http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/orc_merge5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge5.q.out b/ql/src/test/results/clientpositive/llap/orc_merge5.q.out index fafba53..6eba365 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge5.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge5.q.out @@ -36,6 +36,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -58,8 +61,36 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orc_merge5b + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(10,0)), _col4 (type: timestamp) + outputColumnNames: userid, string1, subtype, decimal1, ts + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Dependency Collection @@ -77,6 +108,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: userid, string1, subtype, decimal1, ts + Column Types: bigint, string, double, decimal(10,0), timestamp + Table: default.orc_merge5b PREHOOK: query: insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 PREHOOK: type: QUERY @@ -131,6 +166,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -153,8 +191,36 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orc_merge5b + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(10,0)), _col4 (type: timestamp) + outputColumnNames: userid, string1, subtype, decimal1, ts + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-8 Conditional Operator @@ -181,6 +247,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: userid, string1, subtype, decimal1, ts + Column Types: bigint, string, double, decimal(10,0), timestamp + Table: default.orc_merge5b Stage: Stage-4 Tez
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/orc_merge6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge6.q.out b/ql/src/test/results/clientpositive/llap/orc_merge6.q.out index e5672fd..1583007 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge6.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge6.q.out @@ -36,6 +36,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -58,8 +61,44 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orc_merge5a + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(10,0)), _col4 (type: timestamp), '2000' (type: string), UDFToInteger('24') (type: int) + outputColumnNames: userid, string1, subtype, decimal1, ts, year, hour + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + keys: year (type: string), hour (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,bitvector:binary>), _col6 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + keys: KEY._col0 (type: string), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col6 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Dependency Collection @@ -80,6 +119,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: userid, string1, subtype, decimal1, ts + Column Types: bigint, string, double, decimal(10,0), timestamp + Table: default.orc_merge5a PREHOOK: query: insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 PREHOOK: type: QUERY @@ -176,6 +219,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -198,8 +244,44 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orc_merge5a + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(10,0)), _col4 (type: timestamp), '2000' (type: string), UDFToInteger('24') (type: int) + outputColumnNames: userid, string1, subtype, decimal1, ts, year, hour + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + keys: year (type: string), hour (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: int) + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,bitvector:binary>), _col6 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + keys: KEY._col0 (type: string), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col6 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-8 Conditional Operator @@ -229,6 +311,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: userid, string1, subtype, decimal1, ts + Column Types: bigint, string, double, decimal(10,0), timestamp + Table: default.orc_merge5a Stage: Stage-4 Tez http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/orc_merge7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge7.q.out b/ql/src/test/results/clientpositive/llap/orc_merge7.q.out index f224822..914672d 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge7.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge7.q.out @@ -36,6 +36,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -54,8 +57,44 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orc_merge5a + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(10,0)), _col4 (type: timestamp), _col5 (type: double) + outputColumnNames: userid, string1, subtype, decimal1, ts, st + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + keys: st (type: double) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + keys: KEY._col0 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Dependency Collection @@ -75,6 +114,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: userid, string1, subtype, decimal1, ts + Column Types: bigint, string, double, decimal(10,0), timestamp + Table: default.orc_merge5a PREHOOK: query: insert overwrite table orc_merge5a partition (st) select userid,string1,subtype,decimal1,ts,subtype from orc_merge5 PREHOOK: type: QUERY @@ -210,6 +253,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -228,8 +274,44 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orc_merge5a + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(10,0)), _col4 (type: timestamp), _col5 (type: double) + outputColumnNames: userid, string1, subtype, decimal1, ts, st + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + keys: st (type: double) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + keys: KEY._col0 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-8 Conditional Operator @@ -258,6 +340,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: userid, string1, subtype, decimal1, ts + Column Types: bigint, string, double, decimal(10,0), timestamp + Table: default.orc_merge5a Stage: Stage-4 Tez http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/orc_merge_diff_fs.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge_diff_fs.q.out b/ql/src/test/results/clientpositive/llap/orc_merge_diff_fs.q.out index 5669a5b..64b8460 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge_diff_fs.