danny0405 commented on code in PR #17562: URL: https://github.com/apache/hudi/pull/17562#discussion_r2621797830
########## hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/source/enumerator/HoodieContinuousSplitEnumerator.java: ########## @@ -0,0 +1,133 @@ +/* + * 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.hudi.source.enumerator; + +import org.apache.hudi.common.util.Option; +import org.apache.hudi.source.ScanContext; +import org.apache.hudi.source.split.HoodieContinuousSplitBatch; +import org.apache.hudi.source.split.HoodieContinuousSplitDiscover; +import org.apache.hudi.source.split.HoodieSourceSplit; +import org.apache.hudi.source.split.HoodieSplitProvider; + +import org.apache.flink.api.connector.source.SplitEnumeratorContext; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.util.Objects; +import java.util.concurrent.atomic.AtomicReference; + +/** + * Continuous Hoodie enumerator that discovers Hoodie splits from new Hoodie commits of upstream Hoodie table. + */ +public class HoodieContinuousSplitEnumerator extends AbstractHoodieSplitEnumerator { + private static final Logger LOG = LoggerFactory.getLogger(HoodieContinuousSplitEnumerator.class); + + private final SplitEnumeratorContext<HoodieSourceSplit> enumeratorContext; + private final HoodieSplitProvider splitProvider; + private final HoodieContinuousSplitDiscover splitDiscover; + private final ScanContext scanContext; + + /** + * Instant for the last enumerated commit. Next incremental enumeration should be based off + * this as the starting position. + */ + private final AtomicReference<HoodieEnumeratorPosition> position; + + public HoodieContinuousSplitEnumerator( + SplitEnumeratorContext<HoodieSourceSplit> enumeratorContext, + HoodieSplitProvider splitProvider, + HoodieContinuousSplitDiscover splitDiscover, + ScanContext scanContext, + Option<HoodieSplitEnumeratorState> enumStateOpt) { + super(enumeratorContext, splitProvider); + this.enumeratorContext = enumeratorContext; + this.splitProvider = splitProvider; + this.splitDiscover = splitDiscover; + this.scanContext = scanContext; + this.position = new AtomicReference<>(); + + if (enumStateOpt.isPresent()) { + this.position.set(HoodieEnumeratorPosition.of(enumStateOpt.get().getLastEnumeratedInstant(), enumStateOpt.get().getLastEnumeratedInstantOffset())); + } else { + this.position.set(HoodieEnumeratorPosition.of(scanContext.getStartInstant(), scanContext.getStartInstant())); + } + } + + @Override + public void start() { + super.start(); + enumeratorContext.callAsync( + this::discoverSplits, + this::processDiscoveredSplits, + 0L, + scanContext.getScanInterval().toMillis()); + } + + @Override + boolean shouldWaitForMoreSplits() { + return true; + } + + @Override + public HoodieSplitEnumeratorState snapshotState(long checkpointId) throws Exception { + return new HoodieSplitEnumeratorState(splitProvider.state(), position.get().issuedInstant(), position.get().issuedOffset()); + } + + private HoodieContinuousSplitBatch discoverSplits() { + int pendingSplitNumber = splitProvider.pendingSplitCount(); + if (pendingSplitNumber > scanContext.getMaxPendingSplits()) { + LOG.info( + "Pause split discovery as the assigner already has too many pending splits: {}", + pendingSplitNumber); + return HoodieContinuousSplitBatch.EMPTY; + } + return splitDiscover.discoverSplits(position.get().issuedOffset().isPresent() ? position.get().issuedOffset().get() : null); + } + + private void processDiscoveredSplits(HoodieContinuousSplitBatch result, Throwable throwable) { + if (throwable != null) { + throw new RuntimeException("Failed to discover new splits", throwable); + } + + if (Objects.equals(result.getFromInstant(), position.get().issuedOffset().get())) { + if (!result.getSplits().isEmpty()) { + splitProvider.onDiscoveredSplits(result.getSplits()); + LOG.info( Review Comment: do we need to log for each split findings here, is it a little verbose? -- 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]
