fapaul commented on a change in pull request #16796: URL: https://github.com/apache/flink/pull/16796#discussion_r688381282
########## File path: flink-connectors/flink-connector-kafka/src/main/java/org/apache/flink/streaming/connectors/kafka/table/BufferedUpsertWriter.java ########## @@ -0,0 +1,209 @@ +/* + * 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.flink.streaming.connectors.kafka.table; + +import org.apache.flink.api.common.typeutils.TypeSerializer; +import org.apache.flink.api.connector.sink.SinkWriter; +import org.apache.flink.api.java.tuple.Tuple2; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.types.DataType; +import org.apache.flink.table.types.logical.LogicalType; +import org.apache.flink.types.RowKind; +import org.apache.flink.util.concurrent.ExecutorThreadFactory; + +import javax.annotation.Nullable; + +import java.io.IOException; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.concurrent.Executors; +import java.util.concurrent.ScheduledExecutorService; +import java.util.concurrent.ScheduledFuture; +import java.util.concurrent.TimeUnit; +import java.util.function.Function; + +import static org.apache.flink.streaming.connectors.kafka.table.DynamicKafkaRecordSerializationSchema.createProjectedRow; +import static org.apache.flink.types.RowKind.DELETE; +import static org.apache.flink.types.RowKind.UPDATE_AFTER; +import static org.apache.flink.util.Preconditions.checkArgument; +import static org.apache.flink.util.Preconditions.checkNotNull; + +class BufferedUpsertWriter<WriterState> implements SinkWriter<RowData, Void, WriterState> { + + private final SinkWriter<RowData, ?, WriterState> wrappedWriter; + private final WrappedContext wrappedContext = new WrappedContext(); + private final ScheduledExecutorService scheduler = + Executors.newScheduledThreadPool( + 1, new ExecutorThreadFactory("upsert-kafka-sink-function")); + private final ScheduledFuture<?> scheduledFuture; + private final int batchMaxRowNums; + private final Function<RowData, RowData> valueCopier; + private final Map<RowData, Tuple2<RowData, Long>> reduceBuffer = new HashMap<>(); + private final Function<RowData, RowData> keyExtractor; + + private boolean closed = false; + private int batchCount = 0; + private volatile Exception flushException; + + BufferedUpsertWriter( + SinkWriter<RowData, ?, WriterState> wrappedWriter, + DataType physicalDataType, + int[] keyProjection, + SinkBufferFlushMode bufferFlushMode, + @Nullable TypeSerializer<RowData> typeSerializer) { + checkArgument(bufferFlushMode != null && bufferFlushMode.isEnabled()); + this.wrappedWriter = checkNotNull(wrappedWriter); + this.batchMaxRowNums = bufferFlushMode.getBatchSize(); + long batchIntervalMs = bufferFlushMode.getBatchIntervalMs(); + + List<LogicalType> fields = physicalDataType.getLogicalType().getChildren(); + final RowData.FieldGetter[] keyFieldGetters = + Arrays.stream(keyProjection) + .mapToObj( + targetField -> + RowData.createFieldGetter( + fields.get(targetField), targetField)) + .toArray(RowData.FieldGetter[]::new); + this.keyExtractor = rowData -> createProjectedRow(rowData, RowKind.INSERT, keyFieldGetters); + this.valueCopier = typeSerializer == null ? Function.identity() : typeSerializer::copy; + + this.scheduledFuture = + this.scheduler.scheduleWithFixedDelay( + () -> { + synchronized (BufferedUpsertWriter.this) { + if (!closed) { + try { + flush(); + } catch (Exception e) { + flushException = e; + } + } + } + }, + batchIntervalMs, + batchIntervalMs, + TimeUnit.MILLISECONDS); + } + + @Override + public void write(RowData element, Context context) throws IOException, InterruptedException { + wrappedContext.setContext(context); + addToBuffer(element, context.timestamp()); + } + + @Override + public List<Void> prepareCommit(boolean flush) throws IOException, InterruptedException { + flush(); + return Collections.emptyList(); + } + + @Override + public List<WriterState> snapshotState() throws IOException { + return wrappedWriter.snapshotState(); Review comment: I'll create a ticket as follow-up once this PR is merged to fix in the new sink and also fix in the old one. -- 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]
