diff --git a/ql/src/java/org/apache/hadoop/hive/ql/ppd/SyntheticJoinPredicate.java b/ql/src/java/org/apache/hadoop/hive/ql/ppd/SyntheticJoinPredicate.java index 1f533bc540..e97e44796f 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/ppd/SyntheticJoinPredicate.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/ppd/SyntheticJoinPredicate.java @@ -308,7 +308,22 @@ private boolean createDerivatives(final List resultExprs, final Op CommonJoinOperator joinOp = (CommonJoinOperator) currentOp; // 2. Backtrack expression to join output - final ExprNodeDesc joinExprNode = ExprNodeDescUtils.backtrack(currentNode, op, joinOp); + ExprNodeDesc expr = currentNode; + if (currentOp != op) { + if (expr instanceof ExprNodeColumnDesc) { + // Expression refers to output of current operator, but backtrack methods works + // from the input columns, hence we need to make resolution for current operator + // here. If the operator was already the join, there is nothing to do + if (op.getColumnExprMap() != null) { + expr = op.getColumnExprMap().get(((ExprNodeColumnDesc) expr).getColumn()); + } + } else { + // TODO: We can extend to other expression types + // We are done + return true; + } + } + final ExprNodeDesc joinExprNode = ExprNodeDescUtils.backtrack(expr, op, joinOp); if (joinExprNode == null || !(joinExprNode instanceof ExprNodeColumnDesc)) { // TODO: We can extend to other expression types // We are done diff --git a/ql/src/test/queries/clientpositive/perf/cbo_query24.q b/ql/src/test/queries/clientpositive/perf/cbo_query24.q index 02bcbafb7e..8994de7a23 100644 --- a/ql/src/test/queries/clientpositive/perf/cbo_query24.q +++ b/ql/src/test/queries/clientpositive/perf/cbo_query24.q @@ -24,7 +24,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name diff --git a/ql/src/test/queries/clientpositive/perf/query24.q b/ql/src/test/queries/clientpositive/perf/query24.q index 007d7ee415..b3cdaef4a5 100644 --- a/ql/src/test/queries/clientpositive/perf/query24.q +++ b/ql/src/test/queries/clientpositive/perf/query24.q @@ -24,7 +24,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name diff --git a/ql/src/test/results/clientpositive/perf/spark/query24.q.out b/ql/src/test/results/clientpositive/perf/spark/query24.q.out index 4e2e8e7cf6..91fe702cde 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query24.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query24.q.out @@ -1,4 +1,4 @@ -Warning: Map Join MAPJOIN[104][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[107][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain with ssales as (select c_last_name @@ -23,7 +23,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name @@ -79,7 +80,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name @@ -138,8 +140,8 @@ STAGE PLANS: Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) - 1 _col0 (type: int) + 0 _col2 (type: string) + 1 _col4 (type: string) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -147,43 +149,43 @@ STAGE PLANS: Stage: Stage-2 Spark Edges: - Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 975), Map 20 (PARTITION-LEVEL SORT, 975) - Reducer 14 <- Map 21 (PARTITION-LEVEL SORT, 486), Reducer 13 (PARTITION-LEVEL SORT, 486) - Reducer 15 <- Map 22 (PARTITION-LEVEL SORT, 564), Reducer 14 (PARTITION-LEVEL SORT, 564) - Reducer 16 <- Map 23 (PARTITION-LEVEL SORT, 899), Reducer 15 (PARTITION-LEVEL SORT, 899) - Reducer 17 <- Reducer 16 (GROUP, 640) + Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 887), Map 20 (PARTITION-LEVEL SORT, 887) + Reducer 14 <- Map 21 (PARTITION-LEVEL SORT, 989), Reducer 13 (PARTITION-LEVEL SORT, 989) + Reducer 15 <- Map 22 (PARTITION-LEVEL SORT, 442), Reducer 14 (PARTITION-LEVEL SORT, 442) + Reducer 16 <- Map 23 (PARTITION-LEVEL SORT, 516), Reducer 15 (PARTITION-LEVEL SORT, 516) + Reducer 17 <- Reducer 16 (GROUP, 529) Reducer 18 <- Reducer 17 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 12 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (ss_ticket_number is not null and ss_item_sk is not null and ss_store_sk is not null and ss_customer_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: customer_address + filterExpr: (ca_address_sk is not null and ca_zip is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (ca_address_sk is not null and ca_zip is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + expressions: ca_address_sk (type: int), ca_state (type: string), ca_zip (type: string), ca_country (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col6, _col8, _col9 + 0 _col2 (type: string) + 1 _col4 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 input vertices: 1 Map 19 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col9 (type: string) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col7 (type: string) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -191,23 +193,43 @@ STAGE PLANS: Map Operator Tree: TableScan alias: customer - filterExpr: (c_customer_sk is not null and c_birth_country is not null) (type: boolean) + filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (c_birth_country is not null and c_customer_sk is not null) (type: boolean) + predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string), c_birth_country (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: c_customer_sk (type: int), c_current_addr_sk (type: int), c_first_name (type: string), c_last_name (type: string), c_birth_country (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string) Execution mode: vectorized Map 21 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (ss_ticket_number is not null and ss_item_sk is not null and ss_store_sk is not null and ss_customer_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + Execution mode: vectorized + Map 22 Map Operator Tree: TableScan alias: item @@ -227,7 +249,7 @@ STAGE PLANS: Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: decimal(7,2)), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int) Execution mode: vectorized - Map 22 + Map 23 Map Operator Tree: TableScan alias: store_returns @@ -246,109 +268,92 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 23 - Map Operator Tree: - TableScan - alias: customer_address - filterExpr: (upper(ca_country) is not null and ca_zip is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ca_zip is not null and upper(ca_country) is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ca_state (type: string), ca_zip (type: string), ca_country (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string), upper(_col2) (type: string) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), upper(_col2) (type: string) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized Reducer 13 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3, _col4, _col6, _col8, _col9, _col11, _col12, _col13 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col9 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string) + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col1, _col3, _col4, _col5, _col7, _col9, _col11, _col12, _col13 + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col13 <> upper(_col3)) (type: boolean) + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col9 (type: int), _col4 (type: int) + sort order: ++ + Map-reduce partition columns: _col9 (type: int), _col4 (type: int) + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col5 (type: string), _col7 (type: string), _col11 (type: string), _col12 (type: string) Reducer 14 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3, _col4, _col6, _col8, _col9, _col11, _col12, _col13, _col15, _col16, _col17, _col18, _col19 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + 0 _col9 (type: int), _col4 (type: int) + 1 _col1 (type: int), _col2 (type: int) + outputColumnNames: _col1, _col5, _col7, _col11, _col12, _col14, _col17, _col18 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col3 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col3 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col9 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col15 (type: decimal(7,2)), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: int) + key expressions: _col14 (type: int) + sort order: + + Map-reduce partition columns: _col14 (type: int) + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col5 (type: string), _col7 (type: string), _col11 (type: string), _col12 (type: string), _col17 (type: int), _col18 (type: decimal(7,2)) Reducer 15 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int), _col3 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col4, _col6, _col8, _col9, _col11, _col12, _col13, _col15, _col16, _col17, _col18, _col19 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + 0 _col14 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col5, _col7, _col11, _col12, _col14, _col17, _col18, _col20, _col21, _col22, _col23, _col24 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col9 (type: string), _col13 (type: string) + key expressions: _col14 (type: int), _col17 (type: int) sort order: ++ - Map-reduce partition columns: _col9 (type: string), _col13 (type: string) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col11 (type: string), _col12 (type: string), _col15 (type: decimal(7,2)), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: int) + Map-reduce partition columns: _col14 (type: int), _col17 (type: int) + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col5 (type: string), _col7 (type: string), _col11 (type: string), _col12 (type: string), _col18 (type: decimal(7,2)), _col20 (type: decimal(7,2)), _col21 (type: string), _col22 (type: string), _col23 (type: string), _col24 (type: int) Reducer 16 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col9 (type: string), _col13 (type: string) - 1 _col1 (type: string), upper(_col2) (type: string) - outputColumnNames: _col4, _col6, _col8, _col11, _col12, _col15, _col16, _col17, _col18, _col19, _col22 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + 0 _col14 (type: int), _col17 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col1, _col5, _col7, _col11, _col12, _col18, _col20, _col21, _col22, _col23, _col24 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col4) - keys: _col11 (type: string), _col12 (type: string), _col6 (type: string), _col8 (type: string), _col15 (type: decimal(7,2)), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: int), _col22 (type: string) + aggregations: sum(_col18) + keys: _col11 (type: string), _col12 (type: string), _col1 (type: string), _col5 (type: string), _col7 (type: string), _col20 (type: decimal(7,2)), _col21 (type: string), _col22 (type: string), _col23 (type: string), _col24 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: string) + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: decimal(7,2)), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int) sort order: ++++++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: string) - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: decimal(7,2)), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int) + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE value expressions: _col10 (type: decimal(17,2)) Reducer 17 Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: decimal(7,2)), KEY._col5 (type: string), KEY._col6 (type: string), KEY._col7 (type: string), KEY._col8 (type: int), KEY._col9 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: decimal(7,2)), KEY._col6 (type: string), KEY._col7 (type: string), KEY._col8 (type: string), KEY._col9 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col10 (type: decimal(17,2)) outputColumnNames: _col10 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col10), count(_col10) mode: hash @@ -381,7 +386,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 9 Map Operator Tree: TableScan alias: store @@ -396,8 +401,8 @@ STAGE PLANS: Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) - 1 _col0 (type: int) + 0 _col2 (type: string) + 1 _col4 (type: string) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -405,11 +410,11 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 400), Map 7 (PARTITION-LEVEL SORT, 400) - Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 1009), Reducer 2 (PARTITION-LEVEL SORT, 1009) - Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 564), Reducer 3 (PARTITION-LEVEL SORT, 564) - Reducer 5 <- Map 11 (PARTITION-LEVEL SORT, 899), Reducer 4 (PARTITION-LEVEL SORT, 899) - Reducer 6 <- Reducer 5 (GROUP PARTITION-LEVEL SORT, 640) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 400), Map 6 (PARTITION-LEVEL SORT, 400) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1009), Reducer 8 (PARTITION-LEVEL SORT, 1009) + Reducer 4 <- Map 11 (PARTITION-LEVEL SORT, 516), Reducer 3 (PARTITION-LEVEL SORT, 516) + Reducer 5 <- Reducer 4 (GROUP PARTITION-LEVEL SORT, 529) + Reducer 8 <- Map 10 (PARTITION-LEVEL SORT, 887), Map 7 (PARTITION-LEVEL SORT, 887) #### A masked pattern was here #### Vertices: Map 1 @@ -433,6 +438,26 @@ STAGE PLANS: value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) Execution mode: vectorized Map 10 + Map Operator Tree: + TableScan + alias: customer + filterExpr: (c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c_customer_sk (type: int), c_current_addr_sk (type: int), c_first_name (type: string), c_last_name (type: string), c_birth_country (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string) + Execution mode: vectorized + Map 11 Map Operator Tree: TableScan alias: store_returns @@ -451,27 +476,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 11 - Map Operator Tree: - TableScan - alias: customer_address - filterExpr: (upper(ca_country) is not null and ca_zip is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (ca_zip is not null and upper(ca_country) is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ca_state (type: string), ca_zip (type: string), ca_country (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string), upper(_col2) (type: string) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), upper(_col2) (type: string) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized - Map 7 + Map 6 Map Operator Tree: TableScan alias: item @@ -491,29 +496,39 @@ STAGE PLANS: Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: decimal(7,2)), _col2 (type: string), _col4 (type: string), _col5 (type: int) Execution mode: vectorized - Map 9 + Map 7 Map Operator Tree: TableScan - alias: customer - filterExpr: (c_customer_sk is not null and c_birth_country is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + alias: customer_address + filterExpr: (ca_address_sk is not null and ca_zip is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (c_birth_country is not null and c_customer_sk is not null) (type: boolean) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + predicate: (ca_address_sk is not null and ca_zip is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string), c_birth_country (type: string) + expressions: ca_address_sk (type: int), ca_state (type: string), ca_zip (type: string), ca_country (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col4 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 + input vertices: + 1 Map 9 + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col7 (type: string) Execution mode: vectorized - Reducer 2 Local Work: Map Reduce Local Work + Reducer 2 Reduce Operator Tree: Join Operator condition map: @@ -523,38 +538,28 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col6, _col7, _col9, _col10 Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col15 - input vertices: - 1 Map 8 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col12 (type: string), _col14 (type: string), _col15 (type: string) + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col3, _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col15, _col17, _col18, _col19 - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + 0 _col1 (type: int), _col2 (type: int) + 1 _col0 (type: int), _col9 (type: int) + outputColumnNames: _col0, _col3, _col4, _col6, _col7, _col9, _col10, _col13, _col14, _col17, _col21, _col23 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col3 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col3 (type: int) - Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col12 (type: string), _col14 (type: string), _col15 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: string) + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col13 (type: string), _col14 (type: string), _col17 (type: string), _col21 (type: string), _col23 (type: string) Reducer 4 Reduce Operator Tree: Join Operator @@ -563,61 +568,45 @@ STAGE PLANS: keys: 0 _col0 (type: int), _col3 (type: int) 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col15, _col17, _col18, _col19 - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col15 (type: string), _col19 (type: string) - sort order: ++ - Map-reduce partition columns: _col15 (type: string), _col19 (type: string) - Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col12 (type: string), _col14 (type: string), _col17 (type: string), _col18 (type: string) - Reducer 5 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col15 (type: string), _col19 (type: string) - 1 _col1 (type: string), upper(_col2) (type: string) - outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col17, _col18, _col22 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col13, _col14, _col17, _col21, _col23 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col4) - keys: _col17 (type: string), _col18 (type: string), _col12 (type: string), _col22 (type: string), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col14 (type: string) + keys: _col13 (type: string), _col14 (type: string), _col21 (type: string), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col17 (type: string), _col23 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string) + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: decimal(7,2)), _col4 (type: string), _col5 (type: string), _col6 (type: int), _col7 (type: string), _col8 (type: string) sort order: +++++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE value expressions: _col9 (type: decimal(17,2)) - Reducer 6 + Reducer 5 Execution mode: vectorized Local Work: Map Reduce Local Work Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: decimal(7,2)), KEY._col5 (type: string), KEY._col6 (type: string), KEY._col7 (type: int), KEY._col8 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: decimal(7,2)), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: int), KEY._col7 (type: string), KEY._col8 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col9 (type: decimal(17,2)) - outputColumnNames: _col1, _col2, _col7, _col9 - Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col4, _col5, _col7, _col9 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col9) - keys: _col1 (type: string), _col2 (type: string), _col7 (type: string) + keys: _col4 (type: string), _col5 (type: string), _col7 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 231911707 Data size: 20459318134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string), _col3 (type: decimal(27,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 231911707 Data size: 20459318134 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -627,21 +616,44 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4 input vertices: 1 Reducer 18 - Statistics: Num rows: 231911707 Data size: 74494745865 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 191662559 Data size: 61565902849 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col3 > _col4) (type: boolean) - Statistics: Num rows: 77303902 Data size: 24831581847 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63887519 Data size: 20521967402 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: decimal(27,2)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 77303902 Data size: 24831581847 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63887519 Data size: 20521967402 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 77303902 Data size: 24831581847 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63887519 Data size: 20521967402 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 + Reducer 8 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col1, _col3, _col4, _col5, _col7, _col9, _col11, _col12, _col13 + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col13 <> upper(_col3)) (type: boolean) + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col9 (type: int), _col11 (type: string), _col12 (type: string), _col1 (type: string), _col4 (type: int), _col5 (type: string), _col7 (type: string) + outputColumnNames: _col0, _col2, _col3, _col6, _col9, _col10, _col12 + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col9 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col9 (type: int) + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string), _col3 (type: string), _col6 (type: string), _col10 (type: string), _col12 (type: string) Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query23.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query23.q.out index baf790e064..ace7cf5b79 100644 --- a/ql/src/test/results/clientpositive/perf/tez/cbo_query23.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query23.q.out @@ -1,7 +1,7 @@ -Warning: Shuffle Join MERGEJOIN[589][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product -Warning: Shuffle Join MERGEJOIN[590][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product -Warning: Shuffle Join MERGEJOIN[592][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product -Warning: Shuffle Join MERGEJOIN[593][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product +Warning: Shuffle Join MERGEJOIN[593][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product +Warning: Shuffle Join MERGEJOIN[594][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product +Warning: Shuffle Join MERGEJOIN[596][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product +Warning: Shuffle Join MERGEJOIN[597][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product PREHOOK: query: explain cbo with frequent_ss_items as (select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date solddate,count(*) cnt diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query24.