org.apache.flink.api.common.serialization.TypeInformationSerializationSchema Java Examples

FlinkKafkaShuffleConsumer(
		String topic,
		TypeInformationSerializationSchema<T> schema,
		TypeSerializer<T> typeSerializer,
		Properties props) {
	// The schema is needed to call the right FlinkKafkaConsumer constructor.
	// It is never used, can be `null`, but `null` confuses the compiler.
	super(topic, schema, props);
	this.typeSerializer = typeSerializer;

	Preconditions.checkArgument(
		props.getProperty(PRODUCER_PARALLELISM) != null,
		"Missing producer parallelism for Kafka Shuffle");
	producerParallelism = PropertiesUtil.getInt(props, PRODUCER_PARALLELISM, Integer.MAX_VALUE);
}
 

/**
 * Tests the proper consumption when having more Flink sources than Kafka partitions, which means
 * that some Flink sources will read no partitions.
 */
public void runMultipleSourcesOnePartitionExactlyOnceTest() throws Exception {
	final String topic = "manyToOneTopic";
	final int numPartitions = 5;
	final int numElementsPerPartition = 1000;
	final int totalElements = numPartitions * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	final int parallelism = 8;

	createTestTopic(topic, numPartitions, 1);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic,
			numPartitions,
			numElementsPerPartition,
			true);

	// run the topology that fails and recovers

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(parallelism);
	// set the number of restarts to one. The failing mapper will fail once, then it's only success exceptions.
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));
	env.getConfig().disableSysoutLogging();
	env.setBufferTimeout(0);

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);
	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
		.addSource(kafkaSource)
		.map(new PartitionValidatingMapper(numPartitions, 1))
		.map(new FailingIdentityMapper<Integer>(failAfterElements))
		.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	FailingIdentityMapper.failedBefore = false;
	tryExecute(env, "multi-source-one-partitions exactly once test");

	deleteTestTopic(topic);
}
 

protected void writeAppendSequence(
		String topicName,
		final int originalNumElements,
		final int numElementsToAppend,
		final int parallelism) throws Exception {

	LOG.info("\n===================================\n" +
		"== Appending sequence of " + numElementsToAppend + " into " + topicName +
		"===================================");

	final TypeInformation<Tuple2<Integer, Integer>> resultType =
		TypeInformation.of(new TypeHint<Tuple2<Integer, Integer>>() {});

	final SerializationSchema<Tuple2<Integer, Integer>> serSchema =
			new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig());

	final KafkaDeserializationSchema<Tuple2<Integer, Integer>> deserSchema =
		new KafkaDeserializationSchemaWrapper<>(
			new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig()));

	// -------- Write the append sequence --------

	StreamExecutionEnvironment writeEnv = StreamExecutionEnvironment.getExecutionEnvironment();
	writeEnv.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	DataStream<Tuple2<Integer, Integer>> stream = writeEnv.addSource(new RichParallelSourceFunction<Tuple2<Integer, Integer>>() {

		private boolean running = true;

		@Override
		public void run(SourceContext<Tuple2<Integer, Integer>> ctx) throws Exception {
			int cnt = originalNumElements;
			int partition = getRuntimeContext().getIndexOfThisSubtask();

			while (running && cnt < numElementsToAppend + originalNumElements) {
				ctx.collect(new Tuple2<>(partition, cnt));
				cnt++;
			}
		}

		@Override
		public void cancel() {
			running = false;
		}
	}).setParallelism(parallelism);

	// the producer must not produce duplicates
	Properties producerProperties = FlinkKafkaProducerBase.getPropertiesFromBrokerList(brokerConnectionStrings);
	producerProperties.setProperty("retries", "0");
	producerProperties.putAll(secureProps);

	kafkaServer.produceIntoKafka(stream, topicName, serSchema, producerProperties, new Tuple2FlinkPartitioner(parallelism))
		.setParallelism(parallelism);

	try {
		writeEnv.execute("Write sequence");
	}
	catch (Exception e) {
		throw new Exception("Failed to append sequence to Kafka; append job failed.", e);
	}

	LOG.info("Finished writing append sequence");

	// we need to validate the sequence, because kafka's producers are not exactly once
	LOG.info("Validating sequence");
	while (!getRunningJobs(client).isEmpty()){
		Thread.sleep(50);
	}

	if (!validateSequence(topicName, parallelism, deserSchema, originalNumElements + numElementsToAppend)) {
		throw new Exception("Could not append a valid sequence to Kafka.");
	}
}
 

protected String writeSequence(
		String baseTopicName,
		final int numElements,
		final int parallelism,
		final int replicationFactor) throws Exception {
	LOG.info("\n===================================\n" +
			"== Writing sequence of " + numElements + " into " + baseTopicName + " with p=" + parallelism + "\n" +
			"===================================");

	final TypeInformation<Tuple2<Integer, Integer>> resultType =
			TypeInformation.of(new TypeHint<Tuple2<Integer, Integer>>() {});

	final SerializationSchema<Tuple2<Integer, Integer>> serSchema =
				new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig());

	final KafkaDeserializationSchema<Tuple2<Integer, Integer>> deserSchema =
			new KafkaDeserializationSchemaWrapper<>(
					new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig()));

	final int maxNumAttempts = 10;

	for (int attempt = 1; attempt <= maxNumAttempts; attempt++) {

		final String topicName = baseTopicName + '-' + attempt;

		LOG.info("Writing attempt #" + attempt);

		// -------- Write the Sequence --------

		createTestTopic(topicName, parallelism, replicationFactor);

		StreamExecutionEnvironment writeEnv = StreamExecutionEnvironment.getExecutionEnvironment();
		writeEnv.getConfig().setRestartStrategy(RestartStrategies.noRestart());
		DataStream<Tuple2<Integer, Integer>> stream = writeEnv.addSource(new RichParallelSourceFunction<Tuple2<Integer, Integer>>() {

			private boolean running = true;

			@Override
			public void run(SourceContext<Tuple2<Integer, Integer>> ctx) throws Exception {
				int cnt = 0;
				int partition = getRuntimeContext().getIndexOfThisSubtask();

				while (running && cnt < numElements) {
					ctx.collect(new Tuple2<>(partition, cnt));
					cnt++;
				}
			}

			@Override
			public void cancel() {
				running = false;
			}
		}).setParallelism(parallelism);

		// the producer must not produce duplicates
		Properties producerProperties = FlinkKafkaProducerBase.getPropertiesFromBrokerList(brokerConnectionStrings);
		producerProperties.setProperty("retries", "0");
		producerProperties.putAll(secureProps);

		kafkaServer.produceIntoKafka(stream, topicName, serSchema, producerProperties, new Tuple2FlinkPartitioner(parallelism))
				.setParallelism(parallelism);

		try {
			writeEnv.execute("Write sequence");
		}
		catch (Exception e) {
			LOG.error("Write attempt failed, trying again", e);
			deleteTestTopic(topicName);
			waitUntilNoJobIsRunning(client);
			continue;
		}

		LOG.info("Finished writing sequence");

		// -------- Validate the Sequence --------

		// we need to validate the sequence, because kafka's producers are not exactly once
		LOG.info("Validating sequence");

		waitUntilNoJobIsRunning(client);

		if (validateSequence(topicName, parallelism, deserSchema, numElements)) {
			// everything is good!
			return topicName;
		}
		else {
			deleteTestTopic(topicName);
			// fall through the loop
		}
	}

	throw new Exception("Could not write a valid sequence to Kafka after " + maxNumAttempts + " attempts");
}
 

public void runBrokerFailureTest() throws Exception {
	final String topic = "brokerFailureTestTopic";

	final int parallelism = 2;
	final int numElementsPerPartition = 1000;
	final int totalElements = parallelism * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	createTestTopic(topic, parallelism, 2);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic, parallelism, numElementsPerPartition, true);

