rdblue commented on a change in pull request #2305: URL: https://github.com/apache/iceberg/pull/2305#discussion_r739573099
########## File path: flink/src/main/java/org/apache/iceberg/flink/source/reader/ArrayPoolDataIteratorBatcher.java ########## @@ -0,0 +1,116 @@ +/* + * 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.reader; + +import java.io.IOException; +import java.io.UncheckedIOException; +import org.apache.flink.configuration.Configuration; +import org.apache.flink.connector.base.source.reader.RecordsWithSplitIds; +import org.apache.flink.connector.base.source.reader.SourceReaderOptions; +import org.apache.flink.connector.file.src.util.Pool; +import org.apache.flink.connector.file.src.util.RecordAndPosition; +import org.apache.iceberg.flink.FlinkConfigOptions; +import org.apache.iceberg.flink.source.DataIterator; +import org.apache.iceberg.flink.source.Position; +import org.apache.iceberg.io.CloseableIterator; + +class ArrayPoolDataIteratorBatcher<T> implements DataIteratorBatcher<T> { + private final Configuration config; + private final RecordFactory<T> recordFactory; + + ArrayPoolDataIteratorBatcher(Configuration config, RecordFactory<T> recordFactory) { + this.config = config; + this.recordFactory = recordFactory; + } + + @Override + public CloseableIterator<RecordsWithSplitIds<RecordAndPosition<T>>> apply( + String splitId, DataIterator<T> inputIterator) { + return new ArrayPoolBatchIterator(splitId, inputIterator); + } + + private class ArrayPoolBatchIterator implements CloseableIterator<RecordsWithSplitIds<RecordAndPosition<T>>> { + + private final String splitId; + private final DataIterator<T> inputIterator; + private final int batchSize; + private final Pool<T[]> pool; + + ArrayPoolBatchIterator(String splitId, DataIterator<T> inputIterator) { + this.splitId = splitId; + this.inputIterator = inputIterator; + this.batchSize = config.getInteger(FlinkConfigOptions.SOURCE_READER_FETCH_RECORD_BATCH_SIZE); + this.pool = createPoolOfBatches(config.getInteger(SourceReaderOptions.ELEMENT_QUEUE_CAPACITY)); + } + + @Override + public boolean hasNext() { + return inputIterator.hasNext(); + } + + @Override + public RecordsWithSplitIds<RecordAndPosition<T>> next() { + final T[] batch = getCachedEntry(); + int num = 0; + while (inputIterator.hasNext() && num < batchSize) { + T nextRecord = inputIterator.next(); + recordFactory.clone(nextRecord, batch[num]); Review comment: What is this doing? Is `clone` expensive? It could be that the record produced by `inputIterator` is reused and `clone` call is making a copy because this can't call `inputIterator.next()` until the copy is made since the record is not consumed immediately. If that's the case, then I think there should be a comment to point out what's going on. -- 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]