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query24.q.out index 53220d2b0e..1d005b86e1 100644 --- a/ql/src/test/results/clientpositive/perf/tez/cbo_query24.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query24.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[290][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 8' is a cross product +Warning: Shuffle Join MERGEJOIN[301][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 6' is a cross product PREHOOK: query: explain cbo with ssales as (select c_last_name @@ -23,7 +23,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name @@ -79,7 +80,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name @@ -115,57 +117,58 @@ CBO PLAN: HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3]) HiveJoin(condition=[>($3, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_last_name=[$1], c_first_name=[$0], s_store_name=[$2], $f3=[$3]) - HiveAggregate(group=[{1, 2, 7}], agg#0=[sum($9)]) - HiveProject(ca_state=[$0], c_first_name=[$1], c_last_name=[$2], i_current_price=[$3], i_size=[$4], i_units=[$5], i_manager_id=[$6], s_store_name=[$7], s_state=[$8], $f9=[$9]) - HiveAggregate(group=[{0, 6, 7, 15, 16, 18, 19, 21, 23}], agg#0=[sum($13)]) - HiveJoin(condition=[AND(=($8, UPPER($2)), =($24, $1))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_state=[$8], ca_zip=[$9], ca_country=[$10]) - HiveFilter(condition=[AND(IS NOT NULL(UPPER($10)), IS NOT NULL($9))]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveJoin(condition=[AND(=($9, $1), =($6, $0))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) - HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2))]) - HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_first_name=[$8], c_last_name=[$9], c_birth_country=[$14]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($14))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($2, $11)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_sales_price=[$13]) - HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($7), IS NOT NULL($3))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_color=[CAST(_UTF-16LE'orchid'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_units=[$18], i_manager_id=[$20]) - HiveFilter(condition=[AND(=($17, _UTF-16LE'orchid'), IS NOT NULL($0))]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(s_store_sk=[$0], s_store_name=[$5], s_market_id=[CAST(7):INTEGER], s_state=[$24], s_zip=[$25]) - HiveFilter(condition=[AND(=($10, 7), IS NOT NULL($0), IS NOT NULL($25))]) - HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveAggregate(group=[{4, 5, 7}], agg#0=[sum($9)]) + HiveProject(i_current_price=[$0], i_size=[$1], i_units=[$2], i_manager_id=[$3], c_first_name=[$4], c_last_name=[$5], ca_state=[$6], s_store_name=[$7], s_state=[$8], $f9=[$9]) + HiveAggregate(group=[{8, 9, 11, 12, 15, 16, 19, 23, 25}], agg#0=[sum($6)]) + HiveJoin(condition=[AND(=($5, $1), =($2, $0))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) + HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2))]) + HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) + HiveJoin(condition=[AND(=($1, $11), =($2, $20))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_sales_price=[$13]) + HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($7), IS NOT NULL($3))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_color=[CAST(_UTF-16LE'orchid'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_units=[$18], i_manager_id=[$20]) + HiveFilter(condition=[AND(=($17, _UTF-16LE'orchid'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$1], c_first_name=[$2], c_last_name=[$3], c_birth_country=[$4], ca_address_sk=[$5], ca_state=[$6], ca_zip=[$7], ca_country=[$8], s_store_sk=[$9], s_store_name=[$10], s_market_id=[$11], s_state=[$12], s_zip=[$13]) + HiveJoin(condition=[AND(=($1, $5), <>($4, UPPER($8)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4], c_first_name=[$8], c_last_name=[$9], c_birth_country=[$14]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($8, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_zip=[$9], ca_country=[$10]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($9))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], s_market_id=[CAST(7):INTEGER], s_state=[$24], s_zip=[$25]) + HiveFilter(condition=[AND(=($10, 7), IS NOT NULL($0), IS NOT NULL($25))]) + HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject(_o__c0=[*(0.05, /($0, $1))]) HiveAggregate(group=[{}], agg#0=[sum($10)], agg#1=[count($10)]) - HiveProject(c_first_name=[$0], c_last_name=[$1], s_store_name=[$2], s_state=[$3], i_current_price=[$4], i_size=[$5], i_color=[$6], i_units=[$7], i_manager_id=[$8], ca_state=[$9], $f10=[$10]) - HiveAggregate(group=[{3, 4, 12, 14, 17, 18, 19, 20, 21, 22}], agg#0=[sum($10)]) - HiveJoin(condition=[AND(=($5, UPPER($24)), =($15, $23))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[AND(=($9, $1), =($6, $0))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) - HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2))]) - HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveJoin(condition=[=($4, $14)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_first_name=[$8], c_last_name=[$9], c_birth_country=[$14]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($14))]) + HiveProject(c_first_name=[$0], c_last_name=[$1], ca_state=[$2], s_store_name=[$3], s_state=[$4], i_current_price=[$5], i_size=[$6], i_color=[$7], i_units=[$8], i_manager_id=[$9], $f10=[$10]) + HiveAggregate(group=[{7, 8, 11, 15, 17, 20, 21, 22, 23, 24}], agg#0=[sum($4)]) + HiveJoin(condition=[AND(=($3, $26), =($0, $25))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $19)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($1, $5), =($2, $14))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_sales_price=[$13]) + HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($7), IS NOT NULL($3))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveJoin(condition=[AND(=($1, $5), <>($4, UPPER($8)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4], c_first_name=[$8], c_last_name=[$9], c_birth_country=[$14]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_sales_price=[$13]) - HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($7), IS NOT NULL($3))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveJoin(condition=[=($8, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_zip=[$9], ca_country=[$10]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($9))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveProject(s_store_sk=[$0], s_store_name=[$5], s_market_id=[CAST(7):INTEGER], s_state=[$24], s_zip=[$25]) HiveFilter(condition=[AND(=($10, 7), IS NOT NULL($0), IS NOT NULL($25))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_color=[$17], i_units=[$18], i_manager_id=[$20]) - HiveFilter(condition=[IS NOT NULL($0)]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_state=[$8], ca_zip=[$9], ca_country=[$10]) - HiveFilter(condition=[AND(IS NOT NULL(UPPER($10)), IS NOT NULL($9))]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_color=[$17], i_units=[$18], i_manager_id=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) + HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2))]) + HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query24.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query24.q.out index 34cc51b62c..0801f34472 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query24.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query24.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[287][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 8' is a cross product +Warning: Shuffle Join MERGEJOIN[298][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 6' is a cross product PREHOOK: query: explain cbo with ssales as (select c_last_name @@ -23,7 +23,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name @@ -79,7 +80,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name @@ -115,54 +117,55 @@ CBO PLAN: HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3]) HiveJoin(condition=[>($3, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_last_name=[$1], c_first_name=[$0], s_store_name=[$2], $f3=[$3]) - HiveAggregate(group=[{1, 2, 7}], agg#0=[sum($9)]) - HiveProject(ca_state=[$0], c_first_name=[$1], c_last_name=[$2], i_current_price=[$3], i_size=[$4], i_units=[$5], i_manager_id=[$6], s_store_name=[$7], s_state=[$8], $f9=[$9]) - HiveAggregate(group=[{0, 6, 7, 15, 16, 17, 18, 20, 21}], agg#0=[sum($13)]) - HiveJoin(condition=[AND(=($8, $2), =($22, $1))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ca_state=[$8], ca_zip=[$9], UPPER=[UPPER($10)]) - HiveFilter(condition=[AND(IS NOT NULL(UPPER($10)), IS NOT NULL($9))]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) - HiveJoin(condition=[AND(=($9, $1), =($6, $0))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) - HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_first_name=[$8], c_last_name=[$9], c_birth_country=[$14]) - HiveFilter(condition=[IS NOT NULL($14)]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($2, $10)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_sales_price=[$13]) - HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($3))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_units=[$18], i_manager_id=[$20]) - HiveFilter(condition=[=($17, _UTF-16LE'orchid')]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(s_store_sk=[$0], s_store_name=[$5], s_state=[$24], s_zip=[$25]) - HiveFilter(condition=[AND(=($10, 7), IS NOT NULL($25))]) - HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(_o__c0=[*(0.05, /($0, $1))]) - HiveAggregate(group=[{}], agg#0=[sum($10)], agg#1=[count($10)]) - HiveProject(c_first_name=[$0], c_last_name=[$1], s_store_name=[$2], s_state=[$3], i_current_price=[$4], i_size=[$5], i_color=[$6], i_units=[$7], i_manager_id=[$8], ca_state=[$9], $f10=[$10]) - HiveAggregate(group=[{3, 4, 12, 13, 16, 17, 18, 19, 20, 21}], agg#0=[sum($10)]) - HiveJoin(condition=[AND(=($5, $23), =($14, $22))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[AND(=($9, $1), =($6, $0))], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) - HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveJoin(condition=[=($4, $13)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_first_name=[$8], c_last_name=[$9], c_birth_country=[$14]) - HiveFilter(condition=[IS NOT NULL($14)]) + HiveAggregate(group=[{4, 5, 7}], agg#0=[sum($9)]) + HiveProject(i_current_price=[$0], i_size=[$1], i_units=[$2], i_manager_id=[$3], c_first_name=[$4], c_last_name=[$5], ca_state=[$6], s_store_name=[$7], s_state=[$8], $f9=[$9]) + HiveAggregate(group=[{8, 9, 10, 11, 14, 15, 18, 22, 23}], agg#0=[sum($6)]) + HiveJoin(condition=[AND(=($5, $1), =($2, $0))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) + HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) + HiveJoin(condition=[AND(=($1, $10), =($2, $19))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_sales_price=[$13]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($3))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_units=[$18], i_manager_id=[$20]) + HiveFilter(condition=[=($17, _UTF-16LE'orchid')]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$1], c_first_name=[$2], c_last_name=[$3], c_birth_country=[$4], ca_address_sk=[$5], ca_state=[$6], ca_zip=[$7], UPPER=[$8], s_store_sk=[$9], s_store_name=[$10], s_state=[$11], s_zip=[$12]) + HiveJoin(condition=[AND(=($1, $5), <>($4, $8))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4], c_first_name=[$8], c_last_name=[$9], c_birth_country=[$14]) + HiveFilter(condition=[IS NOT NULL($4)]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($2, $5)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_sales_price=[$13]) - HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($3))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveJoin(condition=[=($7, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_zip=[$9], UPPER=[UPPER($10)]) + HiveFilter(condition=[IS NOT NULL($9)]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) HiveProject(s_store_sk=[$0], s_store_name=[$5], s_state=[$24], s_zip=[$25]) HiveFilter(condition=[AND(=($10, 7), IS NOT NULL($25))]) HiveTableScan(table=[[default, store]], table:alias=[store]) - HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_color=[$17], i_units=[$18], i_manager_id=[$20]) - HiveTableScan(table=[[default, item]], table:alias=[item]) - HiveProject(ca_state=[$8], ca_zip=[$9], UPPER=[UPPER($10)]) - HiveFilter(condition=[AND(IS NOT NULL(UPPER($10)), IS NOT NULL($9))]) - HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveProject(_o__c0=[*(0.05, /($0, $1))]) + HiveAggregate(group=[{}], agg#0=[sum($10)], agg#1=[count($10)]) + HiveProject(c_first_name=[$0], c_last_name=[$1], ca_state=[$2], s_store_name=[$3], s_state=[$4], i_current_price=[$5], i_size=[$6], i_color=[$7], i_units=[$8], i_manager_id=[$9], $f10=[$10]) + HiveAggregate(group=[{9, 10, 13, 17, 18, 21, 22, 23, 24, 25}], agg#0=[sum($6)]) + HiveJoin(condition=[AND(=($5, $1), =($2, $0))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9]) + HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) + HiveJoin(condition=[=($0, $18)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($17, $12), =($2, $14))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $5)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9], ss_sales_price=[$13]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($3))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveJoin(condition=[AND(=($1, $5), <>($4, $8))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4], c_first_name=[$8], c_last_name=[$9], c_birth_country=[$14]) + HiveFilter(condition=[IS NOT NULL($4)]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_zip=[$9], UPPER=[UPPER($10)]) + HiveFilter(condition=[IS NOT NULL($9)]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], s_state=[$24], s_zip=[$25]) + HiveFilter(condition=[AND(=($10, 7), IS NOT NULL($25))]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(i_item_sk=[$0], i_current_price=[$5], i_size=[$15], i_color=[$17], i_units=[$18], i_manager_id=[$20]) + HiveTableScan(table=[[default, item]], table:alias=[item]) diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query6.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query6.q.out index ef53060740..cbf372a753 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query6.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query6.q.out @@ -1,4 +1,4 @@ -Warning: Map Join MAPJOIN[172][bigTable=?] in task 'Reducer 15' is a cross product +Warning: Map Join MAPJOIN[170][bigTable=?] in task 'Reducer 15' is a cross product PREHOOK: query: explain cbo select a.ca_state state, count(*) cnt from customer_address a diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out index ff4c05f3fb..b7f97780c7 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query18.q.out @@ -99,56 +99,56 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_179] - Limit [LIM_178] (rows=100 width=1165) + File Output Operator [FS_177] + Limit [LIM_176] (rows=100 width=1165) Number of rows:100 - Select Operator [SEL_177] (rows=10969055 width=1165) + Select Operator [SEL_175] (rows=10969055 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_176] - Select Operator [SEL_175] (rows=10969055 width=1165) + SHUFFLE [RS_174] + Select Operator [SEL_173] (rows=10969055 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Group By Operator [GBY_174] (rows=10969055 width=1229) + Group By Operator [GBY_172] (rows=10969055 width=1229) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)","sum(VALUE._col8)","count(VALUE._col9)","sum(VALUE._col10)","count(VALUE._col11)","sum(VALUE._col12)","count(VALUE._col13)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col0, _col1, _col2, _col3, _col4 Group By Operator [GBY_39] (rows=10969055 width=1229) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(_col15)","count(_col15)","sum(_col16)","count(_col16)","sum(_col17)","count(_col17)","sum(_col18)","count(_col18)","sum(_col19)","count(_col19)","sum(_col3)","count(_col3)","sum(_col22)","count(_col22)"],keys:_col5, _col6, _col7, _col10, 0L - Merge Join Operator [MERGEJOIN_142] (rows=2193811 width=811) + Merge Join Operator [MERGEJOIN_140] (rows=2193811 width=811) Conds:RS_35._col0=RS_36._col3(Inner),Output:["_col3","_col5","_col6","_col7","_col10","_col15","_col16","_col17","_col18","_col19","_col22"] <-Reducer 3 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_35] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_138] (rows=4959744 width=368) - Conds:RS_32._col1=RS_150._col0(Inner),Output:["_col0","_col3","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_136] (rows=4959744 width=368) + Conds:RS_32._col1=RS_148._col0(Inner),Output:["_col0","_col3","_col5","_col6","_col7"] <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_150] + SHUFFLE [RS_148] PartitionCols:_col0 - Select Operator [SEL_149] (rows=1861800 width=4) + Select Operator [SEL_147] (rows=1861800 width=4) Output:["_col0"] TableScan [TS_6] (rows=1861800 width=4) default@customer_demographics,cd2,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_137] (rows=4890586 width=371) - Conds:RS_145._col2=RS_148._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_135] (rows=4890586 width=371) + Conds:RS_143._col2=RS_146._col0(Inner),Output:["_col0","_col1","_col3","_col5","_col6","_col7"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_145] + SHUFFLE [RS_143] PartitionCols:_col2 - Select Operator [SEL_144] (rows=35631408 width=119) + Select Operator [SEL_142] (rows=35631408 width=119) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_143] (rows=35631408 width=19) + Filter Operator [FIL_141] (rows=35631408 width=19) predicate:((c_birth_month) IN (9, 5, 12, 4, 1, 10) and c_current_addr_sk is not null and c_current_cdemo_sk is not null) TableScan [TS_0] (rows=80000000 width=19) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk","c_birth_month","c_birth_year"] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_148] + SHUFFLE [RS_146] PartitionCols:_col0 - Select Operator [SEL_147] (rows=5490196 width=285) + Select Operator [SEL_145] (rows=5490196 width=285) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_146] (rows=5490196 width=285) + Filter Operator [FIL_144] (rows=5490196 width=285) predicate:(ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') TableScan [TS_3] (rows=40000000 width=285) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_state","ca_country"] @@ -157,83 +157,83 @@ Stage-0 PartitionCols:_col3 Select Operator [SEL_28] (rows=15983481 width=735) Output:["_col1","_col3","_col6","_col7","_col8","_col9","_col10","_col13"] - Merge Join Operator [MERGEJOIN_141] (rows=15983481 width=735) - Conds:RS_25._col3=RS_173._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] + Merge Join Operator [MERGEJOIN_139] (rows=15983481 width=735) + Conds:RS_25._col3=RS_171._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_173] + SHUFFLE [RS_171] PartitionCols:_col0 - Select Operator [SEL_172] (rows=462000 width=104) + Select Operator [SEL_170] (rows=462000 width=104) Output:["_col0","_col1"] TableScan [TS_17] (rows=462000 width=104) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_140] (rows=15983481 width=639) - Conds:RS_22._col2=RS_161._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] + Merge Join Operator [MERGEJOIN_138] (rows=15983481 width=639) + Conds:RS_22._col2=RS_159._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_161] + PARTITION_ONLY_SHUFFLE [RS_159] PartitionCols:_col0 - Select Operator [SEL_160] (rows=103433 width=116) + Select Operator [SEL_158] (rows=103433 width=116) Output:["_col0","_col1"] - Filter Operator [FIL_159] (rows=103433 width=187) + Filter Operator [FIL_157] (rows=103433 width=187) predicate:((cd_education_status = 'College') and (cd_gender = 'M')) TableScan [TS_14] (rows=1861800 width=187) default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_education_status","cd_dep_count"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_139] (rows=100578970 width=565) - Conds:RS_171._col0=RS_153._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_137] (rows=100578970 width=565) + Conds:RS_169._col0=RS_151._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Map 14 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_153] + PARTITION_ONLY_SHUFFLE [RS_151] PartitionCols:_col0 - Select Operator [SEL_152] (rows=652 width=4) + Select Operator [SEL_150] (rows=652 width=4) Output:["_col0"] - Filter Operator [FIL_151] (rows=652 width=8) + Filter Operator [FIL_149] (rows=652 width=8) predicate:(d_year = 2001) TableScan [TS_11] (rows=73049 width=8) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_171] + SHUFFLE [RS_169] PartitionCols:_col0 - Select Operator [SEL_170] (rows=283692098 width=573) + Select Operator [SEL_168] (rows=283692098 width=573) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_169] (rows=283692098 width=466) + Filter Operator [FIL_167] (rows=283692098 width=466) predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_23_cd1_cd_demo_sk_min) AND DynamicValue(RS_23_cd1_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_23_cd1_cd_demo_sk_bloom_filter))) and (cs_bill_customer_sk BETWEEN DynamicValue(RS_35_customer_c_customer_sk_min) AND DynamicValue(RS_35_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_35_customer_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) TableScan [TS_8] (rows=287989836 width=466) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_bill_cdemo_sk","cs_item_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt","cs_net_profit"] <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_158] - Group By Operator [GBY_157] (rows=1 width=12) + BROADCAST [RS_156] + Group By Operator [GBY_155] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_156] - Group By Operator [GBY_155] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_154] + Group By Operator [GBY_153] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_154] (rows=652 width=4) + Select Operator [SEL_152] (rows=652 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_152] + Please refer to the previous Select Operator [SEL_150] <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_166] - Group By Operator [GBY_165] (rows=1 width=12) + BROADCAST [RS_164] + Group By Operator [GBY_163] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_164] - Group By Operator [GBY_163] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_162] + Group By Operator [GBY_161] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_162] (rows=103433 width=4) + Select Operator [SEL_160] (rows=103433 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_160] + Please refer to the previous Select Operator [SEL_158] <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_168] - Group By Operator [GBY_167] (rows=1 width=12) + BROADCAST [RS_166] + Group By Operator [GBY_165] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=4890586)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_123] - Group By Operator [GBY_122] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_117] + Group By Operator [GBY_116] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4890586)"] - Select Operator [SEL_121] (rows=4959744 width=4) + Select Operator [SEL_115] (rows=4959744 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_138] + Please refer to the previous Merge Join Operator [MERGEJOIN_136] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query24.