	// find leader to shut down
	int leaderId = kafkaServer.getLeaderToShutDown(topic);

	LOG.info("Leader to shutdown {}", leaderId);

	// run the topology (the consumers must handle the failures)

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(parallelism);
	env.enableCheckpointing(500);
	env.setRestartStrategy(RestartStrategies.noRestart());

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);
	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
			.addSource(kafkaSource)
			.map(new PartitionValidatingMapper(parallelism, 1))
			.map(new BrokerKillingMapper<Integer>(leaderId, failAfterElements))
			.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	BrokerKillingMapper.killedLeaderBefore = false;
	tryExecute(env, "Broker failure once test");

	// start a new broker:
	kafkaServer.restartBroker(leaderId);
}
 

/**
 * Tests the proper consumption when having more Flink sources than Kafka partitions, which means
 * that some Flink sources will read no partitions.
 */
public void runMultipleSourcesOnePartitionExactlyOnceTest() throws Exception {
	final String topic = "manyToOneTopic";
	final int numPartitions = 5;
	final int numElementsPerPartition = 1000;
	final int totalElements = numPartitions * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	final int parallelism = 8;

	createTestTopic(topic, numPartitions, 1);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic,
			numPartitions,
			numElementsPerPartition,
			true);

	// run the topology that fails and recovers

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(parallelism);
	// set the number of restarts to one. The failing mapper will fail once, then it's only success exceptions.
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));
			env.setBufferTimeout(0);

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);
	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
		.addSource(kafkaSource)
		.map(new PartitionValidatingMapper(numPartitions, 1))
		.map(new FailingIdentityMapper<Integer>(failAfterElements))
		.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	FailingIdentityMapper.failedBefore = false;
	tryExecute(env, "multi-source-one-partitions exactly once test");

	deleteTestTopic(topic);
}
 

/**
 * Tests the proper consumption when having fewer Flink sources than Kafka partitions, so
 * one Flink source will read multiple Kafka partitions.
 */
public void runOneSourceMultiplePartitionsExactlyOnceTest() throws Exception {
	final String topic = "oneToManyTopic";
	final int numPartitions = 5;
	final int numElementsPerPartition = 1000;
	final int totalElements = numPartitions * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	final int parallelism = 2;

	createTestTopic(topic, numPartitions, 1);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic,
			numPartitions,
			numElementsPerPartition,
			true);

	// run the topology that fails and recovers

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(parallelism);
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);
	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
			.addSource(kafkaSource)
			.map(new PartitionValidatingMapper(numPartitions, 3))
			.map(new FailingIdentityMapper<Integer>(failAfterElements))
			.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	FailingIdentityMapper.failedBefore = false;
	tryExecute(env, "One-source-multi-partitions exactly once test");

	deleteTestTopic(topic);
}
 

/**
 * Tests the proper consumption when having a 1:1 correspondence between kafka partitions and
 * Flink sources.
 */
public void runOneToOneExactlyOnceTest() throws Exception {

	final String topic = "oneToOneTopic";
	final int parallelism = 5;
	final int numElementsPerPartition = 1000;
	final int totalElements = parallelism * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	createTestTopic(topic, parallelism, 1);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic,
			parallelism,
			numElementsPerPartition,
			true);

	// run the topology that fails and recovers

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(parallelism);
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);

	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
			.addSource(kafkaSource)
			.map(new PartitionValidatingMapper(parallelism, 1))
			.map(new FailingIdentityMapper<Integer>(failAfterElements))
			.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	FailingIdentityMapper.failedBefore = false;
	tryExecute(env, "One-to-one exactly once test");

	deleteTestTopic(topic);
}
 

/**
 * This test sets KafkaProducer so that it will  automatically flush the data and
 * and fails the broker to check whether flushed records since last checkpoint were not duplicated.
 */
protected void testExactlyOnce(boolean regularSink, int sinksCount) throws Exception {
	final String topic = (regularSink ? "exactlyOnceTopicRegularSink" : "exactlyTopicCustomOperator") + sinksCount;
	final int partition = 0;
	final int numElements = 1000;
	final int failAfterElements = 333;

	for (int i = 0; i < sinksCount; i++) {
		createTestTopic(topic + i, 1, 1);
	}

	TypeInformationSerializationSchema<Integer> schema = new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(1);
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));

	Properties properties = new Properties();
	properties.putAll(standardProps);
	properties.putAll(secureProps);

	// process exactly failAfterElements number of elements and then shutdown Kafka broker and fail application
	List<Integer> expectedElements = getIntegersSequence(numElements);

	DataStream<Integer> inputStream = env
		.addSource(new IntegerSource(numElements))
		.map(new FailingIdentityMapper<Integer>(failAfterElements));

	for (int i = 0; i < sinksCount; i++) {
		FlinkKafkaPartitioner<Integer> partitioner = new FlinkKafkaPartitioner<Integer>() {
			@Override
			public int partition(Integer record, byte[] key, byte[] value, String targetTopic, int[] partitions) {
				return partition;
			}
		};

		if (regularSink) {
			StreamSink<Integer> kafkaSink = kafkaServer.getProducerSink(topic + i, schema, properties, partitioner);
			inputStream.addSink(kafkaSink.getUserFunction());
		} else {
			kafkaServer.produceIntoKafka(inputStream, topic + i, schema, properties, partitioner);
		}
	}

	FailingIdentityMapper.failedBefore = false;
	TestUtils.tryExecute(env, "Exactly once test");

	for (int i = 0; i < sinksCount; i++) {
		// assert that before failure we successfully snapshot/flushed all expected elements
		assertExactlyOnceForTopic(
			properties,
			topic + i,
			partition,
			expectedElements,
			KAFKA_READ_TIMEOUT);
		deleteTestTopic(topic + i);
	}
}
 

/**
 * Kafka 0.10 specific test, ensuring Timestamps are properly written to and read from Kafka.
 */
@Ignore("This test is disabled because of: https://issues.apache.org/jira/browse/FLINK-9217")
@Test(timeout = 60000)
public void testTimestamps() throws Exception {

	final String topic = "tstopic";
	createTestTopic(topic, 3, 1);

	// ---------- Produce an event time stream into Kafka -------------------

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
			env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	DataStream<Long> streamWithTimestamps = env.addSource(new SourceFunction<Long>() {
		private static final long serialVersionUID = -2255105836471289626L;
		boolean running = true;

		@Override
		public void run(SourceContext<Long> ctx) throws Exception {
			long i = 0;
			while (running) {
				ctx.collectWithTimestamp(i, i * 2);
				if (i++ == 1000L) {
					running = false;
				}
			}
		}

		@Override
		public void cancel() {
			running = false;
		}
	});

	final TypeInformationSerializationSchema<Long> longSer = new TypeInformationSerializationSchema<>(Types.LONG, env.getConfig());
	FlinkKafkaProducer010.FlinkKafkaProducer010Configuration prod = FlinkKafkaProducer010.writeToKafkaWithTimestamps(streamWithTimestamps, topic, new KeyedSerializationSchemaWrapper<>(longSer), standardProps, new FlinkKafkaPartitioner<Long>() {
		private static final long serialVersionUID = -6730989584364230617L;

		@Override
		public int partition(Long next, byte[] key, byte[] value, String targetTopic, int[] partitions) {
			return (int) (next % 3);
		}
	});
	prod.setParallelism(3);
	prod.setWriteTimestampToKafka(true);
	env.execute("Produce some");

