[
https://issues.apache.org/jira/browse/HIVE-22977?focusedWorklogId=841208&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-841208
]
ASF GitHub Bot logged work on HIVE-22977:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 23/Jan/23 18:32
Start Date: 23/Jan/23 18:32
Worklog Time Spent: 10m
Work Description: SourabhBadhya commented on code in PR #3801:
URL: https://github.com/apache/hive/pull/3801#discussion_r1084407044
##########
ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/MergeCompactor.java:
##########
@@ -0,0 +1,210 @@
+/*
+ * 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.hive.ql.txn.compactor;
+
+import org.apache.hadoop.fs.FileStatus;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hive.common.ValidWriteIdList;
+import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.metastore.api.Partition;
+import org.apache.hadoop.hive.metastore.api.StorageDescriptor;
+import org.apache.hadoop.hive.metastore.api.Table;
+import org.apache.hadoop.hive.metastore.txn.CompactionInfo;
+import org.apache.hadoop.hive.ql.io.AcidDirectory;
+import org.apache.hadoop.hive.ql.io.AcidOutputFormat;
+import org.apache.hadoop.hive.ql.io.AcidUtils;
+import org.apache.hadoop.hive.ql.io.orc.OrcFile;
+import org.apache.hadoop.hive.ql.io.orc.Reader;
+import org.apache.hadoop.hive.ql.metadata.HiveException;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.regex.Matcher;
+
+final class MergeCompactor extends QueryCompactor {
+
+ private static final Logger LOG =
LoggerFactory.getLogger(MergeCompactor.class.getName());
+
+ @Override
+ public boolean run(HiveConf hiveConf, Table table, Partition partition,
StorageDescriptor storageDescriptor,
+ ValidWriteIdList writeIds, CompactionInfo compactionInfo,
AcidDirectory dir) throws IOException, HiveException, InterruptedException {
+ if (isMergeCompaction(hiveConf, dir, writeIds, storageDescriptor)) {
+ // Only inserts happened, it is much more performant to merge the files
than running a query
+ Path outputDirPath = getCompactionOutputDirPath(hiveConf, writeIds,
+ compactionInfo.isMajorCompaction(), storageDescriptor);
+ try {
+ return mergeOrcFiles(hiveConf, compactionInfo.isMajorCompaction(),
+ dir, outputDirPath,
AcidUtils.isInsertOnlyTable(table.getParameters()));
+ } catch (Throwable t) {
+ // Error handling, just delete the output directory,
+ // and fall back to query based compaction.
+ FileSystem fs = outputDirPath.getFileSystem(hiveConf);
+ if (fs.exists(outputDirPath)) {
+ fs.delete(outputDirPath, true);
+ }
+ return false;
+ }
+ } else {
+ return false;
+ }
+ }
+
+ /**
+ * Returns whether merge compaction must be enabled or not.
+ * @param conf Hive configuration
+ * @param directory the directory to be scanned
+ * @param validWriteIdList list of valid write IDs
+ * @param storageDescriptor storage descriptor of the underlying table
+ * @return true, if merge compaction must be enabled
+ */
+ private boolean isMergeCompaction(HiveConf conf, AcidDirectory directory,
+ ValidWriteIdList validWriteIdList,
+ StorageDescriptor storageDescriptor) {
+ return conf.getBoolVar(HiveConf.ConfVars.HIVE_MERGE_COMPACTION_ENABLED)
Review Comment:
Done.
Issue Time Tracking
-------------------
Worklog Id: (was: 841208)
Time Spent: 7h 10m (was: 7h)
> Merge delta files instead of running a query in major/minor compaction
> ----------------------------------------------------------------------
>
> Key: HIVE-22977
> URL: https://issues.apache.org/jira/browse/HIVE-22977
> Project: Hive
> Issue Type: Improvement
> Reporter: László Pintér
> Assignee: Sourabh Badhya
> Priority: Major
> Labels: pull-request-available
> Attachments: HIVE-22977.01.patch, HIVE-22977.02.patch
>
> Time Spent: 7h 10m
> Remaining Estimate: 0h
>
> [Compaction Optimiziation]
> We should analyse the possibility to move a delta file instead of running a
> major/minor compaction query.
> Please consider the following use cases:
> - full acid table but only insert queries were run. This means that no
> delete delta directories were created. Is it possible to merge the delta
> directory contents without running a compaction query?
> - full acid table, initiating queries through the streaming API. If there
> are no abort transactions during the streaming, is it possible to merge the
> delta directory contents without running a compaction query?
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
