Can you share the code, may be i/someone can help you out Thanks Best Regards
On Thu, May 21, 2015 at 1:45 PM, Allan Jie <allanmcgr...@gmail.com> wrote: > Hi, > > Just check the logs of datanode, it looks like this: > > 2015-05-20 11:42:14,605 INFO > org.apache.hadoop.hdfs.server.datanode.DataNode.clienttrace: src: / > 10.9.0.48:50676, dest: /10.9.0.17:50010, bytes: 134217728, op: > HDFS_WRITE, cliID: DFSClient_NONMAPREDUCE_804680172_54, offset: 0, srvID: > 39fb78d5-828a-4319-8303-c704fab526e3, blockid: > BP-436159032-10.9.0.16-1431330007172:blk_1073742096_1273, duration: > 16994466261 > 2015-05-20 11:42:14,606 INFO > org.apache.hadoop.hdfs.server.datanode.DataNode: PacketResponder: > BP-436159032-10.9.0.16-1431330007172:blk_1073742096_1273, > type=LAST_IN_PIPELINE, downstreams=0:[] terminating > 2015-05-20 11:42:17,788 INFO > org.apache.hadoop.hdfs.server.datanode.DataNode.clienttrace: src: / > 10.9.0.17:49046, dest: /10.9.0.17:50010, bytes: 134217728, op: > HDFS_WRITE, cliID: DFSClient_NONMAPREDUCE_102926009_54, offset: 0, srvID: > 39fb78d5-828a-4319-8303-c704fab526e3, blockid: > BP-436159032-10.9.0.16-1431330007172:blk_1073742099_1276, duration: > 17829554438 > 2015-05-20 11:42:17,788 INFO > org.apache.hadoop.hdfs.server.datanode.DataNode: PacketResponder: > BP-436159032-10.9.0.16-1431330007172:blk_1073742099_1276, > type=HAS_DOWNSTREAM_IN_PIPELINE terminating > 2015-05-20 11:42:17,904 INFO > org.apache.hadoop.hdfs.server.datanode.DataNode: Receiving > BP-436159032-10.9.0.16-1431330007172:blk_1073742103_1280 src: / > 10.9.0.17:49049 dest: /10.9.0.17:50010 > 2015-05-20 11:42:17,904 WARN > org.apache.hadoop.hdfs.server.datanode.DataNode: IOException in > BlockReceiver constructor. Cause is > 2015-05-20 11:42:17,904 INFO > org.apache.hadoop.hdfs.server.datanode.DataNode: opWriteBlock > BP-436159032-10.9.0.16-1431330007172:blk_1073742103_1280 received exception > org.apache.hadoop.util.DiskChecker$DiskOutOfSpaceException: Out of space: > The volume with the most available space (=114409472 B) is less than the > block size (=134217728 B). > 2015-05-20 11:42:17,905 ERROR > org.apache.hadoop.hdfs.server.datanode.DataNode: > HadoopV26Slave1:50010:DataXceiver error processing WRITE_BLOCK operation > src: /10.9.0.17:49049 dst: /10.9.0.17:50010 > org.apache.hadoop.util.DiskChecker$DiskOutOfSpaceException: Out of space: > The volume with the most available space (=114409472 B) is less than the > block size (=134217728 B). > at > org.apache.hadoop.hdfs.server.datanode.fsdataset.RoundRobinVolumeChoosingPolicy.chooseVolume(RoundRobinVolumeChoosingPolicy.java:67) > at > org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsVolumeList.getNextVolume(FsVolumeList.java:69) > at > org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetImpl.createRbw(FsDatasetImpl.java:1084) > at > org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetImpl.createRbw(FsDatasetImpl.java:114) > at > org.apache.hadoop.hdfs.server.datanode.BlockReceiver.