1

当我使用 JanusGraph 0.2.0 文档第 35 章中的示例时，就可以了。但是当我将 conf/hadoop-graph/hadoop-load.properties 中的 spark.master 从 local[*] 更改为 spark://192.168.63.105:7077 时，我会收到一些警告信息。

JanusGraph 0.2.0 文档的第 35 章中有一个注释：本章中的示例基于本地模式下运行 Spark。在独立模式下使用 Spark 或在 Yarn 或 Mesos 上运行 Spark 时需要额外的配置。什么是附加配置？

警告信息：

> WARN org.apache.tinkerpop.gremlin.spark.process.computer.SparkGraphComputer - class org.apache.hadoop.mapreduce.lib.output.NullOutputFormat does not implement PersistRequestGraphAware and thus, persistence options are unknown -- assuming all options are possible

> WARN org.apache.spark.deploy.client.AppClient$ClientEndpoint - Failed to connect to master 192.168.63.105:7077

> java.lang.RuntimeException: java.io.EOFException
> at java.io.DataInputStream.readFully(DataInputStream.java:197)
> at java.io.DataInputStream.readUTF(DataInputStream.java:609) 
> at java.io.DataInputStream.readFully(DataInputStream.java:564) 
> at org.apache.spark.rpc.netty.RequestMessage$.readRpcAddress(NettyRpcEnv.scala:582)
> at org.apache.spark.rpc.netty.RequestMessage$.apply(NettyRpcEnv.scala:592)
> at org.apache.spark.rpc.netty.NettyRpcHandler.internalReceive(NettyRpcEnv.scala:651)
> at org.apache.spark.rpc.netty.NettyRpcHandler.receive(NettyRpcEnv.scala:636)
> at org.apache.spark.network.server.TransportRequestHandler.processRpcRequest(TransportRequestHandler.java:157)
> at org.apache.spark.network.server.TransportRequestHandler.handle(TransportRequestHandler.java:105)
> at org.apache.spark.network.server.TransportChannelHandler.channelRead(TransportChannelHandler.java:118)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
> at io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:287)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
> at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:102)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
> at org.apache.spark.network.util.TransportFrameDecoder.channelRead(TransportFrameDecoder.java:85)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:336)
> at io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1294)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:357)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:343)
> at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:911)
> at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:131)
> at io.netty.channel.nio.NioEventLoop.processSelectedkey(NioEventLoop.java:643) 
> at io.netty.channel.nio.NioEventLoop.processSelectedkeyOptimized(NioEventLoop.java:566)
> at io.netty.channel.nio.NioEventLoop.processSelectedkey(NioEventLoop.java:480)
> at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:442)
> at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:131)
> at io.netty.util.concurrent.DefaultThreadFactory$DefaultRunnableDecorator.run(DefaultThreadFactory.java:144)
> at java.lang.Thread.run(Thread.java:745)

> at org.apache.spark.network.client.TransportResponseHandler.handle(TransportResponseHandler.java:186)
> at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:106)
> at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:51)
> at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:356)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:342)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:335)
> at io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:286)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:356)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:342)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:335)
> at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:102)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:356)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:342)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:335)
> at org.apache.spark.network.util.TransportFrameDecoder.channelRead(TransportFrameDecoder.java:86)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:356)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:342)
> at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:335)
> at io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1302)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:356)
> at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:342)
> at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:919)
> at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:131)
> at io.netty.channel.nio.NioEventLoop.processSelectedkey(NioEventLoop.java:646)
> at io.netty.channel.nio.NioEventLoop.processSelectedkeyOptimized(NioEventLoop.java:581)
> at io.netty.channel.nio.NioEventLoop.processSelectedkey(NioEventLoop.java:498)
> at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:460)
> at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:131)
> at java.lang.Thread.run(Thread.java:745)

我的配置文件是 conf/janusgraph-hbase-es-test-spark.properties，其内容如下：

storage.backend=hbase
storage.hostname=192.168.63.105,192.168.63.107,192.168.63.109
storage.hbase.ext.hbase.zookeeper.property.clientPort=2181
storage.hbase.table=janus_test_spark_7077
gremlin.graph=org.janusgraph.core.JanusGraphFactory
cache.db-cache=true
cache.db-cache-clean-wait=20
cache.db-cache-time=18000
cache.db-cache-size=0.5
index.search.backend=elasticsearch
index.search.hostname=192.168.63.105,192.168.63.107,192.168.63.109
index.search.elasticsearch.client-only=true

我使用的 spark 版本是 spark-2.2.0-bin-hadoop2.7。

我也尝试了 spark-1.6.0-bin-hadoop2.6，警告信息如下：

WARN org.apache.spark.scheduler.TaskSetManager - Lost task 0.0 in stage 0.0 (TID 0, SparkWorker109): java.io.InvalidClassException: org.apache.spark.rdd.MapPartitionsRDD; local class incompatible: stream classdesc serialVersionUID=6732270565076291202, local class SerialVersionUID=-1059539896677275380

at java.io.ObjectStreamClass.initNonProxy(ObjectStreamClass.java:616)
at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1630)
at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1521)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1781)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2018)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1942)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1808)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:373)
at org.apache.spark.serializer:JavaDeserializationStream.readObject(JavaSerializer.scala:76)
at org.apache.spark.serializer:JavaSerializerInstance.deserialize(JavaSerializer.scala:115)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:64)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)

感谢您的关注和帮助。

4

1 回答 1

0

这是我的 hadoop-load.properties。

#
# SparkGraphComputer Configuration
#
spark.master=yarn-client
spark.executor.memory=512m
spark.serializer=org.apache.spark.serializer.KryoSerializer
spark.app.name=janusgraph-data-load
spark.app.id=janusgraph-data-load
spark.executor.extraClassPath=/opt/janusgraph-lib/*:/etc/hadoop/conf:/etc/hbase/conf:/etc/spark/conf
#hdp version
spark.yarn.am.extraJavaOptions=-Dhdp.version=2.6.1.0-129
spark.executor.extraJavaOptions=-Dhdp.version=2.6.1.0-129
spark.driver.extraJavaOptions=-Dhdp.version=2.6.1.0-129
于 2017-11-21T09:13:24.097 回答