deniskuzZ commented on code in PR #3801: URL: https://github.com/apache/hive/pull/3801#discussion_r1084949145
########## 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) + && storageDescriptor.getOutputFormat().equalsIgnoreCase("org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat") + && !hasDeleteOrAbortedDirectories(directory, validWriteIdList); + } + + /** + * Scan a directory for delete deltas or aborted directories. + * @param directory the directory to be scanned + * @param validWriteIdList list of valid write IDs + * @return true, if delete or aborted directory found + */ + private boolean hasDeleteOrAbortedDirectories(AcidDirectory directory, ValidWriteIdList validWriteIdList) { + if (!directory.getCurrentDirectories().isEmpty()) { + final long minWriteId = validWriteIdList.getMinOpenWriteId() == null ? 1 : validWriteIdList.getMinOpenWriteId(); + final long maxWriteId = validWriteIdList.getHighWatermark(); + return directory.getCurrentDirectories().stream() + .filter(AcidUtils.ParsedDeltaLight::isDeleteDelta) + .filter(delta -> delta.getMinWriteId() >= minWriteId) + .anyMatch(delta -> delta.getMaxWriteId() <= maxWriteId) || !directory.getAbortedDirectories().isEmpty(); Review Comment: the question was why check the min/max writeId ranges if directory.getCurrentDirectories() should already be prefiltered based on validWriteIdList? -- 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: gitbox-unsubscr...@hive.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
