[
https://issues.apache.org/jira/browse/HIVE-11268?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Soundararajan Velu updated HIVE-11268:
--------------------------------------
Description:
Getting the below exception using, ORC table format, the table has 250 files
with one file size 14gb and rest 11mb,
table properties, TBLPROPERTIES (
'COLUMN_STATS_ACCURATE'='false',
'numFiles'='250',
'numRows'='-1',
'orc.compress'='SNAPPY',
'orc.compress.size'='262144',
'orc.create.index'='true',
'orc.row.index.stride'='10000',
'orc.stripe.size'='67108864',
'rawDataSize'='-1',
'totalSize'='16950715052',
'transient_lastDdlTime'='1436932029')
Even a select * limit 1; on the table gives this exception, when I delete the
14gb file, the issues are gone,
Stack Trace,
2015-07-15 21:28:29,435 ERROR [main]: CliDriver
(SessionState.java:printError(979)) - Failed with exception
java.io.IOException:com.google.protobuf.InvalidProtocolBufferException:
Protocol message was too large. May be malicious. Use
CodedInputStream.setSizeLimit() to increase the size limit.
java.io.IOException: com.google.protobuf.InvalidProtocolBufferException:
Protocol message was too large. May be malicious. Use
CodedInputStream.setSizeLimit() to increase the size limit.
at
org.apache.hadoop.hive.ql.exec.FetchOperator.getNextRow(FetchOperator.java:507)
at
org.apache.hadoop.hive.ql.exec.FetchOperator.pushRow(FetchOperator.java:414)
at org.apache.hadoop.hive.ql.exec.FetchTask.fetch(FetchTask.java:140)
at org.apache.hadoop.hive.ql.Driver.getResults(Driver.java:1674)
at
org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:233)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:165)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at
org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:736)
at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:681)
at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:621)
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.hadoop.util.RunJar.run(RunJar.java:221)
at org.apache.hadoop.util.RunJar.main(RunJar.java:136)
Caused by: com.google.protobuf.InvalidProtocolBufferException: Protocol message
was too large. May be malicious. Use CodedInputStream.setSizeLimit() to
increase the size limit.
at
com.google.protobuf.InvalidProtocolBufferException.sizeLimitExceeded(InvalidProtocolBufferException.java:110)
at
com.google.protobuf.CodedInputStream.refillBuffer(CodedInputStream.java:755)
at
com.google.protobuf.CodedInputStream.readRawByte(CodedInputStream.java:769)
at
com.google.protobuf.CodedInputStream.readRawLittleEndian64(CodedInputStream.java:493)
at
com.google.protobuf.CodedInputStream.readDouble(CodedInputStream.java:178)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics.<init>(OrcProto.java:755)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics.<init>(OrcProto.java:705)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics$1.parsePartialFrom(OrcProto.java:798)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics$1.parsePartialFrom(OrcProto.java:793)
at
com.google.protobuf.CodedInputStream.readMessage(CodedInputStream.java:309)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics.<init>(OrcProto.java:4884)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics.<init>(OrcProto.java:4813)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics$1.parsePartialFrom(OrcProto.java:5005)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics$1.parsePartialFrom(OrcProto.java:5000)
at
com.google.protobuf.CodedInputStream.readMessage(CodedInputStream.java:309)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics.<init>(OrcProto.java:14334)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics.<init>(OrcProto.java:14281)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics$1.parsePartialFrom(OrcProto.java:14370)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics$1.parsePartialFrom(OrcProto.java:14365)
