[
https://issues.apache.org/jira/browse/DRILL-3871?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14981104#comment-14981104
]
ASF GitHub Bot commented on DRILL-3871:
---------------------------------------
Github user adeneche commented on a diff in the pull request:
https://github.com/apache/drill/pull/219#discussion_r43432757
--- Diff:
exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/columnreaders/NullableColumnReader.java
---
@@ -29,117 +29,152 @@
import parquet.hadoop.metadata.ColumnChunkMetaData;
abstract class NullableColumnReader<V extends ValueVector> extends
ColumnReader<V>{
-
- int nullsFound;
- // used to skip nulls found
- int rightBitShift;
- // used when copying less than a byte worth of data at a time, to
indicate the number of used bits in the current byte
- int bitsUsed;
- BaseDataValueVector castedBaseVector;
- NullableVectorDefinitionSetter castedVectorMutator;
- long definitionLevelsRead;
- long totalDefinitionLevelsRead;
+ private static final org.slf4j.Logger logger =
org.slf4j.LoggerFactory.getLogger(NullableColumnReader.class);
+ protected BaseDataValueVector castedBaseVector;
+ protected NullableVectorDefinitionSetter castedVectorMutator;
+ private long definitionLevelsRead = 0;
NullableColumnReader(ParquetRecordReader parentReader, int allocateSize,
ColumnDescriptor descriptor, ColumnChunkMetaData columnChunkMetaData,
boolean fixedLength, V v, SchemaElement schemaElement)
throws ExecutionSetupException {
super(parentReader, allocateSize, descriptor, columnChunkMetaData,
fixedLength, v, schemaElement);
castedBaseVector = (BaseDataValueVector) v;
castedVectorMutator = (NullableVectorDefinitionSetter) v.getMutator();
- totalDefinitionLevelsRead = 0;
}
-
- @Override
- public void processPages(long recordsToReadInThisPass) throws
IOException {
- int indexInOutputVector = 0;
+ @Override public void processPages(long recordsToReadInThisPass)
+ throws IOException {
readStartInBytes = 0;
readLength = 0;
readLengthInBits = 0;
recordsReadInThisIteration = 0;
vectorData = castedBaseVector.getBuffer();
- // values need to be spaced out where nulls appear in the column
- // leaving blank space for nulls allows for random access to values
- // to optimize copying data out of the buffered disk stream, runs of
defined values
- // are located and copied together, rather than copying individual
values
-
- long runStart = pageReader.readPosInBytes;
- int runLength;
- int currentDefinitionLevel;
- boolean lastValueWasNull;
- boolean lastRunBrokenByNull = false;
- while (indexInOutputVector < recordsToReadInThisPass &&
indexInOutputVector < valueVec.getValueCapacity()){
- // read a page if needed
+ // values need to be spaced out where nulls appear in the column
+ // leaving blank space for nulls allows for random access to values
+ // to optimize copying data out of the buffered disk stream, runs of
defined values
+ // are located and copied together, rather than copying individual
values
+
+ int runLength = -1; // number of non-null records in this pass.
+ int nullRunLength = -1; // number of consecutive null records that we
read.
+ int currentDefinitionLevel = -1;
+ int readCount = 0; // the record number we last read.
+ int writeCount = 0; // the record number we last wrote to the value
vector.
+ // This was previously the indexInOutputVector
variable
+ boolean haveMoreData; // true if we have more data and have not filled
the vector
+
+ while (readCount < recordsToReadInThisPass && writeCount <
valueVec.getValueCapacity()) {
+ // read a page if needed
if (!pageReader.hasPage()
- || ((readStartInBytes + readLength >= pageReader.byteLength &&
bitsUsed == 0) &&
- definitionLevelsRead >= pageReader.currentPageCount)) {
- if (!pageReader.next()) {
- break;
- }
- definitionLevelsRead = 0;
+ || (definitionLevelsRead >= pageReader.currentPageCount)) {
+ if (!pageReader.next()) {
+ break;
}
- lastValueWasNull = true;
- runLength = 0;
- if (lastRunBrokenByNull ) {
- nullsFound = 1;
- lastRunBrokenByNull = false;
- } else {
- nullsFound = 0;
- }
- // loop to find the longest run of defined values available, can
be preceded by several nulls
- while(indexInOutputVector < recordsToReadInThisPass
- && indexInOutputVector < valueVec.getValueCapacity()
- && definitionLevelsRead < pageReader.currentPageCount) {
+ //New page. Reset the definition level.
