LeonBein commented on a change in pull request #15109: URL: https://github.com/apache/flink/pull/15109#discussion_r595508344
########## File path: flink-connectors/flink-connector-hbase/src/main/java/org/apache/flink/connector/hbase/sink/writer/HBaseWriter.java ########## @@ -0,0 +1,172 @@ +/* + * 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.connector.hbase.sink.writer; + +import org.apache.flink.api.connector.sink.Sink; +import org.apache.flink.api.connector.sink.SinkWriter; +import org.apache.flink.connector.hbase.HBaseEvent; +import org.apache.flink.connector.hbase.sink.HBaseSinkCommittable; +import org.apache.flink.connector.hbase.sink.HBaseSinkOptions; +import org.apache.flink.connector.hbase.sink.HBaseSinkSerializer; +import org.apache.flink.connector.hbase.util.HBaseConfigurationUtil; + +import org.apache.flink.shaded.curator4.org.apache.curator.shaded.com.google.common.io.Closer; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.hbase.Cell; +import org.apache.hadoop.hbase.TableName; +import org.apache.hadoop.hbase.client.Connection; +import org.apache.hadoop.hbase.client.ConnectionFactory; +import org.apache.hadoop.hbase.client.Delete; +import org.apache.hadoop.hbase.client.Mutation; +import org.apache.hadoop.hbase.client.Put; +import org.apache.hadoop.hbase.client.Table; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Collections; +import java.util.List; +import java.util.Properties; +import java.util.Timer; +import java.util.TimerTask; +import java.util.concurrent.ArrayBlockingQueue; + +/** HBaseWriter. */ +public class HBaseWriter<IN> implements SinkWriter<IN, HBaseSinkCommittable, Mutation> { + + private static final Logger LOG = LoggerFactory.getLogger(HBaseWriter.class); + + private final int queueLimit; + private final int maxLatencyMs; + private final HBaseSinkSerializer<IN> sinkSerializer; + private final ArrayBlockingQueue<Mutation> pendingMutations; + private final Connection connection; + private final Table table; + private long lastFlushTimeStamp = 0; + private TimerTask batchSendTimer; + + public HBaseWriter( + Sink.InitContext context, + List<Mutation> states, + HBaseSinkSerializer<IN> sinkSerializer, + byte[] serializedConfig, + Properties properties) { + this.sinkSerializer = sinkSerializer; + this.queueLimit = HBaseSinkOptions.getQueueLimit(properties); + this.maxLatencyMs = HBaseSinkOptions.getMaxLatency(properties); + String tableName = HBaseSinkOptions.getTableName(properties); + + // Queue limit is multiplied by 2, to reduce the probability of blocking while committing + this.pendingMutations = new ArrayBlockingQueue<>(2 * queueLimit); + pendingMutations.addAll(states); + + Configuration hbaseConfiguration = + HBaseConfigurationUtil.deserializeConfiguration(serializedConfig, null); + try { + connection = ConnectionFactory.createConnection(hbaseConfiguration); + table = connection.getTable(TableName.valueOf(tableName)); + } catch (IOException e) { + throw new RuntimeException("Connection to HBase couldn't be established", e); + } + + startBatchSendTimer(); + LOG.debug("started sink writer"); + } + + private void startBatchSendTimer() { + batchSendTimer = + new TimerTask() { + @Override + public void run() { + long diff = System.currentTimeMillis() - lastFlushTimeStamp; + if (diff > maxLatencyMs) { + LOG.debug("Time based flushing of mutations"); + flushBuffer(); + } + } + }; + new Timer().scheduleAtFixedRate(batchSendTimer, 0, maxLatencyMs / 2); + } + + private void flushBuffer() { + lastFlushTimeStamp = System.currentTimeMillis(); Review comment: ✅ in 3bb1c083ed229952ee642c8a02b42a89eb4c3063 was made volatile, as any batch flush resets the timer ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
