我正在使用spark 1.5.0并开发一个火花流应用程序。应用程序从HDFS读取文件,将rdd转换为数据帧并在每个数据帧上执行多个查询。
应用程序运行大约24小时,然后崩溃。 应用程序主日志/驱动程序日志显示:
Exception in thread "dag-scheduler-event-loop" java.lang.OutOfMemoryError: GC overhead limit exceeded
at java.lang.Class.getDeclaredMethods0(Native Method)
at java.lang.Class.privateGetDeclaredMethods(Class.java:2701)
at java.lang.Class.getDeclaredMethod(Class.java:2128)
at java.io.ObjectStreamClass.getInheritableMethod(ObjectStreamClass.java:1442)
at java.io.ObjectStreamClass.access$2200(ObjectStreamClass.java:72)
at java.io.ObjectStreamClass$2.run(ObjectStreamClass.java:508)
at java.io.ObjectStreamClass$2.run(ObjectStreamClass.java:472)
at java.security.AccessController.doPrivileged(Native Method)
at java.io.ObjectStreamClass.<init>(ObjectStreamClass.java:472)
at java.io.ObjectStreamClass.lookup(ObjectStreamClass.java:369)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1134)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at scala.collection.immutable.$colon$colon.writeObject(List.scala:379)
at sun.reflect.GeneratedMethodAccessor1511.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1028)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
Exception in thread "JobGenerator" java.lang.OutOfMemoryError: GC overhead limit exceeded
at java.util.zip.ZipCoder.getBytes(ZipCoder.java:80)
at java.util.zip.ZipFile.getEntry(ZipFile.java:310)
at java.util.jar.JarFile.getEntry(JarFile.java:240)
at sun.net.www.protocol.jar.URLJarFile.getEntry(URLJarFile.java:128)
at sun.net.www.protocol.jar.JarURLConnection.connect(JarURLConnection.java:132)
at sun.net.www.protocol.jar.JarURLConnection.getInputStream(JarURLConnection.java:150)
at java.net.URLClassLoader.getResourceAsStream(URLClassLoader.java:238)
at java.lang.Class.getResourceAsStream(Class.java:2223)
at org.apache.spark.util.ClosureCleaner$.getClassReader(ClosureCleaner.scala:38)
at org.apache.spark.util.ClosureCleaner$.getInnerClosureClasses(ClosureCleaner.scala:81)
at org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:187)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:122)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2032)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:314)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:313)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:306)
at org.apache.spark.rdd.RDD.map(RDD.scala:313)
at org.apache.spark.streaming.dstream.MappedDStream$$anonfun$compute$1.apply(MappedDStream.scala:35)
at org.apache.spark.streaming.dstream.MappedDStream$$anonfun$compute$1.apply(MappedDStream.scala:35)
at scala.Option.map(Option.scala:145)
at org.apache.spark.streaming.dstream.MappedDStream.compute(MappedDStream.scala:35)
at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:350)
at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:350)
at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57)
at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:349)
at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:349)
at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:399)
at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:344)
at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:342)
at scala.Option.orElse(Option.scala:257)
我收集了驱动程序堆转储,它说可能的内存泄漏来自org.apache.spark.sql.execution.ui.SQLListener
同样在我的applciation主网址中,我可以看到数千个SQL tabs eg:-> SQL 1, SQL2 .. SQL 2000
,并且这些数量的标签不断增加。
是否有人知道为什么这些SQL标签不断增加并建议GC异常。 感谢
答案 0 :(得分:0)