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query24.q.out index 7fbbc0518e..fb77386d6e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query24.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query24.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[287][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 8' is a cross product +Warning: Shuffle Join MERGEJOIN[298][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 6' is a cross product PREHOOK: query: explain with ssales as (select c_last_name @@ -23,7 +23,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name @@ -79,7 +80,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name @@ -114,230 +116,248 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) -Map 24 <- Reducer 20 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Map 9 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) -Reducer 12 <- Map 22 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 23 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Reducer 13 (SIMPLE_EDGE) -Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 16 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE) -Reducer 19 <- Map 21 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 20 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 21 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 22 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Map 23 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) +Map 25 <- Reducer 22 (BROADCAST_EDGE) +Reducer 10 <- Map 24 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) +Reducer 15 <- Map 23 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Map 13 (SIMPLE_EDGE), Map 23 (SIMPLE_EDGE) +Reducer 19 <- Map 25 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 20 <- Map 21 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) +Reducer 22 <- Map 21 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 24 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 7 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 8 - File Output Operator [FS_88] - Select Operator [SEL_87] (rows=78393744 width=380) + Reducer 6 + File Output Operator [FS_91] + Select Operator [SEL_90] (rows=1313165 width=380) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_86] (rows=78393744 width=492) + Filter Operator [FIL_89] (rows=1313165 width=492) predicate:(_col3 > _col4) - Merge Join Operator [MERGEJOIN_287] (rows=235181232 width=492) + Merge Join Operator [MERGEJOIN_298] (rows=3939496 width=492) Conds:(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_340] - Select Operator [SEL_339] (rows=1 width=112) + <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_350] + Select Operator [SEL_349] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_338] (rows=1 width=120) + Group By Operator [GBY_348] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] - <-Reducer 14 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_337] - Group By Operator [GBY_336] (rows=1 width=120) + <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_347] + Group By Operator [GBY_346] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col10)","count(_col10)"] - Select Operator [SEL_335] (rows=2121289008973 width=932) + Select Operator [SEL_345] (rows=8029453 width=932) Output:["_col10"] - Group By Operator [GBY_334] (rows=2121289008973 width=932) + Group By Operator [GBY_344] (rows=8029453 width=932) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9 - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_75] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_78] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Group By Operator [GBY_74] (rows=2121289008973 width=932) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col4)"],keys:_col10, _col11, _col6, _col7, _col14, _col15, _col16, _col17, _col18, _col21 - Merge Join Operator [MERGEJOIN_286] (rows=2121289008973 width=932) - Conds:RS_70._col12, _col8=RS_323._col2, _col1(Inner),Output:["_col4","_col6","_col7","_col10","_col11","_col14","_col15","_col16","_col17","_col18","_col21"] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] - PartitionCols:_col2, _col1 - Select Operator [SEL_321] (rows=40000000 width=359) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_320] (rows=40000000 width=272) - predicate:(ca_zip is not null and upper(ca_country) is not null) - TableScan [TS_14] (rows=40000000 width=272) - default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_state","ca_zip","ca_country"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_70] - PartitionCols:_col12, _col8 - Merge Join Operator [MERGEJOIN_285] (rows=537799796 width=1023) - Conds:RS_67._col0, _col3=RS_319._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col8","_col10","_col11","_col12","_col14","_col15","_col16","_col17","_col18"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_319] - PartitionCols:_col0, _col1 - Select Operator [SEL_317] (rows=57591150 width=8) - Output:["_col0","_col1"] - TableScan [TS_12] (rows=57591150 width=8) - default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_67] - PartitionCols:_col0, _col3 - Merge Join Operator [MERGEJOIN_284] (rows=385681992 width=1029) - Conds:RS_64._col0=RS_291._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col8","_col10","_col11","_col12","_col14","_col15","_col16","_col17","_col18"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_291] - PartitionCols:_col0 - Select Operator [SEL_289] (rows=462000 width=384) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - TableScan [TS_3] (rows=462000 width=384) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"] - <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_64] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_283] (rows=385681992 width=648) - Conds:RS_61._col1=RS_316._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col8","_col10","_col11","_col12"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_316] - PartitionCols:_col0 - Select Operator [SEL_314] (rows=80000000 width=276) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_313] (rows=80000000 width=276) - predicate:c_birth_country is not null - TableScan [TS_9] (rows=80000000 width=276) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_first_name","c_last_name","c_birth_country"] - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_61] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_282] (rows=385681992 width=379) - Conds:RS_333._col2=RS_302._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col7","_col8"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_302] - PartitionCols:_col0 - Select Operator [SEL_299] (rows=155 width=267) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_298] (rows=155 width=271) - predicate:((s_market_id = 7) and s_zip is not null) - TableScan [TS_6] (rows=1704 width=270) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"] - <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_333] - PartitionCols:_col2 - Select Operator [SEL_332] (rows=525333486 width=122) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_331] (rows=525333486 width=122) - predicate:((ss_store_sk BETWEEN DynamicValue(RS_59_store_s_store_sk_min) AND DynamicValue(RS_59_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_59_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_store_sk is not null) - TableScan [TS_42] (rows=575995635 width=122) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_330] - Group By Operator [GBY_329] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_307] - Group By Operator [GBY_305] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_303] (rows=155 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_299] - <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_328] - Select Operator [SEL_327] (rows=235181232 width=380) - Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_326] (rows=235181232 width=380) - Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col9)"],keys:_col1, _col2, _col7 - Select Operator [SEL_325] (rows=365777643230 width=843) - Output:["_col1","_col2","_col7","_col9"] - Group By Operator [GBY_324] (rows=365777643230 width=843) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8 - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_34] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_33] (rows=365777643230 width=843) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col15, _col16, _col11, _col20, _col6, _col7, _col8, _col9, _col12 - Merge Join Operator [MERGEJOIN_281] (rows=365777643230 width=843) - Conds:RS_29._col13, _col17=RS_322._col1, _col2(Inner),Output:["_col4","_col6","_col7","_col8","_col9","_col11","_col12","_col15","_col16","_col20"] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_322] - PartitionCols:_col1, _col2 - Please refer to the previous Select Operator [SEL_321] - <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_29] - PartitionCols:_col13, _col17 - Merge Join Operator [MERGEJOIN_280] (rows=92733777 width=910) - Conds:RS_26._col0, _col3=RS_318._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_318] + Group By Operator [GBY_77] (rows=8029453 width=932) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col13)"],keys:_col2, _col3, _col6, _col15, _col16, _col19, _col20, _col21, _col22, _col23 + Merge Join Operator [MERGEJOIN_297] (rows=13238221 width=865) + Conds:RS_73._col9, _col12=RS_333._col0, _col1(Inner),Output:["_col2","_col3","_col6","_col13","_col15","_col16","_col19","_col20","_col21","_col22","_col23"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_333] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_317] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_26] - PartitionCols:_col0, _col3 - Merge Join Operator [MERGEJOIN_279] (rows=56246341 width=899) - Conds:RS_23._col1=RS_315._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_315] + Select Operator [SEL_331] (rows=57591150 width=8) + Output:["_col0","_col1"] + TableScan [TS_23] (rows=57591150 width=8) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_73] + PartitionCols:_col9, _col12 + Merge Join Operator [MERGEJOIN_296] (rows=8029453 width=828) + Conds:RS_70._col9=RS_302._col0(Inner),Output:["_col2","_col3","_col6","_col9","_col12","_col13","_col15","_col16","_col19","_col20","_col21","_col22","_col23"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_302] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_314] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_23] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_278] (rows=56246341 width=630) - Conds:RS_20._col2=RS_300._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col7","_col8","_col9","_col11","_col12","_col13"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_300] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_299] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_20] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_277] (rows=76612563 width=382) - Conds:RS_312._col0=RS_292._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_292] - PartitionCols:_col0 - Select Operator [SEL_290] (rows=7000 width=295) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_288] (rows=7000 width=384) - predicate:(i_color = 'orchid') - Please refer to the previous TableScan [TS_3] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_312] - PartitionCols:_col0 - Select Operator [SEL_311] (rows=525333486 width=122) + Select Operator [SEL_300] (rows=462000 width=384) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + TableScan [TS_3] (rows=462000 width=384) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_70] + PartitionCols:_col9 + Merge Join Operator [MERGEJOIN_295] (rows=8029453 width=448) + Conds:RS_67._col7, _col11=RS_316._col3, _col0(Inner),Output:["_col2","_col3","_col6","_col9","_col12","_col13","_col15","_col16"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_316] + PartitionCols:_col3, _col0 + Select Operator [SEL_314] (rows=155 width=267) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_313] (rows=155 width=271) + predicate:((s_market_id = 7) and s_zip is not null) + TableScan [TS_9] (rows=1704 width=270) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"] + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_67] + PartitionCols:_col7, _col11 + Merge Join Operator [MERGEJOIN_294] (rows=525333486 width=473) + Conds:RS_64._col0=RS_343._col1(Inner),Output:["_col2","_col3","_col6","_col7","_col9","_col11","_col12","_col13"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_343] + PartitionCols:_col1 + Select Operator [SEL_342] (rows=525333486 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_310] (rows=525333486 width=122) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_18_item_i_item_sk_min) AND DynamicValue(RS_18_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_18_item_i_item_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_21_store_s_store_sk_min) AND DynamicValue(RS_21_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_21_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=122) + Filter Operator [FIL_341] (rows=525333486 width=122) + predicate:((ss_store_sk BETWEEN DynamicValue(RS_68_store_s_store_sk_min) AND DynamicValue(RS_68_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_68_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_store_sk is not null) + TableScan [TS_50] (rows=575995635 width=122) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_297] - Group By Operator [GBY_296] (rows=1 width=12) + <-Reducer 22 [BROADCAST_EDGE] vectorized + BROADCAST [RS_340] + Group By Operator [GBY_339] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_295] - Group By Operator [GBY_294] (rows=1 width=12) + <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_319] + Group By Operator [GBY_318] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_293] (rows=7000 width=4) + Select Operator [SEL_317] (rows=155 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_290] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_309] - Group By Operator [GBY_308] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_306] - Group By Operator [GBY_304] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_301] (rows=155 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_299] + Please refer to the previous Select Operator [SEL_314] + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_64] + PartitionCols:_col0 + Filter Operator [FIL_63] (rows=80000000 width=635) + predicate:(_col4 <> _col8) + Merge Join Operator [MERGEJOIN_293] (rows=80000000 width=635) + Conds:RS_323._col1=RS_312._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col6","_col7","_col8"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_312] + PartitionCols:_col0 + Select Operator [SEL_310] (rows=40000000 width=363) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_309] (rows=40000000 width=276) + predicate:ca_zip is not null + TableScan [TS_6] (rows=40000000 width=276) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_zip","ca_country"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_323] + PartitionCols:_col1 + Select Operator [SEL_321] (rows=80000000 width=280) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_320] (rows=80000000 width=280) + predicate:c_current_addr_sk is not null + TableScan [TS_12] (rows=80000000 width=280) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name","c_birth_country"] + <-Reducer 5 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_338] + Select Operator [SEL_337] (rows=3939496 width=380) + Output:["_col0","_col1","_col2","_col3"] + Group By Operator [GBY_336] (rows=3939496 width=380) + Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col9)"],keys:_col4, _col5, _col7 + Select Operator [SEL_335] (rows=84010488 width=843) + Output:["_col4","_col5","_col7","_col9"] + Group By Operator [GBY_334] (rows=84010488 width=843) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8 + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_36] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_35] (rows=84010488 width=843) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col12, _col13, _col20, _col6, _col7, _col8, _col9, _col16, _col21 + Merge Join Operator [MERGEJOIN_292] (rows=138508741 width=824) + Conds:RS_31._col0, _col3=RS_332._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col8","_col9","_col12","_col13","_col16","_col20","_col21"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_332] + PartitionCols:_col0, _col1 + Please refer to the previous Select Operator [SEL_331] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_31] + PartitionCols:_col0, _col3 + Merge Join Operator [MERGEJOIN_291] (rows=84010488 width=820) + Conds:RS_28._col1, _col2=RS_29._col0, _col9(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col8","_col9","_col12","_col13","_col16","_col20","_col21"] + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_29] + PartitionCols:_col0, _col9 + Select Operator [SEL_22] (rows=7276996 width=724) + Output:["_col0","_col2","_col3","_col6","_col9","_col10","_col11"] + Filter Operator [FIL_21] (rows=7276996 width=724) + predicate:(_col12 <> _col3) + Merge Join Operator [MERGEJOIN_290] (rows=7276996 width=724) + Conds:RS_18._col0=RS_322._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col8","_col10","_col11","_col12"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_322] + PartitionCols:_col1 + Please refer to the previous Select Operator [SEL_321] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_289] (rows=611379 width=452) + Conds:RS_311._col2=RS_315._col3(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_315] + PartitionCols:_col3 + Please refer to the previous Select Operator [SEL_314] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_311] + PartitionCols:_col2 + Please refer to the previous Select Operator [SEL_310] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_28] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_288] (rows=76612563 width=382) + Conds:RS_330._col0=RS_303._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_303] + PartitionCols:_col0 + Select Operator [SEL_301] (rows=7000 width=295) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_299] (rows=7000 width=384) + predicate:(i_color = 'orchid') + Please refer to the previous TableScan [TS_3] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_330] + PartitionCols:_col0 + Select Operator [SEL_329] (rows=525333486 width=122) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_328] (rows=525333486 width=122) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_29_customer_c_customer_sk_min) AND DynamicValue(RS_29_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_29_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_26_item_i_item_sk_min) AND DynamicValue(RS_26_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_26_item_i_item_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_29_store_s_store_sk_min) AND DynamicValue(RS_29_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_29_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_325] + Group By Operator [GBY_324] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=6636187)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_149] + Group By Operator [GBY_148] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=6636187)"] + Select Operator [SEL_147] (rows=7276996 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_22] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_327] + Group By Operator [GBY_326] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_154] + Group By Operator [GBY_153] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_152] (rows=7276996 width=8) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_22] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_308] + Group By Operator [GBY_307] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_306] + Group By Operator [GBY_305] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_304] (rows=7000 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_301] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query33.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query33.q.out index c82c41575d..6d7c620dea 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query33.