http://git-wip-us.apache.org/repos/asf/hive/blob/aed21d0b/ql/src/test/results/clientpositive/llap/vector_outer_join3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_join3.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_join3.q.out index fbd294e..5729237 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_join3.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_join3.q.out @@ -226,7 +226,7 @@ NULL NULL -850295959 -1887561756 NULL NULL WMIgGA73 4hA4KQj2vD3fI6gX82220d NULL NULL NULL -886426182 -1887561756 NULL NULL 0i88xYq3gx1nW4vKjp7vBp3 4hA4KQj2vD3fI6gX82220d NULL 1969-12-31 16:00:04.472 true false NULL NULL -899422227 -1645852809 NULL NULL 73xdw4X xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:07.395 false false NULL NULL -971543377 -1645852809 NULL NULL uN803aW xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:05.43 false false -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select c.cstring1 from small_alltypesorc_a c left outer join small_alltypesorc_a cd @@ -235,7 +235,7 @@ left outer join small_alltypesorc_a hd on hd.cstring1 = c.cstring1 ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select c.cstring1 from small_alltypesorc_a c left outer join small_alltypesorc_a cd @@ -244,7 +244,112 @@ left outer join small_alltypesorc_a hd on hd.cstring1 = c.cstring1 ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 20 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cint (type: int), cstring1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 3 + Statistics: Num rows: 40 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 4 + Statistics: Num rows: 80 Data size: 640 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: cd + Statistics: Num rows: 20 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 20 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 4 + Map Operator Tree: + TableScan + alias: hd + Statistics: Num rows: 20 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cstring1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 20 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 20 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: -- SORT_QUERY_RESULTS select count(*) from (select c.cstring1 @@ -270,7 +375,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@small_alltypesorc_a #### A masked pattern was here #### 20 -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select c.cstring1 from small_alltypesorc_a c left outer join small_alltypesorc_a cd @@ -279,7 +384,7 @@ left outer join small_alltypesorc_a hd on hd.cstring1 = c.cstring1 ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select c.cstring1 from small_alltypesorc_a c left outer join small_alltypesorc_a cd @@ -288,7 +393,112 @@ left outer join small_alltypesorc_a hd on hd.cstring1 = c.cstring1 ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 20 Data size: 2939 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cstring1 (type: string), cstring2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 2939 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + input vertices: + 1 Map 3 + Statistics: Num rows: 21 Data size: 1869 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 4 + Statistics: Num rows: 42 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: cd + Statistics: Num rows: 20 Data size: 1960 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cstring2 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 20 Data size: 1960 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 20 Data size: 1960 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 4 + Map Operator Tree: + TableScan + alias: hd + Statistics: Num rows: 20 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cstring1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 20 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 20 Data size: 979 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: -- SORT_QUERY_RESULTS select count(*) from (select c.cstring1 @@ -314,7 +524,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@small_alltypesorc_a #### A masked pattern was here #### 28 -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select c.cstring1 from small_alltypesorc_a c left outer join small_alltypesorc_a cd @@ -323,7 +533,7 @@ left outer join small_alltypesorc_a hd on hd.cstring1 = c.cstring1 and hd.cint = c.cint ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select c.cstring1 from small_alltypesorc_a c left outer join small_alltypesorc_a cd @@ -332,7 +542,112 @@ left outer join small_alltypesorc_a hd on hd.cstring1 = c.cstring1 and hd.cint = c.cint ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez #### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 20 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cint (type: int), cbigint (type: bigint), cstring1 (type: string), cstring2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 20 Data size: 3143 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col1 (type: bigint), _col3 (type: string) + 1 _col0 (type: bigint), _col1 (type: string) + outputColumnNames: _col0, _col2 + input vertices: + 1 Map 3 + Statistics: Num rows: 20 Data size: 1860 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: int), _col2 (type: string) + 1 _col0 (type: int), _col1 (type: string) + input vertices: + 1 Map 4 + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: cd + Statistics: Num rows: 20 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cbigint (type: bigint), cstring2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: bigint), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: bigint), _col1 (type: string) + Statistics: Num rows: 20 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 4 + Map Operator Tree: + TableScan + alias: hd + Statistics: Num rows: 20 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cint (type: int), cstring1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 20 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: -- SORT_QUERY_RESULTS select count(*) from (select c.cstring1