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge_diff_fs.q.out @@ -60,6 +60,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -78,8 +81,44 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), UDFToString(_col2) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Dependency Collection @@ -100,6 +139,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.orcfile_merge1 PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part) SELECT key, value, PMOD(HASH(key), 2) as part @@ -145,6 +188,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -163,8 +209,44 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1b + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), UDFToString(_col2) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-8 Conditional Operator @@ -194,6 +276,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.orcfile_merge1b Stage: Stage-4 Tez @@ -275,6 +361,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -293,8 +382,44 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orcfile_merge1c + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), UDFToString(_col2) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-8 Conditional Operator @@ -324,6 +449,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.orcfile_merge1c Stage: Stage-4 Tez http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/orc_merge_incompat1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge_incompat1.q.out b/ql/src/test/results/clientpositive/llap/orc_merge_incompat1.q.out index ae7250a..0e9b34f 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge_incompat1.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge_incompat1.q.out @@ -36,6 +36,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -57,8 +60,36 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orc_merge5b + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(10,0)), _col4 (type: timestamp) + outputColumnNames: userid, string1, subtype, decimal1, ts + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 2696 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 2760 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Dependency Collection @@ -76,6 +107,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: userid, string1, subtype, decimal1, ts + Column Types: bigint, string, double, decimal(10,0), timestamp + Table: default.orc_merge5b PREHOOK: query: insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/orc_merge_incompat2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge_incompat2.q.out b/ql/src/test/results/clientpositive/llap/orc_merge_incompat2.q.out index c1822a1..7be4ffa 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge_incompat2.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge_incompat2.q.out @@ -36,6 +36,9 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: @@ -54,8 +57,44 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde name: default.orc_merge5a + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(10,0)), _col4 (type: timestamp), _col5 (type: double) + outputColumnNames: userid, string1, subtype, decimal1, ts, st + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + keys: st (type: double) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + keys: KEY._col0 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(10,0),max:decimal(10,0),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-2 Dependency Collection @@ -75,6 +114,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: userid, string1, subtype, decimal1, ts + Column Types: bigint, string, double, decimal(10,0), timestamp + Table: default.orc_merge5a PREHOOK: query: insert overwrite table orc_merge5a partition (st) select userid,string1,subtype,decimal1,ts,subtype from orc_merge5 order by userid PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out b/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out index d93f604..9f20f77 100644 --- a/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_predicate_pushdown.q.out @@ -133,19 +133,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - Statistics: Num rows: 1049 Data size: 3992 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 4188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(t) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1049 Data size: 3992 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 4188 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: all inputs @@ -156,10 +156,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -191,19 +191,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - Statistics: Num rows: 1049 Data size: 3992 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 4188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(t) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1049 Data size: 3992 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 4188 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: all inputs @@ -214,10 +214,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -321,22 +321,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - Statistics: Num rows: 1049 Data size: 3992 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 4188 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToInteger(t) > -2) and (t < 0)) (type: boolean) - Statistics: Num rows: 116 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(t) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 116 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: all inputs @@ -347,10 +347,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -389,22 +389,22 @@ STAGE PLANS: TableScan alias: orc_pred filterExpr: ((t < 0) and (UDFToInteger(t) > -2)) (type: boolean) - Statistics: Num rows: 1049 Data size: 3992 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 4188 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((UDFToInteger(t) > -2) and (t < 0)) (type: boolean) - Statistics: Num rows: 116 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(t) (type: int) outputColumnNames: _col0 - Statistics: Num rows: 116 Data size: 441 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap LLAP IO: all inputs @@ -415,10 +415,10 @@ STAGE PLANS: aggregations: sum(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -589,18 +589,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - Statistics: Num rows: 1049 Data size: 187624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 105941 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((not (t) IN (-1, -2, -3)) and (s like 'bob%') and s is not null and t BETWEEN 25 AND 30) (type: boolean) - Statistics: Num rows: 54 Data size: 9658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 5656 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), s (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 54 Data size: 9658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 5656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ - Statistics: Num rows: 54 Data size: 9658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 5656 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Reducer 2 @@ -609,10 +609,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 54 Data size: 9658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 5656 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 54 Data size: 9658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 5656 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -655,18 +655,18 @@ STAGE PLANS: TableScan alias: orc_pred filterExpr: (s is not null and (s like 'bob%') and (not (t) IN (-1, -2, -3)) and t BETWEEN 25 AND 30) (type: boolean) - Statistics: Num rows: 1049 Data size: 187624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 105941 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((not (t) IN (-1, -2, -3)) and (s like 'bob%') and s is not null and t BETWEEN 25 AND 30) (type: boolean) - Statistics: Num rows: 54 Data size: 9658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 5656 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), s (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 54 Data size: 9658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 5656 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ - Statistics: Num rows: 54 Data size: 9658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 5656 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap LLAP IO: all inputs Reducer 2 @@ -675,10 +675,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 54 Data size: 9658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 5656 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 54 Data size: 9658 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 5656 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -786,18 +786,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - Statistics: Num rows: 1049 Data size: 199600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d < 12.0) and (d >= 10.0) and (not (s like '%car%')) and (s like '%son') and (t > 0) and UDFToInteger(si) BETWEEN 300 AND 400) (type: boolean) - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -808,13 +808,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -865,18 +865,18 @@ STAGE PLANS: TableScan alias: orc_pred filterExpr: ((d >= 10.0) and (d < 12.0) and (s like '%son') and (t > 0) and UDFToInteger(si) BETWEEN 300 AND 400 and (not (s like '%car%'))) (type: boolean) - Statistics: Num rows: 1049 Data size: 199600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d < 12.0) and (d >= 10.0) and (not (s like '%car%')) and (s like '%son') and (t > 0) and UDFToInteger(si) BETWEEN 300 AND 400) (type: boolean) - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -887,13 +887,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1010,18 +1010,18 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - Statistics: Num rows: 1049 Data size: 199600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d < 12.0) and (d >= 10) and (not (s like '%car%')) and (s like '%son') and (t <> 101) and (t > 0) and (t > 10) and si BETWEEN 300 AND 400) (type: boolean) - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -1032,14 +1032,14 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Reducer 3 @@ -1048,13 +1048,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1110,18 +1110,18 @@ STAGE PLANS: TableScan alias: orc_pred filterExpr: ((t > 10) and (t <> 101) and (d >= 10) and (d < 12.0) and (s like '%son') and (not (s like '%car%')) and (t > 0) and si BETWEEN 300 AND 400) (type: boolean) - Statistics: Num rows: 1049 Data size: 199600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1049 Data size: 118521 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((d < 12.0) and (d >= 10) and (not (s like '%car%')) and (s like '%son') and (t <> 101) and (t > 0) and (t > 10) and si BETWEEN 300 AND 400) (type: boolean) - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Execution mode: llap @@ -1132,14 +1132,14 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: - - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: double) Reducer 3 @@ -1148,13 +1148,13 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), VALUE._col2 (type: double), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 113 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/parallel.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/parallel.q.out b/ql/src/test/results/clientpositive/llap/parallel.q.out index 3beb340..4ac3fbb 100644 --- a/ql/src/test/results/clientpositive/llap/parallel.q.out +++ b/ql/src/test/results/clientpositive/llap/parallel.q.out @@ -39,6 +39,8 @@ STAGE PLANS: Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (ONE_TO_ONE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -93,6 +95,19 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src_a + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Group By Operator keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete @@ -106,6 +121,49 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src_b + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-3 Dependency Collection @@ -123,6 +181,10 @@ STAGE PLANS: Stage: Stage-4 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_a Stage: Stage-1 Move Operator @@ -137,6 +199,10 @@ STAGE PLANS: Stage: Stage-5 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.src_b PREHOOK: query: from (select key, value from src group by key, value) s insert overwrite table src_a select s.key, s.value group by s.key, s.value
