You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@crunch.apache.org by "Ryan Blue (JIRA)" <ji...@apache.org> on 2015/04/23 00:17:59 UTC
[jira] [Updated] (CRUNCH-512) Distributed cache cannot find jar
files when using LocalJobRunner.
[ https://issues.apache.org/jira/browse/CRUNCH-512?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Ryan Blue updated CRUNCH-512:
-----------------------------
Description:
I have a Crunch-based task that uses the LocalJobRunner when it is copying data to or from HDFS. When HDFS is the default FS and I'm using LocalJobRunner, I get a FileNotFoundException in the distributed cache code with a strange looking URI:
{code}
1 job failure(s) occurred:
org.kitesdk.tools.CopyTask: Kite(dataset:file:/tmp/eb3b9643-1be3-400e-96d1-6e095fb3c5... ID=1 (1/1)(1): java.io.FileNotFoundException: File does not exist: hdfs://quickstart.cloudera:8020/usr/lib/hive/lib/antlr-runtime-3.4.jar
at org.apache.hadoop.hdfs.DistributedFileSystem$17.doCall(DistributedFileSystem.java:1093)
at org.apache.hadoop.hdfs.DistributedFileSystem$17.doCall(DistributedFileSystem.java:1085)
at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus(DistributedFileSystem.java:1085)
at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.getFileStatus(ClientDistributedCacheManager.java:288)
at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.getFileStatus(ClientDistributedCacheManager.java:224)
at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.determineTimestamps(ClientDistributedCacheManager.java:99)
at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.determineTimestampsAndCacheVisibilities(ClientDistributedCacheManager.java:57)
at org.apache.hadoop.mapreduce.JobSubmitter.copyAndConfigureFiles(JobSubmitter.java:267)
at org.apache.hadoop.mapreduce.JobSubmitter.copyAndConfigureFiles(JobSubmitter.java:388)
at org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:481)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1295)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1292)
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:1642)
at org.apache.hadoop.mapreduce.Job.submit(Job.java:1292)
at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchControlledJob.submit(CrunchControlledJob.java:329)
at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchJobControl.startReadyJobs(CrunchJobControl.java:204)
at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchJobControl.pollJobStatusAndStartNewOnes(CrunchJobControl.java:238)
at org.apache.crunch.impl.mr.exec.MRExecutor.monitorLoop(MRExecutor.java:112)
at org.apache.crunch.impl.mr.exec.MRExecutor.access$000(MRExecutor.java:55)
at org.apache.crunch.impl.mr.exec.MRExecutor$1.run(MRExecutor.java:83)
at java.lang.Thread.run(Thread.java:745)
{code}
It looks similar to HDFS-7031, where file:/ paths were getting incorrectly qualified using HDFS information.
was:
I have a Crunch-based task that uses the LocalJobRunner when it is copying data to or from HDFS. When HDFS is the default FS and I'm using LocalJobRunner, I get a FileNotFoundException in the distributed cache code with a strange looking URI:
{code}
1 job failure(s) occurred:
org.kitesdk.tools.CopyTask: Kite(dataset:file:/tmp/eb3b9643-1be3-400e-96d1-6e095fb3c5... ID=1 (1/1)(1): java.io.FileNotFoundException: File does not exist: hdfs://quickstart.cloudera:8020/usr/lib/hive/lib/antlr-ru
ntime-3.4.jar
at org.apache.hadoop.hdfs.DistributedFileSystem$17.doCall(DistributedFileSystem.java:1093)
at org.apache.hadoop.hdfs.DistributedFileSystem$17.doCall(DistributedFileSystem.java:1085)
at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus(DistributedFileSystem.java:1085)
at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.getFileStatus(ClientDistributedCacheManager.java:288)
at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.getFileStatus(ClientDistributedCacheManager.java:224)
at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.determineTimestamps(ClientDistributedCacheManager.java:99)
at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.determineTimestampsAndCacheVisibilities(ClientDistributedCacheManager.java:57)
at org.apache.hadoop.mapreduce.JobSubmitter.copyAndConfigureFiles(JobSubmitter.java:267)
at org.apache.hadoop.mapreduce.JobSubmitter.copyAndConfigureFiles(JobSubmitter.java:388)
at org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:481)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1295)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1292)
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:1642)
at org.apache.hadoop.mapreduce.Job.submit(Job.java:1292)
at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchControlledJob.submit(CrunchControlledJob.java:329)
at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchJobControl.startReadyJobs(CrunchJobControl.java:204)
at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchJobControl.pollJobStatusAndStartNewOnes(CrunchJobControl.java:238)
at org.apache.crunch.impl.mr.exec.MRExecutor.monitorLoop(MRExecutor.java:112)
at org.apache.crunch.impl.mr.exec.MRExecutor.access$000(MRExecutor.java:55)
at org.apache.crunch.impl.mr.exec.MRExecutor$1.run(MRExecutor.java:83)
at java.lang.Thread.run(Thread.java:745)
{code}
It looks similar to HDFS-7031, where file:/ paths were getting incorrectly qualified using HDFS information.
