Author: szehon Date: Tue Dec 23 01:33:55 2014 New Revision: 1647464 URL: http://svn.apache.org/r1647464 Log: HIVE-9173 : Fix auto_join29.q, auto_join_without_localtask.q determinism (Jimmy Xiang via Szehon)
Modified: hive/branches/spark/ql/src/test/queries/clientpositive/auto_join29.q hive/branches/spark/ql/src/test/queries/clientpositive/auto_join_without_localtask.q hive/branches/spark/ql/src/test/results/clientpositive/auto_join29.q.out hive/branches/spark/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join29.q.out hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out Modified: hive/branches/spark/ql/src/test/queries/clientpositive/auto_join29.q URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/queries/clientpositive/auto_join29.q?rev=1647464&r1=1647463&r2=1647464&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/queries/clientpositive/auto_join29.q (original) +++ hive/branches/spark/ql/src/test/queries/clientpositive/auto_join29.q Tue Dec 23 01:33:55 2014 @@ -1,4 +1,7 @@ set hive.auto.convert.join = true; + +-- SORT_QUERY_RESULTS + explain SELECT * FROM src src1 LEFT OUTER JOIN src src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) RIGHT OUTER JOIN src src3 ON (src2.key = src3.key AND src3.key < 10) SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value; Modified: hive/branches/spark/ql/src/test/queries/clientpositive/auto_join_without_localtask.q URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/queries/clientpositive/auto_join_without_localtask.q?rev=1647464&r1=1647463&r2=1647464&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/queries/clientpositive/auto_join_without_localtask.q (original) +++ hive/branches/spark/ql/src/test/queries/clientpositive/auto_join_without_localtask.q Tue Dec 23 01:33:55 2014 @@ -17,13 +17,13 @@ select a.* from src a join src b on a.ke set hive.auto.convert.join.noconditionaltask.size=100; explain -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40; +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40; -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40; +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40; set hive.mapjoin.localtask.max.memory.usage = 0.0001; set hive.mapjoin.check.memory.rows = 2; -- fallback to common join -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40; +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40; Modified: hive/branches/spark/ql/src/test/results/clientpositive/auto_join29.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/auto_join29.q.out?rev=1647464&r1=1647463&r2=1647464&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/auto_join29.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/auto_join29.q.out Tue Dec 23 01:33:55 2014 @@ -1,7 +1,11 @@ -PREHOOK: query: explain +PREHOOK: query: -- SORT_QUERY_RESULTS + +explain SELECT * FROM src src1 LEFT OUTER JOIN src src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) RIGHT OUTER JOIN src src3 ON (src2.key = src3.key AND src3.key < 10) SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: -- SORT_QUERY_RESULTS + +explain SELECT * FROM src src1 LEFT OUTER JOIN src src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) RIGHT OUTER JOIN src src3 ON (src2.key = src3.key AND src3.key < 10) SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: @@ -2000,6 +2004,28 @@ POSTHOOK: query: SELECT * FROM src src1 POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 2 val_2 2 val_2 +NULL NULL 4 val_4 4 val_4 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 8 val_8 8 val_8 +NULL NULL 9 val_9 9 val_9 NULL NULL NULL NULL 10 val_10 NULL NULL NULL NULL 100 val_100 NULL NULL NULL NULL 100 val_100 @@ -2490,28 +2516,6 @@ NULL NULL NULL NULL 97 val_97 NULL NULL NULL NULL 97 val_97 NULL NULL NULL NULL 98 val_98 NULL NULL NULL NULL 98 val_98 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 2 val_2 2 val_2 -NULL NULL 4 val_4 4 val_4 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 8 val_8 8 val_8 -NULL NULL 9 val_9 9 val_9 PREHOOK: query: explain SELECT * FROM src src1 JOIN src src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) LEFT OUTER JOIN src src3 ON (src2.key = src3.key AND src3.key < 10) SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value PREHOOK: type: QUERY Modified: hive/branches/spark/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out?rev=1647464&r1=1647463&r2=1647464&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/auto_join_without_localtask.q.out Tue Dec 23 01:33:55 2014 @@ -595,30 +595,31 @@ RUN: Stage-3:MAPRED 103 val_103 103 val_103 PREHOOK: query: explain -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 PREHOOK: type: QUERY POSTHOOK: query: explain -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-10 is a root stage , consists of Stage-13, Stage-14, Stage-1 - Stage-13 has a backup stage: Stage-1 - Stage-8 depends on stages: Stage-13 - Stage-7 depends on stages: Stage-1, Stage-8, Stage-9 , consists of Stage-11, Stage-6, Stage-2 - Stage-11 has a backup stage: Stage-2 - Stage-5 depends on stages: Stage-11 - Stage-6 has a backup stage: Stage-2 - Stage-2 + Stage-11 is a root stage , consists of Stage-14, Stage-15, Stage-1 Stage-14 has a backup stage: Stage-1 Stage-9 depends on stages: Stage-14 + Stage-8 depends on stages: Stage-1, Stage-9, Stage-10 , consists of Stage-12, Stage-7, Stage-2 + Stage-12 has a backup stage: Stage-2 + Stage-6 depends on stages: Stage-12 + Stage-3 depends on stages: Stage-2, Stage-6, Stage-7 + Stage-7 has a backup stage: Stage-2 + Stage-2 + Stage-15 has a backup stage: Stage-1 + Stage-10 depends on stages: Stage-15 Stage-1 - Stage-0 depends on stages: Stage-5, Stage-6, Stage-2 + Stage-0 depends on stages: Stage-3 STAGE PLANS: - Stage: Stage-10 + Stage: Stage-11 Conditional Operator - Stage: Stage-13 + Stage: Stage-14 Map Reduce Local Work Alias -> Map Local Tables: b @@ -638,7 +639,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) - Stage: Stage-8 + Stage: Stage-9 Map Reduce Map Operator Tree: TableScan @@ -664,10 +665,10 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-11 + Stage: Stage-12 Map Reduce Local Work Alias -> Map Local Tables: c @@ -687,7 +688,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 value (type: string) - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -701,21 +702,40 @@ STAGE PLANS: 0 _col1 (type: string) 1 value (type: string) outputColumnNames: _col0, _col1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Limit - Number of rows: 40 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work - Stage: Stage-6 + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 40 + Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-7 Map Reduce Map Operator Tree: TableScan @@ -732,17 +752,12 @@ STAGE PLANS: 0 _col1 (type: string) 1 value (type: string) outputColumnNames: _col0, _col1 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Limit - Number of rows: 40 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work Alias -> Map Local Tables: @@ -783,22 +798,14 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 40 - Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Stage: Stage-14 + Stage: Stage-15 Map Reduce Local Work Alias -> Map Local Tables: a @@ -818,7 +825,7 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) - Stage: Stage-9 + Stage: Stage-10 Map Reduce Map Operator Tree: TableScan @@ -892,62 +899,63 @@ STAGE PLANS: Processor Tree: ListSink -PREHOOK: query: select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +PREHOOK: query: select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### -POSTHOOK: query: select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +POSTHOOK: query: select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -RUN: Stage-10:CONDITIONAL +RUN: Stage-11:CONDITIONAL RUN: Stage-14:MAPREDLOCAL RUN: Stage-9:MAPRED -RUN: Stage-7:CONDITIONAL -RUN: Stage-11:MAPREDLOCAL -RUN: Stage-5:MAPRED -238 val_238 -238 val_238 -238 val_238 -238 val_238 -311 val_311 -311 val_311 -311 val_311 -311 val_311 -311 val_311 -311 val_311 -311 val_311 -311 val_311 -311 val_311 -165 val_165 -165 val_165 -165 val_165 -165 val_165 -409 val_409 -409 val_409 -409 val_409 -409 val_409 -409 val_409 -409 val_409 -409 val_409 -409 val_409 -409 val_409 -255 val_255 -255 val_255 -255 val_255 -255 val_255 -278 val_278 -278 val_278 -278 val_278 -278 val_278 -484 val_484 -265 val_265 -265 val_265 -265 val_265 -265 val_265 -193 val_193 +RUN: Stage-8:CONDITIONAL +RUN: Stage-12:MAPREDLOCAL +RUN: Stage-6:MAPRED +RUN: Stage-3:MAPRED +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +104 val_104 +104 val_104 +104 val_104 +104 val_104 +104 val_104 +104 val_104 +104 val_104 +104 val_104 +105 val_105 +111 val_111 +113 val_113 +113 val_113 +113 val_113 +113 val_113 +113 val_113 +113 val_113 +113 val_113 +113 val_113 +114 val_114 +116 val_116 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +119 val_119 +119 val_119 +119 val_119 +119 val_119 PREHOOK: query: -- fallback to common join -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### @@ -956,16 +964,17 @@ ATTEMPT: Execute BackupTask: org.apache. FAILED: Execution Error, return code 3 from org.apache.hadoop.hive.ql.exec.mr.MapredLocalTask ATTEMPT: Execute BackupTask: org.apache.hadoop.hive.ql.exec.mr.MapRedTask POSTHOOK: query: -- fallback to common join -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### -RUN: Stage-10:CONDITIONAL +RUN: Stage-11:CONDITIONAL RUN: Stage-14:MAPREDLOCAL RUN: Stage-1:MAPRED -RUN: Stage-7:CONDITIONAL -RUN: Stage-11:MAPREDLOCAL +RUN: Stage-8:CONDITIONAL +RUN: Stage-12:MAPREDLOCAL RUN: Stage-2:MAPRED +RUN: Stage-3:MAPRED 103 val_103 103 val_103 103 val_103 Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join29.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join29.q.out?rev=1647464&r1=1647463&r2=1647464&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join29.