Hi,
When we run mllib word2vec(spark-1.1.0), driver get stuck with 100% cup
usage. Here is the jstack output:
"main" prio=10 tid=0x0000000040112800 nid=0x46f2 runnable
[0x000000004162e000]
java.lang.Thread.State: RUNNABLE
at
java.io.ObjectOutputStream$BlockDataOutputStream.drain(ObjectOutputStream.java:1847)
at
java.io.ObjectOutputStream$BlockDataOutputStream.write(ObjectOutputStream.java:1778)
at java.io.DataOutputStream.writeInt(DataOutputStream.java:182)
at java.io.DataOutputStream.writeFloat(DataOutputStream.java:225)
at
java.io.ObjectOutputStream$BlockDataOutputStream.writeFloats(ObjectOutputStream.java:2064)
at
java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1310)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1154)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1518)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1483)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1400)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1158)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1518)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1483)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1400)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1158)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1518)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1483)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1400)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1158)
at
java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:330)
at
org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:42)
at
org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:73)
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:164)
at
org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:158)
at org.apache.spark.SparkContext.clean(SparkContext.scala:1242)
at org.apache.spark.rdd.RDD.mapPartitionsWithIndex(RDD.scala:610)
at
org.apache.spark.mllib.feature.Word2Vec$$anonfun$fit$1.apply$mcVI$sp(Word2Vec.scala:291)
at scala.collection.immutable.Range.foreach$mVc$sp(Range.scala:141)
at org.apache.spark.mllib.feature.Word2Vec.fit(Word2Vec.scala:290)
at com.baidu.inf.WordCount$.main(WordCount.scala:31)
at com.baidu.inf.WordCount.main(WordCount.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
at java.lang.reflect.Method.invoke(Method.java:597)
at
org.apache.spark.deploy.SparkSubmit$.launch(SparkSubmit.scala:328)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:75)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
--
Best Regards
