Apache spark 无法在Spark Streaming中获取广播\u 4的广播\u片段0

我正在运行一个spark流媒体应用程序，输入源为Kafka。spark的版本是1.4.0

我的应用程序在下运行正常，但现在，当我启用检查点时，运行作业，然后重新启动作业，以查看检查点是否正常工作，我会将以下内容淹没到日志中，作业会停止

你能帮我解决这个问题吗。如果需要其他信息，请告诉我。基本上，我想将检查点功能添加到我的spark流应用程序中

15/10/30 13:23:00 INFO TorrentBroadcast: Started reading broadcast variable 4
java.io.IOException: org.apache.spark.SparkException: Failed to get broadcast_4_piece0 of broadcast_4
    at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1257)
    at org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:165)
    at org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:64)
    at org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:64)
    at org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:88)
    at com.toi.columbia.aggregate.util.CalendarUtil.isRecordCassandraInsertableV1(CalendarUtil.java:103)
    at com.toi.columbia.aggregate.stream.v1.AdvPublisherV1$3.call(AdvPublisherV1.java:124)
    at com.toi.columbia.aggregate.stream.v1.AdvPublisherV1$3.call(AdvPublisherV1.java:110)
    at org.apache.spark.streaming.api.java.JavaDStreamLike$$anonfun$fn$1$1.apply(JavaDStreamLike.scala:172)
    at org.apache.spark.streaming.api.java.JavaDStreamLike$$anonfun$fn$1$1.apply(JavaDStreamLike.scala:172)
    at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
    at com.datastax.spark.connector.util.CountingIterator.hasNext(CountingIterator.scala:10)
    at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
    at scala.collection.Iterator$class.foreach(Iterator.scala:727)
    at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
    at com.datastax.spark.connector.writer.TableWriter.measureMaxInsertSize(TableWriter.scala:89)
    at com.datastax.spark.connector.writer.TableWriter.com$datastax$spark$connector$writer$TableWriter$$optimumBatchSize(TableWriter.scala:107)
    at com.datastax.spark.connector.writer.TableWriter$$anonfun$write$1.apply(TableWriter.scala:133)
    at com.datastax.spark.connector.writer.TableWriter$$anonfun$write$1.apply(TableWriter.scala:127)
    at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$withSessionDo$1.apply(CassandraConnector.scala:98)
    at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$withSessionDo$1.apply(CassandraConnector.scala:97)
    at com.datastax.spark.connector.cql.CassandraConnector.closeResourceAfterUse(CassandraConnector.scala:149)
    at com.datastax.spark.connector.cql.CassandraConnector.withSessionDo(CassandraConnector.scala:97)
    at com.datastax.spark.connector.writer.TableWriter.write(TableWriter.scala:127)
    at com.datastax.spark.connector.streaming.DStreamFunctions$$anonfun$saveToCassandra$1$$anonfun$apply$1.apply(DStreamFunctions.scala:26)
    at com.datastax.spark.connector.streaming.DStreamFunctions$$anonfun$saveToCassandra$1$$anonfun$apply$1.apply(DStreamFunctions.scala:26)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
    at org.apache.spark.scheduler.Task.run(Task.scala:70)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.SparkException: Failed to get broadcast_4_piece0 of broadcast_4
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1$$anonfun$2.apply(TorrentBroadcast.scala:138)
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1$$anonfun$2.apply(TorrentBroadcast.scala:138)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply$mcVI$sp(TorrentBroadcast.scala:137)
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala:120)
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala:120)
    at scala.collection.immutable.List.foreach(List.scala:318)
    at org.apache.spark.broadcast.TorrentBroadcast.org$apache$spark$broadcast$TorrentBroadcast$$readBlocks(TorrentBroadcast.scala:120)
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$1.apply(TorrentBroadcast.scala:175)
    at org.apache.spark.u