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join29.q.out Tue Dec 23 01:33:55 2014 @@ -1,7 +1,11 @@ -PREHOOK: query: explain +PREHOOK: query: -- SORT_QUERY_RESULTS + +explain SELECT * FROM src src1 LEFT OUTER JOIN src src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) RIGHT OUTER JOIN src src3 ON (src2.key = src3.key AND src3.key < 10) SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: -- SORT_QUERY_RESULTS + +explain SELECT * FROM src src1 LEFT OUTER JOIN src src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) RIGHT OUTER JOIN src src3 ON (src2.key = src3.key AND src3.key < 10) SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: @@ -2036,6 +2040,28 @@ POSTHOOK: query: SELECT * FROM src src1 POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 0 val_0 0 val_0 +NULL NULL 2 val_2 2 val_2 +NULL NULL 4 val_4 4 val_4 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 5 val_5 5 val_5 +NULL NULL 8 val_8 8 val_8 +NULL NULL 9 val_9 9 val_9 NULL NULL NULL NULL 10 val_10 NULL NULL NULL NULL 100 val_100 NULL NULL NULL NULL 100 val_100 @@ -2526,28 +2552,6 @@ NULL NULL NULL NULL 97 val_97 NULL NULL NULL NULL 97 val_97 NULL NULL NULL NULL 98 val_98 NULL NULL NULL NULL 98 val_98 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 0 val_0 0 val_0 -NULL NULL 2 val_2 2 val_2 -NULL NULL 4 val_4 4 val_4 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 5 val_5 5 val_5 -NULL NULL 8 val_8 8 val_8 -NULL NULL 9 val_9 9 val_9 PREHOOK: query: explain SELECT * FROM src src1 JOIN src src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) LEFT OUTER JOIN src src3 ON (src2.key = src3.key AND src3.key < 10) SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value PREHOOK: type: QUERY Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out?rev=1647464&r1=1647463&r2=1647464&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out Tue Dec 23 01:33:55 2014 @@ -291,10 +291,10 @@ RUN: Stage-1:MAPRED 103 val_103 103 val_103 PREHOOK: query: explain -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 PREHOOK: type: QUERY POSTHOOK: query: explain -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage @@ -304,8 +304,9 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 5 (PARTITION-LEVEL SORT, 3) + Reducer 3 <- Map 6 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3) + Reducer 4 <- Reducer 3 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -322,7 +323,7 @@ STAGE PLANS: Map-reduce partition columns: key (type: string) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: string) - Map 4 + Map 5 Map Operator Tree: TableScan alias: b @@ -335,7 +336,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: key (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Map 5 + Map 6 Map Operator Tree: TableScan alias: c @@ -374,20 +375,26 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 40 + Reducer 4 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 40 + Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -395,15 +402,23 @@ STAGE PLANS: Processor Tree: ListSink -PREHOOK: query: select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +PREHOOK: query: select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### -POSTHOOK: query: select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +POSTHOOK: query: select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### RUN: Stage-1:MAPRED +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 104 val_104 104 val_104 104 val_104 @@ -412,6 +427,8 @@ RUN: Stage-1:MAPRED 104 val_104 104 val_104 104 val_104 +105 val_105 +111 val_111 113 val_113 113 val_113 113 val_113 @@ -420,41 +437,39 @@ RUN: Stage-1:MAPRED 113 val_113 113 val_113 113 val_113 +114 val_114 116 val_116 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 119 val_119 119 val_119 119 val_119 119 val_119 PREHOOK: query: -- fallback to common join -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 PREHOOK: type: QUERY PREHOOK: Input: default@src #### A masked pattern was here #### POSTHOOK: query: -- fallback to common join -select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 limit 40 +select a.* from src a join src b on a.key=b.key join src c on a.value=c.value where a.key>100 order by a.key, a.value limit 40 POSTHOOK: type: QUERY POSTHOOK: Input: default@src #### A masked pattern was here #### RUN: Stage-1:MAPRED +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 +103 val_103 104 val_104 104 val_104 104 val_104 @@ -463,6 +478,8 @@ RUN: Stage-1:MAPRED 104 val_104 104 val_104 104 val_104 +105 val_105 +111 val_111 113 val_113 113 val_113 113 val_113 @@ -471,26 +488,16 @@ RUN: Stage-1:MAPRED 113 val_113 113 val_113 113 val_113 +114 val_114 116 val_116 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 -119 val_119 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 +118 val_118 119 val_119 119 val_119 119 val_119