loquisgon commented on a change in pull request #11294: URL: https://github.com/apache/druid/pull/11294#discussion_r665806195
########## File path: server/src/main/java/org/apache/druid/segment/realtime/appenderator/BatchAppenderator.java ########## @@ -0,0 +1,1141 @@ +/* + * 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.druid.segment.realtime.appenderator; + +import com.fasterxml.jackson.databind.ObjectMapper; +import com.google.common.annotations.VisibleForTesting; +import com.google.common.base.Preconditions; +import com.google.common.base.Stopwatch; +import com.google.common.base.Supplier; +import com.google.common.collect.ImmutableList; +import com.google.common.collect.Iterables; +import com.google.common.collect.Lists; +import com.google.common.primitives.Ints; +import com.google.common.util.concurrent.Futures; +import com.google.common.util.concurrent.ListenableFuture; +import org.apache.druid.data.input.Committer; +import org.apache.druid.data.input.InputRow; +import org.apache.druid.java.util.common.FileUtils; +import org.apache.druid.java.util.common.IAE; +import org.apache.druid.java.util.common.ISE; +import org.apache.druid.java.util.common.Pair; +import org.apache.druid.java.util.common.RetryUtils; +import org.apache.druid.java.util.common.StringUtils; +import org.apache.druid.java.util.common.io.Closer; +import org.apache.druid.java.util.emitter.EmittingLogger; +import org.apache.druid.query.Query; +import org.apache.druid.query.QueryRunner; +import org.apache.druid.query.SegmentDescriptor; +import org.apache.druid.segment.IndexIO; +import org.apache.druid.segment.IndexMerger; +import org.apache.druid.segment.QueryableIndex; +import org.apache.druid.segment.QueryableIndexSegment; +import org.apache.druid.segment.ReferenceCountingSegment; +import org.apache.druid.segment.incremental.IncrementalIndexAddResult; +import org.apache.druid.segment.incremental.IndexSizeExceededException; +import org.apache.druid.segment.incremental.ParseExceptionHandler; +import org.apache.druid.segment.incremental.RowIngestionMeters; +import org.apache.druid.segment.indexing.DataSchema; +import org.apache.druid.segment.loading.DataSegmentPusher; +import org.apache.druid.segment.realtime.FireDepartmentMetrics; +import org.apache.druid.segment.realtime.FireHydrant; +import org.apache.druid.segment.realtime.plumber.Sink; +import org.apache.druid.timeline.DataSegment; +import org.joda.time.Interval; + +import javax.annotation.Nullable; +import java.io.Closeable; +import java.io.File; +import java.io.IOException; +import java.nio.channels.FileChannel; +import java.nio.channels.FileLock; +import java.nio.file.StandardOpenOption; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collection; +import java.util.List; +import java.util.Map; +import java.util.concurrent.ConcurrentHashMap; +import java.util.concurrent.ConcurrentMap; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.atomic.AtomicBoolean; +import java.util.concurrent.atomic.AtomicInteger; +import java.util.concurrent.atomic.AtomicLong; +import java.util.stream.Collectors; + +public class BatchAppenderator implements Appenderator +{ + public static final int ROUGH_OVERHEAD_PER_SINK = 5000; + // Rough estimate of memory footprint of empty FireHydrant based on actual heap dumps + public static final int ROUGH_OVERHEAD_PER_HYDRANT = 1000; + + private static final EmittingLogger log = new EmittingLogger(BatchAppenderator.class); + private static final String IDENTIFIER_FILE_NAME = "identifier.json"; + + private final String myId; + private final DataSchema schema; + private final AppenderatorConfig tuningConfig; + private final FireDepartmentMetrics metrics; + private final DataSegmentPusher dataSegmentPusher; + private final ObjectMapper objectMapper; + private final IndexIO indexIO; + private final IndexMerger indexMerger; + /** + * This map needs to be concurrent because it's accessed and mutated from multiple threads from where + * this Appenderator is used (and methods like {@link #add(SegmentIdWithShardSpec, InputRow, Supplier, boolean)} are + * called). It could also be accessed (but not mutated) potentially in the context + * of any thread from {@link #drop}. + */ + private final ConcurrentMap<SegmentIdWithShardSpec, Sink> sinks = new ConcurrentHashMap<>(); + private final long maxBytesTuningConfig; + private final boolean skipBytesInMemoryOverheadCheck; + + /** + * The following sinks metadata map and associated class are the way to retain metadata now that sinks + * are being completely removed from memory after each incremental persist. + */ + private final ConcurrentHashMap<SegmentIdWithShardSpec, SinkMetadata> sinksMetadata = new ConcurrentHashMap<>(); + + /** + * This class is used for information that needs to be kept related to Sinks as + * they are persisted and removed from memory at every incremental persist. + * The information is used for sanity checks and as information required + * for functionality, depending in the field that is used. More info about the + * fields is annotated as comments in the class + */ + private static class SinkMetadata Review comment: Done -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
