kfaraz commented on code in PR #20006: URL: https://github.com/apache/druid/pull/20006#discussion_r3782086736
########## processing/src/main/java/org/apache/druid/timeline/SegmentDetail.java: ########## @@ -0,0 +1,132 @@ +/* + * 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.timeline; + +import com.fasterxml.jackson.annotation.JsonCreator; +import com.fasterxml.jackson.annotation.JsonValue; +import org.apache.druid.java.util.common.IAE; + +import javax.annotation.Nullable; +import java.util.Collection; +import java.util.EnumSet; + +/** + * The optional top-level fields of a {@link DataSegment}: the ones that a segment can be returned without, so that a + * caller that does not need them can avoid paying for them in serialization size and heap. + * <p> + * The rest of {@link DataSegment} is never optional: {@link DataSegment#getId()} (and therefore the dataSource, + * interval, and version), {@link DataSegment#getShardSpec()}, {@link DataSegment#getBinaryVersion()}, and + * {@link DataSegment#getSize()} are always populated. + * <p> + * Use {@link DataSegment#retainOnlyDetails} to drop the details that are not wanted. + * + * @see org.apache.druid.indexing.common.actions.RetrieveUsedSegmentsAction + */ +public enum SegmentDetail Review Comment: would `SegmentMetadataField` be a better name? ########## indexing-service/src/main/java/org/apache/druid/indexing/common/actions/RetrieveUsedSegmentsAction.java: ########## @@ -112,6 +160,11 @@ public TypeReference<Collection<DataSegment>> getReturnTypeReference() @Override public Collection<DataSegment> perform(Task task, TaskActionToolbox toolbox) + { + return retainRequestedDetails(retrieveSegments(task, toolbox)); Review Comment: We could consider pushing down the details filter to the storage layer, at least for the `SegmentDetail.none()` since that translates to just fetching the used segment IDs, which could be answered by the primary key itself. That said, the segment metadata incremental cache is now enabled by default on Overlord, so I am not sure if it would really add much value. ########## server/src/main/java/org/apache/druid/segment/realtime/appenderator/BaseAppenderatorDriver.java: ########## @@ -686,12 +687,18 @@ ListenableFuture<SegmentsAndCommitMetadata> publishInBackground( // Clean up pushed segments if they are physically disjoint from the published ones (this means // they were probably pushed by a replica, and with the unique paths option). - final boolean physicallyDisjoint = Sets.intersection( - publishedSegments.stream().map(DataSegment::getLoadSpec).collect(Collectors.toSet()), - ourSegments.stream().map(DataSegment::getLoadSpec).collect(Collectors.toSet()) - ).isEmpty(); + final Set<Map<String, Object>> publishedLoadSpecs = + publishedSegments.stream().map(DataSegment::getLoadSpec).collect(Collectors.toSet()); + final Set<Map<String, Object>> ourLoadSpecs = + ourSegments.stream().map(DataSegment::getLoadSpec).collect(Collectors.toSet()); + + if (publishedLoadSpecs.contains(null) || ourLoadSpecs.contains(null)) { + // We don't expect loadSpecs to be missing. If they are, it may indicate a bug in something. + throw DruidException.defensive("Unexpectedly null loadSpec encountered"); Review Comment: Might be useful to include the segment ID which had a null load spec. -- 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]
