我是pig新手，正在尝试在我们的5节点hadoop集群上运行以下pigscript。下面的脚本给出了一个关系中两列的交集
register '/home/workspace/Pig/setIntersecUdf.jar';
define Inter com.cs.pig.SetIntersection();
a = load '/home/pig/pig-0.12.0/input/location.txt' as (location:chararray);
b = load '/home/pig/pig-0.12.0/input/location.txt' as (location:chararray);
c = CROSS a,b parallel 10;
c = DISTINCT c;
d = Foreach c generate $0,$1,Inter($0,$1) as intersection;
e = Filter d by intersection !='[]' parallel 10;
e = Filter e by $0!=$1 parallel 10;
Store e into '/home/Documents/Pig_output';我有一个6MB的文件，其中包含像圣地亚哥ca或圣d ca的位置。我希望第三列是两者的交叉点，即[san，ca]。我有一个包含321372条记录的文件，必须将其与自身交叉，以获得两列，这样我就可以一次处理每个元组。
正如我所指出的，这个6MB的文件转换成大约1.9TB，因此，我的作业由于磁盘空间不足而失败。
我可以对此脚本进行哪些更改以使其高效运行？
下面是我得到的错误：
Java.io.IOException: org.apache.hadoop.ipc.RemoteException: java.io.IOException: File /tmp/temp-10926921/tmp-1823693600/_temporary/_attempt_201401171541_0001_r_000000_0/part-r-00000 could only be replicated to 0 nodes, instead of 1
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getAdditionalBlock(FSNamesystem.java:1639)
at org.apache.hadoop.hdfs.server.namenode.NameNode.addBlock(NameNode.java:736)
at sun.reflect.GeneratedMethodAccessor29.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
at java.lang.reflect.Method.invoke(Method.java:597)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:578)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:1393)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:1389)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:396)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1149)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:1387)
at org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigGenericMapReduce$Reduce.runPipeline(PigGenericMapReduce.java:469)
at org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigGenericMapReduce$Reduce.processOnePackageOutput(PigGenericMapReduce.java:432)
at org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigGenericMapReduce$Reduce.reduce(PigGenericMapReduce.java:404)
at org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigGenericMapReduce$Reduce.reduce(PigGenericMapReduce.java:256)
at org.apache.hadoop.mapreduce.Reducer.run(Reducer.java:176)
at org.apache.hadoop.mapred.ReduceTask.runNewReducer(ReduceTask.java:650)
at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:418)
at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:396)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1149)
at org.apache.hadoop.mapred.Child.main(Child.java:249) Caused by: org.apache.hadoop.ipc.RemoteException: java.io.IOException: File /tmp/temp-10926921/tmp-1823693600/_temporary/_attempt_201401171541_0001_r_000000_0/part-r-00000 could only be replicated to 0 nodes, instead of 1
at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getAdditionalBlock(FSNamesystem.java:1639)
at org.apache.hadoop.hdfs.server.namenode.NameNode.addBlock(NameNode.java:736)
at sun.reflect.GeneratedMethodAccessor29.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
at java.lang.reflect.Method.invoke(Method.java:597)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:578)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:1393)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:1389)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:396)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1149)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:1387)
at org.apache.hadoop.ipc.Client.call(Client.java:1107)
at org.apache.hadoop.ipc.RPC$Invoker.invoke(RPC.java:229)
at $Proxy2.addBlock(Unknown Source)
at sun.reflect.GeneratedMethodAccessor4.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
at java.lang.reflect.Method.invoke(Method.java:597)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:85)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:62)
at $Proxy2.addBlock(Unknown Source)
at org.apache.hadoop.hdfs.DFSClient$DFSOutputStream.locateFollowingBlock(DFSClient.java:3686)
at org.apache.hadoop.hdfs.DFSClient$DFSOutputStream.nextBlockOutputStream(DFSClient.java:3546)
at org.apache.hadoop.hdfs.DFSClient$DFSOutputStream.access$2600(DFSClient.java:2749)
at org.apache.hadoop.hdfs.DFSClient$DFSOutputStream$DataStreamer.run(DFSClient.java:2989)
2条答案
按热度按时间nzk0hqpo1#
首先是
DISTINCT之后CROSS不太可能做任何事。DISTINCT尊重顺序，所以它只会去掉完全相同的元组。只有在输入文件中有同一行的多个行时，才会出现这种情况。这个
e = Filter e by $0!=$1... 应该在找到线的交点之前完成。不管怎样，你都要把它们扔掉，所以你要尽快做到这一点。要解决这个问题，您需要限制
CROSS不知怎么的。我不知道您的数据是什么样子的，或者您希望输出什么，但是GROUP预先按状态Map数据应该减少元组的数量CROSS会让人大吃一惊。但是，对于以下情况，这不会返回交叉点：foo CA以及foo CT.nwwlzxa72#
交叉关系会导致数据量的大幅增加，甚至在数量级上也是如此。通常有一种更有效的解决方案，它依赖于数据本身。如果您可以从每个集合中添加一些记录，并解释所需的输出应该包含什么，社区将能够为您提供帮助。