http://git-wip-us.apache.org/repos/asf/hive/blob/aed21d0b/ql/src/test/results/clientpositive/llap/vector_outer_join4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_join4.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_join4.q.out index b9b97f6..75d783f 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_join4.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_join4.q.out @@ -246,19 +246,82 @@ NULL NULL -850295959 -1887561756 NULL NULL WMIgGA73 4hA4KQj2vD3fI6gX82220d NULL NULL NULL -886426182 -1887561756 NULL NULL 0i88xYq3gx1nW4vKjp7vBp3 4hA4KQj2vD3fI6gX82220d NULL 1969-12-31 16:00:04.472 true false NULL NULL -899422227 -1645852809 NULL NULL 73xdw4X xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:07.395 false false NULL NULL -971543377 -1645852809 NULL NULL uN803aW xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:05.43 false false -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select * from small_alltypesorc_b c left outer join small_alltypesorc_b cd on cd.cint = c.cint PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select * from small_alltypesorc_b c left outer join small_alltypesorc_b cd on cd.cint = c.cint POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE) #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 30 Data size: 7167 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 30 Data size: 7167 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col2 (type: int) + 1 _col2 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 + input vertices: + 1 Map 2 + Statistics: Num rows: 81 Data size: 49734 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 81 Data size: 49734 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 + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 2 + Map Operator Tree: + TableScan + alias: cd + Statistics: Num rows: 30 Data size: 7167 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + Statistics: Num rows: 30 Data size: 7167 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 30 Data size: 7167 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) + Execution mode: vectorized, llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: -- SORT_QUERY_RESULTS select * @@ -331,19 +394,81 @@ NULL NULL -850295959 -1887561756 NULL NULL WMIgGA73 4hA4KQj2vD3fI6gX82220d NULL NULL NULL -886426182 -1887561756 NULL NULL 0i88xYq3gx1nW4vKjp7vBp3 4hA4KQj2vD3fI6gX82220d NULL 1969-12-31 16:00:04.472 true false NULL NULL -886426182 -1887561756 NULL NULL 0i88xYq3gx1nW4vKjp7vBp3 4hA4KQj2vD3fI6gX82220d NULL 1969-12-31 16:00:04.472 true false NULL NULL -899422227 -1645852809 NULL NULL 73xdw4X xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:07.395 false false NULL NULL -899422227 -1645852809 NULL NULL 73xdw4X xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:07.395 false false NULL NULL -971543377 -1645852809 NULL NULL uN803aW xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:05.43 false false NULL NULL -971543377 -1645852809 NULL NULL uN803aW xH7445Rals48VOulSyR5F NULL 1969-12-31 16:00:05.43 false false -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select c.ctinyint from small_alltypesorc_b c left outer join small_alltypesorc_b hd on hd.ctinyint = c.ctinyint PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select c.ctinyint from small_alltypesorc_b c left outer join small_alltypesorc_b hd on hd.ctinyint = c.ctinyint POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 2 (BROADCAST_EDGE) #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + outputColumnNames: _col0 + input vertices: + 1 Map 2 + Statistics: Num rows: 450 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 450 Data size: 1800 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 + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 2 + Map Operator Tree: + TableScan + alias: hd + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: -- SORT_QUERY_RESULTS select c.ctinyint @@ -772,7 +897,7 @@ NULL NULL NULL NULL -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select c.ctinyint from small_alltypesorc_b c left outer join small_alltypesorc_b cd @@ -781,7 +906,7 @@ left outer join small_alltypesorc_b hd on hd.ctinyint = c.ctinyint ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select c.ctinyint from small_alltypesorc_b c left outer join small_alltypesorc_b cd @@ -790,7 +915,112 @@ left outer join small_alltypesorc_b hd on hd.ctinyint = c.ctinyint ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez #### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 30 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), cint (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 30 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0 + input vertices: + 1 Map 3 + Statistics: Num rows: 81 Data size: 324 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + input vertices: + 1 Map 4 + Statistics: Num rows: 1215 Data size: 9720 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: cd + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 4 + Map Operator Tree: + TableScan + alias: hd + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 30 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: -- SORT_QUERY_RESULTS select count(*) from (select c.ctinyint http://git-wip-us.apache.org/repos/asf/hive/blob/aed21d0b/ql/src/test/results/clientpositive/llap/vector_outer_join5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_join5.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_join5.q.out index eb61044..8a18738 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_join5.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_join5.q.out @@ -66,21 +66,100 @@ POSTHOOK: query: ANALYZE TABLE small_table COMPUTE STATISTICS FOR COLUMNS POSTHOOK: type: QUERY POSTHOOK: Input: default@small_table #### A masked pattern was here #### -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select s.*, st.* from sorted_mod_4 s left outer join small_table st on s.ctinyint = st.ctinyint ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select s.*, st.