---

我相信您正在创建内部的广播变量

JavaStreamingContextFactory factory = new JavaStreamingContextFactory() {}

尝试在此重写的方法之外创建广播变量

从您的异常中可以清楚地看到，当您重新启动chekpointed应用程序时，广播变量没有初始化

15/10/30 13:23:00 INFO TorrentBroadcast: Started reading broadcast variable 4
java.io.IOException: org.apache.spark.SparkException: Failed to get broadcast_4_piece0 of broadcast_4
    at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1257)
    at org.apache.spark.broadcast.TorrentBroadcast.readBroadcastBlock(TorrentBroadcast.scala:165)
    at org.apache.spark.broadcast.TorrentBroadcast._value$lzycompute(TorrentBroadcast.scala:64)
    at org.apache.spark.broadcast.TorrentBroadcast._value(TorrentBroadcast.scala:64)
    at org.apache.spark.broadcast.TorrentBroadcast.getValue(TorrentBroadcast.scala:88)
    at com.toi.columbia.aggregate.util.CalendarUtil.isRecordCassandraInsertableV1(CalendarUtil.java:103)
    at com.toi.columbia.aggregate.stream.v1.AdvPublisherV1$3.call(AdvPublisherV1.java:124)
    at com.toi.columbia.aggregate.stream.v1.AdvPublisherV1$3.call(AdvPublisherV1.java:110)
    at org.apache.spark.streaming.api.java.JavaDStreamLike$$anonfun$fn$1$1.apply(JavaDStreamLike.scala:172)
    at org.apache.spark.streaming.api.java.JavaDStreamLike$$anonfun$fn$1$1.apply(JavaDStreamLike.scala:172)
    at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
    at com.datastax.spark.connector.util.CountingIterator.hasNext(CountingIterator.scala:10)
    at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
    at scala.collection.Iterator$class.foreach(Iterator.scala:727)
    at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
    at com.datastax.spark.connector.writer.TableWriter.measureMaxInsertSize(TableWriter.scala:89)
    at com.datastax.spark.connector.writer.TableWriter.com$datastax$spark$connector$writer$TableWriter$$optimumBatchSize(TableWriter.scala:107)
    at com.datastax.spark.connector.writer.TableWriter$$anonfun$write$1.apply(TableWriter.scala:133)
    at com.datastax.spark.connector.writer.TableWriter$$anonfun$write$1.apply(TableWriter.scala:127)
    at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$withSessionDo$1.apply(CassandraConnector.scala:98)
    at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$withSessionDo$1.apply(CassandraConnector.scala:97)
    at com.datastax.spark.connector.cql.CassandraConnector.closeResourceAfterUse(CassandraConnector.scala:149)
    at com.datastax.spark.connector.cql.CassandraConnector.withSessionDo(CassandraConnector.scala:97)
    at com.datastax.spark.connector.writer.TableWriter.write(TableWriter.scala:127)
    at com.datastax.spark.connector.streaming.DStreamFunctions$$anonfun$saveToCassandra$1$$anonfun$apply$1.apply(DStreamFunctions.scala:26)
    at com.datastax.spark.connector.streaming.DStreamFunctions$$anonfun$saveToCassandra$1$$anonfun$apply$1.apply(DStreamFunctions.scala:26)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
    at org.apache.spark.scheduler.Task.run(Task.scala:70)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.SparkException: Failed to get broadcast_4_piece0 of broadcast_4
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1$$anonfun$2.apply(TorrentBroadcast.scala:138)
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1$$anonfun$2.apply(TorrentBroadcast.scala:138)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply$mcVI$sp(TorrentBroadcast.scala:137)
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala:120)
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$org$apache$spark$broadcast$TorrentBroadcast$$readBlocks$1.apply(TorrentBroadcast.scala:120)
    at scala.collection.immutable.List.foreach(List.scala:318)
    at org.apache.spark.broadcast.TorrentBroadcast.org$apache$spark$broadcast$TorrentBroadcast$$readBlocks(TorrentBroadcast.scala:120)
    at org.apache.spark.broadcast.TorrentBroadcast$$anonfun$readBroadcastBlock$1.apply(TorrentBroadcast.scala:175)
    at org.apache.spark.u

---

干杯

也许你忘了增加spark.cleaner.ttl的

看这里