[
https://issues.apache.org/jira/browse/HIVE-27020?focusedWorklogId=852028&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-852028
]
ASF GitHub Bot logged work on HIVE-27020:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 21/Mar/23 14:03
Start Date: 21/Mar/23 14:03
Worklog Time Spent: 10m
Work Description: veghlaci05 commented on code in PR #4091:
URL: https://github.com/apache/hive/pull/4091#discussion_r1143419790
##########
ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/handler/AcidTxnCleaner.java:
##########
@@ -0,0 +1,125 @@
+/*
+ * 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.handler;
+
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hive.common.ValidReadTxnList;
+import org.apache.hadoop.hive.common.ValidReaderWriteIdList;
+import org.apache.hadoop.hive.common.ValidTxnList;
+import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.metastore.api.GetValidWriteIdsRequest;
+import org.apache.hadoop.hive.metastore.api.GetValidWriteIdsResponse;
+import org.apache.hadoop.hive.metastore.api.MetaException;
+import org.apache.hadoop.hive.metastore.api.NoSuchTxnException;
+import org.apache.hadoop.hive.metastore.api.Table;
+import org.apache.hadoop.hive.metastore.metrics.AcidMetricService;
+import org.apache.hadoop.hive.metastore.txn.AcidTxnInfo;
+import org.apache.hadoop.hive.metastore.txn.TxnCommonUtils;
+import org.apache.hadoop.hive.metastore.txn.TxnStore;
+import org.apache.hadoop.hive.ql.io.AcidDirectory;
+import org.apache.hadoop.hive.ql.io.AcidUtils;
+import
org.apache.hadoop.hive.ql.txn.compactor.CleanupRequest.CleanupRequestBuilder;
+import org.apache.hadoop.hive.ql.txn.compactor.CompactorUtil;
+import org.apache.hadoop.hive.ql.txn.compactor.FSRemover;
+import org.apache.hadoop.hive.ql.txn.compactor.MetadataCache;
+import org.apache.hive.common.util.Ref;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.util.BitSet;
+import java.util.Collections;
+import java.util.List;
+import java.util.Map;
+
+import static org.apache.commons.collections.ListUtils.subtract;
+
+/**
+ * An abstract class extending TaskHandler which contains the common methods
from
+ * CompactionCleaner and AbortedTxnCleaner.
+ */
+abstract class AcidTxnCleaner extends TaskHandler {
Review Comment:
Why not merge this class with `TaskHandler`? Both are abstract, and
TaskHandler has no other subclasses. I see no reason keeping these classes
separate.
##########
ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/handler/AbortedTxnCleaner.java:
##########
@@ -0,0 +1,168 @@
+/*
+ * 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.handler;
+
+import org.apache.hadoop.hive.common.ValidReaderWriteIdList;
+import org.apache.hadoop.hive.common.ValidTxnList;
+import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.metastore.api.MetaException;
+import org.apache.hadoop.hive.metastore.api.Partition;
+import org.apache.hadoop.hive.metastore.api.Table;
+import org.apache.hadoop.hive.metastore.metrics.MetricsConstants;
+import org.apache.hadoop.hive.metastore.metrics.PerfLogger;
+import org.apache.hadoop.hive.metastore.txn.AcidTxnInfo;
+import org.apache.hadoop.hive.metastore.txn.TxnStore;
+import org.apache.hadoop.hive.metastore.txn.TxnUtils;
+import org.apache.hadoop.hive.metastore.utils.MetaStoreUtils;
+import org.apache.hadoop.hive.ql.txn.compactor.CompactorUtil;
+import org.apache.hadoop.hive.ql.txn.compactor.CompactorUtil.ThrowingRunnable;
+import org.apache.hadoop.hive.ql.txn.compactor.FSRemover;
+import org.apache.hadoop.hive.ql.txn.compactor.MetadataCache;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.util.Collections;
+import java.util.List;
+import java.util.concurrent.TimeUnit;
+import java.util.stream.Collectors;
+
+import static java.util.Objects.isNull;
+
+/**
+ * Abort-cleanup based implementation of TaskHandler.
+ * Provides implementation of creation of abort clean tasks.
+ */
+class AbortedTxnCleaner extends AcidTxnCleaner {
Review Comment:
+1 I think we should have a dedicated Unit test class for it.
Issue Time Tracking
-------------------
Worklog Id: (was: 852028)
Time Spent: 3h 40m (was: 3.5h)
> Implement a separate handler to handle aborted transaction cleanup
> ------------------------------------------------------------------
>
> Key: HIVE-27020
> URL: https://issues.apache.org/jira/browse/HIVE-27020
> Project: Hive
> Issue Type: Sub-task
> Reporter: Sourabh Badhya
> Assignee: Sourabh Badhya
> Priority: Major
> Labels: pull-request-available
> Time Spent: 3h 40m
> Remaining Estimate: 0h
>
> As described in the parent task, once the cleaner is separated into different
> entities, implement a separate handler which can create requests for aborted
> transactions cleanup. This would move the aborted transaction cleanup
> exclusively to the cleaner.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