	// ---------- Consume stream from Kafka -------------------

	env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
			env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	FlinkKafkaConsumer010<Long> kafkaSource = new FlinkKafkaConsumer010<>(topic, new LimitedLongDeserializer(), standardProps);
	kafkaSource.assignTimestampsAndWatermarks(new AssignerWithPunctuatedWatermarks<Long>() {
		private static final long serialVersionUID = -4834111073247835189L;

		@Nullable
		@Override
		public Watermark checkAndGetNextWatermark(Long lastElement, long extractedTimestamp) {
			if (lastElement % 10 == 0) {
				return new Watermark(lastElement);
			}
			return null;
		}

		@Override
		public long extractTimestamp(Long element, long previousElementTimestamp) {
			return previousElementTimestamp;
		}
	});

	DataStream<Long> stream = env.addSource(kafkaSource);
	GenericTypeInfo<Object> objectTypeInfo = new GenericTypeInfo<>(Object.class);
	stream.transform("timestamp validating operator", objectTypeInfo, new TimestampValidatingOperator()).setParallelism(1);

	env.execute("Consume again");

	deleteTestTopic(topic);
}
 

/**
 * Kafka 0.11 specific test, ensuring Timestamps are properly written to and read from Kafka.
 */
@Test(timeout = 60000)
public void testTimestamps() throws Exception {

	final String topic = "tstopic";
	createTestTopic(topic, 3, 1);

	// ---------- Produce an event time stream into Kafka -------------------

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
			env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	DataStream<Long> streamWithTimestamps = env.addSource(new SourceFunction<Long>() {
		private static final long serialVersionUID = -2255115836471289626L;
		boolean running = true;

		@Override
		public void run(SourceContext<Long> ctx) throws Exception {
			long i = 0;
			while (running) {
				ctx.collectWithTimestamp(i, i * 2);
				if (i++ == 1110L) {
					running = false;
				}
			}
		}

		@Override
		public void cancel() {
			running = false;
		}
	});

	final TypeInformationSerializationSchema<Long> longSer = new TypeInformationSerializationSchema<>(Types.LONG, env.getConfig());
	FlinkKafkaProducer011<Long> prod = new FlinkKafkaProducer011<>(topic, new KeyedSerializationSchemaWrapper<>(longSer), standardProps, Optional.of(new FlinkKafkaPartitioner<Long>() {
		private static final long serialVersionUID = -6730989584364230617L;

		@Override
		public int partition(Long next, byte[] key, byte[] value, String targetTopic, int[] partitions) {
			return (int) (next % 3);
		}
	}));
	prod.setWriteTimestampToKafka(true);

	streamWithTimestamps.addSink(prod).setParallelism(3);

	env.execute("Produce some");

	// ---------- Consume stream from Kafka -------------------

	env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
			env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	FlinkKafkaConsumer011<Long> kafkaSource = new FlinkKafkaConsumer011<>(topic, new LimitedLongDeserializer(), standardProps);
	kafkaSource.assignTimestampsAndWatermarks(new AssignerWithPunctuatedWatermarks<Long>() {
		private static final long serialVersionUID = -4834111173247835189L;

		@Nullable
		@Override
		public Watermark checkAndGetNextWatermark(Long lastElement, long extractedTimestamp) {
			if (lastElement % 11 == 0) {
				return new Watermark(lastElement);
			}
			return null;
		}

		@Override
		public long extractTimestamp(Long element, long previousElementTimestamp) {
			return previousElementTimestamp;
		}
	});

	DataStream<Long> stream = env.addSource(kafkaSource);
	GenericTypeInfo<Object> objectTypeInfo = new GenericTypeInfo<>(Object.class);
	stream.transform("timestamp validating operator", objectTypeInfo, new TimestampValidatingOperator()).setParallelism(1);

	env.execute("Consume again");

	deleteTestTopic(topic);
}
 

/**
 * Kafka 20 specific test, ensuring Timestamps are properly written to and read from Kafka.
 */
@Test(timeout = 60000)
public void testTimestamps() throws Exception {

	final String topic = "tstopic";
	createTestTopic(topic, 3, 1);

	// ---------- Produce an event time stream into Kafka -------------------

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
			env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	DataStream<Long> streamWithTimestamps = env.addSource(new SourceFunction<Long>() {
		private static final long serialVersionUID = -2255115836471289626L;
		boolean running = true;

		@Override
		public void run(SourceContext<Long> ctx) throws Exception {
			long i = 0;
			while (running) {
				ctx.collectWithTimestamp(i, i * 2);
				if (i++ == 1110L) {
					running = false;
				}
			}
		}

		@Override
		public void cancel() {
			running = false;
		}
	});

	final TypeInformationSerializationSchema<Long> longSer = new TypeInformationSerializationSchema<>(Types.LONG, env.getConfig());
	FlinkKafkaProducer<Long> prod = new FlinkKafkaProducer<>(topic, new KeyedSerializationSchemaWrapper<>(longSer), standardProps, Optional.of(new FlinkKafkaPartitioner<Long>() {
		private static final long serialVersionUID = -6730989584364230617L;

		@Override
		public int partition(Long next, byte[] key, byte[] value, String targetTopic, int[] partitions) {
			return (int) (next % 3);
		}
	}));
	prod.setWriteTimestampToKafka(true);

	streamWithTimestamps.addSink(prod).setParallelism(3);

	env.execute("Produce some");

	// ---------- Consume stream from Kafka -------------------

	env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
			env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	FlinkKafkaConsumer<Long> kafkaSource = new FlinkKafkaConsumer<>(topic, new KafkaITCase.LimitedLongDeserializer(), standardProps);
	kafkaSource.assignTimestampsAndWatermarks(new AssignerWithPunctuatedWatermarks<Long>() {
		private static final long serialVersionUID = -4834111173247835189L;

		@Nullable
		@Override
		public Watermark checkAndGetNextWatermark(Long lastElement, long extractedTimestamp) {
			if (lastElement % 11 == 0) {
				return new Watermark(lastElement);
			}
			return null;
		}

		@Override
		public long extractTimestamp(Long element, long previousElementTimestamp) {
			return previousElementTimestamp;
		}
	});

	DataStream<Long> stream = env.addSource(kafkaSource);
	GenericTypeInfo<Object> objectTypeInfo = new GenericTypeInfo<>(Object.class);
	stream.transform("timestamp validating operator", objectTypeInfo, new TimestampValidatingOperator()).setParallelism(1);

	env.execute("Consume again");

	deleteTestTopic(topic);
}
 

/**
 * The read side of {@link FlinkKafkaShuffle#persistentKeyBy}.
 *
 * <p>Each consumer task should read kafka partitions equal to the key group indices it is assigned.
 * The number of kafka partitions is the maximum parallelism of the consumer.
 * This version only supports numberOfPartitions = consumerParallelism.
 * In the case of using {@link TimeCharacteristic#EventTime}, a consumer task is responsible to emit
 * watermarks. Watermarks are read from the corresponding Kafka partitions. Notice that a consumer task only starts
 * to emit a watermark after receiving at least one watermark from each producer task to make sure watermarks
 * are monotonically increasing. Hence a consumer task needs to know `producerParallelism` as well.
 *
 * <p>Attention: make sure kafkaProperties include
 * {@link FlinkKafkaShuffle#PRODUCER_PARALLELISM} and {@link FlinkKafkaShuffle#PARTITION_NUMBER} explicitly.
 * {@link FlinkKafkaShuffle#PRODUCER_PARALLELISM} is the parallelism of the producer.
 * {@link FlinkKafkaShuffle#PARTITION_NUMBER} is the number of partitions.
 * They are not necessarily the same and allowed to be set independently.
 *
 * @see FlinkKafkaShuffle#persistentKeyBy
 * @see FlinkKafkaShuffle#writeKeyBy
 *
 * @param topic 			The topic of Kafka where data is persisted
 * @param env 				Execution environment. readKeyBy's environment can be different from writeKeyBy's
 * @param typeInformation 	Type information of the data persisted in Kafka
 * @param kafkaProperties 	kafka properties for Kafka Consumer
 * @param keySelector 		key selector to retrieve key
 * @param <T> 				Schema type
 * @param <K> 				Key type
 * @return Keyed data stream
 */
public static <T, K> KeyedStream<T, K> readKeyBy(
		String topic,
		StreamExecutionEnvironment env,
		TypeInformation<T> typeInformation,
		Properties kafkaProperties,
		KeySelector<T, K> keySelector) {