+ currentDefinitionLevel = -1;
+ definitionLevelsRead = 0;
+ recordsReadInThisIteration = 0;
+ }
+
+ nullRunLength = 0;
+ runLength = 0;
+
+ //
+ // Let's skip the next run of nulls if any ...
+ //
+
+ // If we are reentering this loop, the currentDefinitionLevel has
already been read
+ if (currentDefinitionLevel < 0) {
+ currentDefinitionLevel = pageReader.definitionLevels.readInteger();
+ }
+ haveMoreData = readCount < recordsToReadInThisPass
+ && writeCount + nullRunLength < valueVec.getValueCapacity()
+ && definitionLevelsRead < pageReader.currentPageCount;
+ while (haveMoreData && currentDefinitionLevel < columnDescriptor
+ .getMaxDefinitionLevel()) {
+ readCount++;
+ nullRunLength++;
+ definitionLevelsRead++;
+ haveMoreData = readCount < recordsToReadInThisPass
+ && writeCount + nullRunLength < valueVec.getValueCapacity()
+ && definitionLevelsRead < pageReader.currentPageCount;
+ if (haveMoreData) {
currentDefinitionLevel =
pageReader.definitionLevels.readInteger();
- definitionLevelsRead++;
- indexInOutputVector++;
- totalDefinitionLevelsRead++;
- if ( currentDefinitionLevel <
columnDescriptor.getMaxDefinitionLevel()){
- // a run of non-null values was found, break out of this loop
to do a read in the outer loop
- if ( ! lastValueWasNull ){
- lastRunBrokenByNull = true;
- break;
- }
- nullsFound++;
- lastValueWasNull = true;
- }
- else{
- if (lastValueWasNull){
- runLength = 0;
- lastValueWasNull = false;
- }
- runLength++;
- castedVectorMutator.setIndexDefined(indexInOutputVector - 1);
- }
}
- valuesReadInCurrentPass += nullsFound;
+ }
+ //
+ // Write the nulls if any
+ //
+ if (nullRunLength > 0) {
+ int writerIndex =
+ ((BaseDataValueVector) valueVec).getBuffer().writerIndex();
+ castedBaseVector.getBuffer().setIndex(0, writerIndex + (int) Math
--- End diff --
previous code seemed to handle `dataTypeLengthInBits <= 8` separately. Is
it no longer required/needed ?
> Exception on inner join when join predicate is int96 field generated by impala
> ------------------------------------------------------------------------------
>
> Key: DRILL-3871
> URL: https://issues.apache.org/jira/browse/DRILL-3871
> Project: Apache Drill
> Issue Type: Bug
> Components: Execution - Data Types
> Affects Versions: 1.2.0
> Reporter: Victoria Markman
> Assignee: Deneche A. Hakim
> Priority: Critical
> Labels: int96
> Fix For: 1.3.0
>
> Attachments: tables.tar
>
>
> Both tables in the join where created by impala, with column c_timestamp
> being parquet int96.