at
com.google.protobuf.CodedInputStream.readMessage(CodedInputStream.java:309)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata.<init>(OrcProto.java:15008)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata.<init>(OrcProto.java:14955)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata$1.parsePartialFrom(OrcProto.java:15044)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata$1.parsePartialFrom(OrcProto.java:15039)
at
com.google.protobuf.AbstractParser.parsePartialFrom(AbstractParser.java:200)
at com.google.protobuf.AbstractParser.parseFrom(AbstractParser.java:217)
at com.google.protobuf.AbstractParser.parseFrom(AbstractParser.java:223)
at com.google.protobuf.AbstractParser.parseFrom(AbstractParser.java:49)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata.parseFrom(OrcProto.java:15155)
at
org.apache.hadoop.hive.ql.io.orc.ReaderImpl$MetaInfoObjExtractor.<init>(ReaderImpl.java:471)
at
org.apache.hadoop.hive.ql.io.orc.ReaderImpl.<init>(ReaderImpl.java:317)
at
org.apache.hadoop.hive.ql.io.orc.OrcFile.createReader(OrcFile.java:237)
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getReader(OrcInputFormat.java:1220)
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getRecordReader(OrcInputFormat.java:1129)
at
org.apache.hadoop.hive.ql.exec.FetchOperator$FetchInputFormatSplit.getRecordReader(FetchOperator.java:673)
at
org.apache.hadoop.hive.ql.exec.FetchOperator.getRecordReader(FetchOperator.java:323)
at
org.apache.hadoop.hive.ql.exec.FetchOperator.getNextRow(FetchOperator.java:445)
... 15 more
was:
Getting the below exception using, ORC table format, the table has 250 files
with 1 file size 14gb and rest 11mb, table properties, TBLPROPERTIES (
'COLUMN_STATS_ACCURATE'='false',
'numFiles'='250',
'numRows'='-1',
'orc.compress'='SNAPPY',
'orc.compress.size'='262144',
'orc.create.index'='true',
'orc.row.index.stride'='10000',
'orc.stripe.size'='67108864',
'rawDataSize'='-1',
'totalSize'='16950715052',
'transient_lastDdlTime'='1436932029')
Stack Trace,
2015-07-15 21:28:29,435 ERROR [main]: CliDriver
(SessionState.java:printError(979)) - Failed with exception
java.io.IOException:com.google.protobuf.InvalidProtocolBufferException:
Protocol message was too large. May be malicious. Use
CodedInputStream.setSizeLimit() to increase the size limit.
java.io.IOException: com.google.protobuf.InvalidProtocolBufferException:
Protocol message was too large. May be malicious. Use
CodedInputStream.setSizeLimit() to increase the size limit.
at
org.apache.hadoop.hive.ql.exec.FetchOperator.getNextRow(FetchOperator.java:507)
at
org.apache.hadoop.hive.ql.exec.FetchOperator.pushRow(FetchOperator.java:414)
at org.apache.hadoop.hive.ql.exec.FetchTask.fetch(FetchTask.java:140)
at org.apache.hadoop.hive.ql.Driver.getResults(Driver.java:1674)
at
org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:233)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:165)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at
org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:736)
at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:681)
at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:621)
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.hadoop.util.RunJar.run(RunJar.java:221)
at org.apache.hadoop.util.RunJar.main(RunJar.java:136)
Caused by: com.google.protobuf.InvalidProtocolBufferException: Protocol message
was too large. May be malicious. Use CodedInputStream.setSizeLimit() to
increase the size limit.