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query33.q.out @@ -194,57 +194,57 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_372] - Limit [LIM_371] (rows=59 width=115) + File Output Operator [FS_368] + Limit [LIM_367] (rows=59 width=115) Number of rows:100 - Select Operator [SEL_370] (rows=59 width=115) + Select Operator [SEL_366] (rows=59 width=115) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_369] - Group By Operator [GBY_368] (rows=59 width=115) + SHUFFLE [RS_365] + Group By Operator [GBY_364] (rows=59 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] <-Reducer 11 [CONTAINS] vectorized - Reduce Output Operator [RS_392] + Reduce Output Operator [RS_388] PartitionCols:_col0 - Group By Operator [GBY_391] (rows=59 width=115) + Group By Operator [GBY_387] (rows=59 width=115) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_390] (rows=19 width=115) + Group By Operator [GBY_386] (rows=19 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_109] PartitionCols:_col0 Group By Operator [GBY_108] (rows=19 width=115) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_308] (rows=11364 width=3) + Merge Join Operator [MERGEJOIN_304] (rows=11364 width=3) Conds:RS_104._col0=RS_105._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_104] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_297] (rows=461514 width=7) - Conds:RS_323._col1=RS_329._col0(Inner),Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_293] (rows=461514 width=7) + Conds:RS_319._col1=RS_325._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] + SHUFFLE [RS_319] PartitionCols:_col1 - Select Operator [SEL_322] (rows=460848 width=7) + Select Operator [SEL_318] (rows=460848 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_321] (rows=460848 width=7) + Filter Operator [FIL_317] (rows=460848 width=7) predicate:i_manufact_id is not null TableScan [TS_0] (rows=462000 width=7) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_manufact_id"] <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_329] + FORWARD [RS_325] PartitionCols:_col0 - Group By Operator [GBY_328] (rows=692 width=3) + Group By Operator [GBY_324] (rows=692 width=3) Output:["_col0"],keys:KEY._col0 <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_327] + SHUFFLE [RS_323] PartitionCols:_col0 - Group By Operator [GBY_326] (rows=692 width=3) + Group By Operator [GBY_322] (rows=692 width=3) Output:["_col0"],keys:i_manufact_id - Select Operator [SEL_325] (rows=46085 width=93) + Select Operator [SEL_321] (rows=46085 width=93) Output:["i_manufact_id"] - Filter Operator [FIL_324] (rows=46085 width=93) + Filter Operator [FIL_320] (rows=46085 width=93) predicate:((i_category = 'Books') and i_manufact_id is not null) TableScan [TS_3] (rows=462000 width=93) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_category","i_manufact_id"] @@ -253,198 +253,198 @@ Stage-0 PartitionCols:_col2 Select Operator [SEL_100] (rows=788222 width=110) Output:["_col2","_col4"] - Merge Join Operator [MERGEJOIN_305] (rows=788222 width=110) - Conds:RS_97._col2=RS_352._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_301] (rows=788222 width=110) + Conds:RS_97._col2=RS_348._col0(Inner),Output:["_col1","_col3"] <-Map 25 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_352] + PARTITION_ONLY_SHUFFLE [RS_348] PartitionCols:_col0 - Select Operator [SEL_347] (rows=8000000 width=4) + Select Operator [SEL_343] (rows=8000000 width=4) Output:["_col0"] - Filter Operator [FIL_346] (rows=8000000 width=112) + Filter Operator [FIL_342] (rows=8000000 width=112) predicate:(ca_gmt_offset = -6) TableScan [TS_16] (rows=40000000 width=112) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_97] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_304] (rows=3941109 width=118) - Conds:RS_389._col0=RS_336._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_300] (rows=3941109 width=118) + Conds:RS_385._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 17 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_336] + PARTITION_ONLY_SHUFFLE [RS_332] PartitionCols:_col0 - Select Operator [SEL_331] (rows=50 width=4) + Select Operator [SEL_327] (rows=50 width=4) Output:["_col0"] - Filter Operator [FIL_330] (rows=50 width=12) + Filter Operator [FIL_326] (rows=50 width=12) predicate:((d_moy = 3) and (d_year = 1999)) TableScan [TS_13] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 30 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_389] + SHUFFLE [RS_385] PartitionCols:_col0 - Select Operator [SEL_388] (rows=143931246 width=123) + Select Operator [SEL_384] (rows=143931246 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_387] (rows=143931246 width=123) + Filter Operator [FIL_383] (rows=143931246 width=123) predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_98_customer_address_ca_address_sk_min) AND DynamicValue(RS_98_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_98_customer_address_ca_address_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_95_date_dim_d_date_sk_min) AND DynamicValue(RS_95_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_95_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) TableScan [TS_85] (rows=144002668 width=123) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_384] - Group By Operator [GBY_383] (rows=1 width=12) + BROADCAST [RS_380] + Group By Operator [GBY_379] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_343] - Group By Operator [GBY_340] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_339] + Group By Operator [GBY_336] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_337] (rows=50 width=4) + Select Operator [SEL_333] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_331] + Please refer to the previous Select Operator [SEL_327] <-Reducer 28 [BROADCAST_EDGE] vectorized - BROADCAST [RS_386] - Group By Operator [GBY_385] (rows=1 width=12) + BROADCAST [RS_382] + Group By Operator [GBY_381] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_359] - Group By Operator [GBY_356] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_355] + Group By Operator [GBY_352] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_353] (rows=8000000 width=4) + Select Operator [SEL_349] (rows=8000000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_347] + Please refer to the previous Select Operator [SEL_343] <-Reducer 4 [CONTAINS] vectorized - Reduce Output Operator [RS_367] + Reduce Output Operator [RS_363] PartitionCols:_col0 - Group By Operator [GBY_366] (rows=59 width=115) + Group By Operator [GBY_362] (rows=59 width=115) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_365] (rows=64 width=115) + Group By Operator [GBY_361] (rows=64 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col0 Group By Operator [GBY_33] (rows=64 width=115) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_306] (rows=41476 width=3) + Merge Join Operator [MERGEJOIN_302] (rows=41476 width=3) Conds:RS_29._col0=RS_30._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_297] + Please refer to the previous Merge Join Operator [MERGEJOIN_293] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col2 Select Operator [SEL_25] (rows=2876890 width=4) Output:["_col2","_col4"] - Merge Join Operator [MERGEJOIN_299] (rows=2876890 width=4) - Conds:RS_22._col2=RS_348._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_295] (rows=2876890 width=4) + Conds:RS_22._col2=RS_344._col0(Inner),Output:["_col1","_col3"] <-Map 25 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_348] + PARTITION_ONLY_SHUFFLE [RS_344] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_347] + Please refer to the previous Select Operator [SEL_343] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_22] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_298] (rows=14384447 width=4) - Conds:RS_364._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_294] (rows=14384447 width=4) + Conds:RS_360._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 17 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_332] + PARTITION_ONLY_SHUFFLE [RS_328] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_331] + Please refer to the previous Select Operator [SEL_327] <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_364] + SHUFFLE [RS_360] PartitionCols:_col0 - Select Operator [SEL_363] (rows=525327191 width=118) + Select Operator [SEL_359] (rows=525327191 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_362] (rows=525327191 width=118) + Filter Operator [FIL_358] (rows=525327191 width=118) predicate:((ss_addr_sk BETWEEN DynamicValue(RS_23_customer_address_ca_address_sk_min) AND DynamicValue(RS_23_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_23_customer_address_ca_address_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) TableScan [TS_10] (rows=575995635 width=118) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_345] - Group By Operator [GBY_344] (rows=1 width=12) + BROADCAST [RS_341] + Group By Operator [GBY_340] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_341] - Group By Operator [GBY_338] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_337] + Group By Operator [GBY_334] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_333] (rows=50 width=4) + Select Operator [SEL_329] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_331] + Please refer to the previous Select Operator [SEL_327] <-Reducer 26 [BROADCAST_EDGE] vectorized - BROADCAST [RS_361] - Group By Operator [GBY_360] (rows=1 width=12) + BROADCAST [RS_357] + Group By Operator [GBY_356] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_357] - Group By Operator [GBY_354] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_353] + Group By Operator [GBY_350] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_349] (rows=8000000 width=4) + Select Operator [SEL_345] (rows=8000000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_347] + Please refer to the previous Select Operator [SEL_343] <-Reducer 9 [CONTAINS] vectorized - Reduce Output Operator [RS_382] + Reduce Output Operator [RS_378] PartitionCols:_col0 - Group By Operator [GBY_381] (rows=59 width=115) + Group By Operator [GBY_377] (rows=59 width=115) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_380] (rows=35 width=115) + Group By Operator [GBY_376] (rows=35 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_71] PartitionCols:_col0 Group By Operator [GBY_70] (rows=35 width=115) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_307] (rows=22352 width=3) + Merge Join Operator [MERGEJOIN_303] (rows=22352 width=3) Conds:RS_66._col0=RS_67._col3(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_297] + Please refer to the previous Merge Join Operator [MERGEJOIN_293] <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_67] PartitionCols:_col3 Select Operator [SEL_62] (rows=1550375 width=13) Output:["_col3","_col4"] - Merge Join Operator [MERGEJOIN_302] (rows=1550375 width=13) - Conds:RS_59._col1=RS_350._col0(Inner),Output:["_col2","_col3"] + Merge Join Operator [MERGEJOIN_298] (rows=1550375 width=13) + Conds:RS_59._col1=RS_346._col0(Inner),Output:["_col2","_col3"] <-Map 25 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_350] + PARTITION_ONLY_SHUFFLE [RS_346] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_347] + Please refer to the previous Select Operator [SEL_343] <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_59] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_301] (rows=7751872 width=98) - Conds:RS_379._col0=RS_334._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_297] (rows=7751872 width=98) + Conds:RS_375._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 17 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_334] + PARTITION_ONLY_SHUFFLE [RS_330] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_331] + Please refer to the previous Select Operator [SEL_327] <-Map 29 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_379] + SHUFFLE [RS_375] PartitionCols:_col0 - Select Operator [SEL_378] (rows=285117733 width=123) + Select Operator [SEL_374] (rows=285117733 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_377] (rows=285117733 width=123) + Filter Operator [FIL_373] (rows=285117733 width=123) predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_60_customer_address_ca_address_sk_min) AND DynamicValue(RS_60_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_60_customer_address_ca_address_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_57_date_dim_d_date_sk_min) AND DynamicValue(RS_57_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_57_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_sold_date_sk is not null) TableScan [TS_47] (rows=287989836 width=123) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_374] - Group By Operator [GBY_373] (rows=1 width=12) + BROADCAST [RS_370] + Group By Operator [GBY_369] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_342] - Group By Operator [GBY_339] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_338] + Group By Operator [GBY_335] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_335] (rows=50 width=4) + Select Operator [SEL_331] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_331] + Please refer to the previous Select Operator [SEL_327] <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_376] - Group By Operator [GBY_375] (rows=1 width=12) + BROADCAST [RS_372] + Group By Operator [GBY_371] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_358] - Group By Operator [GBY_355] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_354] + Group By Operator [GBY_351] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_351] (rows=8000000 width=4) + Select Operator [SEL_347] (rows=8000000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_347] + Please refer to the previous Select Operator [SEL_343] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query56.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query56.q.out index b57ded3f6b..cac7668b88 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query56.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query56.q.out @@ -183,55 +183,55 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_370] - Limit [LIM_369] (rows=100 width=212) + File Output Operator [FS_366] + Limit [LIM_365] (rows=100 width=212) Number of rows:100 - Select Operator [SEL_368] (rows=430 width=212) + Select Operator [SEL_364] (rows=430 width=212) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_367] - Group By Operator [GBY_366] (rows=430 width=212) + SHUFFLE [RS_363] + Group By Operator [GBY_362] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] <-Reducer 10 [CONTAINS] vectorized - Reduce Output Operator [RS_382] + Reduce Output Operator [RS_378] PartitionCols:_col0 - Group By Operator [GBY_381] (rows=430 width=212) + Group By Operator [GBY_377] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_380] (rows=430 width=212) + Group By Operator [GBY_376] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_69] PartitionCols:_col0 Group By Operator [GBY_68] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_304] (rows=373066 width=100) + Merge Join Operator [MERGEJOIN_300] (rows=373066 width=100) Conds:RS_64._col0=RS_65._col3(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_64] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_294] (rows=17170 width=104) - Conds:RS_319._col1=RS_325._col0(Inner),Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_290] (rows=17170 width=104) + Conds:RS_315._col1=RS_321._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_319] + SHUFFLE [RS_315] PartitionCols:_col1 - Select Operator [SEL_318] (rows=462000 width=104) + Select Operator [SEL_314] (rows=462000 width=104) Output:["_col0","_col1"] TableScan [TS_0] (rows=462000 width=104) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_325] + FORWARD [RS_321] PartitionCols:_col0 - Group By Operator [GBY_324] (rows=11550 width=100) + Group By Operator [GBY_320] (rows=11550 width=100) Output:["_col0"],keys:KEY._col0 <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] + SHUFFLE [RS_319] PartitionCols:_col0 - Group By Operator [GBY_322] (rows=11550 width=100) + Group By Operator [GBY_318] (rows=11550 width=100) Output:["_col0"],keys:i_item_id - Select Operator [SEL_321] (rows=23100 width=189) + Select Operator [SEL_317] (rows=23100 width=189) Output:["i_item_id"] - Filter Operator [FIL_320] (rows=23100 width=189) + Filter Operator [FIL_316] (rows=23100 width=189) predicate:(i_color) IN ('orchid', 'chiffon', 'lace') TableScan [TS_2] (rows=462000 width=189) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_id","i_color"] @@ -240,231 +240,231 @@ Stage-0 PartitionCols:_col3 Select Operator [SEL_60] (rows=1550375 width=13) Output:["_col3","_col4"] - Merge Join Operator [MERGEJOIN_299] (rows=1550375 width=13) - Conds:RS_57._col1=RS_346._col0(Inner),Output:["_col2","_col3"] + Merge Join Operator [MERGEJOIN_295] (rows=1550375 width=13) + Conds:RS_57._col1=RS_342._col0(Inner),Output:["_col2","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_346] + PARTITION_ONLY_SHUFFLE [RS_342] PartitionCols:_col0 - Select Operator [SEL_343] (rows=8000000 width=4) + Select Operator [SEL_339] (rows=8000000 width=4) Output:["_col0"] - Filter Operator [FIL_342] (rows=8000000 width=112) + Filter Operator [FIL_338] (rows=8000000 width=112) predicate:(ca_gmt_offset = -8) TableScan [TS_15] (rows=40000000 width=112) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_57] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_298] (rows=7751872 width=98) - Conds:RS_379._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_294] (rows=7751872 width=98) + Conds:RS_375._col0=RS_326._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_330] + PARTITION_ONLY_SHUFFLE [RS_326] PartitionCols:_col0 - Select Operator [SEL_327] (rows=50 width=4) + Select Operator [SEL_323] (rows=50 width=4) Output:["_col0"] - Filter Operator [FIL_326] (rows=50 width=12) + Filter Operator [FIL_322] (rows=50 width=12) predicate:((d_moy = 1) and (d_year = 2000)) TableScan [TS_12] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 32 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_379] + SHUFFLE [RS_375] PartitionCols:_col0 - Select Operator [SEL_378] (rows=285117733 width=123) + Select Operator [SEL_374] (rows=285117733 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_377] (rows=285117733 width=123) + Filter Operator [FIL_373] (rows=285117733 width=123) predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_58_customer_address_ca_address_sk_min) AND DynamicValue(RS_58_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_58_customer_address_ca_address_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_64_item_i_item_sk_min) AND DynamicValue(RS_64_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_64_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_55_date_dim_d_date_sk_min) AND DynamicValue(RS_55_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_55_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_sold_date_sk is not null) TableScan [TS_45] (rows=287989836 width=123) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_376] - Group By Operator [GBY_375] (rows=1 width=12) + BROADCAST [RS_372] + Group By Operator [GBY_371] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_239] - Group By Operator [GBY_238] (rows=1 width=12) + SHUFFLE [RS_237] + Group By Operator [GBY_236] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_237] (rows=17170 width=4) + Select Operator [SEL_235] (rows=17170 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_294] + Please refer to the previous Merge Join Operator [MERGEJOIN_290] <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_372] - Group By Operator [GBY_371] (rows=1 width=12) + BROADCAST [RS_368] + Group By Operator [GBY_367] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_338] - Group By Operator [GBY_335] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_334] + Group By Operator [GBY_331] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_331] (rows=50 width=4) + Select Operator [SEL_327] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_327] + Please refer to the previous Select Operator [SEL_323] <-Reducer 30 [BROADCAST_EDGE] vectorized - BROADCAST [RS_374] - Group By Operator [GBY_373] (rows=1 width=12) + BROADCAST [RS_370] + Group By Operator [GBY_369] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_354] - Group By Operator [GBY_351] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_350] + Group By Operator [GBY_347] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_347] (rows=8000000 width=4) + Select Operator [SEL_343] (rows=8000000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_343] + Please refer to the previous Select Operator [SEL_339] <-Reducer 13 [CONTAINS] vectorized - Reduce Output Operator [RS_394] + Reduce Output Operator [RS_390] PartitionCols:_col0 - Group By Operator [GBY_393] (rows=430 width=212) + Group By Operator [GBY_389] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_392] (rows=430 width=212) + Group By Operator [GBY_388] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_106] PartitionCols:_col0 Group By Operator [GBY_105] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_305] (rows=189670 width=190) + Merge Join Operator [MERGEJOIN_301] (rows=189670 width=190) Conds:RS_101._col0=RS_102._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_101] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_294] + Please refer to the previous Merge Join Operator [MERGEJOIN_290] <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_102] PartitionCols:_col2 Select Operator [SEL_97] (rows=788222 width=110) Output:["_col2","_col4"] - Merge Join Operator [MERGEJOIN_302] (rows=788222 width=110) - Conds:RS_94._col2=RS_348._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_298] (rows=788222 width=110) + Conds:RS_94._col2=RS_344._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_348] + PARTITION_ONLY_SHUFFLE [RS_344] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_343] + Please refer to the previous Select Operator [SEL_339] <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_94] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_301] (rows=3941109 width=118) - Conds:RS_391._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_297] (rows=3941109 width=118) + Conds:RS_387._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_332] + PARTITION_ONLY_SHUFFLE [RS_328] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_327] + Please refer to the previous Select Operator [SEL_323] <-Map 33 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_391] + SHUFFLE [RS_387] PartitionCols:_col0 - Select Operator [SEL_390] (rows=143931246 width=123) + Select Operator [SEL_386] (rows=143931246 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_389] (rows=143931246 width=123) + Filter Operator [FIL_385] (rows=143931246 width=123) predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_95_customer_address_ca_address_sk_min) AND