0
SparkアプリケーションをYarnで実行する際にいくつか問題があります。私は何の問題もなく動作している非常に大規模な統合テストを持っていますが、私はYARN上でアプリケーションを実行するときには、次のようなエラーがスローされます。UTFDataFormatExceptionによって引き起こされたSparkでタスクがシリアル化できません:エンコードされた文字列が長すぎます
17/01/06 11:22:23 ERROR yarn.ApplicationMaster: User class threw exception: org.apache.spark.SparkException: Task not serializable
org.apache.spark.SparkException: Task not serializable
at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:304)
at org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:294)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:122)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2067)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:324)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:323)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.map(RDD.scala:323)
at org.apache.spark.sql.DataFrame.map(DataFrame.scala:1410)
at com.orgx.yy.dd.check.DQCheck$class.runDQCheck(DQCheck.scala:24)
at com.orgx.yy.dd.check.DQBatchCheck.runDQCheck(DQBatchCheck.scala:13)
at com.orgx.yy.dd.check.DQBatchCheck.doCheck(DQBatchCheck.scala:23)
at com.orgx.yy.dd.DQChecker$.main(DQChecker.scala:60)
at com.orgx.yy.dd.DQChecker.main(DQChecker.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:542)
Caused by: java.io.UTFDataFormatException: encoded string too long: 72887 bytes
at java.io.DataOutputStream.writeUTF(DataOutputStream.java:364)
at java.io.DataOutputStream.writeUTF(DataOutputStream.java:323)
at com.typesafe.config.impl.SerializedConfigValue.writeValueData(SerializedConfigValue.java:295)
at com.typesafe.config.impl.SerializedConfigValue.writeValue(SerializedConfigValue.java:369)
at com.typesafe.config.impl.SerializedConfigValue.writeValueData(SerializedConfigValue.java:309)
at com.typesafe.config.impl.SerializedConfigValue.writeValue(SerializedConfigValue.java:369)
at com.typesafe.config.impl.SerializedConfigValue.writeValueData(SerializedConfigValue.java:309)
at com.typesafe.config.impl.SerializedConfigValue.writeValue(SerializedConfigValue.java:369)
at com.typesafe.config.impl.SerializedConfigValue.writeValueData(SerializedConfigValue.java:309)
at com.typesafe.config.impl.SerializedConfigValue.writeValue(SerializedConfigValue.java:369)
at com.typesafe.config.impl.SerializedConfigValue.writeExternal(SerializedConfigValue.java:435)
at java.io.ObjectOutputStream.writeExternalData(ObjectOutputStream.java:1459)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1430)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at scala.collection.immutable.$colon$colon.writeObject(List.scala:379)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1028)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:44)
at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:101)
at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:301)
... 20 more
17/01/06 11:22:24 INFO yarn.ApplicationMaster: Final app status: FAILED, exitCode: 15, (reason: User class threw exception: org.apache.spark.SparkException: Task not serializable)
犯人はjava.io.UTFDataFormatExceptionのようだ:あまりにも長いエンコードされた文字列: 72887バイトで誰でも何が起こっているのか考えている?
例外がスローされたソースコードを見ているかもしれません: 'DataOutputStream.java:364' – maasg
@maasgこれは低レベルJava IOクラスであり、多くの図書館。私はタスクのシリアル化に間違ったことが起こっていると思っていますし、何らかのサイズ制限にぶつかっています。 – ErikHabanero
もし私がそのような質問に答えるつもりなら、それは私が始めようとしているところで、何がうまくいかないのかを知るためです。問題はおそらく他の場所にあると私は同意しますが、あなたはバグの隠れ家にパン粉を追いかける必要があります。 – maasg