Размер моих собранных данных составляет 1,3 г, а все конфигурации памяти драйвера установлены на 3 г.
Почему нехватка памяти все еще происходит??
Это моя подробная конфигурация сообщения об исключении sparkR и OOM.
spark.default.confs=list(spark.cores.max="8",spark.executor.memory="15g",
spark.driver.maxResultSize="3g",spark.driver.memory="3g",spark.driver.extraJavaOptions="-Xms3g")
#
sc <- sparkR.init(master="spark://10.58.70.155:7077",sparkEnvir = spark.default.confs)
ERROR RBackendHandler: dfToCols on org.apache.spark.sql.api.r.SQLUtils failed
java.lang.reflect.InvocationTargetException
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.api.r.RBackendHandler.handleMethodCall(RBackendHandler.scala:142)
at org.apache.spark.api.r.RBackendHandler.channelRead0(RBackendHandler.scala:74)
at org.apache.spark.api.r.RBackendHandler.channelRead0(RBackendHandler.scala:36)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:103)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
at io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:163)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:333)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:319)
at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:787)
at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:130)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:511)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:468)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:382)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:354)
at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:116)
at io.netty.util.concurrent.DefaultThreadFactory$DefaultRunnableDecorator.run(DefaultThreadFactory.java:137)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.OutOfMemoryError: Java heap space
at java.util.Arrays.copyOf(Arrays.java:3236)
at java.io.ByteArrayOutputStream.grow(ByteArrayOutputStream.java:118)
at java.io.ByteArrayOutputStream.ensureCapacity(ByteArrayOutputStream.java:93)
at java.io.ByteArrayOutputStream.write(ByteArrayOutputStream.java:135)
at java.io.DataOutputStream.writeInt(DataOutputStream.java:200)
at org.apache.spark.api.r.SerDe$.writeString(SerDe.scala:296)
at org.apache.spark.api.r.SerDe$.writeObject(SerDe.scala:211)
at org.apache.spark.sql.api.r.SQLUtils$$anonfun$colToRBytes$1.apply(SQLUtils.scala:129)
at org.apache.spark.sql.api.r.SQLUtils$$anonfun$colToRBytes$1.apply(SQLUtils.scala:127)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at org.apache.spark.sql.api.r.SQLUtils$.colToRBytes(SQLUtils.scala:127)
at org.apache.spark.sql.api.r.SQLUtils$$anonfun$dfToCols$1.apply(SQLUtils.scala:108)
at org.apache.spark.sql.api.r.SQLUtils$$anonfun$dfToCols$1.apply(SQLUtils.scala:107)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:108)
at org.apache.spark.sql.api.r.SQLUtils$.dfToCols(SQLUtils.scala:107)
at org.apache.spark.sql.api.r.SQLUtils.dfToCols(SQLUtils.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.api.r.RBackendHandler.handleMethodCall(RBackendHandler.scala:142)
at org.apache.spark.api.r.RBackendHandler.channelRead0(RBackendHandler.scala:74)
Error: returnStatus == 0 is not TRUE
