties.java b/asterixdb/asterix-common/src/main/java/org/apache/asterix/common/config/ReplicationProperties.java
index dd42936..ada3875 100644
--- a/asterixdb/asterix-common/src/main/java/org/apache/asterix/common/config/ReplicationProperties.java
+++ b/asterixdb/asterix-common/src/main/java/org/apache/asterix/common/config/ReplicationProperties.java
@@ -48,7 +48,7 @@
                 "The size in bytes to replicate in each batch"),
         REPLICATION_TIMEOUT(
                 LONG,
-                TimeUnit.SECONDS.toSeconds(30),
+                TimeUnit.SECONDS.toSeconds(120),
                 "The time in seconds to timeout waiting for master or replica to ack"),
         REPLICATION_ENABLED(BOOLEAN, false, "Whether or not data replication is enabled"),
         REPLICATION_FACTOR(NONNEGATIVE_INTEGER, 2, "Number of replicas (backups) to maintain per master replica"),
diff --git a/asterixdb/asterix-replication/src/main/java/org/apache/asterix/replication/messaging/MarkComponentValidTask.java b/asterixdb/asterix-replication/src/main/java/org/apache/asterix/replication/messaging/MarkComponentValidTask.java
index 1ea076d..172bd59 100644
--- a/asterixdb/asterix-replication/src/main/java/org/apache/asterix/replication/messaging/MarkComponentValidTask.java
+++ b/asterixdb/asterix-replication/src/main/java/org/apache/asterix/replication/messaging/MarkComponentValidTask.java
@@ -37,12 +37,15 @@
 import org.apache.asterix.replication.sync.IndexSynchronizer;
 import org.apache.hyracks.api.exceptions.HyracksDataException;
 import org.apache.hyracks.storage.am.lsm.common.impls.IndexComponentFileReference;
+import org.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
 
 /**
  * A task to mark a replicated LSM component as valid
  */
 public class MarkComponentValidTask implements IReplicaTask {
 
+    private static final Logger LOGGER = LogManager.getLogger();
     private final long masterLsn;
     private final long lastComponentId;
     private final String file;
@@ -90,7 +93,9 @@
             // wait until the lsn mapping is flushed to disk
             while (!indexCheckpointManager.isFlushed(masterLsn)) {
                 if (replicationTimeOut <= 0) {
-                    throw new ReplicationException(new TimeoutException("Couldn't receive flush lsn from master"));
+                    LOGGER.warn("{} seconds passed without receiving flush lsn {} from master for component {}",
+                            appCtx.getReplicationProperties().getReplicationTimeOut(), masterLsn, file);
+                    throw new ReplicationException(new TimeoutException("couldn't receive flush lsn from master"));
                 }
                 final long startTime = System.nanoTime();
                 indexCheckpointManager.wait(replicationTimeOut);

-- 
To view, visit https://asterix-gerrit.ics.uci.edu/c/asterixdb/+/16125
To unsubscribe, or for help writing mail filters, visit https://asterix-gerrit.ics.uci.edu/settings

Gerrit-Project: asterixdb
Gerrit-Branch: master
Gerrit-Change-Id: I228620af371d651a84160231cdd832ca1087e7f9
Gerrit-Change-Number: 16125
Gerrit-PatchSet: 1
Gerrit-Owner: Dmitry Lychagin <dm...@couchbase.com>
Gerrit-Reviewer: Ali Alsuliman <al...@gmail.com>
Gerrit-Reviewer: Jenkins <je...@fulliautomatix.ics.uci.edu>
Gerrit-Reviewer: Murtadha Hubail <mh...@apache.org>
Gerrit-MessageType: newchange