diff --git a/ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out b/ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out index fe7e829..1635462 100644 --- a/ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out +++ b/ql/src/test/results/clientpositive/tez/vector_groupby_reduce.q.out @@ -399,7 +399,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Reducer 3 + Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int) @@ -562,31 +562,32 @@ STAGE PLANS: Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: - Map 1 + Map 1 Map Operator Tree: TableScan alias: store_sales Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_ticket_number (type: int), ss_item_sk (type: int), ss_quantity (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: ss_item_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int) + outputColumnNames: ss_item_sk, ss_ticket_number, ss_quantity Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col2) - keys: _col0 (type: int), _col1 (type: int) + aggregations: min(ss_quantity) + keys: ss_item_sk (type: int), ss_ticket_number (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: int) Execution mode: vectorized - Reducer 2 + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -595,18 +596,33 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 44138 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), sum(_col2) - keys: _col0 (type: int) - mode: complete + aggregations: sum(_col0), sum(_col2) + keys: _col1 (type: int) + mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 44138 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 44138 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) Execution mode: vectorized - Reducer 3 + Reducer 3 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint), _col2 (type: bigint) + Execution mode: vectorized + Reducer 4 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint) @@ -771,18 +787,18 @@ STAGE PLANS: Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: - Map 1 + Map 1 Map Operator Tree: TableScan alias: store_sales Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_ticket_number (type: int), ss_item_sk (type: int), ss_quantity (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: ss_item_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int) + outputColumnNames: ss_item_sk, ss_ticket_number, ss_quantity Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col2) - keys: _col0 (type: int), _col1 (type: int) + aggregations: min(ss_quantity) + keys: ss_item_sk (type: int), ss_ticket_number (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE @@ -793,7 +809,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: int) Execution mode: vectorized - Reducer 2 + Reducer 2 Reduce Operator Tree: Group By Operator aggregations: min(VALUE._col0) @@ -807,13 +823,17 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ + Select Operator + expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) Execution mode: vectorized - Reducer 3 + Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: bigint) diff --git a/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out b/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out index fc1997c..3e7077e 100644 --- a/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby_reduce.q.out @@ -550,7 +550,8 @@ POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 @@ -560,19 +561,19 @@ STAGE PLANS: alias: store_sales Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_ticket_number (type: int), ss_item_sk (type: int), ss_quantity (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: ss_item_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int) + outputColumnNames: ss_item_sk, ss_ticket_number, ss_quantity Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col2) - keys: _col0 (type: int), _col1 (type: int) + aggregations: min(ss_quantity) + keys: ss_item_sk (type: int), ss_ticket_number (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: int) Execution mode: vectorized @@ -584,11 +585,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 44138 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), sum(_col2) - keys: _col0 (type: int) - mode: complete + aggregations: sum(_col0), sum(_col2) + keys: _col1 (type: int) + mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 44138 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -603,6 +604,30 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: int) sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 44138 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint), _col2 (type: bigint) + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) Reduce Operator Tree: @@ -769,12 +794,12 @@ STAGE PLANS: alias: store_sales Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_ticket_number (type: int), ss_item_sk (type: int), ss_quantity (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: ss_item_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int) + outputColumnNames: ss_item_sk, ss_ticket_number, ss_quantity Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col2) - keys: _col0 (type: int), _col1 (type: int) + aggregations: min(ss_quantity) + keys: ss_item_sk (type: int), ss_ticket_number (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE @@ -798,12 +823,16 @@ STAGE PLANS: mode: complete outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 22069 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce