使用Kafka Spout的Apache storm给出错误：IllegalStateException

Question

Version Info: 
   "org.apache.storm" % "storm-core" % "1.2.1" 
   "org.apache.storm" % "storm-kafka-client" % "1.2.1" 

我有一个storm拓扑,如下所示：

螺栓ta->螺栓b->螺栓tc->螺栓d

bolta只是对请求进行一些格式化，并发出另一个元组。boltb执行一些处理，并为接受的每个元组发出大约100个元组。boltc和boltd处理这些元组。所有的bolts都实现了basebasicbolt。

2018-11-30T20:01:05.261+05:30 util [ERROR] Async loop died!
java.lang.IllegalStateException: Attempting to emit a message that has already been committed. This should never occur when using the at-least-once processing guarantee.
        at org.apache.storm.kafka.spout.KafkaSpout.emitOrRetryTuple(KafkaSpout.java:471) ~[stormjar.jar:?]
        at org.apache.storm.kafka.spout.KafkaSpout.emitIfWaitingNotEmitted(KafkaSpout.java:440) ~[stormjar.jar:?]
        at org.apache.storm.kafka.spout.KafkaSpout.nextTuple(KafkaSpout.java:308) ~[stormjar.jar:?]
        at org.apache.storm.daemon.executor$fn__4975$fn__4990$fn__5021.invoke(executor.clj:654) ~[storm-core-1.2.1.jar:1.2.1]
        at org.apache.storm.util$async_loop$fn__557.invoke(util.clj:484) [storm-core-1.2.1.jar:1.2.1]
        at clojure.lang.AFn.run(AFn.java:22) [clojure-1.7.0.jar:?]
        at java.lang.Thread.run(Thread.java:745) [?:1.8.0_60]
2018-11-30T20:01:05.262+05:30 executor [ERROR]
java.lang.IllegalStateException: Attempting to emit a message that has already been committed. This should never occur when using the at-least-once processing guarantee.
        at org.apache.storm.kafka.spout.KafkaSpout.emitOrRetryTuple(KafkaSpout.java:471) ~[stormjar.jar:?]
        at org.apache.storm.kafka.spout.KafkaSpout.emitIfWaitingNotEmitted(KafkaSpout.java:440) ~[stormjar.jar:?]
        at org.apache.storm.kafka.spout.KafkaSpout.nextTuple(KafkaSpout.java:308) ~[stormjar.jar:?]
        at org.apache.storm.daemon.executor$fn__4975$fn__4990$fn__5021.invoke(executor.clj:654) ~[storm-core-1.2.1.jar:1.2.1]
        at org.apache.storm.util$async_loop$fn__557.invoke(util.clj:484) [storm-core-1.2.1.jar:1.2.1]
        at clojure.lang.AFn.run(AFn.java:22) [clojure-1.7.0.jar:?]
        at java.lang.Thread.run(Thread.java:745) [?:1.8.0_60]

case class Abc(index: Int, rand: Boolean)

class BoltA  extends BaseBasicBolt {

  override def execute(input: Tuple, collector: BasicOutputCollector): Unit = {
    val inp = input.getBinaryByField("value").getObj[someObj]
    val randomGenerator = new Random()

    var i = 0
    val rand = randomGenerator.nextBoolean()
    1 to 100 foreach {
      collector.emit(new Values(Abc(i, rand).getJsonBytes))
      i += 1
    }
  }

  override def declareOutputFields(declarer: OutputFieldsDeclarer): Unit = {
    declarer.declare(new Fields("boltAout"))
  }

}

class BoltB  extends BaseBasicBolt {

  override def execute(input: Tuple, collector: BasicOutputCollector): Unit = {
    val abc = input.getBinaryByField("boltAout").getObj[Abc]
    println(s"Received ${abc.index}th tuple in BoltB")
    if(abc.index >= 97 && abc.rand){
      println(s"throwing FailedException for ${abc.index}th tuple for")
      throw new FailedException()
    }
  }

  override def declareOutputFields(declarer: OutputFieldsDeclarer): Unit = {
  }
}

private def getKafkaSpoutConfig(source: Config) = KafkaSpoutConfig.builder("connections.kafka.producerConnProps.metadata.broker.list", "queueName")
    .setProp(ConsumerConfig.GROUP_ID_CONFIG, "grp")
    .setProp(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, "org.apache.kafka.common.serialization.ByteArrayDeserializer")
    .setOffsetCommitPeriodMs(100)
    .setRetry(new KafkaSpoutRetryExponentialBackoff(
      KafkaSpoutRetryExponentialBackoff.TimeInterval.milliSeconds(100),
      KafkaSpoutRetryExponentialBackoff.TimeInterval.milliSeconds(100),
      10,
      KafkaSpoutRetryExponentialBackoff.TimeInterval.milliSeconds(3000)
    ))
    .setFirstPollOffsetStrategy(offsetStrategyMapping(ConnektConfig.getOrElse("connections.kafka.consumerConnProps.offset.strategy", "UNCOMMITTED_EARLIEST")))
    .setMaxUncommittedOffsets(ConnektConfig.getOrElse("connections.kafka.consumerConnProps.max.uncommited.offset", 10000))
    .build()

MessageTimeoutInsecons:300

Answer 1

这是由@Stig Rohde Døssing提供的修复方法。问题的确切原因如下：

在STORM-2666和followups的修复中，我们添加了逻辑来处理在下列偏移量已经被加密之后，spout接收到偏移量的ack的情况。问题是，喷口可能会提交所有被抵消的偏移，但不能向前调整消费者位置，或在适当发出之前清除。如果被加密的偏移量远远落后于日志结束的偏移量，则喷口可能会最终轮询它已经提交的偏移量。

修复方法有点错误。当使用者位置落后于提交的偏移量时，我们确保向前调整位置，并清除提交的偏移量之后的任何waitingToEmit消息。我们不清除waitingToEmit，除非我们调整了消费者的位置，结果这是一个问题。