Confirming that I am also hitting the same errors.
host: r3.8xlarge
configuration
spark.serializer org.apache.spark.serializer.KryoSerializer
spark.driver.memory 200g
spark.serializer.objectStreamReset 10
spark.local.dir /mnt/rohanp-data2/
spark.driver.maxResultSize 0
Error
15/11/14 08:03:49 INFO BlockManagerInfo: Added broadcast_5_piece32 in memory
on localhost:56741 (size: 1728.1 KB, free: 103.1 GB)
[29/1049]
15/11/14 08:03:49 INFO SparkContext: Created broadcast 5 from broadcast at
Word2Vec.scala:286
Exception in thread "main" java.lang.OutOfMemoryError
at
java.io.ByteArrayOutputStream.hugeCapacity(ByteArrayOutputStream.java:123)
at
java.io.ByteArrayOutputStream.grow(ByteArrayOutputStream.java:117)
at
java.io.ByteArrayOutputStream.ensureCapacity(ByteArrayOutputStream.java:93)
at
java.io.ByteArrayOutputStream.write(ByteArrayOutputStream.java:153)
at
java.io.ObjectOutputStream$BlockDataOutputStream.drain(ObjectOutputStream.java:1876)
at
java.io.ObjectOutputStream$BlockDataOutputStream.setBlockDataMode(ObjectOutputStream.java:1785)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1188)
at
java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:347)
at
org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:44)
at
org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:84)
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:301)
at
org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:294)
at
org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:122)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2032)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1.apply(RDD.scala:707)
at
org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1.apply(RDD.scala:706)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:310)
at org.apache.spark.rdd.RDD.mapPartitions(RDD.scala:706)
at org.apache.spark.mllib.feature.Word2Vec.fit(Word2Vec.scala:288)
at Word2VecApp$.main(Word2VecApp.scala:13)
at Word2VecApp.main(Word2VecApp.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:674)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at
org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:120)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
15/11/14 08:04:21 INFO SparkContext: Invoking stop() from shutdown hook
15/11/14 08:04:21 INFO SparkUI: Stopped Spark web UI at
http://10.144.64.249:4040
15/11/14 08:04:21 INFO DAGScheduler: Stopping DAGScheduler
Code :
import org.apache.spark._
import org.apache.spark.rdd._
import org.apache.spark.SparkContext._
import org.apache.spark.mllib.feature.{Word2Vec, Word2VecModel}
import org.apache.spark.SparkConf
object Word2VecApp {
def main(args: Array[String]) {
val conf = new SparkConf().setAppName("Word2Vec Application")
val sc = new SparkContext(conf)
val input =
sc.textFile("/mnt/rohanp-data1/data/training_queries.txt").map(line =>
line.split(" ").toSeq)
val word2vec = new Word2Vec()
val model = word2vec.fit(input)
val synonyms = model.findSynonyms("china", 40)
for((synonym, cosineSimilarity) <- synonyms) {
println(s"$synonym $cosineSimilarity")
}
}
}
start command:
../spark-submit --class "Word2VecApp" --master local[30]
target/scala-2.10/word2vec-project_2.10-1.0.jar
--
View this message in context:
http://apache-spark-user-list.1001560.n3.nabble.com/Spark-ClosureCleaner-or-java-serializer-OOM-when-trying-to-grow-tp24796p25383.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