DynamicValue(RS_95_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_95_customer_address_ca_address_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_101_item_i_item_sk_min) AND DynamicValue(RS_101_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_101_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_92_date_dim_d_date_sk_min) AND DynamicValue(RS_92_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_92_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) TableScan [TS_82] (rows=144002668 width=123) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_388] - Group By Operator [GBY_387] (rows=1 width=12) + BROADCAST [RS_384] + Group By Operator [GBY_383] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_285] - Group By Operator [GBY_284] (rows=1 width=12) + SHUFFLE [RS_277] + Group By Operator [GBY_276] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_283] (rows=17170 width=4) + Select Operator [SEL_275] (rows=17170 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_294] + Please refer to the previous Merge Join Operator [MERGEJOIN_290] <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_384] - Group By Operator [GBY_383] (rows=1 width=12) + BROADCAST [RS_380] + Group By Operator [GBY_379] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_339] - Group By Operator [GBY_336] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_335] + Group By Operator [GBY_332] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_333] (rows=50 width=4) + Select Operator [SEL_329] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_327] + Please refer to the previous Select Operator [SEL_323] <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_386] - Group By Operator [GBY_385] (rows=1 width=12) + BROADCAST [RS_382] + Group By Operator [GBY_381] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_355] - Group By Operator [GBY_352] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_351] + Group By Operator [GBY_348] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_349] (rows=8000000 width=4) + Select Operator [SEL_345] (rows=8000000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_343] + Please refer to the previous Select Operator [SEL_339] <-Reducer 4 [CONTAINS] vectorized - Reduce Output Operator [RS_365] + Reduce Output Operator [RS_361] PartitionCols:_col0 - Group By Operator [GBY_364] (rows=430 width=212) + Group By Operator [GBY_360] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_363] (rows=430 width=212) + Group By Operator [GBY_359] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_33] PartitionCols:_col0 Group By Operator [GBY_32] (rows=430 width=212) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_303] (rows=692265 width=100) + Merge Join Operator [MERGEJOIN_299] (rows=692265 width=100) Conds:RS_28._col0=RS_29._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_28] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_294] + Please refer to the previous Merge Join Operator [MERGEJOIN_290] <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col2 Select Operator [SEL_24] (rows=2876890 width=4) Output:["_col2","_col4"] - Merge Join Operator [MERGEJOIN_296] (rows=2876890 width=4) - Conds:RS_21._col2=RS_344._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_292] (rows=2876890 width=4) + Conds:RS_21._col2=RS_340._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_344] + PARTITION_ONLY_SHUFFLE [RS_340] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_343] + Please refer to the previous Select Operator [SEL_339] <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_295] (rows=14384447 width=4) - Conds:RS_362._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_291] (rows=14384447 width=4) + Conds:RS_358._col0=RS_324._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_328] + PARTITION_ONLY_SHUFFLE [RS_324] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_327] + Please refer to the previous Select Operator [SEL_323] <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_362] + SHUFFLE [RS_358] PartitionCols:_col0 - Select Operator [SEL_361] (rows=525327191 width=118) + Select Operator [SEL_357] (rows=525327191 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_360] (rows=525327191 width=118) + Filter Operator [FIL_356] (rows=525327191 width=118) predicate:((ss_addr_sk BETWEEN DynamicValue(RS_22_customer_address_ca_address_sk_min) AND DynamicValue(RS_22_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_22_customer_address_ca_address_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_28_item_i_item_sk_min) AND DynamicValue(RS_28_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_28_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) TableScan [TS_9] (rows=575995635 width=118) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_341] - Group By Operator [GBY_340] (rows=1 width=12) + BROADCAST [RS_337] + Group By Operator [GBY_336] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_337] - Group By Operator [GBY_334] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_333] + Group By Operator [GBY_330] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_329] (rows=50 width=4) + Select Operator [SEL_325] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_327] + Please refer to the previous Select Operator [SEL_323] <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_357] - Group By Operator [GBY_356] (rows=1 width=12) + BROADCAST [RS_353] + Group By Operator [GBY_352] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_353] - Group By Operator [GBY_350] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_349] + Group By Operator [GBY_346] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_345] (rows=8000000 width=4) + Select Operator [SEL_341] (rows=8000000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_343] + Please refer to the previous Select Operator [SEL_339] <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_359] - Group By Operator [GBY_358] (rows=1 width=12) + BROADCAST [RS_355] + Group By Operator [GBY_354] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_203] - Group By Operator [GBY_202] (rows=1 width=12) + SHUFFLE [RS_197] + Group By Operator [GBY_196] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_201] (rows=17170 width=4) + Select Operator [SEL_195] (rows=17170 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_294] + Please refer to the previous Merge Join Operator [MERGEJOIN_290] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query6.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query6.q.out index 85c962f7c2..74bec5cf17 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query6.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query6.q.out @@ -1,4 +1,4 @@ -Warning: Map Join MAPJOIN[172][bigTable=?] in task 'Reducer 15' is a cross product +Warning: Map Join MAPJOIN[170][bigTable=?] in task 'Reducer 15' is a cross product PREHOOK: query: explain select a.ca_state state, count(*) cnt from customer_address a @@ -83,153 +83,153 @@ Stage-0 limit:100 Stage-1 Reducer 10 vectorized - File Output Operator [FS_234] - Limit [LIM_233] (rows=1 width=94) + File Output Operator [FS_232] + Limit [LIM_231] (rows=1 width=94) Number of rows:100 - Select Operator [SEL_232] (rows=1 width=94) + Select Operator [SEL_230] (rows=1 width=94) Output:["_col0","_col1"] <-Reducer 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_231] - Filter Operator [FIL_230] (rows=1 width=94) + SHUFFLE [RS_229] + Filter Operator [FIL_228] (rows=1 width=94) predicate:(_col1 >= 10L) - Group By Operator [GBY_229] (rows=1 width=94) + Group By Operator [GBY_227] (rows=1 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_68] PartitionCols:_col0 Group By Operator [GBY_67] (rows=1 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col9 - Merge Join Operator [MERGEJOIN_175] (rows=316 width=86) - Conds:RS_63._col4=RS_214._col0(Inner),Output:["_col9"] + Merge Join Operator [MERGEJOIN_173] (rows=316 width=86) + Conds:RS_63._col4=RS_212._col0(Inner),Output:["_col9"] <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_214] + SHUFFLE [RS_212] PartitionCols:_col0 - Select Operator [SEL_213] (rows=154000 width=227) + Select Operator [SEL_211] (rows=154000 width=227) Output:["_col0"] - Filter Operator [FIL_212] (rows=154000 width=227) + Filter Operator [FIL_210] (rows=154000 width=227) predicate:(_col4 > _col1) - Map Join Operator [MAPJOIN_211] (rows=462000 width=227) - Conds:RS_208._col0=SEL_210._col2(Inner),HybridGraceHashJoin:true,Output:["_col1","_col3","_col4"] + Map Join Operator [MAPJOIN_209] (rows=462000 width=227) + Conds:RS_206._col0=SEL_208._col2(Inner),HybridGraceHashJoin:true,Output:["_col1","_col3","_col4"] <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_208] + BROADCAST [RS_206] PartitionCols:_col0 - Map Join Operator [MAPJOIN_207] (rows=10 width=202) + Map Join Operator [MAPJOIN_205] (rows=10 width=202) Conds:(Inner),Output:["_col0","_col1"] <-Reducer 5 [BROADCAST_EDGE] vectorized - BROADCAST [RS_204] - Select Operator [SEL_203] (rows=1 width=8) - Filter Operator [FIL_202] (rows=1 width=8) + BROADCAST [RS_202] + Select Operator [SEL_201] (rows=1 width=8) + Filter Operator [FIL_200] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_201] (rows=1 width=8) + Group By Operator [GBY_199] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_200] - Group By Operator [GBY_199] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_198] + Group By Operator [GBY_197] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_198] (rows=25 width=4) - Group By Operator [GBY_197] (rows=25 width=4) + Select Operator [SEL_196] (rows=25 width=4) + Group By Operator [GBY_195] (rows=25 width=4) Output:["_col0"],keys:KEY._col0 <-Map 2 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_187] + SHUFFLE [RS_185] PartitionCols:_col0 - Group By Operator [GBY_185] (rows=25 width=4) + Group By Operator [GBY_183] (rows=25 width=4) Output:["_col0"],keys:d_month_seq - Select Operator [SEL_183] (rows=50 width=12) + Select Operator [SEL_181] (rows=50 width=12) Output:["d_month_seq"] - Filter Operator [FIL_181] (rows=50 width=12) + Filter Operator [FIL_179] (rows=50 width=12) predicate:((d_moy = 2) and (d_year = 2000)) TableScan [TS_3] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_month_seq","d_year","d_moy"] - <-Select Operator [SEL_206] (rows=10 width=202) + <-Select Operator [SEL_204] (rows=10 width=202) Output:["_col0","_col1"] - Group By Operator [GBY_205] (rows=10 width=210) + Group By Operator [GBY_203] (rows=10 width=210) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_196] + SHUFFLE [RS_194] PartitionCols:_col0 - Group By Operator [GBY_195] (rows=10 width=210) + Group By Operator [GBY_193] (rows=10 width=210) Output:["_col0","_col1","_col2"],aggregations:["sum(i_current_price)","count(i_current_price)"],keys:i_category - Filter Operator [FIL_194] (rows=462000 width=201) + Filter Operator [FIL_192] (rows=462000 width=201) predicate:i_category is not null TableScan [TS_22] (rows=462000 width=201) default@item,j,Tbl:COMPLETE,Col:COMPLETE,Output:["i_current_price","i_category"] - <-Select Operator [SEL_210] (rows=462000 width=205) + <-Select Operator [SEL_208] (rows=462000 width=205) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_209] (rows=462000 width=205) + Filter Operator [FIL_207] (rows=462000 width=205) predicate:i_category is not null TableScan [TS_43] (rows=462000 width=205) default@item,i,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_category"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_174] (rows=7192227 width=90) - Conds:RS_223._col5=RS_61._col0(Inner),Output:["_col4","_col9"] + Merge Join Operator [MERGEJOIN_172] (rows=7192227 width=90) + Conds:RS_221._col5=RS_61._col0(Inner),Output:["_col4","_col9"] <-Map 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_223] + SHUFFLE [RS_221] PartitionCols:_col5 - Map Join Operator [MAPJOIN_222] (rows=7192227 width=4) - Conds:RS_193._col0=SEL_221._col0(Inner),HybridGraceHashJoin:true,Output:["_col4","_col5"] + Map Join Operator [MAPJOIN_220] (rows=7192227 width=4) + Conds:RS_191._col0=SEL_219._col0(Inner),HybridGraceHashJoin:true,Output:["_col4","_col5"] <-Map 1 [BROADCAST_EDGE] vectorized - BROADCAST [RS_193] + BROADCAST [RS_191] PartitionCols:_col0 - Map Join Operator [MAPJOIN_192] (rows=660 width=4) - Conds:SEL_191._col1=RS_189._col0(Inner),HybridGraceHashJoin:true,Output:["_col0"] + Map Join Operator [MAPJOIN_190] (rows=660 width=4) + Conds:SEL_189._col1=RS_187._col0(Inner),HybridGraceHashJoin:true,Output:["_col0"] <-Reducer 3 [BROADCAST_EDGE] vectorized - BROADCAST [RS_189] + BROADCAST [RS_187] PartitionCols:_col0 - Group By Operator [GBY_188] (rows=25 width=4) + Group By Operator [GBY_186] (rows=25 width=4) Output:["_col0"],keys:KEY._col0 <-Map 2 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_186] + SHUFFLE [RS_184] PartitionCols:_col0 - Group By Operator [GBY_184] (rows=25 width=4) + Group By Operator [GBY_182] (rows=25 width=4) Output:["_col0"],keys:d_month_seq - Select Operator [SEL_182] (rows=50 width=12) + Select Operator [SEL_180] (rows=50 width=12) Output:["d_month_seq"] - Filter Operator [FIL_180] (rows=50 width=12) + Filter Operator [FIL_178] (rows=50 width=12) predicate:((d_moy = 2) and (d_year = 2000) and d_month_seq is not null) Please refer to the previous TableScan [TS_3] - <-Select Operator [SEL_191] (rows=73049 width=8) + <-Select Operator [SEL_189] (rows=73049 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_190] (rows=73049 width=8) + Filter Operator [FIL_188] (rows=73049 width=8) predicate:d_month_seq is not null TableScan [TS_0] (rows=73049 width=8) default@date_dim,d,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] - <-Select Operator [SEL_221] (rows=525327388 width=11) + <-Select Operator [SEL_219] (rows=525327388 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_220] (rows=525327388 width=11) + Filter Operator [FIL_218] (rows=525327388 width=11) predicate:((ss_item_sk BETWEEN DynamicValue(RS_64_i_i_item_sk_min) AND DynamicValue(RS_64_i_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_64_i_i_item_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) TableScan [TS_10] (rows=575995635 width=11) default@store_sales,s,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_219] - Group By Operator [GBY_218] (rows=1 width=12) + BROADCAST [RS_217] + Group By Operator [GBY_216] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_217] - Group By Operator [GBY_216] (rows=1 width=12) + SHUFFLE [RS_215] + Group By Operator [GBY_214] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_215] (rows=154000 width=4) + Select Operator [SEL_213] (rows=154000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_213] + Please refer to the previous Select Operator [SEL_211] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_61] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_171] (rows=80000000 width=90) - Conds:RS_226._col1=RS_228._col0(Inner),Output:["_col0","_col3"] + Merge Join Operator [MERGEJOIN_169] (rows=80000000 width=90) + Conds:RS_224._col1=RS_226._col0(Inner),Output:["_col0","_col3"] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_226] + SHUFFLE [RS_224] PartitionCols:_col1 - Select Operator [SEL_225] (rows=80000000 width=8) + Select Operator [SEL_223] (rows=80000000 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_224] (rows=80000000 width=8) + Filter Operator [FIL_222] (rows=80000000 width=8) predicate:c_current_addr_sk is not null TableScan [TS_13] (rows=80000000 width=8) default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_228] + SHUFFLE [RS_226] PartitionCols:_col0 - Select Operator [SEL_227] (rows=40000000 width=90) + Select Operator [SEL_225] (rows=40000000 width=90) Output:["_col0","_col1"] TableScan [TS_16] (rows=40000000 width=90) default@customer_address,a,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query60.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query60.q.out index cb94e4fddf..5ba912a105 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query60.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query60.q.out @@ -203,57 +203,57 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_375] - Limit [LIM_374] (rows=100 width=212) + File Output Operator [FS_371] + Limit [LIM_370] (rows=100 width=212) Number of rows:100 - Select Operator [SEL_373] (rows=1717 width=212) + Select Operator [SEL_369] (rows=1717 width=212) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_372] - Group By Operator [GBY_371] (rows=1717 width=212) + SHUFFLE [RS_368] + Group By Operator [GBY_367] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] <-Reducer 10 [CONTAINS] vectorized - Reduce Output Operator [RS_388] + Reduce Output Operator [RS_384] PartitionCols:_col0 - Group By Operator [GBY_387] (rows=1717 width=212) + Group By Operator [GBY_383] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Top N Key Operator [TNK_386] (rows=5151 width=212) + Top N Key Operator [TNK_382] (rows=5151 width=212) keys:_col0,sort order:+,top n:100 - Group By Operator [GBY_385] (rows=1717 width=212) + Group By Operator [GBY_381] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_69] PartitionCols:_col0 Group By Operator [GBY_68] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_305] (rows=746132 width=100) + Merge Join Operator [MERGEJOIN_301] (rows=746132 width=100) Conds:RS_64._col0=RS_65._col3(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_64] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_295] (rows=34340 width=104) - Conds:RS_323._col1=RS_329._col0(Inner),Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_291] (rows=34340 width=104) + Conds:RS_319._col1=RS_325._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] + SHUFFLE [RS_319] PartitionCols:_col1 - Select Operator [SEL_322] (rows=462000 width=104) + Select Operator [SEL_318] (rows=462000 width=104) Output:["_col0","_col1"] TableScan [TS_0] (rows=462000 width=104) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_329] + FORWARD [RS_325] PartitionCols:_col0 - Group By Operator [GBY_328] (rows=23100 width=100) + Group By Operator [GBY_324] (rows=23100 width=100) Output:["_col0"],keys:KEY._col0 <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_327] + SHUFFLE [RS_323] PartitionCols:_col0 - Group By Operator [GBY_326] (rows=23100 width=100) + Group By Operator [GBY_322] (rows=23100 width=100) Output:["_col0"],keys:i_item_id - Select Operator [SEL_325] (rows=46200 width=190) + Select Operator [SEL_321] (rows=46200 width=190) Output:["i_item_id"] - Filter Operator [FIL_324] (rows=46200 width=190) + Filter Operator [FIL_320] (rows=46200 width=190) predicate:(i_category = 'Children') TableScan [TS_2] (rows=462000 width=190) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_id","i_category"] @@ -262,235 +262,235 @@ Stage-0 PartitionCols:_col3 Select Operator [SEL_60] (rows=1550375 width=13) Output:["_col3","_col4"] - Merge Join Operator [MERGEJOIN_300] (rows=1550375 width=13) - Conds:RS_57._col1=RS_350._col0(Inner),Output:["_col2","_col3"] + Merge Join Operator [MERGEJOIN_296] (rows=1550375 width=13) + Conds:RS_57._col1=RS_346._col0(Inner),Output:["_col2","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_350] + PARTITION_ONLY_SHUFFLE [RS_346] PartitionCols:_col0 - Select Operator [SEL_347] (rows=8000000 width=4) + Select Operator [SEL_343] (rows=8000000 width=4) Output:["_col0"] - Filter Operator [FIL_346] (rows=8000000 width=112) + Filter Operator [FIL_342] (rows=8000000 width=112) predicate:(ca_gmt_offset = -6) TableScan [TS_15] (rows=40000000 width=112) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] <-Reducer 22 [SIMPLE_EDGE] SHUFFLE [RS_57] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_299] (rows=7751872 width=98) - Conds:RS_384._col0=RS_334._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_295] (rows=7751872 width=98) + Conds:RS_380._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_334] + PARTITION_ONLY_SHUFFLE [RS_330] PartitionCols:_col0 - Select Operator [SEL_331] (rows=50 width=4) + Select Operator [SEL_327] (rows=50 width=4) Output:["_col0"] - Filter Operator [FIL_330] (rows=50 width=12) + Filter Operator [FIL_326] (rows=50 width=12) predicate:((d_moy = 9) and (d_year = 1999)) TableScan [TS_12] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 32 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_384] + SHUFFLE [RS_380] PartitionCols:_col0 - Select Operator [SEL_383] (rows=285117733 width=123) + Select Operator [SEL_379] (rows=285117733 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_382] (rows=285117733 width=123) + Filter Operator [FIL_378] (rows=285117733 width=123) predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_58_customer_address_ca_address_sk_min) AND DynamicValue(RS_58_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_58_customer_address_ca_address_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_64_item_i_item_sk_min) AND DynamicValue(RS_64_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_64_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_55_date_dim_d_date_sk_min) AND DynamicValue(RS_55_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_55_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_sold_date_sk is not null) TableScan [TS_45] (rows=287989836 width=123) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_381] - Group By Operator [GBY_380] (rows=1 width=12) + BROADCAST [RS_377] + Group By Operator [GBY_376] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_240] - Group By Operator [GBY_239] (rows=1 width=12) + SHUFFLE [RS_238] + Group By Operator [GBY_237] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_238] (rows=34340 width=4) + Select Operator [SEL_236] (rows=34340 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_295] + Please refer to the previous Merge Join Operator [MERGEJOIN_291] <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_377] - Group By Operator [GBY_376] (rows=1 width=12) + BROADCAST [RS_373] + Group By Operator [GBY_372] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_342] - Group By Operator [GBY_339] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_338] + Group By Operator [GBY_335] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_335] (rows=50 width=4) + Select Operator [SEL_331] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_331] + Please refer to the previous Select Operator [SEL_327] <-Reducer 30 [BROADCAST_EDGE] vectorized - BROADCAST [RS_379] - Group By Operator [GBY_378] (rows=1 width=12) + BROADCAST [RS_375] + Group By Operator [GBY_374] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_358] - Group By Operator [GBY_355] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_354] + Group By Operator [GBY_351] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_351] (rows=8000000 width=4) + Select Operator [SEL_347] (rows=8000000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_347] + Please refer to the previous Select Operator [SEL_343] <-Reducer 13 [CONTAINS] vectorized - Reduce Output Operator [RS_401] + Reduce Output Operator [RS_397] PartitionCols:_col0 - Group By Operator [GBY_400] (rows=1717 width=212) + Group By Operator [GBY_396] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Top N Key Operator [TNK_399] (rows=5151 width=212) + Top N Key Operator [TNK_395] (rows=5151 width=212) keys:_col0,sort order:+,top n:100 - Group By Operator [GBY_398] (rows=1717 width=212) + Group By Operator [GBY_394] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_106] PartitionCols:_col0 Group By Operator [GBY_105] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_306] (rows=379339 width=201) + Merge Join Operator [MERGEJOIN_302] (rows=379339 width=201) Conds:RS_101._col0=RS_102._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_101] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_295] + Please refer to the previous Merge Join Operator [MERGEJOIN_291] <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_102] PartitionCols:_col2 Select Operator [SEL_97] (rows=788222 width=110) Output:["_col2","_col4"] - Merge Join Operator [MERGEJOIN_303] (rows=788222 width=110) - Conds:RS_94._col2=RS_352._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_299] (rows=788222 width=110) + Conds:RS_94._col2=RS_348._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_352] + PARTITION_ONLY_SHUFFLE [RS_348] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_347] + Please refer to the previous Select Operator [SEL_343] <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_94] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_302] (rows=3941109 width=118) - Conds:RS_397._col0=RS_336._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_298] (rows=3941109 width=118) + Conds:RS_393._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_336] + PARTITION_ONLY_SHUFFLE [RS_332] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_331] + Please refer to the previous Select Operator [SEL_327] <-Map 33 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_397] + SHUFFLE [RS_393] PartitionCols:_col0 - Select Operator [SEL_396] (rows=143931246 width=123) + Select Operator [SEL_392] (rows=143931246 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_395] (rows=143931246 width=123) + Filter Operator [FIL_391] (rows=143931246 width=123) predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_95_customer_address_ca_address_sk_min) AND DynamicValue(RS_95_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_95_customer_address_ca_address_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_101_item_i_item_sk_min) AND DynamicValue(RS_101_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_101_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_92_date_dim_d_date_sk_min) AND DynamicValue(RS_92_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_92_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) TableScan [TS_82] (rows=144002668 width=123) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_394] - Group By Operator [GBY_393] (rows=1 width=12) + BROADCAST [RS_390] + Group By Operator [GBY_389] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_286] - Group By Operator [GBY_285] (rows=1 width=12) + SHUFFLE [RS_278] + Group By Operator [GBY_277] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_284] (rows=34340 width=4) + Select Operator [SEL_276] (rows=34340 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_295] + Please refer to the previous Merge Join Operator [MERGEJOIN_291] <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_390] - Group By Operator [GBY_389] (rows=1 width=12) + BROADCAST [RS_386] + Group By Operator [GBY_385] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_343] - Group By Operator [GBY_340] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_339] + Group By Operator [GBY_336] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_337] (rows=50 width=4) + Select Operator [SEL_333] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_331] + Please refer to the previous Select Operator [SEL_327] <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_392] - Group By Operator [GBY_391] (rows=1 width=12) + BROADCAST [RS_388] + Group By Operator [GBY_387] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_359] - Group By Operator [GBY_356] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_355] + Group By Operator [GBY_352] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_353] (rows=8000000 width=4) + Select Operator [SEL_349] (rows=8000000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_347] + Please refer to the previous Select Operator [SEL_343] <-Reducer 4 [CONTAINS] vectorized - Reduce Output Operator [RS_370] + Reduce Output Operator [RS_366] PartitionCols:_col0 - Group By Operator [GBY_369] (rows=1717 width=212) + Group By Operator [GBY_365] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Top N Key Operator [TNK_368] (rows=5151 width=212) + Top N Key Operator [TNK_364] (rows=5151 width=212) keys:_col0,sort order:+,top n:100 - Group By Operator [GBY_367] (rows=1717 width=212) + Group By Operator [GBY_363] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_33] PartitionCols:_col0 Group By Operator [GBY_32] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_304] (rows=1384530 width=100) + Merge Join Operator [MERGEJOIN_300] (rows=1384530 width=100) Conds:RS_28._col0=RS_29._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_28] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_295] + Please refer to the previous Merge Join Operator [MERGEJOIN_291] <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col2 Select Operator [SEL_24] (rows=2876890 width=4) Output:["_col2","_col4"] - Merge Join Operator [MERGEJOIN_297] (rows=2876890 width=4) - Conds:RS_21._col2=RS_348._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_293] (rows=2876890 width=4) + Conds:RS_21._col2=RS_344._col0(Inner),Output:["_col1","_col3"] <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_348] + PARTITION_ONLY_SHUFFLE [RS_344] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_347] + Please refer to the previous Select Operator [SEL_343] <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_296] (rows=14384447 width=4) - Conds:RS_366._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_292] (rows=14384447 width=4) + Conds:RS_362._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_332] + PARTITION_ONLY_SHUFFLE [RS_328] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_331] + Please refer to the previous Select Operator [SEL_327] <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_366] + SHUFFLE [RS_362] PartitionCols:_col0 - Select Operator [SEL_365] (rows=525327191 width=118) + Select Operator [SEL_361] (rows=525327191 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_364] (rows=525327191 width=118) + Filter Operator [FIL_360] (rows=525327191 width=118) predicate:((ss_addr_sk BETWEEN DynamicValue(RS_22_customer_address_ca_address_sk_min) AND DynamicValue(RS_22_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_22_customer_address_ca_address_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_28_item_i_item_sk_min) AND DynamicValue(RS_28_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_28_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) TableScan [TS_9] (rows=575995635 width=118) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] <-Reducer 21 [BROADCAST_EDGE] vectorized - BROADCAST [RS_345] - Group By Operator [GBY_344] (rows=1 width=12) + BROADCAST [RS_341] + Group By Operator [GBY_340] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_341] - Group By Operator [GBY_338] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_337] + Group By Operator [GBY_334] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_333] (rows=50 width=4) + Select Operator [SEL_329] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_331] + Please refer to the previous Select Operator [SEL_327] <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_361] - Group By Operator [GBY_360] (rows=1 width=12) + BROADCAST [RS_357] + Group By Operator [GBY_356] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_357] - Group By Operator [GBY_354] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_353] + Group By Operator [GBY_350] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_349] (rows=8000000 width=4) + Select Operator [SEL_345] (rows=8000000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_347] + Please refer to the previous Select Operator [SEL_343] <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_363] - Group By Operator [GBY_362] (rows=1 width=12) + BROADCAST [RS_359] + Group By Operator [GBY_358] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_204] - Group By Operator [GBY_203] (rows=1 width=12) + SHUFFLE [RS_198] + Group By Operator [GBY_197] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_202] (rows=34340 width=4) + Select Operator [SEL_196] (rows=34340 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_295] + Please refer to the previous Merge Join Operator [MERGEJOIN_291] diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query95.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query95.q.out index c286c74e4a..fd709f99dd 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query95.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query95.q.out @@ -98,37 +98,37 @@ Stage-0 limit:-1 Stage-1 Reducer 9 vectorized - File Output Operator [FS_265] - Limit [LIM_264] (rows=1 width=240) + File Output Operator [FS_273] + Limit [LIM_272] (rows=1 width=240) Number of rows:100 - Select Operator [SEL_263] (rows=1 width=240) + Select Operator [SEL_271] (rows=1 width=240) Output:["_col0","_col1","_col2"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_262] - Select Operator [SEL_261] (rows=1 width=240) + SHUFFLE [RS_270] + Select Operator [SEL_269] (rows=1 width=240) Output:["_col1","_col2","_col3"] - Group By Operator [GBY_260] (rows=1 width=232) + Group By Operator [GBY_268] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_259] - Group By Operator [GBY_258] (rows=1 width=232) + PARTITION_ONLY_SHUFFLE [RS_267] + Group By Operator [GBY_266] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(_col0)","sum(_col1)","sum(_col2)"] - Group By Operator [GBY_257] (rows=143895019 width=228) + Group By Operator [GBY_265] (rows=143895019 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_101] PartitionCols:_col0 Group By Operator [GBY_100] (rows=143895019 width=228) Output:["_col0","_col2","_col3"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col3 - Merge Join Operator [MERGEJOIN_219] (rows=83469759007 width=227) + Merge Join Operator [MERGEJOIN_227] (rows=83469759007 width=227) Conds:RS_47._col3=RS_48._col0(Inner),Output:["_col3","_col4","_col5"] <-Reducer 19 [ONE_TO_ONE_EDGE] FORWARD [RS_48] PartitionCols:_col0 Select Operator [SEL_34] (rows=1384229738 width=4) Output:["_col0"] - Merge Join Operator [MERGEJOIN_213] (rows=1384229738 width=4) - Conds:RS_31._col0=RS_256.wr_order_number(Inner),Output:["_col14"] + Merge Join Operator [MERGEJOIN_221] (rows=1384229738 width=4) + Conds:RS_31._col0=RS_264.wr_order_number(Inner),Output:["_col14"] <-Reducer 18 [ONE_TO_ONE_EDGE] FORWARD [RS_31] PartitionCols:_col0 @@ -136,129 +136,129 @@ Stage-0 Output:["_col0"] Filter Operator [FIL_28] (rows=1411940834 width=11) predicate:(_col0 <> _col2) - Merge Join Operator [MERGEJOIN_212] (rows=1411940834 width=11) - Conds:RS_252._col1=RS_255._col1(Inner),Output:["_col0","_col1","_col2"] + Merge Join Operator [MERGEJOIN_220] (rows=1411940834 width=11) + Conds:RS_260._col1=RS_263._col1(Inner),Output:["_col0","_col1","_col2"] <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_252] + SHUFFLE [RS_260] PartitionCols:_col1 - Select Operator [SEL_251] (rows=144002668 width=7) + Select Operator [SEL_259] (rows=144002668 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_250] (rows=144002668 width=7) + Filter Operator [FIL_258] (rows=144002668 width=7) predicate:(in_bloom_filter(ws_order_number, DynamicValue(RS_44_ws1_ws_order_number_bloom_filter)) and ws_order_number BETWEEN DynamicValue(RS_44_ws1_ws_order_number_min) AND DynamicValue(RS_44_ws1_ws_order_number_max)) TableScan [TS_21] (rows=144002668 width=7) default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_248] - Group By Operator [GBY_247] (rows=1 width=12) + BROADCAST [RS_256] + Group By Operator [GBY_255] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_163] - Group By Operator [GBY_162] (rows=1 width=12) + SHUFFLE [RS_179] + Group By Operator [GBY_178] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_161] (rows=5022875 width=8) + Select Operator [SEL_177] (rows=5022875 width=8) Output:["_col0"] - Merge Join Operator [MERGEJOIN_216] (rows=5022875 width=227) - Conds:RS_41._col2=RS_238._col0(Inner),Output:["_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_224] (rows=5022875 width=227) + Conds:RS_41._col2=RS_246._col0(Inner),Output:["_col3","_col4","_col5"] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_238] + SHUFFLE [RS_246] PartitionCols:_col0 - Select Operator [SEL_237] (rows=12 width=4) + Select Operator [SEL_245] (rows=12 width=4) Output:["_col0"] - Filter Operator [FIL_236] (rows=12 width=92) + Filter Operator [FIL_244] (rows=12 width=92) predicate:(web_company_name = 'pri') TableScan [TS_9] (rows=84 width=92) default@web_site,web_site,Tbl:COMPLETE,Col:COMPLETE,Output:["web_site_sk","web_company_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_215] (rows=15673790 width=231) - Conds:RS_38._col1=RS_230._col0(Inner),Output:["_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_223] (rows=15673790 width=231) + Conds:RS_38._col1=RS_238._col0(Inner),Output:["_col2","_col3","_col4","_col5"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_230] + SHUFFLE [RS_238] PartitionCols:_col0 - Select Operator [SEL_229] (rows=784314 width=4) + Select Operator [SEL_237] (rows=784314 width=4) Output:["_col0"] - Filter Operator [FIL_228] (rows=784314 width=90) + Filter Operator [FIL_236] (rows=784314 width=90) predicate:(ca_state = 'TX') TableScan [TS_6] (rows=40000000 width=90) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_214] (rows=15987241 width=235) - Conds:RS_246._col0=RS_222._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_222] (rows=15987241 width=235) + Conds:RS_254._col0=RS_230._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_222] + SHUFFLE [RS_230] PartitionCols:_col0 - Select Operator [SEL_221] (rows=8116 width=98) + Select Operator [SEL_229] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_220] (rows=8116 width=98) + Filter Operator [FIL_228] (rows=8116 width=98) predicate:CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' TableScan [TS_3] (rows=73049 width=98) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_246] + SHUFFLE [RS_254] PartitionCols:_col0 - Select Operator [SEL_245] (rows=143895019 width=239) + Select Operator [SEL_253] (rows=143895019 width=239) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_244] (rows=143895019 width=239) + Filter Operator [FIL_252] (rows=143895019 width=239) predicate:((ws_ship_addr_sk BETWEEN DynamicValue(RS_39_customer_address_ca_address_sk_min) AND DynamicValue(RS_39_customer_address_ca_address_sk_max) and in_bloom_filter(ws_ship_addr_sk, DynamicValue(RS_39_customer_address_ca_address_sk_bloom_filter))) and (ws_ship_date_sk BETWEEN DynamicValue(RS_36_date_dim_d_date_sk_min) AND DynamicValue(RS_36_date_dim_d_date_sk_max) and in_bloom_filter(ws_ship_date_sk, DynamicValue(RS_36_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_42_web_site_web_site_sk_min) AND DynamicValue(RS_42_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_42_web_site_web_site_sk_bloom_filter))) and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) TableScan [TS_0] (rows=144002668 width=239) default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_ship_date_sk","ws_ship_addr_sk","ws_web_site_sk","ws_order_number","ws_ext_ship_cost","ws_net_profit"] <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_227] - Group By Operator [GBY_226] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_225] - Group By Operator [GBY_224] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_223] (rows=8116 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_221] - <-Reducer 14 [BROADCAST_EDGE] vectorized BROADCAST [RS_235] Group By Operator [GBY_234] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_233] Group By Operator [GBY_232] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_231] (rows=784314 width=4) + Select Operator [SEL_231] (rows=8116 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_229] - <-Reducer 16 [BROADCAST_EDGE] vectorized + <-Reducer 14 [BROADCAST_EDGE] vectorized BROADCAST [RS_243] Group By Operator [GBY_242] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_241] Group By Operator [GBY_240] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_239] (rows=12 width=4) + Select Operator [SEL_239] (rows=784314 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_237] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_251] + Group By Operator [GBY_250] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_249] + Group By Operator [GBY_248] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_247] (rows=12 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_245] <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_255] + SHUFFLE [RS_263] PartitionCols:_col1 - Select Operator [SEL_254] (rows=144002668 width=7) + Select Operator [SEL_262] (rows=144002668 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_253] (rows=144002668 width=7) + Filter Operator [FIL_261] (rows=144002668 width=7) predicate:(in_bloom_filter(ws_order_number, DynamicValue(RS_44_ws1_ws_order_number_bloom_filter)) and ws_order_number BETWEEN DynamicValue(RS_44_ws1_ws_order_number_min) AND DynamicValue(RS_44_ws1_ws_order_number_max)) TableScan [TS_23] (rows=144002668 width=7) default@web_sales,ws2,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_249] - Please refer to the previous Group By Operator [GBY_247] + BROADCAST [RS_257] + Please refer to the previous Group By Operator [GBY_255] <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_256] + SHUFFLE [RS_264] PartitionCols:wr_order_number TableScan [TS_30] (rows=14398467 width=4) default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_order_number"] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_47] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_218] (rows=482885639 width=227) + Merge Join Operator [MERGEJOIN_226] (rows=482885639 width=227) Conds:RS_44._col3=RS_45._col0(Inner),Output:["_col3","_col4","_col5"] <-Reducer 18 [ONE_TO_ONE_EDGE] FORWARD [RS_45] @@ -267,5 +267,5 @@ Stage-0 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col3 - Please refer to the previous Merge Join Operator [MERGEJOIN_216] + Please refer to the previous Merge Join Operator [MERGEJOIN_224] diff --git a/ql/src/test/results/clientpositive/perf/tez/query18.q.out b/ql/src/test/results/clientpositive/perf/tez/query18.q.out index 1fa1b9e3f2..58fb7a79f5 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query18.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query18.q.out @@ -99,16 +99,16 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_184] - Limit [LIM_183] (rows=100 width=1165) + File Output Operator [FS_182] + Limit [LIM_181] (rows=100 width=1165) Number of rows:100 - Select Operator [SEL_182] (rows=10969055 width=1165) + Select Operator [SEL_180] (rows=10969055 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_181] - Select Operator [SEL_180] (rows=10969055 width=1165) + SHUFFLE [RS_179] + Select Operator [SEL_178] (rows=10969055 width=1165) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Group By Operator [GBY_179] (rows=10969055 width=1229) + Group By Operator [GBY_177] (rows=10969055 width=1229) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)","sum(VALUE._col8)","count(VALUE._col9)","sum(VALUE._col10)","count(VALUE._col11)","sum(VALUE._col12)","count(VALUE._col13)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_43] @@ -117,42 +117,42 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col6)","count(_col6)","sum(_col7)","count(_col7)","sum(_col8)","count(_col8)","sum(_col9)","count(_col9)","sum(_col10)","count(_col10)"],keys:_col0, _col1, _col2, _col3, 0L Select Operator [SEL_40] (rows=2193811 width=618) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Merge Join Operator [MERGEJOIN_145] (rows=2193811 width=618) + Merge Join Operator [MERGEJOIN_143] (rows=2193811 width=618) Conds:RS_37._col0=RS_38._col3(Inner),Output:["_col4","_col6","_col7","_col8","_col11","_col16","_col17","_col18","_col19","_col20","_col26"] <-Reducer 3 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_37] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_141] (rows=4959744 width=287) - Conds:RS_34._col1=RS_154._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_139] (rows=4959744 width=287) + Conds:RS_34._col1=RS_152._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8"] <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_154] + SHUFFLE [RS_152] PartitionCols:_col0 - Select Operator [SEL_153] (rows=1861800 width=4) + Select Operator [SEL_151] (rows=1861800 width=4) Output:["_col0"] - Filter Operator [FIL_152] (rows=1861800 width=4) + Filter Operator [FIL_150] (rows=1861800 width=4) predicate:cd_demo_sk is not null TableScan [TS_6] (rows=1861800 width=4) default@customer_demographics,cd2,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_140] (rows=4890586 width=290) - Conds:RS_148._col2=RS_151._col0(Inner),Output:["_col0","_col1","_col4","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_138] (rows=4890586 width=290) + Conds:RS_146._col2=RS_149._col0(Inner),Output:["_col0","_col1","_col4","_col6","_col7","_col8"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_148] + SHUFFLE [RS_146] PartitionCols:_col2 - Select Operator [SEL_147] (rows=35631408 width=19) + Select Operator [SEL_145] (rows=35631408 width=19) Output:["_col0","_col1","_col2","_col4"] - Filter Operator [FIL_146] (rows=35631408 width=19) + Filter Operator [FIL_144] (rows=35631408 width=19) predicate:((c_birth_month) IN (9, 5, 12, 4, 1, 10) and c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) TableScan [TS_0] (rows=80000000 width=19) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk","c_birth_month","c_birth_year"] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_151] + SHUFFLE [RS_149] PartitionCols:_col0 - Select Operator [SEL_150] (rows=5490196 width=285) + Select Operator [SEL_148] (rows=5490196 width=285) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_149] (rows=5490196 width=285) + Filter Operator [FIL_147] (rows=5490196 width=285) predicate:((ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') and ca_address_sk is not null) TableScan [TS_3] (rows=40000000 width=285) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county","ca_state","ca_country"] @@ -161,85 +161,85 @@ Stage-0 PartitionCols:_col3 Select Operator [SEL_30] (rows=15983481 width=529) Output:["_col1","_col3","_col6","_col7","_col8","_col9","_col10","_col16"] - Merge Join Operator [MERGEJOIN_144] (rows=15983481 width=529) - Conds:RS_27._col3=RS_178._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col14","_col16"] + Merge Join Operator [MERGEJOIN_142] (rows=15983481 width=529) + Conds:RS_27._col3=RS_176._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col14","_col16"] <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_178] + SHUFFLE [RS_176] PartitionCols:_col0 - Select Operator [SEL_177] (rows=462000 width=104) + Select Operator [SEL_175] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_176] (rows=462000 width=104) + Filter Operator [FIL_174] (rows=462000 width=104) predicate:i_item_sk is not null TableScan [TS_18] (rows=462000 width=104) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_143] (rows=15983481 width=433) - Conds:RS_24._col2=RS_165._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col14"] + Merge Join Operator [MERGEJOIN_141] (rows=15983481 width=433) + Conds:RS_24._col2=RS_163._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col14"] <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_165] + PARTITION_ONLY_SHUFFLE [RS_163] PartitionCols:_col0 - Select Operator [SEL_164] (rows=103433 width=184) + Select Operator [SEL_162] (rows=103433 width=184) Output:["_col0","_col3"] - Filter Operator [FIL_163] (rows=103433 width=187) + Filter Operator [FIL_161] (rows=103433 width=187) predicate:((cd_education_status = 'College') and (cd_gender = 'M') and cd_demo_sk is not null) TableScan [TS_15] (rows=1861800 width=187) default@customer_demographics,cd1,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_education_status","cd_dep_count"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_142] (rows=100578970 width=459) - Conds:RS_175._col0=RS_157._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_140] (rows=100578970 width=459) + Conds:RS_173._col0=RS_155._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Map 14 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_157] + PARTITION_ONLY_SHUFFLE [RS_155] PartitionCols:_col0 - Select Operator [SEL_156] (rows=652 width=8) + Select Operator [SEL_154] (rows=652 width=8) Output:["_col0"] - Filter Operator [FIL_155] (rows=652 width=8) + Filter Operator [FIL_153] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) TableScan [TS_12] (rows=73049 width=8) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_175] + SHUFFLE [RS_173] PartitionCols:_col0 - Select Operator [SEL_174] (rows=283692098 width=466) + Select Operator [SEL_172] (rows=283692098 width=466) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_173] (rows=283692098 width=466) + Filter Operator [FIL_171] (rows=283692098 width=466) predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_25_cd1_cd_demo_sk_min) AND DynamicValue(RS_25_cd1_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_25_cd1_cd_demo_sk_bloom_filter))) and (cs_bill_customer_sk BETWEEN DynamicValue(RS_37_customer_c_customer_sk_min) AND DynamicValue(RS_37_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_37_customer_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) TableScan [TS_9] (rows=287989836 width=466) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_bill_cdemo_sk","cs_item_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt","cs_net_profit"] <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_162] - Group By Operator [GBY_161] (rows=1 width=12) + BROADCAST [RS_160] + Group By Operator [GBY_159] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_160] - Group By Operator [GBY_159] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_158] + Group By Operator [GBY_157] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_158] (rows=652 width=4) + Select Operator [SEL_156] (rows=652 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_156] + Please refer to the previous Select Operator [SEL_154] <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_170] - Group By Operator [GBY_169] (rows=1 width=12) + BROADCAST [RS_168] + Group By Operator [GBY_167] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_168] - Group By Operator [GBY_167] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_166] + Group By Operator [GBY_165] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_166] (rows=103433 width=4) + Select Operator [SEL_164] (rows=103433 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_164] + Please refer to the previous Select Operator [SEL_162] <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_172] - Group By Operator [GBY_171] (rows=1 width=12) + BROADCAST [RS_170] + Group By Operator [GBY_169] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=4890586)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_126] - Group By Operator [GBY_125] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_120] + Group By Operator [GBY_119] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=4890586)"] - Select Operator [SEL_124] (rows=4959744 width=4) + Select Operator [SEL_118] (rows=4959744 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_141] + Please refer to the previous Merge Join Operator [MERGEJOIN_139] diff --git a/ql/src/test/results/clientpositive/perf/tez/query23.q.out b/ql/src/test/results/clientpositive/perf/tez/query23.q.out index 61d1dd7338..77847929b4 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query23.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query23.q.out @@ -1,7 +1,7 @@ -Warning: Shuffle Join MERGEJOIN[589][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product -Warning: Shuffle Join MERGEJOIN[590][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product -Warning: Shuffle Join MERGEJOIN[592][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product -Warning: Shuffle Join MERGEJOIN[593][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product +Warning: Shuffle Join MERGEJOIN[593][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product +Warning: Shuffle Join MERGEJOIN[594][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product +Warning: Shuffle Join MERGEJOIN[596][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product +Warning: Shuffle Join MERGEJOIN[597][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product PREHOOK: query: explain with frequent_ss_items as (select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date solddate,count(*) cnt @@ -166,37 +166,37 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_695] - Limit [LIM_694] (rows=1 width=112) + File Output Operator [FS_699] + Limit [LIM_698] (rows=1 width=112) Number of rows:100 - Group By Operator [GBY_693] (rows=1 width=112) + Group By Operator [GBY_697] (rows=1 width=112) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Union 5 [CUSTOM_SIMPLE_EDGE] <-Reducer 12 [CONTAINS] - Reduce Output Operator [RS_604] - Group By Operator [GBY_603] (rows=1 width=112) + Reduce Output Operator [RS_608] + Group By Operator [GBY_607] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_601] (rows=1 width=112) + Select Operator [SEL_605] (rows=1 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_600] (rows=1 width=116) + Merge Join Operator [MERGEJOIN_604] (rows=1 width=116) Conds:RS_248._col2=RS_249._col0(Inner),Output:["_col3","_col4"] <-Reducer 11 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_248] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_588] (rows=155 width=0) - Conds:RS_245._col1=RS_638._col0(Inner),Output:["_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_592] (rows=155 width=0) + Conds:RS_245._col1=RS_642._col0(Inner),Output:["_col2","_col3","_col4"] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_638] + SHUFFLE [RS_642] PartitionCols:_col0 - Group By Operator [GBY_635] (rows=2235 width=4) + Group By Operator [GBY_639] (rows=2235 width=4) Output:["_col0"],keys:_col1 - Select Operator [SEL_634] (rows=6548799 width=12) + Select Operator [SEL_638] (rows=6548799 width=12) Output:["_col1"] - Filter Operator [FIL_633] (rows=6548799 width=12) + Filter Operator [FIL_637] (rows=6548799 width=12) predicate:(_col3 > 4L) - Select Operator [SEL_632] (rows=19646398 width=12) + Select Operator [SEL_636] (rows=19646398 width=12) Output:["_col0","_col3"] - Group By Operator [GBY_631] (rows=19646398 width=290) + Group By Operator [GBY_635] (rows=19646398 width=290) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_24] @@ -205,96 +205,96 @@ Stage-0 Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 Select Operator [SEL_21] (rows=19646398 width=282) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_573] (rows=19646398 width=282) - Conds:RS_18._col1=RS_630._col0(Inner),Output:["_col3","_col5","_col6"] + Merge Join Operator [MERGEJOIN_577] (rows=19646398 width=282) + Conds:RS_18._col1=RS_634._col0(Inner),Output:["_col3","_col5","_col6"] <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_630] + SHUFFLE [RS_634] PartitionCols:_col0 - Select Operator [SEL_629] (rows=462000 width=188) + Select Operator [SEL_633] (rows=462000 width=188) Output:["_col0","_col1"] - Filter Operator [FIL_628] (rows=462000 width=188) + Filter Operator [FIL_632] (rows=462000 width=188) predicate:i_item_sk is not null TableScan [TS_12] (rows=462000 width=188) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc"] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_572] (rows=19646398 width=98) - Conds:RS_627._col0=RS_619._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_576] (rows=19646398 width=98) + Conds:RS_631._col0=RS_623._col0(Inner),Output:["_col1","_col3"] <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_619] + PARTITION_ONLY_SHUFFLE [RS_623] PartitionCols:_col0 - Select Operator [SEL_618] (rows=2609 width=102) + Select Operator [SEL_622] (rows=2609 width=102) Output:["_col0","_col1"] - Filter Operator [FIL_617] (rows=2609 width=102) + Filter Operator [FIL_621] (rows=2609 width=102) predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) TableScan [TS_9] (rows=73049 width=102) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_year"] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_627] + SHUFFLE [RS_631] PartitionCols:_col0 - Select Operator [SEL_626] (rows=550076554 width=7) + Select Operator [SEL_630] (rows=550076554 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_625] (rows=550076554 width=7) + Filter Operator [FIL_629] (rows=550076554 width=7) predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) TableScan [TS_6] (rows=575995635 width=7) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_624] - Group By Operator [GBY_623] (rows=1 width=12) + BROADCAST [RS_628] + Group By Operator [GBY_627] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_622] - Group By Operator [GBY_621] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_626] + Group By Operator [GBY_625] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_620] (rows=2609 width=4) + Select Operator [SEL_624] (rows=2609 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_618] + Please refer to the previous Select Operator [SEL_622] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_245] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_579] (rows=3941102 width=122) - Conds:RS_702._col0=RS_609._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_583] (rows=3941102 width=122) + Conds:RS_706._col0=RS_613._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_609] + PARTITION_ONLY_SHUFFLE [RS_613] PartitionCols:_col0 - Select Operator [SEL_606] (rows=50 width=12) + Select Operator [SEL_610] (rows=50 width=12) Output:["_col0"] - Filter Operator [FIL_605] (rows=50 width=12) + Filter Operator [FIL_609] (rows=50 width=12) predicate:((d_moy = 1) and (d_year = 1999) and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 44 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_702] + SHUFFLE [RS_706] PartitionCols:_col0 - Select Operator [SEL_701] (rows=143930993 width=127) + Select Operator [SEL_705] (rows=143930993 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_700] (rows=143930993 width=127) + Filter Operator [FIL_704] (rows=143930993 width=127) predicate:((ws_item_sk BETWEEN DynamicValue(RS_246_item_i_item_sk_min) AND DynamicValue(RS_246_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_246_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_243_date_dim_d_date_sk_min) AND DynamicValue(RS_243_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_243_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) TableScan [TS_126] (rows=144002668 width=127) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_quantity","ws_list_price"] <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_697] - Group By Operator [GBY_696] (rows=1 width=12) + BROADCAST [RS_701] + Group By Operator [GBY_700] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_614] - Group By Operator [GBY_612] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_618] + Group By Operator [GBY_616] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_610] (rows=50 width=4) + Select Operator [SEL_614] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_606] + Please refer to the previous Select Operator [SEL_610] <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_699] - Group By Operator [GBY_698] (rows=1 width=12) + BROADCAST [RS_703] + Group By Operator [GBY_702] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_643] - Group By Operator [GBY_641] (rows=1 width=12) + SHUFFLE [RS_647] + Group By Operator [GBY_645] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_639] (rows=2235 width=4) + Select Operator [SEL_643] (rows=2235 width=4) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_635] + Please refer to the previous Group By Operator [GBY_639] <-Reducer 34 [SIMPLE_EDGE] SHUFFLE [RS_249] PartitionCols:_col0 @@ -302,29 +302,29 @@ Stage-0 Output:["_col0"] Filter Operator [FIL_240] (rows=471875 width=228) predicate:(_col3 > (0.95 * _col1)) - Merge Join Operator [MERGEJOIN_593] (rows=1415625 width=228) + Merge Join Operator [MERGEJOIN_597] (rows=1415625 width=228) Conds:(Inner),Output:["_col1","_col2","_col3"] <-Reducer 33 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_237] - Merge Join Operator [MERGEJOIN_592] (rows=1 width=112) + Merge Join Operator [MERGEJOIN_596] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_708] - Select Operator [SEL_707] (rows=1 width=8) - Filter Operator [FIL_706] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_712] + Select Operator [SEL_711] (rows=1 width=8) + Filter Operator [FIL_710] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_705] (rows=1 width=8) + Group By Operator [GBY_709] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_704] (rows=1 width=8) - Group By Operator [GBY_703] (rows=1 width=8) + Select Operator [SEL_708] (rows=1 width=8) + Group By Operator [GBY_707] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_676] - Group By Operator [GBY_672] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_680] + Group By Operator [GBY_676] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_668] (rows=11859 width=116) + Select Operator [SEL_672] (rows=11859 width=116) Output:["_col0"] - Group By Operator [GBY_665] (rows=11859 width=116) + Group By Operator [GBY_669] (rows=11859 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 26 [SIMPLE_EDGE] SHUFFLE [RS_51] @@ -333,65 +333,65 @@ Stage-0 Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 Select Operator [SEL_48] (rows=18762463 width=4) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_575] (rows=18762463 width=4) - Conds:RS_45._col1=RS_663._col0(Inner),Output:["_col2","_col3","_col6"] + Merge Join Operator [MERGEJOIN_579] (rows=18762463 width=4) + Conds:RS_45._col1=RS_667._col0(Inner),Output:["_col2","_col3","_col6"] <-Map 41 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_663] + SHUFFLE [RS_667] PartitionCols:_col0 - Select Operator [SEL_661] (rows=80000000 width=4) + Select Operator [SEL_665] (rows=80000000 width=4) Output:["_col0"] - Filter Operator [FIL_660] (rows=80000000 width=4) + Filter Operator [FIL_664] (rows=80000000 width=4) predicate:c_customer_sk is not null TableScan [TS_96] (rows=80000000 width=4) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk"] <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_574] (rows=18762463 width=0) - Conds:RS_659._col0=RS_651._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_578] (rows=18762463 width=0) + Conds:RS_663._col0=RS_655._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 36 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_651] + PARTITION_ONLY_SHUFFLE [RS_655] PartitionCols:_col0 - Select Operator [SEL_650] (rows=2609 width=8) + Select Operator [SEL_654] (rows=2609 width=8) Output:["_col0"] - Filter Operator [FIL_649] (rows=2609 width=8) + Filter Operator [FIL_653] (rows=2609 width=8) predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) TableScan [TS_36] (rows=73049 width=8) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_659] + SHUFFLE [RS_663] PartitionCols:_col0 - Select Operator [SEL_658] (rows=525327388 width=118) + Select Operator [SEL_662] (rows=525327388 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_657] (rows=525327388 width=118) + Filter Operator [FIL_661] (rows=525327388 width=118) predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_43_date_dim_d_date_sk_min) AND DynamicValue(RS_43_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) TableScan [TS_33] (rows=575995635 width=118) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"] <-Reducer 37 [BROADCAST_EDGE] vectorized - BROADCAST [RS_656] - Group By Operator [GBY_655] (rows=1 width=12) + BROADCAST [RS_660] + Group By Operator [GBY_659] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 36 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_654] - Group By Operator [GBY_653] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_658] + Group By Operator [GBY_657] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_652] (rows=2609 width=4) + Select Operator [SEL_656] (rows=2609 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_650] + Please refer to the previous Select Operator [SEL_654] <-Reducer 35 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_710] - Group By Operator [GBY_709] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_714] + Group By Operator [GBY_713] (rows=1 width=112) Output:["_col0"],aggregations:["max(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_677] - Group By Operator [GBY_673] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_681] + Group By Operator [GBY_677] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_669] (rows=11859 width=116) + Select Operator [SEL_673] (rows=11859 width=116) Output:["_col1"] - Please refer to the previous Group By Operator [GBY_665] + Please refer to the previous Group By Operator [GBY_669] <-Reducer 43 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_717] - Group By Operator [GBY_716] (rows=1415625 width=116) + PARTITION_ONLY_SHUFFLE [RS_721] + Group By Operator [GBY_720] (rows=1415625 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 42 [SIMPLE_EDGE] SHUFFLE [RS_231] @@ -400,89 +400,89 @@ Stage-0 Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 Select Operator [SEL_228] (rows=550080312 width=114) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_586] (rows=550080312 width=114) - Conds:RS_715._col0=RS_664._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_590] (rows=550080312 width=114) + Conds:RS_719._col0=RS_668._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 41 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_664] + SHUFFLE [RS_668] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_661] + Please refer to the previous Select Operator [SEL_665] <-Map 45 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_715] + SHUFFLE [RS_719] PartitionCols:_col0 - Select Operator [SEL_714] (rows=550080312 width=114) + Select Operator [SEL_718] (rows=550080312 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_713] (rows=550080312 width=114) + Filter Operator [FIL_717] (rows=550080312 width=114) predicate:((ss_customer_sk BETWEEN DynamicValue(RS_248_web_sales_ws_bill_customer_sk_min) AND DynamicValue(RS_248_web_sales_ws_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_248_web_sales_ws_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) TableScan [TS_219] (rows=575995635 width=114) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_712] - Group By Operator [GBY_711] (rows=1 width=12) + BROADCAST [RS_716] + Group By Operator [GBY_715] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 