> {code}
> 0: jdbc:drill:schema=dfs> select
> . . . . . . . . . . . . > max(t1.c_timestamp),
> . . . . . . . . . . . . > min(t1.c_timestamp),
> . . . . . . . . . . . . > count(t1.c_timestamp)
> . . . . . . . . . . . . > from
> . . . . . . . . . . . . > imp_t1 t1
> . . . . . . . . . . . . > inner join
> . . . . . . . . . . . . > imp_t2 t2
> . . . . . . . . . . . . > on (t1.c_timestamp = t2.c_timestamp)
> . . . . . . . . . . . . > ;
> java.lang.RuntimeException: java.sql.SQLException: SYSTEM ERROR:
> TProtocolException: Required field 'uncompressed_page_size' was not found in
> serialized data! Struct: PageHeader(type:null, uncompressed_page_size:0,
> compressed_page_size:0)
> Fragment 0:0
> [Error Id: eb6a5df8-fc59-409b-957a-59cb1079b5b8 on atsqa4-133.qa.lab:31010]
> at sqlline.IncrementalRows.hasNext(IncrementalRows.java:73)
> at
> sqlline.TableOutputFormat$ResizingRowsProvider.next(TableOutputFormat.java:87)
> at sqlline.TableOutputFormat.print(TableOutputFormat.java:118)
> at sqlline.SqlLine.print(SqlLine.java:1583)
> at sqlline.Commands.execute(Commands.java:852)
> at sqlline.Commands.sql(Commands.java:751)
> at sqlline.SqlLine.dispatch(SqlLine.java:738)
> at sqlline.SqlLine.begin(SqlLine.java:612)
> at sqlline.SqlLine.start(SqlLine.java:366)
> at sqlline.SqlLine.main(SqlLine.java:259)
> {code}
> drillbit.log
> {code}
> 2015-09-30 21:15:45,710 [29f3aefe-3209-a6e6-0418-500dac60a339:foreman] INFO
> o.a.d.exec.store.parquet.Metadata - Took 0 ms to get file statuses
> 2015-09-30 21:15:45,712 [29f3aefe-3209-a6e6-0418-500dac60a339:foreman] INFO
> o.a.d.exec.store.parquet.Metadata - Fetch parquet metadata: Executed 1 out of
> 1 using 1 threads. Time: 1ms total, 1.645381ms avg, 1ms max.
> 2015-09-30 21:15:45,712 [29f3aefe-3209-a6e6-0418-500dac60a339:foreman] INFO
> o.a.d.exec.store.parquet.Metadata - Fetch parquet metadata: Executed 1 out of
> 1 using 1 threads. Earliest start: 1.332000 μs, Latest start: 1.332000 μs,
> Average start: 1.332000 μs .
> 2015-09-30 21:15:45,830 [29f3aefe-3209-a6e6-0418-500dac60a339:frag:0:0] INFO
> o.a.d.e.w.fragment.FragmentExecutor -
> 29f3aefe-3209-a6e6-0418-500dac60a339:0:0: State change requested
> AWAITING_ALLOCATION --> RUNNING
> 2015-09-30 21:15:45,830 [29f3aefe-3209-a6e6-0418-500dac60a339:frag:0:0] INFO
> o.a.d.e.w.f.FragmentStatusReporter -
> 29f3aefe-3209-a6e6-0418-500dac60a339:0:0: State to report: RUNNING
> 2015-09-30 21:15:45,925 [29f3aefe-3209-a6e6-0418-500dac60a339:frag:0:0] INFO
> o.a.d.e.w.fragment.FragmentExecutor -
> 29f3aefe-3209-a6e6-0418-500dac60a339:0:0: State change requested RUNNING -->
> FAILED
> 2015-09-30 21:15:45,930 [29f3aefe-3209-a6e6-0418-500dac60a339:frag:0:0] INFO
> o.a.d.e.w.fragment.FragmentExecutor -
> 29f3aefe-3209-a6e6-0418-500dac60a339:0:0: State change requested FAILED -->
> FINISHED
> 2015-09-30 21:15:45,931 [29f3aefe-3209-a6e6-0418-500dac60a339:frag:0:0] ERROR
> o.a.d.e.w.fragment.FragmentExecutor - SYSTEM ERROR: TProtocolException:
> Required field 'uncompressed_page_size' was not found in serialized data!