	TypeSerializer<T> typeSerializer = typeInformation.createSerializer(env.getConfig());
	TypeInformationSerializationSchema<T> schema =
		new TypeInformationSerializationSchema<>(typeInformation, typeSerializer);

	SourceFunction<T> kafkaConsumer  =
		new FlinkKafkaShuffleConsumer<>(topic, schema, typeSerializer, kafkaProperties);

	// TODO: consider situations where numberOfPartitions != consumerParallelism
	Preconditions.checkArgument(
		kafkaProperties.getProperty(PARTITION_NUMBER) != null,
		"Missing partition number for Kafka Shuffle");
	int numberOfPartitions = PropertiesUtil.getInt(kafkaProperties, PARTITION_NUMBER, Integer.MIN_VALUE);
	DataStream<T> outputDataStream = env.addSource(kafkaConsumer).setParallelism(numberOfPartitions);

	return DataStreamUtils.reinterpretAsKeyedStream(outputDataStream, keySelector);
}
 

protected void writeAppendSequence(
		String topicName,
		final int originalNumElements,
		final int numElementsToAppend,
		final int parallelism) throws Exception {

	LOG.info("\n===================================\n" +
		"== Appending sequence of " + numElementsToAppend + " into " + topicName +
		"===================================");

	final TypeInformation<Tuple2<Integer, Integer>> resultType =
		TypeInformation.of(new TypeHint<Tuple2<Integer, Integer>>() {});

	final KeyedSerializationSchema<Tuple2<Integer, Integer>> serSchema =
		new KeyedSerializationSchemaWrapper<>(
			new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig()));

	final KafkaDeserializationSchema<Tuple2<Integer, Integer>> deserSchema =
		new KafkaDeserializationSchemaWrapper<>(
			new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig()));

	// -------- Write the append sequence --------

	StreamExecutionEnvironment writeEnv = StreamExecutionEnvironment.getExecutionEnvironment();
	writeEnv.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	writeEnv.getConfig().disableSysoutLogging();

	DataStream<Tuple2<Integer, Integer>> stream = writeEnv.addSource(new RichParallelSourceFunction<Tuple2<Integer, Integer>>() {

		private boolean running = true;

		@Override
		public void run(SourceContext<Tuple2<Integer, Integer>> ctx) throws Exception {
			int cnt = originalNumElements;
			int partition = getRuntimeContext().getIndexOfThisSubtask();

			while (running && cnt < numElementsToAppend + originalNumElements) {
				ctx.collect(new Tuple2<>(partition, cnt));
				cnt++;
			}
		}

		@Override
		public void cancel() {
			running = false;
		}
	}).setParallelism(parallelism);

	// the producer must not produce duplicates
	Properties producerProperties = FlinkKafkaProducerBase.getPropertiesFromBrokerList(brokerConnectionStrings);
	producerProperties.setProperty("retries", "0");
	producerProperties.putAll(secureProps);

	kafkaServer.produceIntoKafka(stream, topicName, serSchema, producerProperties, new Tuple2FlinkPartitioner(parallelism))
		.setParallelism(parallelism);

	try {
		writeEnv.execute("Write sequence");
	}
	catch (Exception e) {
		throw new Exception("Failed to append sequence to Kafka; append job failed.", e);
	}

	LOG.info("Finished writing append sequence");

	// we need to validate the sequence, because kafka's producers are not exactly once
	LOG.info("Validating sequence");
	while (!getRunningJobs(client).isEmpty()){
		Thread.sleep(50);
	}

	if (!validateSequence(topicName, parallelism, deserSchema, originalNumElements + numElementsToAppend)) {
		throw new Exception("Could not append a valid sequence to Kafka.");
	}
}
 

protected String writeSequence(
		String baseTopicName,
		final int numElements,
		final int parallelism,
		final int replicationFactor) throws Exception {
	LOG.info("\n===================================\n" +
			"== Writing sequence of " + numElements + " into " + baseTopicName + " with p=" + parallelism + "\n" +
			"===================================");

	final TypeInformation<Tuple2<Integer, Integer>> resultType =
			TypeInformation.of(new TypeHint<Tuple2<Integer, Integer>>() {});

	final KeyedSerializationSchema<Tuple2<Integer, Integer>> serSchema =
			new KeyedSerializationSchemaWrapper<>(
					new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig()));

	final KafkaDeserializationSchema<Tuple2<Integer, Integer>> deserSchema =
			new KafkaDeserializationSchemaWrapper<>(
					new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig()));

	final int maxNumAttempts = 10;

	for (int attempt = 1; attempt <= maxNumAttempts; attempt++) {

		final String topicName = baseTopicName + '-' + attempt;

		LOG.info("Writing attempt #" + attempt);

		// -------- Write the Sequence --------

		createTestTopic(topicName, parallelism, replicationFactor);

		StreamExecutionEnvironment writeEnv = StreamExecutionEnvironment.getExecutionEnvironment();
		writeEnv.getConfig().setRestartStrategy(RestartStrategies.noRestart());
		writeEnv.getConfig().disableSysoutLogging();

		DataStream<Tuple2<Integer, Integer>> stream = writeEnv.addSource(new RichParallelSourceFunction<Tuple2<Integer, Integer>>() {

			private boolean running = true;

			@Override
			public void run(SourceContext<Tuple2<Integer, Integer>> ctx) throws Exception {
				int cnt = 0;
				int partition = getRuntimeContext().getIndexOfThisSubtask();

				while (running && cnt < numElements) {
					ctx.collect(new Tuple2<>(partition, cnt));
					cnt++;
				}
			}

			@Override
			public void cancel() {
				running = false;
			}
		}).setParallelism(parallelism);

		// the producer must not produce duplicates
		Properties producerProperties = FlinkKafkaProducerBase.getPropertiesFromBrokerList(brokerConnectionStrings);
		producerProperties.setProperty("retries", "0");
		producerProperties.putAll(secureProps);

		kafkaServer.produceIntoKafka(stream, topicName, serSchema, producerProperties, new Tuple2FlinkPartitioner(parallelism))
				.setParallelism(parallelism);

		try {
			writeEnv.execute("Write sequence");
		}
		catch (Exception e) {
			LOG.error("Write attempt failed, trying again", e);
			deleteTestTopic(topicName);
			waitUntilNoJobIsRunning(client);
			continue;
		}

		LOG.info("Finished writing sequence");