* from sorted_mod_4 s left outer join small_table st on s.ctinyint = st.ctinyint ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + input vertices: + 1 Map 3 + Statistics: Num rows: 6444 Data size: 51552 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: st + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from (select s.*, st.* from sorted_mod_4 s left outer join small_table st @@ -100,21 +179,103 @@ POSTHOOK: Input: default@small_table POSTHOOK: Input: default@sorted_mod_4 #### A masked pattern was here #### 6876 -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select s.ctinyint, s.cmodint, sm.cbigint from sorted_mod_4 s left outer join small_table sm on s.ctinyint = sm.ctinyint and s.cmodint = 2 ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select s.ctinyint, s.cmodint, sm.cbigint from sorted_mod_4 s left outer join small_table sm on s.ctinyint = sm.ctinyint and s.cmodint = 2 ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez #### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), cmodint (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + filter predicates: + 0 {(_col1 = 2)} + 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + input vertices: + 1 Map 3 + Statistics: Num rows: 6444 Data size: 51552 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: sm + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from (select s.ctinyint, s.cmodint, sm.cbigint from sorted_mod_4 s left outer join small_table sm @@ -134,21 +295,103 @@ POSTHOOK: Input: default@small_table POSTHOOK: Input: default@sorted_mod_4 #### A masked pattern was here #### 6058 -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select s.ctinyint, s.cmodint, sm.cbigint from sorted_mod_4 s left outer join small_table sm on s.ctinyint = sm.ctinyint and pmod(s.ctinyint, 4) = s.cmodint ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select s.ctinyint, s.cmodint, sm.cbigint from sorted_mod_4 s left outer join small_table sm on s.ctinyint = sm.ctinyint and pmod(s.ctinyint, 4) = s.cmodint ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), cmodint (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + filter predicates: + 0 {((UDFToInteger(_col0) pmod 4) = _col1)} + 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + input vertices: + 1 Map 3 + Statistics: Num rows: 6444 Data size: 51552 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: sm + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from (select s.ctinyint, s.cmodint, sm.cbigint from sorted_mod_4 s left outer join small_table sm @@ -168,21 +411,103 @@ POSTHOOK: Input: default@small_table POSTHOOK: Input: default@sorted_mod_4 #### A masked pattern was here #### 6248 -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select s.ctinyint, s.cmodint, sm.cbigint from sorted_mod_4 s left outer join small_table sm on s.ctinyint = sm.ctinyint and s.ctinyint < 100 ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select s.ctinyint, s.cmodint, sm.cbigint from sorted_mod_4 s left outer join small_table sm on s.ctinyint = sm.ctinyint and s.ctinyint < 100 ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez #### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + filter predicates: + 0 {(_col0 < 100)} + 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + input vertices: + 1 Map 3 + Statistics: Num rows: 6444 Data size: 51552 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: sm + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from (select s.ctinyint, s.cmodint, sm.cbigint from sorted_mod_4 s left outer join small_table sm @@ -202,7 +527,7 @@ POSTHOOK: Input: default@small_table POSTHOOK: Input: default@sorted_mod_4 #### A masked pattern was here #### 6876 -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select s.*, sm.*, s2.* from sorted_mod_4 s left outer join small_table sm @@ -211,7 +536,7 @@ left outer join sorted_mod_4 s2 on s2.ctinyint = s.ctinyint ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select s.*, sm.*, s2.* from sorted_mod_4 s left outer join small_table sm @@ -220,7 +545,119 @@ left outer join sorted_mod_4 s2 on s2.ctinyint = s.ctinyint ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint), cmodint (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 UDFToLong(_col1) (type: bigint) + 1 (_col0 pmod 8) (type: bigint) + outputColumnNames: _col0 + input vertices: + 1 Map 4 + Statistics: Num rows: 151450 Data size: 605800 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 151450 Data size: 605800 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 4 + Map Operator Tree: + TableScan + alias: sm + Statistics: Num rows: 100 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cbigint (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 100 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: (_col0 pmod 8) (type: bigint) + sort order: + + Map-reduce partition columns: (_col0 pmod 8) (type: bigint) + Statistics: Num rows: 100 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: s2 + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: ctinyint (type: tinyint) + outputColumnNames: _col0 + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: tinyint) + 1 _col0 (type: tinyint) + Statistics: Num rows: 9760469 Data size: 78083752 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from (select s.*, sm.*, s2.* from sorted_mod_4 s left outer join small_table sm @@ -306,21 +743,100 @@ POSTHOOK: query: ANALYZE TABLE small_table2 COMPUTE STATISTICS FOR COLUMNS POSTHOOK: type: QUERY POSTHOOK: Input: default@small_table2 #### A masked pattern was here #### -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select s.*, st.* from mod_8_mod_4 s left outer join small_table2 st on s.cmodtinyint = st.cmodtinyint ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select s.*, st.* from mod_8_mod_4 s left outer join small_table2 st on s.cmodtinyint = st.cmodtinyint ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cmodtinyint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 3 + Statistics: Num rows: 40386 Data size: 323088 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: st + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cmodtinyint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from (select s.