at
com.google.protobuf.InvalidProtocolBufferException.sizeLimitExceeded(InvalidProtocolBufferException.java:110)
at
com.google.protobuf.CodedInputStream.refillBuffer(CodedInputStream.java:755)
at
com.google.protobuf.CodedInputStream.readRawByte(CodedInputStream.java:769)
at
com.google.protobuf.CodedInputStream.readRawLittleEndian64(CodedInputStream.java:493)
at
com.google.protobuf.CodedInputStream.readDouble(CodedInputStream.java:178)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics.<init>(OrcProto.java:755)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics.<init>(OrcProto.java:705)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics$1.parsePartialFrom(OrcProto.java:798)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics$1.parsePartialFrom(OrcProto.java:793)
at
com.google.protobuf.CodedInputStream.readMessage(CodedInputStream.java:309)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics.<init>(OrcProto.java:4884)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics.<init>(OrcProto.java:4813)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics$1.parsePartialFrom(OrcProto.java:5005)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics$1.parsePartialFrom(OrcProto.java:5000)
at
com.google.protobuf.CodedInputStream.readMessage(CodedInputStream.java:309)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics.<init>(OrcProto.java:14334)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics.<init>(OrcProto.java:14281)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics$1.parsePartialFrom(OrcProto.java:14370)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics$1.parsePartialFrom(OrcProto.java:14365)
at
com.google.protobuf.CodedInputStream.readMessage(CodedInputStream.java:309)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata.<init>(OrcProto.java:15008)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata.<init>(OrcProto.java:14955)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata$1.parsePartialFrom(OrcProto.java:15044)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata$1.parsePartialFrom(OrcProto.java:15039)
at
com.google.protobuf.AbstractParser.parsePartialFrom(AbstractParser.java:200)
at com.google.protobuf.AbstractParser.parseFrom(AbstractParser.java:217)
at com.google.protobuf.AbstractParser.parseFrom(AbstractParser.java:223)
at com.google.protobuf.AbstractParser.parseFrom(AbstractParser.java:49)
at
org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata.parseFrom(OrcProto.java:15155)
at
org.apache.hadoop.hive.ql.io.orc.ReaderImpl$MetaInfoObjExtractor.<init>(ReaderImpl.java:471)
at
org.apache.hadoop.hive.ql.io.orc.ReaderImpl.<init>(ReaderImpl.java:317)
at
org.apache.hadoop.hive.ql.io.orc.OrcFile.createReader(OrcFile.java:237)
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getReader(OrcInputFormat.java:1220)
at
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getRecordReader(OrcInputFormat.java:1129)
at
org.apache.hadoop.hive.ql.exec.FetchOperator$FetchInputFormatSplit.getRecordReader(FetchOperator.java:673)
at
org.apache.hadoop.hive.ql.exec.FetchOperator.getRecordReader(FetchOperator.java:323)
at
org.apache.hadoop.hive.ql.exec.FetchOperator.getNextRow(FetchOperator.java:445)
... 15 more
> java.io.IOException: com.google.protobuf.InvalidProtocolBufferException:
> Protocol message was too large. May be malicious. Use
> CodedInputStream.setSizeLimit() to increase the size limit.
> --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
>
> Key: HIVE-11268
> URL: https://issues.apache.org/jira/browse/HIVE-11268
> Project: Hive
> Issue Type: Bug
> Components: Hive
> Affects Versions: 1.2.0
> Environment: Hive 1.2
> Reporter: Soundararajan Velu
> Priority: Critical
>
> Getting the below exception using, ORC table format, the table has 250 files
> with one file size 14gb and rest 11mb,
> table properties, TBLPROPERTIES (
> 'COLUMN_STATS_ACCURATE'='false',
> 'numFiles'='250',
> 'numRows'='-1',
> 'orc.compress'='SNAPPY',
> 'orc.compress.size'='262144',
> 'orc.create.index'='true',
> 'orc.row.index.stride'='10000',
> 'orc.stripe.size'='67108864',
> 'rawDataSize'='-1',
> 'totalSize'='16950715052',
> 'transient_lastDdlTime'='1436932029')
> Even a select * limit 1; on the table gives this exception, when I delete the
> 14gb file, the issues are gone,
> Stack Trace,
> 2015-07-15 21:28:29,435 ERROR [main]: CliDriver
> (SessionState.java:printError(979)) - Failed with exception
> java.io.IOException:com.google.protobuf.InvalidProtocolBufferException:
> Protocol message was too large. May be malicious. Use
> CodedInputStream.setSizeLimit() to increase the size limit.
> java.io.IOException: com.google.protobuf.InvalidProtocolBufferException:
> Protocol message was too large. May be malicious. Use
> CodedInputStream.setSizeLimit() to increase the size limit.