		// -------- Validate the Sequence --------

		// we need to validate the sequence, because kafka's producers are not exactly once
		LOG.info("Validating sequence");

		waitUntilNoJobIsRunning(client);

		if (validateSequence(topicName, parallelism, deserSchema, numElements)) {
			// everything is good!
			return topicName;
		}
		else {
			deleteTestTopic(topicName);
			// fall through the loop
		}
	}

	throw new Exception("Could not write a valid sequence to Kafka after " + maxNumAttempts + " attempts");
}
 

public void runBrokerFailureTest() throws Exception {
	final String topic = "brokerFailureTestTopic";

	final int parallelism = 2;
	final int numElementsPerPartition = 1000;
	final int totalElements = parallelism * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	createTestTopic(topic, parallelism, 2);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic, parallelism, numElementsPerPartition, true);

	// find leader to shut down
	int leaderId = kafkaServer.getLeaderToShutDown(topic);

	LOG.info("Leader to shutdown {}", leaderId);

	// run the topology (the consumers must handle the failures)

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(parallelism);
	env.enableCheckpointing(500);
	env.setRestartStrategy(RestartStrategies.noRestart());
	env.getConfig().disableSysoutLogging();

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);
	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
			.addSource(kafkaSource)
			.map(new PartitionValidatingMapper(parallelism, 1))
			.map(new BrokerKillingMapper<Integer>(leaderId, failAfterElements))
			.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	BrokerKillingMapper.killedLeaderBefore = false;
	tryExecute(env, "Broker failure once test");

	// start a new broker:
	kafkaServer.restartBroker(leaderId);
}
 

/**
 * Kafka 20 specific test, ensuring Timestamps are properly written to and read from Kafka.
 */
@Test(timeout = 60000)
public void testTimestamps() throws Exception {

	final String topic = "tstopic";
	createTestTopic(topic, 3, 1);

	// ---------- Produce an event time stream into Kafka -------------------

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	env.getConfig().disableSysoutLogging();
	env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	DataStream<Long> streamWithTimestamps = env.addSource(new SourceFunction<Long>() {
		private static final long serialVersionUID = -2255115836471289626L;
		boolean running = true;

		@Override
		public void run(SourceContext<Long> ctx) throws Exception {
			long i = 0;
			while (running) {
				ctx.collectWithTimestamp(i, i * 2);
				if (i++ == 1110L) {
					running = false;
				}
			}
		}

		@Override
		public void cancel() {
			running = false;
		}
	});

	final TypeInformationSerializationSchema<Long> longSer = new TypeInformationSerializationSchema<>(Types.LONG, env.getConfig());
	FlinkKafkaProducer<Long> prod = new FlinkKafkaProducer<>(topic, new KeyedSerializationSchemaWrapper<>(longSer), standardProps, Optional.of(new FlinkKafkaPartitioner<Long>() {
		private static final long serialVersionUID = -6730989584364230617L;

		@Override
		public int partition(Long next, byte[] key, byte[] value, String targetTopic, int[] partitions) {
			return (int) (next % 3);
		}
	}));
	prod.setWriteTimestampToKafka(true);

	streamWithTimestamps.addSink(prod).setParallelism(3);

	env.execute("Produce some");

	// ---------- Consume stream from Kafka -------------------

	env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	env.getConfig().disableSysoutLogging();
	env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	FlinkKafkaConsumer<Long> kafkaSource = new FlinkKafkaConsumer<>(topic, new KafkaITCase.LimitedLongDeserializer(), standardProps);
	kafkaSource.assignTimestampsAndWatermarks(new AssignerWithPunctuatedWatermarks<Long>() {
		private static final long serialVersionUID = -4834111173247835189L;

		@Nullable
		@Override
		public Watermark checkAndGetNextWatermark(Long lastElement, long extractedTimestamp) {
			if (lastElement % 11 == 0) {
				return new Watermark(lastElement);
			}
			return null;
		}

		@Override
		public long extractTimestamp(Long element, long previousElementTimestamp) {
			return previousElementTimestamp;
		}
	});

	DataStream<Long> stream = env.addSource(kafkaSource);
	GenericTypeInfo<Object> objectTypeInfo = new GenericTypeInfo<>(Object.class);
	stream.transform("timestamp validating operator", objectTypeInfo, new TimestampValidatingOperator()).setParallelism(1);

	env.execute("Consume again");

	deleteTestTopic(topic);
}
 

/**
 * Tests the proper consumption when having fewer Flink sources than Kafka partitions, so
 * one Flink source will read multiple Kafka partitions.
 */
public void runOneSourceMultiplePartitionsExactlyOnceTest() throws Exception {
	final String topic = "oneToManyTopic";
	final int numPartitions = 5;
	final int numElementsPerPartition = 1000;
	final int totalElements = numPartitions * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	final int parallelism = 2;

	createTestTopic(topic, numPartitions, 1);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic,
			numPartitions,
			numElementsPerPartition,
			true);

	// run the topology that fails and recovers

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(parallelism);
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));
	env.getConfig().disableSysoutLogging();

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);
	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
			.addSource(kafkaSource)
			.map(new PartitionValidatingMapper(numPartitions, 3))
			.map(new FailingIdentityMapper<Integer>(failAfterElements))
			.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	FailingIdentityMapper.failedBefore = false;
	tryExecute(env, "One-source-multi-partitions exactly once test");

	deleteTestTopic(topic);
}
 

/**
 * Tests the proper consumption when having a 1:1 correspondence between kafka partitions and
 * Flink sources.
 */
public void runOneToOneExactlyOnceTest() throws Exception {

	final String topic = "oneToOneTopic";
	final int parallelism = 5;
	final int numElementsPerPartition = 1000;
	final int totalElements = parallelism * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	createTestTopic(topic, parallelism, 1);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic,
			parallelism,
			numElementsPerPartition,
			true);

	// run the topology that fails and recovers

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(parallelism);
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));
	env.getConfig().disableSysoutLogging();

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);

	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
			.addSource(kafkaSource)
			.map(new PartitionValidatingMapper(parallelism, 1))
			.map(new FailingIdentityMapper<Integer>(failAfterElements))
			.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	FailingIdentityMapper.failedBefore = false;
	tryExecute(env, "One-to-one exactly once test");

	deleteTestTopic(topic);
}
 

/**
 * This test sets KafkaProducer so that it will  automatically flush the data and
 * and fails the broker to check whether flushed records since last checkpoint were not duplicated.
 */
protected void testExactlyOnce(boolean regularSink, int sinksCount) throws Exception {
	final String topic = (regularSink ? "exactlyOnceTopicRegularSink" : "exactlyTopicCustomOperator") + sinksCount;
	final int partition = 0;
	final int numElements = 1000;
	final int failAfterElements = 333;

	for (int i = 0; i < sinksCount; i++) {
		createTestTopic(topic + i, 1, 1);
	}

	TypeInformationSerializationSchema<Integer> schema = new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());
	KeyedSerializationSchema<Integer> keyedSerializationSchema = new KeyedSerializationSchemaWrapper<>(schema);

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(1);
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));
	env.getConfig().disableSysoutLogging();

	Properties properties = new Properties();
	properties.putAll(standardProps);
	properties.putAll(secureProps);

	// process exactly failAfterElements number of elements and then shutdown Kafka broker and fail application
	List<Integer> expectedElements = getIntegersSequence(numElements);

	DataStream<Integer> inputStream = env
		.addSource(new IntegerSource(numElements))
		.map(new FailingIdentityMapper<Integer>(failAfterElements));

	for (int i = 0; i < sinksCount; i++) {
		FlinkKafkaPartitioner<Integer> partitioner = new FlinkKafkaPartitioner<Integer>() {
			@Override
			public int partition(Integer record, byte[] key, byte[] value, String targetTopic, int[] partitions) {
				return partition;
			}
		};

		if (regularSink) {
			StreamSink<Integer> kafkaSink = kafkaServer.getProducerSink(topic + i, keyedSerializationSchema, properties, partitioner);
			inputStream.addSink(kafkaSink.getUserFunction());
		} else {
			kafkaServer.produceIntoKafka(inputStream, topic + i, keyedSerializationSchema, properties, partitioner);
		}
	}

	FailingIdentityMapper.failedBefore = false;
	TestUtils.tryExecute(env, "Exactly once test");

	for (int i = 0; i < sinksCount; i++) {
		// assert that before failure we successfully snapshot/flushed all expected elements
		assertExactlyOnceForTopic(
			properties,
			topic + i,
			partition,
			expectedElements,
			KAFKA_READ_TIMEOUT);
		deleteTestTopic(topic + i);
	}
}
 

/**
 * Kafka 0.10 specific test, ensuring Timestamps are properly written to and read from Kafka.
 */
@Ignore("This test is disabled because of: https://issues.apache.org/jira/browse/FLINK-9217")
@Test(timeout = 60000)
public void testTimestamps() throws Exception {

	final String topic = "tstopic";
	createTestTopic(topic, 3, 1);

	// ---------- Produce an event time stream into Kafka -------------------

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	env.getConfig().disableSysoutLogging();
	env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	DataStream<Long> streamWithTimestamps = env.addSource(new SourceFunction<Long>() {
		private static final long serialVersionUID = -2255105836471289626L;
		boolean running = true;

		@Override
		public void run(SourceContext<Long> ctx) throws Exception {
			long i = 0;
			while (running) {
				ctx.collectWithTimestamp(i, i * 2);
				if (i++ == 1000L) {
					running = false;
				}
			}
		}

		@Override
		public void cancel() {
			running = false;
		}
	});

	final TypeInformationSerializationSchema<Long> longSer = new TypeInformationSerializationSchema<>(Types.LONG, env.getConfig());
	FlinkKafkaProducer010.FlinkKafkaProducer010Configuration prod = FlinkKafkaProducer010.writeToKafkaWithTimestamps(streamWithTimestamps, topic, new KeyedSerializationSchemaWrapper<>(longSer), standardProps, new FlinkKafkaPartitioner<Long>() {
		private static final long serialVersionUID = -6730989584364230617L;

		@Override
		public int partition(Long next, byte[] key, byte[] value, String targetTopic, int[] partitions) {
			return (int) (next % 3);
		}
	});
	prod.setParallelism(3);
	prod.setWriteTimestampToKafka(true);
	env.execute("Produce some");

	// ---------- Consume stream from Kafka -------------------

	env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	env.getConfig().disableSysoutLogging();
	env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	FlinkKafkaConsumer010<Long> kafkaSource = new FlinkKafkaConsumer010<>(topic, new LimitedLongDeserializer(), standardProps);
	kafkaSource.assignTimestampsAndWatermarks(new AssignerWithPunctuatedWatermarks<Long>() {
		private static final long serialVersionUID = -4834111073247835189L;

		@Nullable
		@Override
		public Watermark checkAndGetNextWatermark(Long lastElement, long extractedTimestamp) {
			if (lastElement % 10 == 0) {
				return new Watermark(lastElement);
			}
			return null;
		}

		@Override
		public long extractTimestamp(Long element, long previousElementTimestamp) {
			return previousElementTimestamp;
		}
	});

	DataStream<Long> stream = env.addSource(kafkaSource);
	GenericTypeInfo<Object> objectTypeInfo = new GenericTypeInfo<>(Object.class);
	stream.transform("timestamp validating operator", objectTypeInfo, new TimestampValidatingOperator()).setParallelism(1);

	env.execute("Consume again");

	deleteTestTopic(topic);
}
 

/**
 * Kafka 0.11 specific test, ensuring Timestamps are properly written to and read from Kafka.
 */
@Test(timeout = 60000)
public void testTimestamps() throws Exception {

	final String topic = "tstopic";
	createTestTopic(topic, 3, 1);

	// ---------- Produce an event time stream into Kafka -------------------

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	env.getConfig().disableSysoutLogging();
	env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	DataStream<Long> streamWithTimestamps = env.addSource(new SourceFunction<Long>() {
		private static final long serialVersionUID = -2255115836471289626L;
		boolean running = true;

		@Override
		public void run(SourceContext<Long> ctx) throws Exception {
			long i = 0;
			while (running) {
				ctx.collectWithTimestamp(i, i * 2);
				if (i++ == 1110L) {
					running = false;
				}
			}
		}

		@Override
		public void cancel() {
			running = false;
		}
	});

	final TypeInformationSerializationSchema<Long> longSer = new TypeInformationSerializationSchema<>(Types.LONG, env.getConfig());
	FlinkKafkaProducer011<Long> prod = new FlinkKafkaProducer011<>(topic, new KeyedSerializationSchemaWrapper<>(longSer), standardProps, Optional.of(new FlinkKafkaPartitioner<Long>() {
		private static final long serialVersionUID = -6730989584364230617L;

		@Override
		public int partition(Long next, byte[] key, byte[] value, String targetTopic, int[] partitions) {
			return (int) (next % 3);
		}
	}));
	prod.setWriteTimestampToKafka(true);

	streamWithTimestamps.addSink(prod).setParallelism(3);

	env.execute("Produce some");

	// ---------- Consume stream from Kafka -------------------

	env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	env.getConfig().disableSysoutLogging();
	env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	FlinkKafkaConsumer011<Long> kafkaSource = new FlinkKafkaConsumer011<>(topic, new LimitedLongDeserializer(), standardProps);
	kafkaSource.assignTimestampsAndWatermarks(new AssignerWithPunctuatedWatermarks<Long>() {
		private static final long serialVersionUID = -4834111173247835189L;

		@Nullable
		@Override
		public Watermark checkAndGetNextWatermark(Long lastElement, long extractedTimestamp) {
			if (lastElement % 11 == 0) {
				return new Watermark(lastElement);
			}
			return null;
		}

		@Override
		public long extractTimestamp(Long element, long previousElementTimestamp) {
			return previousElementTimestamp;
		}
	});

	DataStream<Long> stream = env.addSource(kafkaSource);
	GenericTypeInfo<Object> objectTypeInfo = new GenericTypeInfo<>(Object.class);
	stream.transform("timestamp validating operator", objectTypeInfo, new TimestampValidatingOperator()).setParallelism(1);

	env.execute("Consume again");

	deleteTestTopic(topic);
}
 

/**
 * Kafka 20 specific test, ensuring Timestamps are properly written to and read from Kafka.
 */
@Test(timeout = 60000)
public void testTimestamps() throws Exception {

	final String topic = "tstopic";
	createTestTopic(topic, 3, 1);

	// ---------- Produce an event time stream into Kafka -------------------

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	env.getConfig().disableSysoutLogging();
	env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	DataStream<Long> streamWithTimestamps = env.addSource(new SourceFunction<Long>() {
		private static final long serialVersionUID = -2255115836471289626L;
		boolean running = true;

		@Override
		public void run(SourceContext<Long> ctx) throws Exception {
			long i = 0;
			while (running) {
				ctx.collectWithTimestamp(i, i * 2);
				if (i++ == 1110L) {
					running = false;
				}
			}
		}