> Distributed cache cannot find jar files when using LocalJobRunner.
> ------------------------------------------------------------------
>
> Key: CRUNCH-512
> URL: https://issues.apache.org/jira/browse/CRUNCH-512
> Project: Crunch
> Issue Type: Bug
> Components: Core
> Affects Versions: 0.11.0
> Reporter: Ryan Blue
> Assignee: Josh Wills
>
> I have a Crunch-based task that uses the LocalJobRunner when it is copying data to or from HDFS. When HDFS is the default FS and I'm using LocalJobRunner, I get a FileNotFoundException in the distributed cache code with a strange looking URI:
> {code}
> 1 job failure(s) occurred:
> org.kitesdk.tools.CopyTask: Kite(dataset:file:/tmp/eb3b9643-1be3-400e-96d1-6e095fb3c5... ID=1 (1/1)(1): java.io.FileNotFoundException: File does not exist: hdfs://quickstart.cloudera:8020/usr/lib/hive/lib/antlr-runtime-3.4.jar
> at org.apache.hadoop.hdfs.DistributedFileSystem$17.doCall(DistributedFileSystem.java:1093)
> at org.apache.hadoop.hdfs.DistributedFileSystem$17.doCall(DistributedFileSystem.java:1085)
> at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
> at org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus(DistributedFileSystem.java:1085)
> at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.getFileStatus(ClientDistributedCacheManager.java:288)
> at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.getFileStatus(ClientDistributedCacheManager.java:224)
> at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.determineTimestamps(ClientDistributedCacheManager.java:99)
> at org.apache.hadoop.mapreduce.filecache.ClientDistributedCacheManager.determineTimestampsAndCacheVisibilities(ClientDistributedCacheManager.java:57)
> at org.apache.hadoop.mapreduce.JobSubmitter.copyAndConfigureFiles(JobSubmitter.java:267)
> at org.apache.hadoop.mapreduce.JobSubmitter.copyAndConfigureFiles(JobSubmitter.java:388)
> at org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:481)
> at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1295)
> at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1292)
> 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:1642)
> at org.apache.hadoop.mapreduce.Job.submit(Job.java:1292)
> at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchControlledJob.submit(CrunchControlledJob.java:329)
> at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchJobControl.startReadyJobs(CrunchJobControl.java:204)
> at org.apache.crunch.hadoop.mapreduce.lib.jobcontrol.CrunchJobControl.pollJobStatusAndStartNewOnes(CrunchJobControl.java:238)
> at org.apache.crunch.impl.mr.exec.MRExecutor.monitorLoop(MRExecutor.java:112)
> at org.apache.crunch.impl.mr.exec.MRExecutor.access$000(MRExecutor.java:55)
> at org.apache.crunch.impl.mr.exec.MRExecutor$1.run(MRExecutor.java:83)
> at java.lang.Thread.run(Thread.java:745)
> {code}
> It looks similar to HDFS-7031, where file:/ paths were getting incorrectly qualified using HDFS information.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)