<init>(BlockReceiver.java:183) > at > org.apache.hadoop.hdfs.server.datanode.DataXceiver.writeBlock(DataXceiver.java:615) > at > org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.opWriteBlock(Receiver.java:137) > at > org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.processOp(Receiver.java:74) > at > org.apache.hadoop.hdfs.server.datanode.DataXceiver.run(DataXceiver.java:235) > at java.lang.Thread.run(Thread.java:745) > 2015-05-20 11:43:59,669 INFO > org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceScanner: Verification > succeeded for BP-436159032-10.9.0.16-1431330007172:blk_1073741999_1176 > 2015-05-20 11:46:10,214 INFO > org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceScanner: Verification > succeeded for BP-436159032-10.9.0.16-1431330007172:blk_1073742000_1177 > 2015-05-20 11:48:35,445 INFO > org.apache.hadoop.hdfs.server.datanode.BlockPoolSliceScanner: Verification > succeeded for BP-436159032-10.9.0.16-1431330007172:blk_1073741990_1167 > 2015-05-20 11:50:04,043 INFO > org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetAsyncDiskService: > Scheduling blk_1073742080_1257 file > /tmp/hadoop-hduser/dfs/data/current/BP-436159032-10.9.0.16-1431330007172/current/finalized/subdir0/subdir1/blk_1073742080 > for deletion > 2015-05-20 11:50:04,136 INFO > org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetAsyncDiskService: > Scheduling blk_1073742081_1258 file > /tmp/hadoop-hduser/dfs/data/current/BP-436159032-10.9.0.16-1431330007172/current/finalized/subdir0/subdir1/blk_1073742081 > for deletion > 2015-05-20 11:50:04,136 INFO > org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetAsyncDiskService: > Scheduling blk_1073742082_1259 file > /tmp/hadoop-hduser/dfs/data/current/BP-436159032-10.9.0.16-1431330007172/current/finalized/subdir0/subdir1/blk_1073742082 > for deletion > 2015-05-20 11:50:04,136 INFO > org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetAsyncDiskService: > Scheduling blk_1073742083_1260 file > /tmp/hadoop-hduser/dfs/data/current/BP-436159032-10.9.0.16-1431330007172/current/finalized/subdir0/subdir1/blk_1073742083 > for deletion > 2015-05-20 11:50:04,136 INFO > org.apache.hadoop.hdfs.server.datanode.fsdataset.impl.FsDatasetAsyncDiskService: > Scheduling blk_1073742084_1261 file > /tmp/hadoop-hduser/dfs/data/current/BP-436159032-10.9.0.16-1431330007172/current/finalized/subdir0/subdir1/blk_1073742084 > for deletion > > > But why this is a hdfs issue, because I think spark broadcast the variable > in memory. > BTW, the datanode logs seems like I don't have any space to save the > storage. So the question comes back, originally I have 50GB for HDFS, why I > broadcast a variable and then that variable will dominate the whole hdfs? > > P.S. when I reduce the data size to only 10 lines (200kb), it works > without problem. > > Best Regards, > Allan > > On 21 May 2015 at 01:30, Akhil Das <ak...@sigmoidanalytics.com> wrote: > >> This is more like an issue with your HDFS setup, can you check in the >> datanode logs? Also try putting a new file in HDFS and see if that works. >> >> Thanks >> Best Regards >> >> On Wed, May 20, 2015 at 11:47 AM, allanjie <allanmcgr...@gmail.com> >> wrote: >> >>> Hi All, >>> The variable I need to broadcast is just 468 MB. >>> >>> >>> When broadcasting, it just “stop” at here: >>> >>> * >>> 15/05/20 11:36:14 INFO Configuration.deprecation: mapred.tip.id is >>> deprecated. Instead, use mapreduce.task.id >>> 15/05/20 11:36:14 INFO Configuration.deprecation: mapred.task.id is >>> deprecated. Instead, use mapreduce.task.attempt.id >>> 15/05/20 11:36:14 INFO Configuration.deprecation: mapred.task.is.map is >>> deprecated. Instead, use mapreduce.task.ismap >>> 15/05/20 11:36:14 INFO Configuration.deprecation: mapred.task.partition >>> is >>> deprecated. Instead, use mapreduce.task.partition >>> 15/05/20 11:36:14 INFO Configuration.deprecation: mapred.job.id is >>> deprecated. Instead, use