		@Override
		public void cancel() {
			running = false;
		}
	});

	final TypeInformationSerializationSchema<Long> longSer = new TypeInformationSerializationSchema<>(Types.LONG, env.getConfig());
	FlinkKafkaProducer<Long> prod = new FlinkKafkaProducer<>(topic, new KeyedSerializationSchemaWrapper<>(longSer), standardProps, Optional.of(new FlinkKafkaPartitioner<Long>() {
		private static final long serialVersionUID = -6730989584364230617L;

		@Override
		public int partition(Long next, byte[] key, byte[] value, String targetTopic, int[] partitions) {
			return (int) (next % 3);
		}
	}));
	prod.setWriteTimestampToKafka(true);

	streamWithTimestamps.addSink(prod).setParallelism(3);

	env.execute("Produce some");

	// ---------- Consume stream from Kafka -------------------

	env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(1);
	env.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	env.getConfig().disableSysoutLogging();
	env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

	FlinkKafkaConsumer<Long> kafkaSource = new FlinkKafkaConsumer<>(topic, new KafkaITCase.LimitedLongDeserializer(), standardProps);
	kafkaSource.assignTimestampsAndWatermarks(new AssignerWithPunctuatedWatermarks<Long>() {
		private static final long serialVersionUID = -4834111173247835189L;

		@Nullable
		@Override
		public Watermark checkAndGetNextWatermark(Long lastElement, long extractedTimestamp) {
			if (lastElement % 11 == 0) {
				return new Watermark(lastElement);
			}
			return null;
		}

		@Override
		public long extractTimestamp(Long element, long previousElementTimestamp) {
			return previousElementTimestamp;
		}
	});

	DataStream<Long> stream = env.addSource(kafkaSource);
	GenericTypeInfo<Object> objectTypeInfo = new GenericTypeInfo<>(Object.class);
	stream.transform("timestamp validating operator", objectTypeInfo, new TimestampValidatingOperator()).setParallelism(1);

	env.execute("Consume again");

	deleteTestTopic(topic);
}
 

protected void writeAppendSequence(
		String topicName,
		final int originalNumElements,
		final int numElementsToAppend,
		final int parallelism) throws Exception {

	LOG.info("\n===================================\n" +
		"== Appending sequence of " + numElementsToAppend + " into " + topicName +
		"===================================");

	final TypeInformation<Tuple2<Integer, Integer>> resultType =
		TypeInformation.of(new TypeHint<Tuple2<Integer, Integer>>() {});

	final KeyedSerializationSchema<Tuple2<Integer, Integer>> serSchema =
		new KeyedSerializationSchemaWrapper<>(
			new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig()));

	final KafkaDeserializationSchema<Tuple2<Integer, Integer>> deserSchema =
		new KafkaDeserializationSchemaWrapper<>(
			new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig()));

	// -------- Write the append sequence --------

	StreamExecutionEnvironment writeEnv = StreamExecutionEnvironment.getExecutionEnvironment();
	writeEnv.getConfig().setRestartStrategy(RestartStrategies.noRestart());
	writeEnv.getConfig().disableSysoutLogging();

	DataStream<Tuple2<Integer, Integer>> stream = writeEnv.addSource(new RichParallelSourceFunction<Tuple2<Integer, Integer>>() {

		private boolean running = true;

		@Override
		public void run(SourceContext<Tuple2<Integer, Integer>> ctx) throws Exception {
			int cnt = originalNumElements;
			int partition = getRuntimeContext().getIndexOfThisSubtask();

			while (running && cnt < numElementsToAppend + originalNumElements) {
				ctx.collect(new Tuple2<>(partition, cnt));
				cnt++;
			}
		}

		@Override
		public void cancel() {
			running = false;
		}
	}).setParallelism(parallelism);

	// the producer must not produce duplicates
	Properties producerProperties = FlinkKafkaProducerBase.getPropertiesFromBrokerList(brokerConnectionStrings);
	producerProperties.setProperty("retries", "0");
	producerProperties.putAll(secureProps);

	kafkaServer.produceIntoKafka(stream, topicName, serSchema, producerProperties, new Tuple2FlinkPartitioner(parallelism))
		.setParallelism(parallelism);

	try {
		writeEnv.execute("Write sequence");
	}
	catch (Exception e) {
		throw new Exception("Failed to append sequence to Kafka; append job failed.", e);
	}

	LOG.info("Finished writing append sequence");

	// we need to validate the sequence, because kafka's producers are not exactly once
	LOG.info("Validating sequence");
	while (!getRunningJobs(client).isEmpty()){
		Thread.sleep(50);
	}

	if (!validateSequence(topicName, parallelism, deserSchema, originalNumElements + numElementsToAppend)) {
		throw new Exception("Could not append a valid sequence to Kafka.");
	}
}
 

protected String writeSequence(
		String baseTopicName,
		final int numElements,
		final int parallelism,
		final int replicationFactor) throws Exception {
	LOG.info("\n===================================\n" +
			"== Writing sequence of " + numElements + " into " + baseTopicName + " with p=" + parallelism + "\n" +
			"===================================");

	final TypeInformation<Tuple2<Integer, Integer>> resultType =
			TypeInformation.of(new TypeHint<Tuple2<Integer, Integer>>() {});

	final KeyedSerializationSchema<Tuple2<Integer, Integer>> serSchema =
			new KeyedSerializationSchemaWrapper<>(
					new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig()));

	final KafkaDeserializationSchema<Tuple2<Integer, Integer>> deserSchema =
			new KafkaDeserializationSchemaWrapper<>(
					new TypeInformationSerializationSchema<>(resultType, new ExecutionConfig()));

	final int maxNumAttempts = 10;

	for (int attempt = 1; attempt <= maxNumAttempts; attempt++) {

		final String topicName = baseTopicName + '-' + attempt;

		LOG.info("Writing attempt #" + attempt);

		// -------- Write the Sequence --------

		createTestTopic(topicName, parallelism, replicationFactor);

		StreamExecutionEnvironment writeEnv = StreamExecutionEnvironment.getExecutionEnvironment();
		writeEnv.getConfig().setRestartStrategy(RestartStrategies.noRestart());
		writeEnv.getConfig().disableSysoutLogging();

		DataStream<Tuple2<Integer, Integer>> stream = writeEnv.addSource(new RichParallelSourceFunction<Tuple2<Integer, Integer>>() {

			private boolean running = true;

			@Override
			public void run(SourceContext<Tuple2<Integer, Integer>> ctx) throws Exception {
				int cnt = 0;
				int partition = getRuntimeContext().getIndexOfThisSubtask();

				while (running && cnt < numElements) {
					ctx.collect(new Tuple2<>(partition, cnt));
					cnt++;
				}
			}

			@Override
			public void cancel() {
				running = false;
			}
		}).setParallelism(parallelism);

		// the producer must not produce duplicates
		Properties producerProperties = FlinkKafkaProducerBase.getPropertiesFromBrokerList(brokerConnectionStrings);
		producerProperties.setProperty("retries", "0");
		producerProperties.putAll(secureProps);

		kafkaServer.produceIntoKafka(stream, topicName, serSchema, producerProperties, new Tuple2FlinkPartitioner(parallelism))
				.setParallelism(parallelism);

		try {
			writeEnv.execute("Write sequence");
		}
		catch (Exception e) {
			LOG.error("Write attempt failed, trying again", e);
			deleteTestTopic(topicName);
			waitUntilNoJobIsRunning(client);
			continue;
		}

		LOG.info("Finished writing sequence");

