jihoonson commented on a change in pull request #11294: URL: https://github.com/apache/druid/pull/11294#discussion_r665812457
########## File path: server/src/test/java/org/apache/druid/segment/realtime/appenderator/BatchAppenderatorTester.java ########## @@ -0,0 +1,859 @@ +/* + * 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.annotation.JsonCreator; +import com.fasterxml.jackson.annotation.JsonProperty; +import com.fasterxml.jackson.databind.ObjectMapper; +import com.google.common.base.Preconditions; +import org.apache.druid.data.input.impl.DimensionsSpec; +import org.apache.druid.data.input.impl.JSONParseSpec; +import org.apache.druid.data.input.impl.MapInputRowParser; +import org.apache.druid.data.input.impl.TimestampSpec; +import org.apache.druid.indexer.partitions.DynamicPartitionsSpec; +import org.apache.druid.indexer.partitions.HashedPartitionsSpec; +import org.apache.druid.indexer.partitions.PartitionsSpec; +import org.apache.druid.jackson.DefaultObjectMapper; +import org.apache.druid.java.util.common.FileUtils; +import org.apache.druid.java.util.common.IAE; +import org.apache.druid.java.util.common.granularity.Granularities; +import org.apache.druid.java.util.emitter.EmittingLogger; +import org.apache.druid.java.util.emitter.core.NoopEmitter; +import org.apache.druid.java.util.emitter.service.ServiceEmitter; +import org.apache.druid.query.aggregation.AggregatorFactory; +import org.apache.druid.query.aggregation.CountAggregatorFactory; +import org.apache.druid.query.aggregation.LongSumAggregatorFactory; +import org.apache.druid.segment.IndexIO; +import org.apache.druid.segment.IndexMerger; +import org.apache.druid.segment.IndexMergerV9; +import org.apache.druid.segment.IndexSpec; +import org.apache.druid.segment.column.ColumnConfig; +import org.apache.druid.segment.incremental.AppendableIndexSpec; +import org.apache.druid.segment.incremental.ParseExceptionHandler; +import org.apache.druid.segment.incremental.RowIngestionMeters; +import org.apache.druid.segment.incremental.SimpleRowIngestionMeters; +import org.apache.druid.segment.indexing.DataSchema; +import org.apache.druid.segment.indexing.TuningConfig; +import org.apache.druid.segment.indexing.granularity.UniformGranularitySpec; +import org.apache.druid.segment.loading.DataSegmentPusher; +import org.apache.druid.segment.realtime.FireDepartmentMetrics; +import org.apache.druid.segment.writeout.OffHeapMemorySegmentWriteOutMediumFactory; +import org.apache.druid.segment.writeout.SegmentWriteOutMediumFactory; +import org.apache.druid.timeline.DataSegment; +import org.apache.druid.timeline.partition.LinearShardSpec; +import org.joda.time.Period; + +import javax.annotation.Nullable; +import java.io.File; +import java.io.IOException; +import java.net.URI; +import java.util.Collections; +import java.util.List; +import java.util.Map; +import java.util.Objects; +import java.util.concurrent.CopyOnWriteArrayList; + +public class BatchAppenderatorTester implements AutoCloseable +{ + public static final String DATASOURCE = "foo"; + + private final DataSchema schema; + private final AppenderatorConfig tuningConfig; + private final FireDepartmentMetrics metrics; + private final DataSegmentPusher dataSegmentPusher; + private final ObjectMapper objectMapper; + private final Appenderator appenderator; + private final ServiceEmitter emitter; + + private final List<DataSegment> pushedSegments = new CopyOnWriteArrayList<>(); + + public BatchAppenderatorTester( + final int maxRowsInMemory + ) + { + this(maxRowsInMemory, -1, null, false); + } + + public BatchAppenderatorTester( + final int maxRowsInMemory, + final boolean enablePushFailure + ) + { + this(maxRowsInMemory, -1, null, enablePushFailure); + } + + public BatchAppenderatorTester( + final int maxRowsInMemory, + final long maxSizeInBytes, + final boolean enablePushFailure + ) + { + this(maxRowsInMemory, maxSizeInBytes, null, enablePushFailure); + } + + public BatchAppenderatorTester( + final int maxRowsInMemory, + final long maxSizeInBytes, + final File basePersistDirectory, + final boolean enablePushFailure + ) + { + this( + maxRowsInMemory, + maxSizeInBytes, + basePersistDirectory, + enablePushFailure, + new SimpleRowIngestionMeters(), + false, + false + ); + } + + public BatchAppenderatorTester( + final int maxRowsInMemory, + final long maxSizeInBytes, + @Nullable final File basePersistDirectory, + final boolean enablePushFailure, + final RowIngestionMeters rowIngestionMeters + ) + { + this(maxRowsInMemory, maxSizeInBytes, basePersistDirectory, enablePushFailure, rowIngestionMeters, + false, false + ); + } + + public