> at
> org.apache.hadoop.hive.ql.exec.FetchOperator.getNextRow(FetchOperator.java:507)
> at
> org.apache.hadoop.hive.ql.exec.FetchOperator.pushRow(FetchOperator.java:414)
> at org.apache.hadoop.hive.ql.exec.FetchTask.fetch(FetchTask.java:140)
> at org.apache.hadoop.hive.ql.Driver.getResults(Driver.java:1674)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:233)
> at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:165)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
> at
> org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:736)
> at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:681)
> at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:621)
> 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.hadoop.util.RunJar.run(RunJar.java:221)
> at org.apache.hadoop.util.RunJar.main(RunJar.java:136)
> Caused by: com.google.protobuf.InvalidProtocolBufferException: Protocol
> message was too large. May be malicious. Use
> CodedInputStream.setSizeLimit() to increase the size limit.
> at
> com.google.protobuf.InvalidProtocolBufferException.sizeLimitExceeded(InvalidProtocolBufferException.java:110)
> at
> com.google.protobuf.CodedInputStream.refillBuffer(CodedInputStream.java:755)
> at
> com.google.protobuf.CodedInputStream.readRawByte(CodedInputStream.java:769)
> at
> com.google.protobuf.CodedInputStream.readRawLittleEndian64(CodedInputStream.java:493)
> at
> com.google.protobuf.CodedInputStream.readDouble(CodedInputStream.java:178)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics.<init>(OrcProto.java:755)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics.<init>(OrcProto.java:705)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics$1.parsePartialFrom(OrcProto.java:798)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$DoubleStatistics$1.parsePartialFrom(OrcProto.java:793)
> at
> com.google.protobuf.CodedInputStream.readMessage(CodedInputStream.java:309)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics.<init>(OrcProto.java:4884)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics.<init>(OrcProto.java:4813)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics$1.parsePartialFrom(OrcProto.java:5005)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$ColumnStatistics$1.parsePartialFrom(OrcProto.java:5000)
> at
> com.google.protobuf.CodedInputStream.readMessage(CodedInputStream.java:309)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics.<init>(OrcProto.java:14334)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics.<init>(OrcProto.java:14281)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics$1.parsePartialFrom(OrcProto.java:14370)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$StripeStatistics$1.parsePartialFrom(OrcProto.java:14365)
> at
> com.google.protobuf.CodedInputStream.readMessage(CodedInputStream.java:309)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata.<init>(OrcProto.java:15008)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata.<init>(OrcProto.java:14955)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata$1.parsePartialFrom(OrcProto.java:15044)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata$1.parsePartialFrom(OrcProto.java:15039)
> at
> com.google.protobuf.AbstractParser.parsePartialFrom(AbstractParser.java:200)
> at
> com.google.protobuf.AbstractParser.parseFrom(AbstractParser.java:217)
> at
> com.google.protobuf.AbstractParser.parseFrom(AbstractParser.java:223)
> at
> com.google.protobuf.AbstractParser.parseFrom(AbstractParser.java:49)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcProto$Metadata.parseFrom(OrcProto.java:15155)
> at
> org.apache.hadoop.hive.ql.io.orc.ReaderImpl$MetaInfoObjExtractor.<init>(ReaderImpl.java:471)
> at
> org.apache.hadoop.hive.ql.io.orc.ReaderImpl.<init>(ReaderImpl.java:317)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcFile.createReader(OrcFile.java:237)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getReader(OrcInputFormat.java:1220)
> at
> org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getRecordReader(OrcInputFormat.java:1129)
> at
> org.apache.hadoop.hive.ql.exec.FetchOperator$FetchInputFormatSplit.getRecordReader(FetchOperator.java:673)
> at
> org.apache.hadoop.hive.ql.exec.FetchOperator.getRecordReader(FetchOperator.java:323)
> at
> org.apache.hadoop.hive.ql.exec.FetchOperator.getNextRow(FetchOperator.java:445)
> ... 15 more
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
