[
https://issues.apache.org/jira/browse/FLINK-6988?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16092698#comment-16092698
]
ASF GitHub Bot commented on FLINK-6988:
---------------------------------------
Github user tzulitai commented on a diff in the pull request:
https://github.com/apache/flink/pull/4239#discussion_r128164162
--- Diff:
flink-connectors/flink-connector-kafka-0.11/src/main/java/org/apache/flink/streaming/connectors/kafka/FlinkKafkaProducer011.java
---
@@ -0,0 +1,818 @@
+/*
+ * 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;
+
+import org.apache.flink.api.common.functions.RuntimeContext;
+import org.apache.flink.api.java.ClosureCleaner;
+import org.apache.flink.api.java.typeutils.GenericTypeInfo;
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.metrics.MetricGroup;
+import org.apache.flink.runtime.util.SerializableObject;
+import org.apache.flink.streaming.api.datastream.DataStream;
+import org.apache.flink.streaming.api.datastream.DataStreamSink;
+import
org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
+import
org.apache.flink.streaming.api.functions.sink.TwoPhaseCommitSinkFunction;
+import org.apache.flink.streaming.api.operators.StreamSink;
+import org.apache.flink.streaming.api.operators.StreamingRuntimeContext;
+import
org.apache.flink.streaming.connectors.kafka.internal.FlinkKafkaProducer;
+import
org.apache.flink.streaming.connectors.kafka.internal.metrics.KafkaMetricMuttableWrapper;
+import
org.apache.flink.streaming.connectors.kafka.partitioner.FlinkFixedPartitioner;
+import
org.apache.flink.streaming.connectors.kafka.partitioner.FlinkKafkaDelegatePartitioner;
+import
org.apache.flink.streaming.connectors.kafka.partitioner.FlinkKafkaPartitioner;
+import org.apache.flink.streaming.runtime.streamrecord.StreamRecord;
+import
org.apache.flink.streaming.util.serialization.KeyedSerializationSchema;
+import
org.apache.flink.streaming.util.serialization.KeyedSerializationSchemaWrapper;
+import org.apache.flink.streaming.util.serialization.SerializationSchema;
+import org.apache.flink.util.ExceptionUtils;
+import org.apache.flink.util.NetUtils;
+
+import org.apache.kafka.clients.producer.Callback;
+import org.apache.kafka.clients.producer.Producer;
+import org.apache.kafka.clients.producer.ProducerConfig;
+import org.apache.kafka.clients.producer.ProducerRecord;
+import org.apache.kafka.clients.producer.RecordMetadata;
+import org.apache.kafka.common.Metric;
+import org.apache.kafka.common.MetricName;
+import org.apache.kafka.common.PartitionInfo;
+import org.apache.kafka.common.serialization.ByteArraySerializer;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import javax.annotation.Nullable;
+
+import java.io.Serializable;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.Comparator;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Properties;
+import java.util.UUID;
+import java.util.concurrent.atomic.AtomicLong;
+
+import static java.util.Objects.requireNonNull;
+
+/**
+ * Flink Sink to produce data into a Kafka topic. This producer is
compatible with Kafka 0.11.x. By default producer
+ * will use {@link Semantic.EXACTLY_ONCE} semantic.
+ *
+ * <p>Implementation note: This producer is a hybrid between a regular
regular sink function (a)
+ * and a custom operator (b).
+ *
+ * <p>For (a), the class implements the SinkFunction and RichFunction
interfaces.
+ * For (b), it extends the StreamTask class.
+ *
+ * <p>Details about approach (a):
+ * Pre Kafka 0.11 producers only follow approach (a), allowing users to
use the producer using the
+ * DataStream.addSink() method.
+ * Since the APIs exposed in that variant do not allow accessing the the
timestamp attached to the record
+ * the Kafka 0.11 producer has a second invocation option, approach (b).
+ *
+ * <p>Details about approach (b):
+ * Kafka 0.11 supports writing the timestamp attached to a record to
Kafka. When adding the
+ * FlinkKafkaProducer011 using the
FlinkKafkaProducer011.writeToKafkaWithTimestamps() method, the Kafka producer
+ * can access the internal record timestamp of the record and write it to
Kafka.
+ *
+ * <p>All methods and constructors in this class are marked with the
approach they are needed for.
