Running test example failed
- Lenguaje dominante
- Java
- Estrellas
- 6.8k
- Forks
- 1.6k
- Merge medio
- 44 min
- PR fusionados (30 d)
- 1
Descripción
./angel-submit \
-Daction.type=train \
-Dangel.app.submit.class=com.tencent.angel.ml.lda.LDARunner \
-Dml.model.class.name=com.tencent.angel.ml.lda.LDAModel \
-Dangel.train.data.path="hdfs://10.1.3.15:8020//angel_data/data/abalone/abalone_8d_train.libsvm" \
-Dangel.log.path="hdfs://10.1.3.15:8020/angel_data/model" \
-Dangel.save.model.path="hdfs://10.1.3.15:8020/angel_data/model" \
-Dsave.doc.topic=true \
-Dsave.word.topic=true \
-Dml.epoch.num=10 \
-Dml.data.type=dummy \
-Dml.feature.index.range=1024 \
-Dangel.job.name=LDAtest \
-Dangel.am.memory.gb=2 \
-Dangel.worker.memory.gb=2 \
-Dangel.ps.memory.gb=4 \
-Dangel.staging.dir="hdfs://10.1.3.15:8020/angel_data/model" \
--queue queue01 \
-Dangel.output.path.deleteonexist=true
Log:
INFO yarn.AngelYarnClient: ApplicationSubmissionContext Queuename : queue02
19/09/16 17:49:21 INFO impl.YarnClientImpl: Submitted application application_1568606003884_0048
19/09/16 17:49:29 INFO yarn.AngelYarnClient: appMaster getTrackingUrl = http://slave1:8088/cluster/app/application_1568606003884_0048/
19/09/16 17:49:29 INFO yarn.AngelYarnClient: master host=10.1.3.16, port=26604
19/09/16 17:49:29 INFO yarn.AngelYarnClient: start to create rpc client to am
19/09/16 17:49:30 INFO client.AngelClient: clientId=1
19/09/16 17:50:45 ERROR yarn.AngelYarnClient: submit application to yarn failed.
com.google.protobuf.ServiceException: java.util.concurrent.ExecutionException: java.io.IOException: Error connecting to /10.1.3.16:26604
at com.tencent.angel.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:317)
at com.sun.proxy.$Proxy25.getAllPSLocation(Unknown Source)
at com.tencent.angel.client.AngelClient.waitForAllPS(AngelClient.java:1108)
at com.tencent.angel.client.yarn.AngelYarnClient.startPSServer(AngelYarnClient.java:172)
at com.tencent.angel.ml.lda.LDARunner.train(LDARunner.scala:107)
at com.tencent.angel.ml.core.MLRunner$class.submit(MLRunner.scala:45)
at com.tencent.angel.ml.lda.LDARunner.submit(LDARunner.scala:29)
at com.tencent.angel.utils.AngelRunJar$1.run(AngelRunJar.java:91)
at com.tencent.angel.utils.AngelRunJar$1.run(AngelRunJar.java:77)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1724)
at com.tencent.angel.utils.AngelRunJar.submit(AngelRunJar.java:77)
at com.tencent.angel.utils.AngelRunJar.main(AngelRunJar.java:44)
Caused by: java.util.concurrent.ExecutionException: java.io.IOException: Error connecting to /10.1.3.16:26604
at com.tencent.angel.ipc.CallFuture.get(CallFuture.java:121)
at com.tencent.angel.ipc.NettyTransceiver.call(NettyTransceiver.java:297)
at com.tencent.angel.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:294)
... 13 more
Caused by: java.io.IOException: Error connecting to /10.1.3.16:26604
at com.tencent.angel.ipc.NettyTransceiver.getChannel(NettyTransceiver.java:149)
at com.tencent.angel.ipc.NettyTransceiver.transceive(NettyTransceiver.java:338)
at com.tencent.angel.ipc.NettyTransceiver.call(NettyTransceiver.java:292)
... 14 more
Caused by: java.net.ConnectException: Connection refused: /10.1.3.16:26604
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)
at io.netty.channel.socket.nio.NioSocketChannel.doFinishConnect(NioSocketChannel.java:208)
at io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:287)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:528)
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)
19/09/16 17:50:45 ERROR utils.AngelRunJar: submit job failed
com.tencent.angel.exception.AngelException: com.google.protobuf.ServiceException: java.util.concurrent.ExecutionException: java.io.IOException: Error connecting to /10.1.3.16:26604
at com.tencent.angel.client.yarn.AngelYarnClient.startPSServer(AngelYarnClient.java:176)
at com.tencent.angel.ml.lda.LDARunner.train(LDARunner.scala:107)
at com.tencent.angel.ml.core.MLRunner$class.submit(MLRunner.scala:45)
at com.tencent.angel.ml.lda.LDARunner.submit(LDARunner.scala:29)
at com.tencent.angel.utils.AngelRunJar$1.run(AngelRunJar.java:91)
at com.tencent.angel.utils.AngelRunJar$1.run(AngelRunJar.java:77)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1724)
at com.tencent.angel.utils.AngelRunJar.submit(AngelRunJar.java:77)
at com.tencent.angel.utils.AngelRunJar.main(AngelRunJar.java:44)
Caused by: com.google.protobuf.ServiceException: java.util.concurrent.ExecutionException: java.io.IOException: Error connecting to /10.1.3.16:26604
at com.tencent.angel.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:317)
at com.sun.proxy.$Proxy25.getAllPSLocation(Unknown Source)
at com.tencent.angel.client.AngelClient.waitForAllPS(AngelClient.java:1108)
at com.tencent.angel.client.yarn.AngelYarnClient.startPSServer(AngelYarnClient.java:172)
... 10 more
Caused by: java.util.concurrent.ExecutionException: java.io.IOException: Error connecting to /10.1.3.16:26604
at com.tencent.angel.ipc.CallFuture.get(CallFuture.java:121)
at com.tencent.angel.ipc.NettyTransceiver.call(NettyTransceiver.java:297)
at com.tencent.angel.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:294)
... 13 more
Caused by: java.io.IOException: Error connecting to /10.1.3.16:26604
at com.tencent.angel.ipc.NettyTransceiver.getChannel(NettyTransceiver.java:149)
at com.tencent.angel.ipc.NettyTransceiver.transceive(NettyTransceiver.java:338)
at com.tencent.angel.ipc.NettyTransceiver.call(NettyTransceiver.java:292)
... 14 more
Caused by: java.net.ConnectException: Connection refused: /10.1.3.16:26604
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)
at io.netty.channel.socket.nio.NioSocketChannel.doFinishConnect(NioSocketChannel.java:208)
at io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:287)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:528)
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)
Guía de contribución
Evaluación
Este issue todavía no se ha evaluado.