> Struct: PageHeader(type:null, uncompressed_page_size:0,
> compressed_page_size:0)
> Fragment 0:0
> [Error Id: eb6a5df8-fc59-409b-957a-59cb1079b5b8 on atsqa4-133.qa.lab:31010]
> org.apache.drill.common.exceptions.UserException: SYSTEM ERROR:
> TProtocolException: Required field 'uncompressed_page_size' was not found in
> serialized data! Struct: PageHeader(type:null, uncompressed_page_size:0,
> compressed_page_size:0)
> Fragment 0:0
> [Error Id: eb6a5df8-fc59-409b-957a-59cb1079b5b8 on atsqa4-133.qa.lab:31010]
> at
> org.apache.drill.common.exceptions.UserException$Builder.build(UserException.java:534)
> ~[drill-common-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.work.fragment.FragmentExecutor.sendFinalState(FragmentExecutor.java:323)
> [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.work.fragment.FragmentExecutor.cleanup(FragmentExecutor.java:178)
> [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.work.fragment.FragmentExecutor.run(FragmentExecutor.java:292)
> [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.common.SelfCleaningRunnable.run(SelfCleaningRunnable.java:38)
> [drill-common-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> [na:1.7.0_71]
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> [na:1.7.0_71]
> at java.lang.Thread.run(Thread.java:745) [na:1.7.0_71]
> Caused by: org.apache.drill.common.exceptions.DrillRuntimeException: Error in
> parquet record reader.
> Message:
> Hadoop path:
> /drill/testdata/subqueries/imp_t2/bf4261140dac8d45-814d66b86bf960b8_853027779_data.0.parq
> Total records read: 10
> Mock records read: 0
> Records to read: 1
> Row group index: 0
> Records in row group: 10
> Parquet Metadata: ParquetMetaData{FileMetaData{schema: message schema {
> optional binary c_varchar (UTF8);
> optional int32 c_integer;
> optional int64 c_bigint;
> optional float c_float;
> optional double c_double;
> optional binary c_date (UTF8);
> optional binary c_time (UTF8);
> optional int96 c_timestamp;
> optional boolean c_boolean;
> optional double d9;
> optional double d18;
> optional double d28;
> optional double d38;
> }
> , metadata: {}}, blocks: [BlockMetaData{10, 1507 [ColumnMetaData{SNAPPY
> [c_varchar] BINARY [PLAIN, PLAIN_DICTIONARY, RLE], 173},
> ColumnMetaData{SNAPPY [c_integer] INT32 [PLAIN, PLAIN_DICTIONARY, RLE],
> 299}, ColumnMetaData{SNAPPY [c_bigint] INT64 [PLAIN, PLAIN_DICTIONARY, RLE],
> 453}, ColumnMetaData{SNAPPY [c_float] FLOAT [PLAIN, PLAIN_DICTIONARY, RLE],
> 581}, ColumnMetaData{SNAPPY [c_double] DOUBLE [PLAIN, PLAIN_DICTIONARY,
> RLE], 747}, ColumnMetaData{SNAPPY [c_date] BINARY [PLAIN, PLAIN_DICTIONARY,
> RLE], 900}, ColumnMetaData{SNAPPY [c_time] BINARY [PLAIN, PLAIN_DICTIONARY,
> RLE], 1045}, ColumnMetaData{SNAPPY [c_timestamp] INT96 [PLAIN,
> PLAIN_DICTIONARY, RLE], 1213}, ColumnMetaData{SNAPPY [c_boolean] BOOLEAN
> [PLAIN, PLAIN_DICTIONARY, RLE], 1293}, ColumnMetaData{SNAPPY [d9] DOUBLE
> [PLAIN, PLAIN_DICTIONARY, RLE], 1448}, ColumnMetaData{SNAPPY [d18] DOUBLE
> [PLAIN, PLAIN_DICTIONARY, RLE], 1609}, ColumnMetaData{SNAPPY [d28] DOUBLE
> [PLAIN, PLAIN_DICTIONARY, RLE], 1771}, ColumnMetaData{SNAPPY [d38] DOUBLE
> [PLAIN, PLAIN_DICTIONARY, RLE], 1933}]}]}
> at
> org.apache.drill.exec.store.parquet.columnreaders.ParquetRecordReader.handleAndRaise(ParquetRecordReader.java:346)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.store.parquet.columnreaders.ParquetRecordReader.next(ParquetRecordReader.java:448)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.ScanBatch.next(ScanBatch.java:183)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:118)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:104)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:94)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:51)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.project.ProjectRecordBatch.innerNext(ProjectRecordBatch.java:129)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:147)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:118)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:104)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.join.HashJoinBatch.executeBuildPhase(HashJoinBatch.java:403)