[
https://issues.apache.org/jira/browse/HIVE-13325?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15205745#comment-15205745
]
Prasanth Jayachandran edited comment on HIVE-13325 at 3/22/16 4:04 AM:
-----------------------------------------------------------------------
[~gopalv]/[~sseth] Can someone please take a look? This patch avoids logging
the full stacktrace.
was (Author: prasanth_j):
[~gopalv]/[~sseth] Can someone please take a look?
> Excessive logging when ORC PPD fails type conversions
> -----------------------------------------------------
>
> Key: HIVE-13325
> URL: https://issues.apache.org/jira/browse/HIVE-13325
> Project: Hive
> Issue Type: Bug
> Components: Logging, ORC
> Affects Versions: 1.3.0, 2.1.0
> Reporter: Siddharth Seth
> Assignee: Prasanth Jayachandran
> Attachments: HIVE-13325.1.patch
>
>
> Timestamp was specified as "YYYY-MM-DD HH:MM:SS": 2016-01-23 00:00:00
> {code}
> 2016-02-10 02:15:43,175 [WARN] [TezChild] |orc.RecordReaderImpl|: Exception
> when evaluating predicate. Skipping ORC PPD. Exception:
> java.lang.IllegalArgumentException: ORC SARGS could not convert from String
> to TIMESTAMP
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.getBaseObjectForComparison(RecordReaderImpl.java:659)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.evaluatePredicateRange(RecordReaderImpl.java:373)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.evaluatePredicateProto(RecordReaderImpl.java:338)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl$SargApplier.pickRowGroups(RecordReaderImpl.java:710)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.pickRowGroups(RecordReaderImpl.java:751)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.readStripe(RecordReaderImpl.java:777)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.advanceStripe(RecordReaderImpl.java:986)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.advanceToNextRow(RecordReaderImpl.java:1019)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.<init>(RecordReaderImpl.java:205)
> at
> org.apache.hadoop.hive.ql.io.orc.ReaderImpl.rowsOptions(ReaderImpl.java:598)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcRawRecordMerger$ReaderPair.<init>(OrcRawRecordMerger.java:183)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcRawRecordMerger$OriginalReaderPair.<init>(OrcRawRecordMerger.java:226)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcRawRecordMerger.<init>(OrcRawRecordMerger.java:437)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getReader(OrcInputFormat.java:1269)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getRecordReader(OrcInputFormat.java:1151)
> at
> org.apache.hadoop.hive.ql.io.HiveInputFormat.getRecordReader(HiveInputFormat.java:249)
> at
> org.apache.hadoop.mapred.split.TezGroupedSplitsInputFormat$TezGroupedSplitsRecordReader.initNextRecordReader(TezGroupedSplitsInputFormat.java:193)
> at
> org.apache.hadoop.mapred.split.TezGroupedSplitsInputFormat$TezGroupedSplitsRecordReader.<init>(TezGroupedSplitsInputFormat.java:135)
> at
> org.apache.hadoop.mapred.split.TezGroupedSplitsInputFormat.getRecordReader(TezGroupedSplitsInputFormat.java:101)
> at
> org.apache.tez.mapreduce.lib.MRReaderMapred.setupOldRecordReader(MRReaderMapred.java:149)
> at
> org.apache.tez.mapreduce.lib.MRReaderMapred.setSplit(MRReaderMapred.java:80)
> at
> org.apache.tez.mapreduce.input.MRInput.initFromEventInternal(MRInput.java:650)
> at
> org.apache.tez.mapreduce.input.MRInput.initFromEvent(MRInput.java:621)
> at
> org.apache.tez.mapreduce.input.MRInputLegacy.checkAndAwaitRecordReaderInitialization(MRInputLegacy.java:145)
> at
> org.apache.tez.mapreduce.input.MRInputLegacy.init(MRInputLegacy.java:109)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordProcessor.getMRInput(MapRecordProcessor.java:406)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordProcessor.init(MapRecordProcessor.java:128)
> at
> org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:149)
> at
> org.apache.hadoop.hive.ql.exec.tez.TezProcessor.run(TezProcessor.java:139)
> at
> org.apache.tez.runtime.LogicalIOProcessorRuntimeTask.run(LogicalIOProcessorRuntimeTask.java:344)
> at
> org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable$1.run(TezTaskRunner.java:181)
> at
> org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable$1.run(TezTaskRunner.java:172)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:415)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
> at
> org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable.callInternal(TezTaskRunner.java:172)
