堆空间错误：SparkListenerBus

Question

I am trying to debug a PySpark program and quite frankly, I am stumped.

I see the following error in the logs. I verified the input parameters - all appear to be in order.

Driver and executors appear to be proper - about 3MB of 7GB being used on each node. I see that the DAG plan that is created is huge. Could it be due to that?

18/02/17 00:59:02 ERROR Utils: throw uncaught fatal error in thread SparkListenerBus

java.lang.OutOfMemoryError: Java heap space

    at java.util.Arrays.copyOfRange(Arrays.java:3664)

    at java.lang.String.<init>(String.java:207)

    at java.lang.StringBuilder.toString(StringBuilder.java:407)

    at com.fasterxml.jackson.core.util.TextBuffer.contentsAsString(TextBuffer.java:356)

    at com.fasterxml.jackson.core.json.ReaderBasedJsonParser.getText(ReaderBasedJsonParser.java:235)

    at org.json4s.jackson.JValueDeserializer.deserialize(JValueDeserializer.scala:20)

    at org.json4s.jackson.JValueDeserializer.deserialize(JValueDeserializer.scala:42)

    at org.json4s.jackson.JValueDeserializer.deserialize(JValueDeserializer.scala:35)

    at com.fasterxml.jackson.databind.ObjectMapper._readMapAndClose(ObjectMapper.java:3736)

    at com.fasterxml.jackson.databind.ObjectMapper.readValue(ObjectMapper.java:2726)

    at org.json4s.jackson.JsonMethods$class.parse(JsonMethods.scala:20)

    at org.json4s.jackson.JsonMethods$.parse(JsonMethods.scala:50)

    at org.apache.spark.util.JsonProtocol$.sparkEventToJson(JsonProtocol.scala:103)

    at org.apache.spark.scheduler.EventLoggingListener.logEvent(EventLoggingListener.scala:134)

    at org.apache.spark.scheduler.EventLoggingListener.onOtherEvent(EventLoggingListener.scala:202)

    at org.apache.spark.scheduler.SparkListenerBus$class.doPostEvent(SparkListenerBus.scala:67)

    at org.apache.spark.scheduler.LiveListenerBus.doPostEvent(LiveListenerBus.scala:36)

    at org.apache.spark.scheduler.LiveListenerBus.doPostEvent(LiveListenerBus.scala:36)

    at org.apache.spark.util.ListenerBus$class.postToAll(ListenerBus.scala:63)

    at org.apache.spark.scheduler.LiveListenerBus.postToAll(LiveListenerBus.scala:36)

    at org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(LiveListenerBus.scala:94)

    at org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply(LiveListenerBus.scala:79)

    at org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply(LiveListenerBus.scala:79)

    at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)

    at org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1.apply$mcV$sp(LiveListenerBus.scala:78)

    at org.apache.spark.util.Utils$.tryOrStopSparkContext(Utils.scala:1245)

    at org.apache.spark.scheduler.LiveListenerBus$$anon$1.run(LiveListenerBus.scala:77)

Exception in thread "SparkListenerBus" java.lang.OutOfMemoryError: Java heap space

    at java.util.Arrays.copyOfRange(Arrays.java:3664)

    at java.lang.String.<init>(String.java:207)

    at java.lang.StringBuilder.toString(StringBuilder.java:407)

    at com.fasterxml.jackson.core.util.TextBuffer.contentsAsString(TextBuffer.java:356)

    at com.fasterxml.jackson.core.json.ReaderBasedJsonParser.getText(ReaderBasedJsonParser.java:235)

    at org.json4s.jackson.JValueDeserializer.deserialize(JValueDeserializer.scala:20)

    at org.json4s.jackson.JValueDeserializer.deserialize(JValueDeserializer.scala:42)

    at org.json4s.jackson.JValueDeserializer.deserialize(JValueDeserializer.scala:35)

    at com.fasterxml.jackson.databind.ObjectMapper._readMapAndClose(ObjectMapper.java:3736)

    at com.fasterxml.jackson.databind.ObjectMapper.readValue(ObjectMapper.java:2726)

    at org.json4s.jackson.JsonMethods$class.parse(JsonMethods.scala:20)

    at org.json4s.jackson.JsonMethods$.parse(JsonMethods.scala:50)

    at org.apache.spark.util.JsonProtocol$.sparkEventToJson(JsonProtocol.scala:103)

    at org.apache.spark.scheduler.EventLoggingListener.logEvent(EventLoggingListener.scala:134)

    at org.apache.spark.scheduler.EventLoggingListener.onOtherEvent(EventLoggingListener.scala:202)

    at org.apache.spark.scheduler.SparkListenerBus$class.doPostEvent(SparkListenerBus.scala:67)

    at org.apache.spark.scheduler.LiveListenerBus.doPostEvent(LiveListenerBus.scala:36)

    at org.apache.spark.scheduler.LiveListenerBus.doPostEvent(LiveListenerBus.scala:36)

    at org.apache.spark.util.ListenerBus$class.postToAll(ListenerBus.scala:63)

    at org.apache.spark.scheduler.LiveListenerBus.postToAll(LiveListenerBus.scala:36)

    at org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(LiveListenerBus.scala:94)

    at org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply(LiveListenerBus.scala:79)

    at org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply(LiveListenerBus.scala:79)

    at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)

    at org.apache.spark.scheduler.LiveListenerBus$$anon$1$$anonfun$run$1.apply$mcV$sp(LiveListenerBus.scala:78)

    at org.apache.spark.util.Utils$.tryOrStopSparkContext(Utils.scala:1245)

    at org.apache.spark.scheduler.LiveListenerBus$$anon$1.run(LiveListenerBus.scala:77)

Answer 1

A workaround for this error is to use the setting:

spark.eventLog.enabled=false 

but as it would imply you do not get any event logs.