+ */
+public class FlinkKafkaProducer011<IN>
+ extends TwoPhaseCommitSinkFunction<IN,
FlinkKafkaProducer011.KafkaTransactionState> {
+ /**
+ * Semantics that can be chosen.
+ * <li>{@link #EXACTLY_ONCE}</li>
+ * <li>{@link #AT_LEAST_ONCE}</li>
+ * <li>{@link #NONE}</li>
+ */
+ public enum Semantic {
+ /**
+ * Semantic.EXACTLY_ONCE the Flink producer will write all
messages in a Kafka transaction that will be
+ * committed to the Kafka on a checkpoint.
+ */
+ EXACTLY_ONCE,
+ /**
+ * Semantic.AT_LEAST_ONCE the Flink producer will wait for all
outstanding messages in the Kafka buffers
+ * to be acknowledged by the Kafka producer on a checkpoint.
+ */
+ AT_LEAST_ONCE,
+ /**
+ * Semantic.NONE means that nothing will be guaranteed.
+ */
+ NONE
+ }
+
+ private static final Logger LOG =
LoggerFactory.getLogger(FlinkKafkaProducerBase.class);
+
+ private static final long serialVersionUID = 1L;
+
+ /**
+ * Configuration key for disabling the metrics reporting.
+ */
+ public static final String KEY_DISABLE_METRICS =
"flink.disable-metrics";
+
+ /**
+ * User defined properties for the Producer.
+ */
+ private final Properties producerConfig;
+
+ /**
+ * The name of the default topic this producer is writing data to.
+ */
+ private final String defaultTopicId;
+
+ /**
+ * (Serializable) SerializationSchema for turning objects used with
Flink into.
+ * byte[] for Kafka.
+ */
+ private final KeyedSerializationSchema<IN> schema;
+
+ /**
+ * User-provided partitioner for assigning an object to a Kafka
partition for each topic.
+ */
+ private final FlinkKafkaPartitioner<IN> flinkKafkaPartitioner;
+
+ /**
+ * Partitions of each topic.
+ */
+ private final Map<String, int[]> topicPartitionsMap;
+
+ /**
+ * Flag controlling whether we are writing the Flink record's timestamp
into Kafka.
+ */
+ private boolean writeTimestampToKafka = false;
+
+ /**
+ * Flag indicating whether to accept failures (and log them), or to
fail on failures.
+ */
+ private boolean logFailuresOnly;
+
+ private Semantic semantic;
+
+ // -------------------------------- Runtime fields
------------------------------------------
+
+ /** The callback than handles error propagation or logging callbacks. */
+ @Nullable
+ private transient Callback callback;
+
+ /** Errors encountered in the async producer are stored here. */
+ @Nullable
+ private transient volatile Exception asyncException;
+
+ /** Lock for accessing the pending records. */
+ private final SerializableObject pendingRecordsLock = new
SerializableObject();
+
+ /** Number of unacknowledged records. */
+ private final AtomicLong pendingRecords = new AtomicLong();
+
+ private final Map<String, KafkaMetricMuttableWrapper>
previouslyCreatedMetrics = new HashMap<>();
--- End diff --
nit: also include Javadoc for consistency.
> Add Apache Kafka 0.11 connector
> -------------------------------
>
> Key: FLINK-6988
> URL: https://issues.apache.org/jira/browse/FLINK-6988
> Project: Flink
> Issue Type: Improvement
> Components: Kafka Connector
> Affects Versions: 1.3.1
> Reporter: Piotr Nowojski
> Assignee: Piotr Nowojski
>
> Kafka 0.11 (it will be released very soon) add supports for transactions.
> Thanks to that, Flink might be able to implement Kafka sink supporting
> "exactly-once" semantic. API changes and whole transactions support is
> described in
> [KIP-98|https://cwiki.apache.org/confluence/display/KAFKA/KIP-98+-+Exactly+Once+Delivery+and+Transactional+Messaging].
> The goal is to mimic implementation of existing BucketingSink. New
> FlinkKafkaProducer011 would
> * upon creation begin transaction, store transaction identifiers into the
> state and would write all incoming data to an output Kafka topic using that
> transaction
> * on `snapshotState` call, it would flush the data and write in state
> information that current transaction is pending to be committed
> * on `notifyCheckpointComplete` we would commit this pending transaction
> * in case of crash between `snapshotState` and `notifyCheckpointComplete` we
> either abort this pending transaction (if not every participant successfully
> saved the snapshot) or restore and commit it.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