> at
> org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable.callInternal(TezTaskRunner.java:168)
> at org.apache.tez.common.CallableWithNdc.call(CallableWithNdc.java:36)
> at java.util.concurrent.FutureTask.run(FutureTask.java:262)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> {code}
> Timestamp specified as unix_ts (seconds): 1453507200
> {code}
> 2016-02-10 02:20:06,588 [WARN] [TezChild] |orc.RecordReaderImpl|: Exception
> when evaluating predicate. Skipping ORC PPD. Exception:
> java.lang.IllegalArgumentException: ORC SARGS could not convert from Integer
> to TIMESTAMP
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.getBaseObjectForComparison(RecordReaderImpl.java:659)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.evaluatePredicateRange(RecordReaderImpl.java:373)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.evaluatePredicateProto(RecordReaderImpl.java:338)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl$SargApplier.pickRowGroups(RecordReaderImpl.java:710)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.pickRowGroups(RecordReaderImpl.java:751)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.readStripe(RecordReaderImpl.java:777)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.advanceStripe(RecordReaderImpl.java:986)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.advanceToNextRow(RecordReaderImpl.java:1019)
> at
> org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.<init>(RecordReaderImpl.java:205)
> at
> org.apache.hadoop.hive.ql.io.orc.ReaderImpl.rowsOptions(ReaderImpl.java:598)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcRawRecordMerger$ReaderPair.<init>(OrcRawRecordMerger.java:183)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcRawRecordMerger$OriginalReaderPair.<init>(OrcRawRecordMerger.java:226)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcRawRecordMerger.<init>(OrcRawRecordMerger.java:437)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getReader(OrcInputFormat.java:1269)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getRecordReader(OrcInputFormat.java:1151)
> at
> org.apache.hadoop.hive.ql.io.HiveInputFormat.getRecordReader(HiveInputFormat.java:249)
> at
> org.apache.hadoop.mapred.split.TezGroupedSplitsInputFormat$TezGroupedSplitsRecordReader.initNextRecordReader(TezGroupedSplitsInputFormat.java:193)
> at
> org.apache.hadoop.mapred.split.TezGroupedSplitsInputFormat$TezGroupedSplitsRecordReader.<init>(TezGroupedSplitsInputFormat.java:135)
> at
> org.apache.hadoop.mapred.split.TezGroupedSplitsInputFormat.getRecordReader(TezGroupedSplitsInputFormat.java:101)
> at
> org.apache.tez.mapreduce.lib.MRReaderMapred.setupOldRecordReader(MRReaderMapred.java:149)
> at
> org.apache.tez.mapreduce.lib.MRReaderMapred.setSplit(MRReaderMapred.java:80)
> at
> org.apache.tez.mapreduce.input.MRInput.initFromEventInternal(MRInput.java:650)
> at
> org.apache.tez.mapreduce.input.MRInput.initFromEvent(MRInput.java:621)
> at
> org.apache.tez.mapreduce.input.MRInputLegacy.checkAndAwaitRecordReaderInitialization(MRInputLegacy.java:145)
> at
> org.apache.tez.mapreduce.input.MRInputLegacy.init(MRInputLegacy.java:109)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordProcessor.getMRInput(MapRecordProcessor.java:406)
> at
> org.apache.hadoop.hive.ql.exec.tez.MapRecordProcessor.init(MapRecordProcessor.java:128)
> at
> org.apache.hadoop.hive.ql.exec.tez.TezProcessor.initializeAndRunProcessor(TezProcessor.java:149)
> at
> org.apache.hadoop.hive.ql.exec.tez.TezProcessor.run(TezProcessor.java:139)
> at
> org.apache.tez.runtime.LogicalIOProcessorRuntimeTask.run(LogicalIOProcessorRuntimeTask.java:344)
> at
> org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable$1.run(TezTaskRunner.java:181)
> at
> org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable$1.run(TezTaskRunner.java:172)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:415)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
> at
> org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable.callInternal(TezTaskRunner.java:172)
> at
> org.apache.tez.runtime.task.TezTaskRunner$TaskRunnerCallable.callInternal(TezTaskRunner.java:168)
> at org.apache.tez.common.CallableWithNdc.call(CallableWithNdc.java:36)
> at java.util.concurrent.FutureTask.run(FutureTask.java:262)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> {code}
> These messages are logged for each and every row group processed in tasks.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