BatchAppenderatorTester( + final int maxRowsInMemory, + final long maxSizeInBytes, + @Nullable final File basePersistDirectory, + final boolean enablePushFailure, + final RowIngestionMeters rowIngestionMeters, + final boolean skipBytesInMemoryOverheadCheck, + final boolean batchFallback + ) + { + objectMapper = new DefaultObjectMapper(); + objectMapper.registerSubtypes(LinearShardSpec.class); + + final Map<String, Object> parserMap = objectMapper.convertValue( + new MapInputRowParser( + new JSONParseSpec( + new TimestampSpec("ts", "auto", null), + new DimensionsSpec(null, null, null), + null, + null, + null + ) + ), + Map.class + ); + schema = new DataSchema( + DATASOURCE, + parserMap, + new AggregatorFactory[]{ + new CountAggregatorFactory("count"), + new LongSumAggregatorFactory("met", "met") + }, + new UniformGranularitySpec(Granularities.MINUTE, Granularities.NONE, null), + null, + objectMapper + ); + tuningConfig = new IndexTuningConfig( + null, + 2, + null, + maxRowsInMemory, + maxSizeInBytes == 0L ? getDefaultMaxBytesInMemory() : maxSizeInBytes, + skipBytesInMemoryOverheadCheck, + null, + null, + null, + null, + null, + null, + null, + null, + null, + null, + null, + null, + OffHeapMemorySegmentWriteOutMediumFactory.instance(), + true, + null, + null, + null, + null + ).withBasePersistDirectory(basePersistDirectory != null ? basePersistDirectory : createNewBasePersistDirectory()); + + metrics = new FireDepartmentMetrics(); + + IndexIO indexIO = new IndexIO( + objectMapper, + new ColumnConfig() + { + @Override + public int columnCacheSizeBytes() + { + return 0; + } + } + ); + IndexMerger indexMerger = new IndexMergerV9( + objectMapper, + indexIO, + OffHeapMemorySegmentWriteOutMediumFactory.instance() + ); + + emitter = new ServiceEmitter( + "test", + "test", + new NoopEmitter() + ); + emitter.start(); + EmittingLogger.registerEmitter(emitter); + dataSegmentPusher = new DataSegmentPusher() + { + private boolean mustFail = true; + + @Deprecated + @Override + public String getPathForHadoop(String dataSource) + { + return getPathForHadoop(); + } + + @Override + public String getPathForHadoop() + { + throw new UnsupportedOperationException(); + } + + @Override + public DataSegment push(File file, DataSegment segment, boolean useUniquePath) throws IOException + { + if (enablePushFailure && mustFail) { + mustFail = false; + throw new IOException("Push failure test"); + } else if (enablePushFailure) { + mustFail = true; + } + pushedSegments.add(segment); + return segment; + } + + @Override + public Map<String, Object> makeLoadSpec(URI uri) + { + throw new UnsupportedOperationException(); + } + }; + appenderator = Appenderators.createOffline( + schema.getDataSource(), + schema, + tuningConfig, + metrics, + dataSegmentPusher, + objectMapper, + indexIO, + indexMerger, + rowIngestionMeters, + new ParseExceptionHandler(rowIngestionMeters, false, Integer.MAX_VALUE, 0), + batchFallback + ); + } + + private long getDefaultMaxBytesInMemory() + { + return (Runtime.getRuntime().totalMemory()) / 3; + } + + public DataSchema getSchema() + { + return schema; + } + + public AppenderatorConfig getTuningConfig() + { + return tuningConfig; + } + + public FireDepartmentMetrics getMetrics() + { + return metrics; + } + + public ObjectMapper getObjectMapper() + { + return objectMapper; + } + + public Appenderator getAppenderator() + { + return appenderator; + } + + public List<DataSegment> getPushedSegments() + { + return pushedSegments; + } + + @Override + public void close() throws Exception + { + appenderator.close(); + emitter.close(); + FileUtils.deleteDirectory(tuningConfig.getBasePersistDirectory()); + } + + private static File createNewBasePersistDirectory() + { + return FileUtils.createTempDir("druid-batch-persist"); + } + + + // copied from druid-indexing as is for testing since it is not accessible from server module, + // we could simplify since not all its functionality is being used + // but leaving as is, it could be useful later + private static class IndexTuningConfig implements AppenderatorConfig Review comment: I don't agree that it's already simple enough. Why is it Jackson-serializable? It doesn't seem to be used in any test. Besides this, I also see lots of methods and parameters deprecated, not in use at all, or not used in any test. I can leave comments on them to help you identify them if you want. I don't think we should keep this code if the reason is just that we might need them in the future. It will be easy to add them back if we need, or we can do even better than now. -- 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]