*, st.* from mod_8_mod_4 s left outer join small_table2 st @@ -340,21 +856,103 @@ POSTHOOK: Input: default@mod_8_mod_4 POSTHOOK: Input: default@small_table2 #### A masked pattern was here #### 39112 -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select s.cmodtinyint, s.cmodint, sm.cbigint from mod_8_mod_4 s left outer join small_table2 sm on s.cmodtinyint = sm.cmodtinyint and s.cmodint = 2 ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select s.cmodtinyint, s.cmodint, sm.cbigint from mod_8_mod_4 s left outer join small_table2 sm on s.cmodtinyint = sm.cmodtinyint and s.cmodint = 2 ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez #### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cmodtinyint (type: int), cmodint (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + filter predicates: + 0 {(_col1 = 2)} + 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 3 + Statistics: Num rows: 40386 Data size: 323088 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: sm + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cmodtinyint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from (select s.cmodtinyint, s.cmodint, sm.cbigint from mod_8_mod_4 s left outer join small_table2 sm @@ -374,21 +972,103 @@ POSTHOOK: Input: default@mod_8_mod_4 POSTHOOK: Input: default@small_table2 #### A masked pattern was here #### 11171 -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select s.cmodtinyint, s.cmodint, sm.cbigint from mod_8_mod_4 s left outer join small_table2 sm on s.cmodtinyint = sm.cmodtinyint and pmod(s.cmodtinyint, 4) = s.cmodint ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select s.cmodtinyint, s.cmodint, sm.cbigint from mod_8_mod_4 s left outer join small_table2 sm on s.cmodtinyint = sm.cmodtinyint and pmod(s.cmodtinyint, 4) = s.cmodint ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cmodtinyint (type: int), cmodint (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + filter predicates: + 0 {((_col0 pmod 4) = _col1)} + 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 3 + Statistics: Num rows: 40386 Data size: 323088 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: sm + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cmodtinyint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from (select s.cmodtinyint, s.cmodint, sm.cbigint from mod_8_mod_4 s left outer join small_table2 sm @@ -408,21 +1088,103 @@ POSTHOOK: Input: default@mod_8_mod_4 POSTHOOK: Input: default@small_table2 #### A masked pattern was here #### 14371 -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select s.cmodtinyint, s.cmodint, sm.cbigint from mod_8_mod_4 s left outer join small_table2 sm on s.cmodtinyint = sm.cmodtinyint and s.cmodtinyint < 3 ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select s.cmodtinyint, s.cmodint, sm.cbigint from mod_8_mod_4 s left outer join small_table2 sm on s.cmodtinyint = sm.cmodtinyint and s.cmodtinyint < 3 ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez #### A masked pattern was here #### + Edges: + Map 1 <- Map 3 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cmodtinyint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + filter predicates: + 0 {(_col0 < 3)} + 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 3 + Statistics: Num rows: 40386 Data size: 323088 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 3 + Map Operator Tree: + TableScan + alias: sm + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cmodtinyint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 100 Data size: 396 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from (select s.cmodtinyint, s.cmodint, sm.cbigint from mod_8_mod_4 s left outer join small_table2 sm @@ -442,7 +1204,7 @@ POSTHOOK: Input: default@mod_8_mod_4 POSTHOOK: Input: default@small_table2 #### A masked pattern was here #### 17792 -PREHOOK: query: explain vectorization detail formatted +PREHOOK: query: explain select count(*) from (select s.*, sm.*, s2.* from mod_8_mod_4 s left outer join small_table2 sm @@ -451,7 +1213,7 @@ left outer join mod_8_mod_4 s2 on s2.cmodtinyint = s.cmodtinyint ) t1 PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail formatted +POSTHOOK: query: explain select count(*) from (select s.*, sm.*, s2.* from mod_8_mod_4 s left outer join small_table2 sm @@ -460,7 +1222,119 @@ left outer join mod_8_mod_4 s2 on s2.cmodtinyint = s.cmodtinyint ) t1 POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cmodtinyint (type: int), cmodint (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 UDFToLong(_col1) (type: bigint) + 1 (_col0 pmod 8) (type: bigint) + outputColumnNames: _col0 + input vertices: + 1 Map 4 + Statistics: Num rows: 151450 Data size: 605800 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 151450 Data size: 605800 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 4 + Map Operator Tree: + TableScan + alias: sm + Statistics: Num rows: 100 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cbigint (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 100 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: (_col0 pmod 8) (type: bigint) + sort order: + + Map-reduce partition columns: (_col0 pmod 8) (type: bigint) + Statistics: Num rows: 100 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Map 5 + Map Operator Tree: + TableScan + alias: s2 + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cmodtinyint (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 6058 Data size: 24232 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: all inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 152914016 Data size: 1223312128 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + 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 + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + PREHOOK: query: select count(*) from (select s.*, sm.*, s2.* from mod_8_mod_4 s left outer join small_table2 sm