[
https://issues.apache.org/jira/browse/HIVE-16650?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Kenneth Jørgensen updated HIVE-16650:
-------------------------------------
Description:
While running a pig query we ran into the following error:
```
job_1494464639124_0002 clickIps,clickIpsGrouped,clicks GROUP_BY
Message: org.apache.pig.backend.executionengine.ExecException: ERROR 2118:
serious problem
at
org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigInputFormat.getSplits(PigInputFormat.java:288)
at
org.apache.hadoop.mapreduce.JobSubmitter.writeNewSplits(JobSubmitter.java:667)
at
org.apache.hadoop.mapreduce.JobSubmitter.writeSplits(JobSubmitter.java:691)
at
org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:526)
at org.apache.hadoop.mapreduce.Job$11.run(Job.java:1385)
at org.apache.hadoop.mapreduce.Job$11.run(Job.java:1382)
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:1635)
at org.apache.hadoop.mapreduce.Job.submit(Job.java:1382)
at
org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob.submit(ControlledJob.java:335)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.pig.backend.hadoop23.PigJobControl.submit(PigJobControl.java:128)
at
org.apache.pig.backend.hadoop23.PigJobControl.run(PigJobControl.java:191)
at java.lang.Thread.run(Thread.java:745)
at
org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher$1.run(MapReduceLauncher.java:257)
Caused by: java.lang.RuntimeException: serious problem
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat$Context.waitForTasks(OrcInputFormat.java:466)
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.generateSplitsInfo(OrcInputFormat.java:922)
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getSplits(OrcInputFormat.java:947)
at
org.apache.hive.hcatalog.mapreduce.HCatBaseInputFormat.getSplits(HCatBaseInputFormat.java:157)
at
org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigInputFormat.getSplits(PigInputFormat.java:274)
... 18 more
Caused by: java.lang.NumberFormatException: For input string:
"59027730032546908947033857045786"
at
java.lang.NumberFormatException.forInputString(NumberFormatException.java:65)
at java.lang.Integer.parseInt(Integer.java:495)
at java.lang.Integer.parseInt(Integer.java:527)
at
org.apache.hadoop.hive.ql.io.AcidUtils.parseBaseBucketFilename(AcidUtils.java:145)
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat$FileGenerator.run(OrcInputFormat.java:534)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
```
After some investigation we found this file in our S3 directory:
`59027730032546908947033857045786_000000`.
Slightly different version, but the error occurs here:
https://github.com/apache/hive/blob/release-1.2.0/ql/src/java/org/apache/hadoop/hive/ql/io/AcidUtils.java#L162
It would appear the regex `[0-9]+_[0-9]+` is detecting the first hash part of
the filename as all numbers and makes some assumption about it, causing the
whole thing to error out with a NumberFormatException.
was:
While running a pig query we ran into the following error:
```
job_1494464639124_0002 clickIps,clickIpsGrouped,clicks GROUP_BY
Message: org.apache.pig.backend.executionengine.ExecException: ERROR 2118:
serious problem
at
org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigInputFormat.getSplits(PigInputFormat.java:288)
at
org.apache.hadoop.mapreduce.JobSubmitter.writeNewSplits(JobSubmitter.java:667)
at
org.apache.hadoop.mapreduce.JobSubmitter.writeSplits(JobSubmitter.java:691)
at
org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:526)
at org.apache.hadoop.mapreduce.Job$11.run(Job.java:1385)
at org.apache.hadoop.mapreduce.Job$11.run(Job.java:1382)
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:1635)
at org.apache.hadoop.mapreduce.Job.submit(Job.java:1382)
at
org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob.submit(ControlledJob.java:335)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.pig.backend.hadoop23.PigJobControl.submit(PigJobControl.java:128)
at
org.apache.pig.backend.hadoop23.PigJobControl.run(PigJobControl.java:191)
at java.lang.Thread.run(Thread.java:745)
at
org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher$1.run(MapReduceLauncher.java:257)
Caused by: java.lang.RuntimeException: serious problem
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat$Context.waitForTasks(OrcInputFormat.java:466)
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.generateSplitsInfo(OrcInputFormat.java:922)
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getSplits(OrcInputFormat.java:947)
at
org.apache.hive.hcatalog.mapreduce.HCatBaseInputFormat.getSplits(HCatBaseInputFormat.java:157)
at
org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigInputFormat.getSplits(PigInputFormat.java:274)
... 18 more
Caused by: java.lang.NumberFormatException: For input string:
"59027730032546908947033857045786"
at
java.lang.NumberFormatException.forInputString(NumberFormatException.java:65)
at java.lang.Integer.parseInt(Integer.java:495)
at java.lang.Integer.parseInt(Integer.java:527)
at
org.apache.hadoop.hive.ql.io.AcidUtils.parseBaseBucketFilename(AcidUtils.java:145)
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat$FileGenerator.run(OrcInputFormat.java:534)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
```
After some investigation we found this file in our S3 directory:
`59027730032546908947033857045786_000000`.