		// -------- Validate the Sequence --------

		// we need to validate the sequence, because kafka's producers are not exactly once
		LOG.info("Validating sequence");

		waitUntilNoJobIsRunning(client);

		if (validateSequence(topicName, parallelism, deserSchema, numElements)) {
			// everything is good!
			return topicName;
		}
		else {
			deleteTestTopic(topicName);
			// fall through the loop
		}
	}

	throw new Exception("Could not write a valid sequence to Kafka after " + maxNumAttempts + " attempts");
}
 

public void runBrokerFailureTest() throws Exception {
	final String topic = "brokerFailureTestTopic";

	final int parallelism = 2;
	final int numElementsPerPartition = 1000;
	final int totalElements = parallelism * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	createTestTopic(topic, parallelism, 2);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic, parallelism, numElementsPerPartition, true);

	// find leader to shut down
	int leaderId = kafkaServer.getLeaderToShutDown(topic);

	LOG.info("Leader to shutdown {}", leaderId);

	// run the topology (the consumers must handle the failures)

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.setParallelism(parallelism);
	env.enableCheckpointing(500);
	env.setRestartStrategy(RestartStrategies.noRestart());
	env.getConfig().disableSysoutLogging();

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);
	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
			.addSource(kafkaSource)
			.map(new PartitionValidatingMapper(parallelism, 1))
			.map(new BrokerKillingMapper<Integer>(leaderId, failAfterElements))
			.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	BrokerKillingMapper.killedLeaderBefore = false;
	tryExecute(env, "Broker failure once test");

	// start a new broker:
	kafkaServer.restartBroker(leaderId);
}
 

/**
 * Tests the proper consumption when having more Flink sources than Kafka partitions, which means
 * that some Flink sources will read no partitions.
 */
public void runMultipleSourcesOnePartitionExactlyOnceTest() throws Exception {
	final String topic = "manyToOneTopic";
	final int numPartitions = 5;
	final int numElementsPerPartition = 1000;
	final int totalElements = numPartitions * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	final int parallelism = 8;

	createTestTopic(topic, numPartitions, 1);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic,
			numPartitions,
			numElementsPerPartition,
			true);

	// run the topology that fails and recovers

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(parallelism);
	// set the number of restarts to one. The failing mapper will fail once, then it's only success exceptions.
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));
	env.getConfig().disableSysoutLogging();
	env.setBufferTimeout(0);

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);
	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
		.addSource(kafkaSource)
		.map(new PartitionValidatingMapper(numPartitions, 1))
		.map(new FailingIdentityMapper<Integer>(failAfterElements))
		.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	FailingIdentityMapper.failedBefore = false;
	tryExecute(env, "multi-source-one-partitions exactly once test");

	deleteTestTopic(topic);
}
 

/**
 * Tests the proper consumption when having fewer Flink sources than Kafka partitions, so
 * one Flink source will read multiple Kafka partitions.
 */
public void runOneSourceMultiplePartitionsExactlyOnceTest() throws Exception {
	final String topic = "oneToManyTopic";
	final int numPartitions = 5;
	final int numElementsPerPartition = 1000;
	final int totalElements = numPartitions * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	final int parallelism = 2;

	createTestTopic(topic, numPartitions, 1);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic,
			numPartitions,
			numElementsPerPartition,
			true);

	// run the topology that fails and recovers

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(parallelism);
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));
	env.getConfig().disableSysoutLogging();

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);
	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
			.addSource(kafkaSource)
			.map(new PartitionValidatingMapper(numPartitions, 3))
			.map(new FailingIdentityMapper<Integer>(failAfterElements))
			.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	FailingIdentityMapper.failedBefore = false;
	tryExecute(env, "One-source-multi-partitions exactly once test");

	deleteTestTopic(topic);
}
 

/**
 * Tests the proper consumption when having a 1:1 correspondence between kafka partitions and
 * Flink sources.
 */
public void runOneToOneExactlyOnceTest() throws Exception {

	final String topic = "oneToOneTopic";
	final int parallelism = 5;
	final int numElementsPerPartition = 1000;
	final int totalElements = parallelism * numElementsPerPartition;
	final int failAfterElements = numElementsPerPartition / 3;

	createTestTopic(topic, parallelism, 1);

	DataGenerators.generateRandomizedIntegerSequence(
			StreamExecutionEnvironment.getExecutionEnvironment(),
			kafkaServer,
			topic,
			parallelism,
			numElementsPerPartition,
			true);

	// run the topology that fails and recovers

	DeserializationSchema<Integer> schema =
			new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(parallelism);
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));
	env.getConfig().disableSysoutLogging();

	Properties props = new Properties();
	props.putAll(standardProps);
	props.putAll(secureProps);

	FlinkKafkaConsumerBase<Integer> kafkaSource = kafkaServer.getConsumer(topic, schema, props);

	env
			.addSource(kafkaSource)
			.map(new PartitionValidatingMapper(parallelism, 1))
			.map(new FailingIdentityMapper<Integer>(failAfterElements))
			.addSink(new ValidatingExactlyOnceSink(totalElements)).setParallelism(1);

	FailingIdentityMapper.failedBefore = false;
	tryExecute(env, "One-to-one exactly once test");

	deleteTestTopic(topic);
}
 

/**
 * This test sets KafkaProducer so that it will  automatically flush the data and
 * and fails the broker to check whether flushed records since last checkpoint were not duplicated.
 */
protected void testExactlyOnce(boolean regularSink, int sinksCount) throws Exception {
	final String topic = (regularSink ? "exactlyOnceTopicRegularSink" : "exactlyTopicCustomOperator") + sinksCount;
	final int partition = 0;
	final int numElements = 1000;
	final int failAfterElements = 333;

	for (int i = 0; i < sinksCount; i++) {
		createTestTopic(topic + i, 1, 1);
	}

	TypeInformationSerializationSchema<Integer> schema = new TypeInformationSerializationSchema<>(BasicTypeInfo.INT_TYPE_INFO, new ExecutionConfig());
	KeyedSerializationSchema<Integer> keyedSerializationSchema = new KeyedSerializationSchemaWrapper<>(schema);

	StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
	env.enableCheckpointing(500);
	env.setParallelism(1);
	env.setRestartStrategy(RestartStrategies.fixedDelayRestart(1, 0));
	env.getConfig().disableSysoutLogging();

	Properties properties = new Properties();
	properties.putAll(standardProps);
	properties.putAll(secureProps);

	// process exactly failAfterElements number of elements and then shutdown Kafka broker and fail application
	List<Integer> expectedElements = getIntegersSequence(numElements);

	DataStream<Integer> inputStream = env
		.addSource(new IntegerSource(numElements))
		.map(new FailingIdentityMapper<Integer>(failAfterElements));

	for (int i = 0; i < sinksCount; i++) {
		FlinkKafkaPartitioner<Integer> partitioner = new FlinkKafkaPartitioner<Integer>() {
			@Override
			public int partition(Integer record, byte[] key, byte[] value, String targetTopic, int[] partitions) {
				return partition;
			}
		};

		if (regularSink) {
			StreamSink<Integer> kafkaSink = kafkaServer.getProducerSink(topic + i, keyedSerializationSchema, properties, partitioner);
			inputStream.addSink(kafkaSink.getUserFunction());
		} else {
			kafkaServer.produceIntoKafka(inputStream, topic + i, keyedSerializationSchema, properties, partitioner);
		}
	}

	FailingIdentityMapper.failedBefore = false;
	TestUtils.tryExecute(env, "Exactly once test");

	for (int i = 0; i < sinksCount; i++) {
		// assert that before failure we successfully snapshot/flushed all expected elements
		assertExactlyOnceForTopic(
			properties,
			topic + i,
			partition,
			expectedElements,
			KAFKA_READ_TIMEOUT);
		deleteTestTopic(topic + i);
	}
}