jihoonson commented on a change in pull request #5492: Native parallel batch indexing without shuffle URL: https://github.com/apache/incubator-druid/pull/5492#discussion_r203215030
########## File path: indexing-service/src/main/java/io/druid/indexing/common/task/ParallelIndexSubTask.java ########## @@ -0,0 +1,431 @@ +/* + * 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 io.druid.indexing.common.task; + +import com.fasterxml.jackson.annotation.JacksonInject; +import com.fasterxml.jackson.annotation.JsonCreator; +import com.fasterxml.jackson.annotation.JsonProperty; +import com.google.common.base.Optional; +import com.google.common.base.Preconditions; +import io.druid.client.indexing.IndexingServiceClient; +import io.druid.data.input.Firehose; +import io.druid.data.input.FirehoseFactory; +import io.druid.data.input.InputRow; +import io.druid.indexer.TaskStatus; +import io.druid.indexing.appenderator.ActionBasedSegmentAllocator; +import io.druid.indexing.appenderator.ActionBasedUsedSegmentChecker; +import io.druid.indexing.common.TaskLockType; +import io.druid.indexing.common.TaskToolbox; +import io.druid.indexing.common.actions.LockTryAcquireAction; +import io.druid.indexing.common.actions.SegmentAllocateAction; +import io.druid.indexing.common.actions.SurrogateAction; +import io.druid.indexing.common.actions.TaskActionClient; +import io.druid.indexing.firehose.IngestSegmentFirehoseFactory; +import io.druid.java.util.common.ISE; +import io.druid.java.util.common.Intervals; +import io.druid.java.util.common.StringUtils; +import io.druid.java.util.common.logger.Logger; +import io.druid.java.util.common.parsers.ParseException; +import io.druid.query.DruidMetrics; +import io.druid.segment.indexing.DataSchema; +import io.druid.segment.indexing.RealtimeIOConfig; +import io.druid.segment.indexing.granularity.GranularitySpec; +import io.druid.segment.realtime.FireDepartment; +import io.druid.segment.realtime.FireDepartmentMetrics; +import io.druid.segment.realtime.RealtimeMetricsMonitor; +import io.druid.segment.realtime.appenderator.Appenderator; +import io.druid.segment.realtime.appenderator.AppenderatorDriverAddResult; +import io.druid.segment.realtime.appenderator.Appenderators; +import io.druid.segment.realtime.appenderator.BaseAppenderatorDriver; +import io.druid.segment.realtime.appenderator.BatchAppenderatorDriver; +import io.druid.segment.realtime.appenderator.SegmentAllocator; +import io.druid.segment.realtime.appenderator.SegmentsAndMetadata; +import io.druid.timeline.DataSegment; +import org.apache.commons.io.FileUtils; +import org.joda.time.Interval; + +import javax.annotation.Nullable; +import java.io.File; +import java.io.IOException; +import java.util.ArrayList; +import java.util.Collections; +import java.util.List; +import java.util.Map; +import java.util.SortedSet; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.TimeoutException; + +/** + * A worker task of {@link ParallelIndexSupervisorTask}. Similar to {@link IndexTask}, but this task + * generates and pushes segments, and reports them to the {@link ParallelIndexSupervisorTask} instead of + * publishing on its own. + */ +public class ParallelIndexSubTask extends AbstractTask Review comment: Those are main differences, and one another thing is that `ParallelIndexSubTask` doesn't collect HLL which is required for perfect rollup. The `IndexTask` would be deprecated once parallel indexing supports perfect rollup and becomes stable, so I think it's easier to maintain both tasks while developing, and delete the deprecated one later. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: dev-unsubscr...@druid.apache.org For additional commands, e-mail: dev-h...@druid.apache.org