Slightly different version, but the error occurs here:
https://github.com/apache/hive/blob/release-1.2.0/ql/src/java/org/apache/hadoop/hive/ql/io/AcidUtils.java#L162
It would appear the regex `[0-9]+_[0-9]+` i detecting the first hash part of
the filenames as all numbers and makes some assumption about it, causing the
whole thing to error out with a NumberFormatException.
> NumberFormatException in AcidUtils.parseBaseBucketFilename
> ----------------------------------------------------------
>
> Key: HIVE-16650
> URL: https://issues.apache.org/jira/browse/HIVE-16650
> Project: Hive
> Issue Type: Bug
> Components: ORC
> Affects Versions: 1.2.0
> Reporter: Kenneth Jørgensen
>
> While running a pig query we ran into the following error:
> ```
> job_1494464639124_0002 clickIps,clickIpsGrouped,clicks GROUP_BY
> Message: org.apache.pig.backend.executionengine.ExecException: ERROR 2118:
> serious problem
> at
> org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigInputFormat.getSplits(PigInputFormat.java:288)
> at
> org.apache.hadoop.mapreduce.JobSubmitter.writeNewSplits(JobSubmitter.java:667)
> at
> org.apache.hadoop.mapreduce.JobSubmitter.writeSplits(JobSubmitter.java:691)
> at
> org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:526)
> at org.apache.hadoop.mapreduce.Job$11.run(Job.java:1385)
> at org.apache.hadoop.mapreduce.Job$11.run(Job.java:1382)
> 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:1635)
> at org.apache.hadoop.mapreduce.Job.submit(Job.java:1382)
> at
> org.apache.hadoop.mapreduce.lib.jobcontrol.ControlledJob.submit(ControlledJob.java:335)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> org.apache.pig.backend.hadoop23.PigJobControl.submit(PigJobControl.java:128)
> at
> org.apache.pig.backend.hadoop23.PigJobControl.run(PigJobControl.java:191)
> at java.lang.Thread.run(Thread.java:745)
> at
> org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.MapReduceLauncher$1.run(MapReduceLauncher.java:257)
> Caused by: java.lang.RuntimeException: serious problem
> at
> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat$Context.waitForTasks(OrcInputFormat.java:466)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.generateSplitsInfo(OrcInputFormat.java:922)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getSplits(OrcInputFormat.java:947)
> at
> org.apache.hive.hcatalog.mapreduce.HCatBaseInputFormat.getSplits(HCatBaseInputFormat.java:157)
> at
> org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigInputFormat.getSplits(PigInputFormat.java:274)
> ... 18 more
> Caused by: java.lang.NumberFormatException: For input string:
> "59027730032546908947033857045786"
> at
> java.lang.NumberFormatException.forInputString(NumberFormatException.java:65)
> at java.lang.Integer.parseInt(Integer.java:495)
> at java.lang.Integer.parseInt(Integer.java:527)
> at
> org.apache.hadoop.hive.ql.io.AcidUtils.parseBaseBucketFilename(AcidUtils.java:145)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat$FileGenerator.run(OrcInputFormat.java:534)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> ```
> After some investigation we found this file in our S3 directory:
> `59027730032546908947033857045786_000000`.
> Slightly different version, but the error occurs here:
> https://github.com/apache/hive/blob/release-1.2.0/ql/src/java/org/apache/hadoop/hive/ql/io/AcidUtils.java#L162
> It would appear the regex `[0-9]+_[0-9]+` is detecting the first hash part of
> the filename as all numbers and makes some assumption about it, causing the
> whole thing to error out with a NumberFormatException.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
