Spark Streaming + Kafka 連携ガイド (Kafka ブローカーバージョン 0.10.0 以降)

import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe

val kafkaParams = Map[String, Object](
  "bootstrap.servers" -> "localhost:9092,anotherhost:9092",
  "key.deserializer" -> classOf[StringDeserializer],
  "value.deserializer" -> classOf[StringDeserializer],
  "group.id" -> "use_a_separate_group_id_for_each_stream",
  "auto.offset.reset" -> "latest",
  "enable.auto.commit" -> (false: java.lang.Boolean)
)

val topics = Array("topicA", "topicB")
val stream = KafkaUtils.createDirectStream[String, String](
  streamingContext,
  PreferConsistent,
  Subscribe[String, String](topics, kafkaParams)
)

stream.map(record => (record.key, record.value))

import java.util.*;
import org.apache.spark.SparkConf;
import org.apache.spark.TaskContext;
import org.apache.spark.api.java.*;
import org.apache.spark.api.java.function.*;
import org.apache.spark.streaming.api.java.*;
import org.apache.spark.streaming.kafka010.*;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.common.TopicPartition;
import org.apache.kafka.common.serialization.StringDeserializer;
import scala.Tuple2;

Map<String, Object> kafkaParams = new HashMap<>();
kafkaParams.put("bootstrap.servers", "localhost:9092,anotherhost:9092");
kafkaParams.put("key.deserializer", StringDeserializer.class);
kafkaParams.put("value.deserializer", StringDeserializer.class);
kafkaParams.put("group.id", "use_a_separate_group_id_for_each_stream");
kafkaParams.put("auto.offset.reset", "latest");
kafkaParams.put("enable.auto.commit", false);

Collection<String> topics = Arrays.asList("topicA", "topicB");

JavaInputDStream<ConsumerRecord<String, String>> stream =
  KafkaUtils.createDirectStream(
    streamingContext,
    LocationStrategies.PreferConsistent(),
    ConsumerStrategies.<String, String>Subscribe(topics, kafkaParams)
  );

stream.mapToPair(record -> new Tuple2<>(record.key(), record.value()));

// Import dependencies and create kafka params as in Create Direct Stream above

val offsetRanges = Array(
  // topic, partition, inclusive starting offset, exclusive ending offset
  OffsetRange("test", 0, 0, 100),
  OffsetRange("test", 1, 0, 100)
)

val rdd = KafkaUtils.createRDD[String, String](sparkContext, kafkaParams, offsetRanges, PreferConsistent)

// Import dependencies and create kafka params as in Create Direct Stream above

OffsetRange[] offsetRanges = {
  // topic, partition, inclusive starting offset, exclusive ending offset
  OffsetRange.create("test", 0, 0, 100),
  OffsetRange.create("test", 1, 0, 100)
};

JavaRDD<ConsumerRecord<String, String>> rdd = KafkaUtils.createRDD(
  sparkContext,
  kafkaParams,
  offsetRanges,
  LocationStrategies.PreferConsistent()
);

stream.foreachRDD { rdd =>
  val offsetRanges = rdd.asInstanceOf[HasOffsetRanges].offsetRanges
  rdd.foreachPartition { iter =>
    val o: OffsetRange = offsetRanges(TaskContext.get.partitionId)
    println(s"${o.topic} ${o.partition} ${o.fromOffset} ${o.untilOffset}")
  }
}

stream.foreachRDD(rdd -> {
  OffsetRange[] offsetRanges = ((HasOffsetRanges) rdd.rdd()).offsetRanges();
  rdd.foreachPartition(consumerRecords -> {
    OffsetRange o = offsetRanges[TaskContext.get().partitionId()];
    System.out.println(
      o.topic() + " " + o.partition() + " " + o.fromOffset() + " " + o.untilOffset());
  });
});

stream.foreachRDD { rdd =>
  val offsetRanges = rdd.asInstanceOf[HasOffsetRanges].offsetRanges

  // some time later, after outputs have completed
  stream.asInstanceOf[CanCommitOffsets].commitAsync(offsetRanges)
}

stream.foreachRDD(rdd -> {
  OffsetRange[] offsetRanges = ((HasOffsetRanges) rdd.rdd()).offsetRanges();

  // some time later, after outputs have completed
  ((CanCommitOffsets) stream.inputDStream()).commitAsync(offsetRanges);
});

// The details depend on your data store, but the general idea looks like this

// begin from the offsets committed to the database
val fromOffsets = selectOffsetsFromYourDatabase.map { resultSet =>
  new TopicPartition(resultSet.string("topic"), resultSet.int("partition")) -> resultSet.long("offset")
}.toMap

val stream = KafkaUtils.createDirectStream[String, String](
  streamingContext,
  PreferConsistent,
  Assign[String, String](fromOffsets.keys.toList, kafkaParams, fromOffsets)
)

stream.foreachRDD { rdd =>
  val offsetRanges = rdd.asInstanceOf[HasOffsetRanges].offsetRanges

  val results = yourCalculation(rdd)

  // begin your transaction

  // update results
  // update offsets where the end of existing offsets matches the beginning of this batch of offsets
  // assert that offsets were updated correctly

  // end your transaction
}

// The details depend on your data store, but the general idea looks like this

// begin from the offsets committed to the database
Map<TopicPartition, Long> fromOffsets = new HashMap<>();
for (resultSet : selectOffsetsFromYourDatabase)
  fromOffsets.put(new TopicPartition(resultSet.string("topic"), resultSet.int("partition")), resultSet.long("offset"));
}

JavaInputDStream<ConsumerRecord<String, String>> stream = KafkaUtils.createDirectStream(
  streamingContext,
  LocationStrategies.PreferConsistent(),
  ConsumerStrategies.<String, String>Assign(fromOffsets.keySet(), kafkaParams, fromOffsets)
);

stream.foreachRDD(rdd -> {
  OffsetRange[] offsetRanges = ((HasOffsetRanges) rdd.rdd()).offsetRanges();
  
  Object results = yourCalculation(rdd);

  // begin your transaction

  // update results
  // update offsets where the end of existing offsets matches the beginning of this batch of offsets
  // assert that offsets were updated correctly

  // end your transaction
});

val kafkaParams = Map[String, Object](
  // the usual params, make sure to change the port in bootstrap.servers if 9092 is not TLS
  "security.protocol" -> "SSL",
  "ssl.truststore.location" -> "/some-directory/kafka.client.truststore.jks",
  "ssl.truststore.password" -> "test1234",
  "ssl.keystore.location" -> "/some-directory/kafka.client.keystore.jks",
  "ssl.keystore.password" -> "test1234",
  "ssl.key.password" -> "test1234"
)

Map<String, Object> kafkaParams = new HashMap<String, Object>();
// the usual params, make sure to change the port in bootstrap.servers if 9092 is not TLS
kafkaParams.put("security.protocol", "SSL");
kafkaParams.put("ssl.truststore.location", "/some-directory/kafka.client.truststore.jks");
kafkaParams.put("ssl.truststore.password", "test1234");
kafkaParams.put("ssl.keystore.location", "/some-directory/kafka.client.keystore.jks");
kafkaParams.put("ssl.keystore.password", "test1234");
kafkaParams.put("ssl.key.password", "test1234");