You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hbase.apache.org by GitBox <gi...@apache.org> on 2021/08/25 14:16:52 UTC
[GitHub] [hbase] wchevreuil commented on a change in pull request #3578: HBASE-25988 Store the store file list by a file
wchevreuil commented on a change in pull request #3578:
URL: https://github.com/apache/hbase/pull/3578#discussion_r695745747
##########
File path: hbase-server/src/main/java/org/apache/hadoop/hbase/regionserver/storefiletracker/FileBasedStoreFileTracker.java
##########
@@ -0,0 +1,135 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.hadoop.hbase.regionserver.storefiletracker;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+import java.util.stream.Collectors;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hbase.regionserver.StoreContext;
+import org.apache.hadoop.hbase.regionserver.StoreFileInfo;
+import org.apache.hadoop.hbase.util.ServerRegionReplicaUtil;
+import org.apache.yetus.audience.InterfaceAudience;
+
+import org.apache.hadoop.hbase.shaded.protobuf.generated.StoreFileTrackerProtos.StoreFileEntry;
+import org.apache.hadoop.hbase.shaded.protobuf.generated.StoreFileTrackerProtos.StoreFileList;
+
+/**
+ * A file based store file tracker.
+ * <p/>
+ * For this tracking way, the store file list will be persistent into a file, so we can write the
+ * new store files directly to the final data directory, as we will not load the broken files. This
+ * will greatly reduce the time for flush and compaction on some object storages as a rename is
+ * actual a copy on them. And it also avoid listing when loading store file list, which could also
+ * speed up the loading of store files as listing is also not a fast operation on most object
+ * storages.
+ */
+@InterfaceAudience.Private
+public class FileBasedStoreFileTracker extends StoreFileTrackerBase {
+
+ private final StoreFileListFile backedFile;
+
+ private final Map<String, StoreFileInfo> storefiles = new HashMap<>();
+
+ public FileBasedStoreFileTracker(Configuration conf, boolean isPrimaryReplica, StoreContext ctx) {
+ super(conf, isPrimaryReplica, ctx);
+ backedFile = new StoreFileListFile(ctx);
+ }
+
+ @Override
+ public List<StoreFileInfo> load() throws IOException {
+ StoreFileList list = backedFile.load();
+ if (list == null) {
+ return Collections.emptyList();
+ }
+ FileSystem fs = ctx.getRegionFileSystem().getFileSystem();
+ List<StoreFileInfo> infos = new ArrayList<>();
+ for (StoreFileEntry entry : list.getStoreFileList()) {
+ infos.add(ServerRegionReplicaUtil.getStoreFileInfo(conf, fs, ctx.getRegionInfo(),
+ ctx.getRegionFileSystem().getRegionInfoForFS(), ctx.getFamily().getNameAsString(),
+ new Path(ctx.getFamilyStoreDirectoryPath(), entry.getName())));
+ }
+ synchronized (storefiles) {
+ for (StoreFileInfo info : infos) {
+ storefiles.put(info.getPath().getName(), info);
+ }
+ }
Review comment:
Do we need synchronized here? Isn't load called once store initialization, meaning all other ops reading storefiles map wouldn't actually happen yet?
##########
File path: hbase-server/src/main/java/org/apache/hadoop/hbase/regionserver/storefiletracker/FileBasedStoreFileTracker.java
##########
@@ -0,0 +1,135 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.hadoop.hbase.regionserver.storefiletracker;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+import java.util.stream.Collectors;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hbase.regionserver.StoreContext;
+import org.apache.hadoop.hbase.regionserver.StoreFileInfo;
+import org.apache.hadoop.hbase.util.ServerRegionReplicaUtil;
+import org.apache.yetus.audience.InterfaceAudience;
+
+import org.apache.hadoop.hbase.shaded.protobuf.generated.StoreFileTrackerProtos.StoreFileEntry;
+import org.apache.hadoop.hbase.shaded.protobuf.generated.StoreFileTrackerProtos.StoreFileList;
+
+/**
+ * A file based store file tracker.
+ * <p/>
+ * For this tracking way, the store file list will be persistent into a file, so we can write the
+ * new store files directly to the final data directory, as we will not load the broken files. This
+ * will greatly reduce the time for flush and compaction on some object storages as a rename is
+ * actual a copy on them. And it also avoid listing when loading store file list, which could also
+ * speed up the loading of store files as listing is also not a fast operation on most object
+ * storages.
+ */
+@InterfaceAudience.Private
+public class FileBasedStoreFileTracker extends StoreFileTrackerBase {
+
+ private final StoreFileListFile backedFile;
+
+ private final Map<String, StoreFileInfo> storefiles = new HashMap<>();
+
+ public FileBasedStoreFileTracker(Configuration conf, boolean isPrimaryReplica, StoreContext ctx) {
+ super(conf, isPrimaryReplica, ctx);
+ backedFile = new StoreFileListFile(ctx);
+ }
+
+ @Override
+ public List<StoreFileInfo> load() throws IOException {
+ StoreFileList list = backedFile.load();
+ if (list == null) {
+ return Collections.emptyList();
+ }
+ FileSystem fs = ctx.getRegionFileSystem().getFileSystem();
+ List<StoreFileInfo> infos = new ArrayList<>();
+ for (StoreFileEntry entry : list.getStoreFileList()) {
+ infos.add(ServerRegionReplicaUtil.getStoreFileInfo(conf, fs, ctx.getRegionInfo(),
+ ctx.getRegionFileSystem().getRegionInfoForFS(), ctx.getFamily().getNameAsString(),
+ new Path(ctx.getFamilyStoreDirectoryPath(), entry.getName())));
+ }
+ synchronized (storefiles) {
+ for (StoreFileInfo info : infos) {
+ storefiles.put(info.getPath().getName(), info);
+ }
+ }
+ return infos;
+ }
+
+ @Override
+ protected boolean requireWritingToTmpDirFirst() {
+ return false;
+ }
+
+ private StoreFileEntry toStoreFileEntry(StoreFileInfo info) {
+ return StoreFileEntry.newBuilder().setName(info.getPath().getName()).setSize(info.getSize())
+ .build();
+ }
+
+ @Override
+ protected void doAddNewStoreFiles(Collection<StoreFileInfo> newFiles) throws IOException {
+ synchronized (storefiles) {
+ StoreFileList.Builder builder = StoreFileList.newBuilder();
+ for (StoreFileInfo info : storefiles.values()) {
+ builder.addStoreFile(toStoreFileEntry(info));
+ }
+ for (StoreFileInfo info : newFiles) {
+ builder.addStoreFile(toStoreFileEntry(info));
+ }
+ backedFile.update(builder);
+ for (StoreFileInfo info : newFiles) {
+ storefiles.put(info.getPath().getName(), info);
Review comment:
Do we really need `storefiles` to be a map? Feels like we could save on some loops if it was a list of StoreFileInfo.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscribe@hbase.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org