mapreduce.job.id >>> 15/05/20 11:36:14 INFO mapred.FileInputFormat: Total input paths to >>> process >>> : 1 >>> 15/05/20 11:36:14 INFO spark.SparkContext: Starting job: saveAsTextFile >>> at >>> Test1.java:90 >>> 15/05/20 11:36:15 INFO scheduler.DAGScheduler: Got job 0 (saveAsTextFile >>> at >>> Test1.java:90) with 4 output partitions (allowLocal=false) >>> 15/05/20 11:36:15 INFO scheduler.DAGScheduler: Final stage: Stage >>> 0(saveAsTextFile at Test1.java:90) >>> 15/05/20 11:36:15 INFO scheduler.DAGScheduler: Parents of final stage: >>> List() >>> 15/05/20 11:36:15 INFO scheduler.DAGScheduler: Missing parents: List() >>> 15/05/20 11:36:15 INFO scheduler.DAGScheduler: Submitting Stage 0 >>> (MapPartitionsRDD[3] at saveAsTextFile at Test1.java:90), which has no >>> missing parents >>> 15/05/20 11:36:15 INFO storage.MemoryStore: ensureFreeSpace(129264) >>> called >>> with curMem=988453294, maxMem=2061647216 >>> 15/05/20 11:36:15 INFO storage.MemoryStore: Block broadcast_2 stored as >>> values in memory (estimated size 126.2 KB, free 1023.4 MB) >>> 15/05/20 11:36:15 INFO storage.MemoryStore: ensureFreeSpace(78190) called >>> with curMem=988582558, maxMem=2061647216 >>> 15/05/20 11:36:15 INFO storage.MemoryStore: Block broadcast_2_piece0 >>> stored >>> as bytes in memory (estimated size 76.4 KB, free 1023.3 MB) >>> 15/05/20 11:36:15 INFO storage.BlockManagerInfo: Added >>> broadcast_2_piece0 in >>> memory on HadoopV26Master:44855 (size: 76.4 KB, free: 1492.4 MB) >>> 15/05/20 11:36:15 INFO storage.BlockManagerMaster: Updated info of block >>> broadcast_2_piece0 >>> 15/05/20 11:36:15 INFO spark.SparkContext: Created broadcast 2 from >>> broadcast at DAGScheduler.scala:839 >>> 15/05/20 11:36:15 INFO scheduler.DAGScheduler: Submitting 4 missing tasks >>> from Stage 0 (MapPartitionsRDD[3] at saveAsTextFile at Test1.java:90) >>> 15/05/20 11:36:15 INFO scheduler.TaskSchedulerImpl: Adding task set 0.0 >>> with >>> 4 tasks >>> 15/05/20 11:36:15 INFO scheduler.TaskSetManager: Starting task 0.0 in >>> stage >>> 0.0 (TID 0, HadoopV26Slave5, NODE_LOCAL, 1387 bytes) >>> 15/05/20 11:36:15 INFO scheduler.TaskSetManager: Starting task 1.0 in >>> stage >>> 0.0 (TID 1, HadoopV26Slave3, NODE_LOCAL, 1387 bytes) >>> 15/05/20 11:36:15 INFO scheduler.TaskSetManager: Starting task 2.0 in >>> stage >>> 0.0 (TID 2, HadoopV26Slave4, NODE_LOCAL, 1387 bytes) >>> 15/05/20 11:36:15 INFO scheduler.TaskSetManager: Starting task 3.0 in >>> stage >>> 0.0 (TID 3, HadoopV26Slave1, NODE_LOCAL, 1387 bytes) >>> 15/05/20 11:36:15 INFO storage.BlockManagerInfo: Added >>> broadcast_2_piece0 in >>> memory on HadoopV26Slave5:45357 (size: 76.4 KB, free: 2.1 GB) >>> 15/05/20 11:36:15 INFO storage.BlockManagerInfo: Added >>> broadcast_2_piece0 in >>> memory on HadoopV26Slave3:57821 (size: 76.4 KB, free: 2.1 GB) >>> ……. >>> 15/05/20 11:36:28 INFO storage.BlockManagerInfo: Added >>> broadcast_1_piece1 in >>> memory on HadoopV26Slave5:45357 (size: 4.0 MB, free: 1646.3 MB) >>> * >>> >>> And didn’t go forward as I still waiting, basically not stop, but more >>> like >>> stuck. >>> >>> I have 6 workers/VMs: each of them has 8GB memory and 12GB disk storage. >>> After a few mins pass, the program stopped and showed something like >>> this: >>> >>> >>> 15/05/20 11:42:45 WARN scheduler.TaskSetManager: Lost task 1.0 in stage >>> 0.0 >>> (TID 1, HadoopV26Slave3): >>> org.apache.hadoop.ipc.RemoteException(java.io.IOException): File >>> >>> /user/output/_temporary/0/_temporary/attempt_201505201136_0000_m_000001_1/part-00001 >>> could only be replicated to 0 nodes instead of minReplication (=1). >>> There >>> are 6 datanode(s) running and no node(s) are excluded in this operation. >>> at >>> >>> org.apache.hadoop.hdfs.server.blockmanagement.BlockManager.chooseTarget4NewBlock(BlockManager.java:1549) >>> at >>> >>> org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getAdditionalBlock(FSNamesystem.java:3200) >>> at >>> >>> org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.addBlock(NameNodeRpcServer.java:641) >>> at >>> >>> org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.addBlock(ClientNamenodeProtocolServerSideTranslatorPB.java:482) >>> at >>> >>> org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java) >>> at >>> >>> org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:619) >>> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:962) >>> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2039) >>> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2035) >>> at java.security.AccessController.doPrivileged(Native Method) >>> at javax.security.auth.Subject.doAs(Subject.java:415) >>> at >>> >>> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1628) >>> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2033) >>> >>> at org.apache.hadoop.ipc.Client.call(Client.java:1468) >>> at org.apache.hadoop.ipc.Client.call(Client.java:1399) >>> at >>> >>> org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:232) >>> at com.sun.proxy.$Proxy13.addBlock(Unknown Source) >>> at >>> >>> org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.addBlock(ClientNamenodeProtocolTranslatorPB.java:399) >>> at sun.reflect.GeneratedMethodAccessor7.invoke(Unknown Source) >>> at >>> >>> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) >>> at java.lang.reflect.Method.invoke(Method.java:606) >>> at >>> >>> org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:187) >>> at >>> >>> org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102) >>> at com.sun.proxy.$Proxy14.addBlock(Unknown Source) >>> at >>> >>> org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.locateFollowingBlock(DFSOutputStream.java:1532) >>> at >>> >>> org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.nextBlockOutputStream(DFSOutputStream.java:1349) >>> at >>> >>> org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.run(DFSOutputStream.java:588) >>> >>> And then I check the volume of each slave, seems that almost all the >>> storage >>> has been dominated. But the variable I broadcast is just 468MB. >>> >>> Originally it is saved in HDFS. And In java program I read it from hdfs >>> and >>> then broadcast that variable. >>> >>> Anyone can help? Really thanks. >>> >>> >>> >>> -- >>> View this message in context: >>> http://apache-spark-user-list.1001560.n3.nabble.com/java-program-Get-Stuck-at-broadcasting-tp22953.html >>> Sent from the Apache Spark User List mailing list archive at Nabble.com. >>> >>> --------------------------------------------------------------------- >>> To unsubscribe, e-mail: user-unsubscr...@spark.apache.org >>> For additional commands, e-mail: user-h...@spark.apache.org >>> >>> >> > > > -- > PhD student, > Social Media Laboratory <http://smedia.ust.hk/>, > Department of Electronic & Computer Engineering > <http://www.ece.ust.hk/ece.php>, > The Hong Kong University of Science and Technology <http://www.ust.hk/>. > Website: http://www.allanjie.net >