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.join.HashJoinBatch.innerNext(HashJoinBatch.java:218)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:147)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:118)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:104)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:94)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:51)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.project.ProjectRecordBatch.innerNext(ProjectRecordBatch.java:129)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:147)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:118)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:104)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:94)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.aggregate.StreamingAggBatch.innerNext(StreamingAggBatch.java:136)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:147)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:118)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:104)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:94)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:51)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.project.ProjectRecordBatch.innerNext(ProjectRecordBatch.java:129)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:147)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:118)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:83)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.ScreenCreator$ScreenRoot.innerNext(ScreenCreator.java:80)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:73)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.work.fragment.FragmentExecutor$1.run(FragmentExecutor.java:258)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.work.fragment.FragmentExecutor$1.run(FragmentExecutor.java:252)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at java.security.AccessController.doPrivileged(Native Method)
> ~[na:1.7.0_71]
> at javax.security.auth.Subject.doAs(Subject.java:415) ~[na:1.7.0_71]
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1566)
> ~[hadoop-common-2.5.1-mapr-1503.jar:na]
> at
> org.apache.drill.exec.work.fragment.FragmentExecutor.run(FragmentExecutor.java:252)
> [drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> ... 4 common frames omitted
> Caused by: java.io.IOException: can not read class parquet.format.PageHeader:
> Required field 'uncompressed_page_size' was not found in serialized data!
> Struct: PageHeader(type:null, uncompressed_page_size:0,
> compressed_page_size:0)
> at parquet.format.Util.read(Util.java:50)
> ~[parquet-format-2.1.1-drill-r1.jar:na]
> at parquet.format.Util.readPageHeader(Util.java:26)
> ~[parquet-format-2.1.1-drill-r1.jar:na]
> at
> org.apache.drill.exec.store.parquet.ColumnDataReader.readPageHeader(ColumnDataReader.java:46)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.store.parquet.columnreaders.PageReader.next(PageReader.java:191)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.store.parquet.columnreaders.NullableColumnReader.processPages(NullableColumnReader.java:76)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.store.parquet.columnreaders.ParquetRecordReader.readAllFixedFields(ParquetRecordReader.java:387)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> at
> org.apache.drill.exec.store.parquet.columnreaders.ParquetRecordReader.next(ParquetRecordReader.java:430)
> ~[drill-java-exec-1.2.0-SNAPSHOT.jar:1.2.0-SNAPSHOT]
> ... 43 common frames omitted
> Caused by: parquet.org.apache.thrift.protocol.TProtocolException: Required
> field 'uncompressed_page_size' was not found in serialized data! Struct:
> PageHeader(type:null, uncompressed_page_size:0, compressed_page_size:0)
> at parquet.format.PageHeader.read(PageHeader.java:905)
> ~[parquet-format-2.1.1-drill-r1.jar:na]
> at parquet.format.Util.read(Util.java:47)
> ~[parquet-format-2.1.1-drill-r1.jar:na]
> ... 49 common frames omitted
> 2015-09-30 21:15:45,951 [BitServer-4] WARN
> o.a.drill.exec.work.foreman.Foreman - Dropping request to move to COMPLETED
> state as query is already at FAILED state (which is terminal).
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
