mxm commented on code in PR #13080: URL: https://github.com/apache/iceberg/pull/13080#discussion_r2100619141
########## flink/v2.0/flink/src/main/java/org/apache/iceberg/flink/sink/dynamic/DynamicWriteResultAggregator.java: ########## @@ -0,0 +1,190 @@ +/* + * 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.iceberg.flink.sink.dynamic; + +import com.github.benmanes.caffeine.cache.Cache; +import com.github.benmanes.caffeine.cache.Caffeine; +import java.io.IOException; +import java.time.Duration; +import java.util.Collection; +import java.util.Map; +import org.apache.flink.annotation.Internal; +import org.apache.flink.core.io.SimpleVersionedSerialization; +import org.apache.flink.streaming.api.connector.sink2.CommittableMessage; +import org.apache.flink.streaming.api.connector.sink2.CommittableSummary; +import org.apache.flink.streaming.api.connector.sink2.CommittableWithLineage; +import org.apache.flink.streaming.api.operators.AbstractStreamOperator; +import org.apache.flink.streaming.api.operators.OneInputStreamOperator; +import org.apache.flink.streaming.runtime.streamrecord.StreamRecord; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Table; +import org.apache.iceberg.catalog.Catalog; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.flink.CatalogLoader; +import org.apache.iceberg.flink.sink.DeltaManifests; +import org.apache.iceberg.flink.sink.DeltaManifestsSerializer; +import org.apache.iceberg.flink.sink.FlinkManifestUtil; +import org.apache.iceberg.flink.sink.IcebergCommittable; +import org.apache.iceberg.flink.sink.ManifestOutputFileFactory; +import org.apache.iceberg.io.WriteResult; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +/** + * Operator which aggregates the individual {@link WriteResult} objects to a single {@link + * IcebergCommittable} per checkpoint (storing the serialized {@link DeltaManifests}, jobId, + * operatorId, checkpointId) + */ +@Internal +class DynamicWriteResultAggregator + extends AbstractStreamOperator<CommittableMessage<DynamicCommittable>> + implements OneInputStreamOperator< + CommittableMessage<DynamicWriteResult>, CommittableMessage<DynamicCommittable>> { + private static final Logger LOG = LoggerFactory.getLogger(DynamicWriteResultAggregator.class); + private static final byte[] EMPTY_MANIFEST_DATA = new byte[0]; + private static final Duration CACHE_EXPIRATION_DURATION = Duration.ofMinutes(1); + + private final CatalogLoader catalogLoader; + private transient Map<WriteTarget, Collection<DynamicWriteResult>> results; + private transient Cache<String, Map<Integer, PartitionSpec>> specs; + private transient Cache<String, ManifestOutputFileFactory> outputFileFactories; + private transient String flinkJobId; + private transient String operatorId; + private transient int subTaskId; + private transient int attemptId; + private transient Catalog catalog; + + DynamicWriteResultAggregator(CatalogLoader catalogLoader) { + this.catalogLoader = catalogLoader; + } + + @Override + public void open() throws Exception { + this.flinkJobId = getContainingTask().getEnvironment().getJobID().toString(); + this.operatorId = getOperatorID().toString(); + this.subTaskId = getRuntimeContext().getTaskInfo().getIndexOfThisSubtask(); + this.attemptId = getRuntimeContext().getTaskInfo().getAttemptNumber(); + this.results = Maps.newHashMap(); + this.specs = + Caffeine.newBuilder().expireAfterWrite(CACHE_EXPIRATION_DURATION).softValues().build(); + this.outputFileFactories = + Caffeine.newBuilder().expireAfterWrite(CACHE_EXPIRATION_DURATION).softValues().build(); + this.catalog = catalogLoader.loadCatalog(); + } + + @Override + public void finish() throws IOException { + prepareSnapshotPreBarrier(Long.MAX_VALUE); + } + + @Override + public void prepareSnapshotPreBarrier(long checkpointId) throws IOException { + // TODO emit something if there is no incoming result for a given table for a given checkpoint Review Comment: It could be interesting for table maintenance, but it isn't strictly required. It is tricky to persist all seen table names here. We need to let go of the data at some point, if there won't be any writes anymore. -- 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: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
