org.apache.iceberg.flink.source.assigner.DefaultSplitAssigner Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of iceberg-flink-1.18 Show documentation
Show all versions of iceberg-flink-1.18 Show documentation
A table format for huge analytic datasets
/*
* 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.source.assigner;
import java.util.ArrayDeque;
import java.util.Collection;
import java.util.PriorityQueue;
import java.util.Queue;
import java.util.concurrent.CompletableFuture;
import java.util.stream.Collectors;
import javax.annotation.Nullable;
import org.apache.flink.annotation.Internal;
import org.apache.iceberg.flink.source.split.IcebergSourceSplit;
import org.apache.iceberg.flink.source.split.IcebergSourceSplitState;
import org.apache.iceberg.flink.source.split.IcebergSourceSplitStatus;
import org.apache.iceberg.flink.source.split.SerializableComparator;
/**
* Since all methods are called in the source coordinator thread by enumerator, there is no need for
* locking.
*/
@Internal
public class DefaultSplitAssigner implements SplitAssigner {
private final Queue pendingSplits;
private CompletableFuture availableFuture;
public DefaultSplitAssigner(SerializableComparator comparator) {
this.pendingSplits = comparator == null ? new ArrayDeque<>() : new PriorityQueue<>(comparator);
}
public DefaultSplitAssigner(
SerializableComparator comparator,
Collection assignerState) {
this(comparator);
// Because default assigner only tracks unassigned splits,
// there is no need to filter splits based on status (unassigned) here.
assignerState.forEach(splitState -> pendingSplits.add(splitState.split()));
}
@Override
public synchronized GetSplitResult getNext(@Nullable String hostname) {
if (pendingSplits.isEmpty()) {
return GetSplitResult.unavailable();
} else {
IcebergSourceSplit split = pendingSplits.poll();
return GetSplitResult.forSplit(split);
}
}
@Override
public void onDiscoveredSplits(Collection splits) {
addSplits(splits);
}
@Override
public void onUnassignedSplits(Collection splits) {
addSplits(splits);
}
private synchronized void addSplits(Collection splits) {
if (!splits.isEmpty()) {
pendingSplits.addAll(splits);
// only complete pending future if new splits are discovered
completeAvailableFuturesIfNeeded();
}
}
/** Simple assigner only tracks unassigned splits */
@Override
public synchronized Collection state() {
return pendingSplits.stream()
.map(split -> new IcebergSourceSplitState(split, IcebergSourceSplitStatus.UNASSIGNED))
.collect(Collectors.toList());
}
@Override
public synchronized CompletableFuture isAvailable() {
if (availableFuture == null) {
availableFuture = new CompletableFuture<>();
}
return availableFuture;
}
@Override
public synchronized int pendingSplitCount() {
return pendingSplits.size();
}
@Override
public long pendingRecords() {
return pendingSplits.stream()
.map(split -> split.task().estimatedRowsCount())
.reduce(0L, Long::sum);
}
private synchronized void completeAvailableFuturesIfNeeded() {
if (availableFuture != null && !pendingSplits.isEmpty()) {
availableFuture.complete(null);
}
availableFuture = null;
}
}