11 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_562] - Group By Operator [GBY_561] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_570] + Group By Operator [GBY_569] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_560] (rows=155 width=0) + Select Operator [SEL_568] (rows=155 width=0) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_588] + Please refer to the previous Merge Join Operator [MERGEJOIN_592] <-Reducer 4 [CONTAINS] - Reduce Output Operator [RS_599] - Group By Operator [GBY_598] (rows=1 width=112) + Reduce Output Operator [RS_603] + Group By Operator [GBY_602] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_596] (rows=1 width=112) + Select Operator [SEL_600] (rows=1 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_595] (rows=1 width=116) + Merge Join Operator [MERGEJOIN_599] (rows=1 width=116) Conds:RS_122._col1=RS_123._col0(Inner),Output:["_col3","_col4"] <-Reducer 3 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_122] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_587] (rows=304 width=0) - Conds:RS_119._col2=RS_636._col0(Inner),Output:["_col1","_col3","_col4"] + Merge Join Operator [MERGEJOIN_591] (rows=304 width=0) + Conds:RS_119._col2=RS_640._col0(Inner),Output:["_col1","_col3","_col4"] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_636] + SHUFFLE [RS_640] PartitionCols:_col0 - Please refer to the previous Group By Operator [GBY_635] + Please refer to the previous Group By Operator [GBY_639] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_119] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_571] (rows=7751875 width=101) - Conds:RS_648._col0=RS_607._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_575] (rows=7751875 width=101) + Conds:RS_652._col0=RS_611._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_607] + PARTITION_ONLY_SHUFFLE [RS_611] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_606] + Please refer to the previous Select Operator [SEL_610] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_648] + SHUFFLE [RS_652] PartitionCols:_col0 - Select Operator [SEL_647] (rows=285117831 width=127) + Select Operator [SEL_651] (rows=285117831 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_646] (rows=285117831 width=127) + Filter Operator [FIL_650] (rows=285117831 width=127) predicate:((cs_item_sk BETWEEN DynamicValue(RS_120_item_i_item_sk_min) AND DynamicValue(RS_120_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_120_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_117_date_dim_d_date_sk_min) AND DynamicValue(RS_117_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_117_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) TableScan [TS_0] (rows=287989836 width=127) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity","cs_list_price"] <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_645] - Group By Operator [GBY_644] (rows=1 width=12) + BROADCAST [RS_649] + Group By Operator [GBY_648] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_642] - Group By Operator [GBY_640] (rows=1 width=12) + SHUFFLE [RS_646] + Group By Operator [GBY_644] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_637] (rows=2235 width=4) + Select Operator [SEL_641] (rows=2235 width=4) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_635] + Please refer to the previous Group By Operator [GBY_639] <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_616] - Group By Operator [GBY_615] (rows=1 width=12) + BROADCAST [RS_620] + Group By Operator [GBY_619] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_613] - Group By Operator [GBY_611] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_617] + Group By Operator [GBY_615] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_608] (rows=50 width=4) + Select Operator [SEL_612] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_606] + Please refer to the previous Select Operator [SEL_610] <-Reducer 30 [SIMPLE_EDGE] SHUFFLE [RS_123] PartitionCols:_col0 @@ -490,43 +490,43 @@ Stage-0 Output:["_col0"] Filter Operator [FIL_114] (rows=471875 width=228) predicate:(_col3 > (0.95 * _col1)) - Merge Join Operator [MERGEJOIN_590] (rows=1415625 width=228) + Merge Join Operator [MERGEJOIN_594] (rows=1415625 width=228) Conds:(Inner),Output:["_col1","_col2","_col3"] <-Reducer 29 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_111] - Merge Join Operator [MERGEJOIN_589] (rows=1 width=112) + Merge Join Operator [MERGEJOIN_593] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_683] - Select Operator [SEL_682] (rows=1 width=8) - Filter Operator [FIL_681] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_687] + Select Operator [SEL_686] (rows=1 width=8) + Filter Operator [FIL_685] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_680] (rows=1 width=8) + Group By Operator [GBY_684] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_679] (rows=1 width=8) - Group By Operator [GBY_678] (rows=1 width=8) + Select Operator [SEL_683] (rows=1 width=8) + Group By Operator [GBY_682] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_674] - Group By Operator [GBY_670] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_678] + Group By Operator [GBY_674] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_666] (rows=11859 width=116) + Select Operator [SEL_670] (rows=11859 width=116) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_665] + Please refer to the previous Group By Operator [GBY_669] <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_685] - Group By Operator [GBY_684] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_689] + Group By Operator [GBY_688] (rows=1 width=112) Output:["_col0"],aggregations:["max(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_675] - Group By Operator [GBY_671] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_679] + Group By Operator [GBY_675] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_667] (rows=11859 width=116) + Select Operator [SEL_671] (rows=11859 width=116) Output:["_col1"] - Please refer to the previous Group By Operator [GBY_665] + Please refer to the previous Group By Operator [GBY_669] <-Reducer 40 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_692] - Group By Operator [GBY_691] (rows=1415625 width=116) + PARTITION_ONLY_SHUFFLE [RS_696] + Group By Operator [GBY_695] (rows=1415625 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 39 [SIMPLE_EDGE] SHUFFLE [RS_105] @@ -535,30 +535,30 @@ Stage-0 Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 Select Operator [SEL_102] (rows=550080312 width=114) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_578] (rows=550080312 width=114) - Conds:RS_690._col0=RS_662._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_582] (rows=550080312 width=114) + Conds:RS_694._col0=RS_666._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 41 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_662] + SHUFFLE [RS_666] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_661] + Please refer to the previous Select Operator [SEL_665] <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_690] + SHUFFLE [RS_694] PartitionCols:_col0 - Select Operator [SEL_689] (rows=550080312 width=114) + Select Operator [SEL_693] (rows=550080312 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_688] (rows=550080312 width=114) + Filter Operator [FIL_692] (rows=550080312 width=114) predicate:((ss_customer_sk BETWEEN DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) TableScan [TS_93] (rows=575995635 width=114) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_687] - Group By Operator [GBY_686] (rows=1 width=12) + BROADCAST [RS_691] + Group By Operator [GBY_690] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_458] - Group By Operator [GBY_457] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_464] + Group By Operator [GBY_463] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_456] (rows=304 width=0) + Select Operator [SEL_462] (rows=304 width=0) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_587] + Please refer to the previous Merge Join Operator [MERGEJOIN_591] diff --git a/ql/src/test/results/clientpositive/perf/tez/query24.q.out b/ql/src/test/results/clientpositive/perf/tez/query24.q.out index 902358a524..43ece85275 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query24.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query24.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[290][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 8' is a cross product +Warning: Shuffle Join MERGEJOIN[301][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 6' is a cross product PREHOOK: query: explain with ssales as (select c_last_name @@ -23,7 +23,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name @@ -79,7 +80,8 @@ where ss_ticket_number = sr_ticket_number and ss_customer_sk = c_customer_sk and ss_item_sk = i_item_sk and ss_store_sk = s_store_sk - and c_birth_country = upper(ca_country) + and c_current_addr_sk = ca_address_sk + and c_birth_country <> upper(ca_country) and s_zip = ca_zip and s_market_id=7 group by c_last_name @@ -114,234 +116,242 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) -Map 24 <- Reducer 20 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Map 9 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) -Reducer 12 <- Map 22 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 23 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Reducer 13 (SIMPLE_EDGE) -Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 16 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE) -Reducer 19 <- Map 21 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 20 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 21 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 22 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Map 23 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) +Map 24 <- Reducer 19 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE) +Reducer 10 <- Map 23 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) +Reducer 15 <- Map 22 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) +Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Map 24 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) +Reducer 19 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 20 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 23 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 7 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 8 - File Output Operator [FS_91] - Select Operator [SEL_90] (rows=78393744 width=380) + Reducer 6 + File Output Operator [FS_94] + Select Operator [SEL_93] (rows=1313165 width=380) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_89] (rows=78393744 width=492) + Filter Operator [FIL_92] (rows=1313165 width=492) predicate:(_col3 > _col4) - Merge Join Operator [MERGEJOIN_290] (rows=235181232 width=492) + Merge Join Operator [MERGEJOIN_301] (rows=3939496 width=492) Conds:(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_345] - Select Operator [SEL_344] (rows=1 width=112) + <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_351] + Select Operator [SEL_350] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_343] (rows=1 width=120) + Group By Operator [GBY_349] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] - <-Reducer 14 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_342] - Group By Operator [GBY_341] (rows=1 width=120) + <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_348] + Group By Operator [GBY_347] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col10)","count(_col10)"] - Select Operator [SEL_340] (rows=2121289008973 width=932) + Select Operator [SEL_346] (rows=576061174 width=932) Output:["_col10"] - Group By Operator [GBY_339] (rows=2121289008973 width=932) + Group By Operator [GBY_345] (rows=576061174 width=932) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9 - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_78] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_81] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Group By Operator [GBY_77] (rows=2121289008973 width=932) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col4)"],keys:_col11, _col12, _col6, _col8, _col15, _col16, _col17, _col18, _col19, _col22 - Merge Join Operator [MERGEJOIN_289] (rows=2121289008973 width=932) - Conds:RS_73._col9, _col13=RS_328._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col8","_col11","_col12","_col15","_col16","_col17","_col18","_col19","_col22"] + Group By Operator [GBY_80] (rows=576061174 width=932) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col18)"],keys:_col11, _col12, _col1, _col5, _col7, _col20, _col21, _col22, _col23, _col24 + Merge Join Operator [MERGEJOIN_300] (rows=589731269 width=928) + Conds:RS_76._col14, _col17=RS_332._col0, _col1(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col18","_col20","_col21","_col22","_col23","_col24"] <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_328] - PartitionCols:_col1, upper(_col2) - Select Operator [SEL_326] (rows=40000000 width=272) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_325] (rows=40000000 width=272) - predicate:(ca_zip is not null and upper(ca_country) is not null) - TableScan [TS_15] (rows=40000000 width=272) - default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_state","ca_zip","ca_country"] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_73] - PartitionCols:_col9, _col13 - Merge Join Operator [MERGEJOIN_288] (rows=537799796 width=1023) - Conds:RS_70._col0, _col3=RS_324._col0, _col1(Inner),Output:["_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_324] - PartitionCols:_col0, _col1 - Select Operator [SEL_322] (rows=57591150 width=8) - Output:["_col0","_col1"] - Filter Operator [FIL_321] (rows=57591150 width=8) - predicate:(sr_item_sk is not null and sr_ticket_number is not null) - TableScan [TS_12] (rows=57591150 width=8) - default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_70] - PartitionCols:_col0, _col3 - Merge Join Operator [MERGEJOIN_287] (rows=385681992 width=1029) - Conds:RS_67._col0=RS_297._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_297] - PartitionCols:_col0 - Select Operator [SEL_294] (rows=462000 width=384) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_292] (rows=462000 width=384) - predicate:i_item_sk is not null - TableScan [TS_3] (rows=462000 width=384) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"] - <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_67] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_286] (rows=385681992 width=648) - Conds:RS_64._col1=RS_320._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_320] - PartitionCols:_col0 - Select Operator [SEL_318] (rows=80000000 width=276) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_317] (rows=80000000 width=276) - predicate:(c_birth_country is not null and c_customer_sk is not null) - TableScan [TS_9] (rows=80000000 width=276) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_first_name","c_last_name","c_birth_country"] - <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_64] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_285] (rows=385681992 width=379) - Conds:RS_338._col2=RS_306._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col8","_col9"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_306] - PartitionCols:_col0 - Select Operator [SEL_303] (rows=155 width=271) - Output:["_col0","_col1","_col3","_col4"] - Filter Operator [FIL_302] (rows=155 width=271) - predicate:((s_market_id = 7) and s_store_sk is not null and s_zip is not null) - TableScan [TS_6] (rows=1704 width=270) - default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"] - <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_338] - PartitionCols:_col2 - Select Operator [SEL_337] (rows=525333486 width=122) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_336] (rows=525333486 width=122) - predicate:((ss_store_sk BETWEEN DynamicValue(RS_62_store_s_store_sk_min) AND DynamicValue(RS_62_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_62_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_43] (rows=575995635 width=122) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_335] - Group By Operator [GBY_334] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_311] - Group By Operator [GBY_309] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_307] (rows=155 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_303] - <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_333] - Select Operator [SEL_332] (rows=235181232 width=380) + SHUFFLE [RS_332] + PartitionCols:_col0, _col1 + Select Operator [SEL_330] (rows=57591150 width=8) + Output:["_col0","_col1"] + Filter Operator [FIL_329] (rows=57591150 width=8) + predicate:(sr_item_sk is not null and sr_ticket_number is not null) + TableScan [TS_23] (rows=57591150 width=8) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_76] + PartitionCols:_col14, _col17 + Merge Join Operator [MERGEJOIN_299] (rows=576061174 width=936) + Conds:RS_73._col14=RS_308._col0(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col14","_col17","_col18","_col20","_col21","_col22","_col23","_col24"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_308] + PartitionCols:_col0 + Select Operator [SEL_305] (rows=462000 width=384) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_303] (rows=462000 width=384) + predicate:i_item_sk is not null + TableScan [TS_3] (rows=462000 width=384) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"] + <-Reducer 18 [SIMPLE_EDGE] + SHUFFLE [RS_73] + PartitionCols:_col14 + Merge Join Operator [MERGEJOIN_298] (rows=576061174 width=555) + Conds:RS_70._col9, _col4=RS_344._col1, _col2(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col14","_col17","_col18"] + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_70] + PartitionCols:_col9, _col4 + Filter Operator [FIL_21] (rows=7276996 width=637) + predicate:(_col13 <> upper(_col3)) + Merge Join Operator [MERGEJOIN_293] (rows=7276996 width=637) + Conds:RS_18._col0=RS_321._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col9","_col11","_col12","_col13"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_321] + PartitionCols:_col1 + Select Operator [SEL_320] (rows=80000000 width=280) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_319] (rows=80000000 width=280) + predicate:(c_current_addr_sk is not null and c_customer_sk is not null) + TableScan [TS_12] (rows=80000000 width=280) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name","c_birth_country"] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_292] (rows=611379 width=365) + Conds:RS_315._col2=RS_318._col4(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col7"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_315] + PartitionCols:_col2 + Select Operator [SEL_314] (rows=40000000 width=276) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_313] (rows=40000000 width=276) + predicate:(ca_address_sk is not null and ca_zip is not null) + TableScan [TS_6] (rows=40000000 width=276) + default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_zip","ca_country"] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_318] + PartitionCols:_col4 + Select Operator [SEL_317] (rows=155 width=271) + Output:["_col0","_col1","_col3","_col4"] + Filter Operator [FIL_316] (rows=155 width=271) + predicate:((s_market_id = 7) and s_store_sk is not null and s_zip is not null) + TableScan [TS_9] (rows=1704 width=270) + default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_344] + PartitionCols:_col1, _col2 + Select Operator [SEL_343] (rows=525333486 width=122) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_342] (rows=525333486 width=122) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_70_customer_c_customer_sk_min) AND DynamicValue(RS_70_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_70_customer_c_customer_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_70_store_s_store_sk_min) AND DynamicValue(RS_70_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_70_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_54] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_339] + Group By Operator [GBY_338] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=6636187)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_250] + Group By Operator [GBY_249] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=6636187)"] + Select Operator [SEL_248] (rows=7276996 width=8) + Output:["_col0"] + Please refer to the previous Filter Operator [FIL_21] + <-Reducer 20 [BROADCAST_EDGE] vectorized + BROADCAST [RS_341] + Group By Operator [GBY_340] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_255] + Group By Operator [GBY_254] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_253] (rows=7276996 width=8) + Output:["_col0"] + Please refer to the previous Filter Operator [FIL_21] + <-Reducer 5 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_337] + Select Operator [SEL_336] (rows=3939496 width=380) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_331] (rows=235181232 width=380) - Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col9)"],keys:_col1, _col2, _col7 - Select Operator [SEL_330] (rows=365777643230 width=843) - Output:["_col1","_col2","_col7","_col9"] - Group By Operator [GBY_329] (rows=365777643230 width=843) + Group By Operator [GBY_335] (rows=3939496 width=380) + Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col9)"],keys:_col4, _col5, _col7 + Select Operator [SEL_334] (rows=84010488 width=843) + Output:["_col4","_col5","_col7","_col9"] + Group By Operator [GBY_333] (rows=84010488 width=843) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8 - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_35] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_37] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_34] (rows=365777643230 width=843) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col17, _col18, _col12, _col22, _col6, _col7, _col9, _col10, _col14 - Merge Join Operator [MERGEJOIN_284] (rows=365777643230 width=843) - Conds:RS_30._col15, _col19=RS_327._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col17","_col18","_col22"] + Group By Operator [GBY_36] (rows=84010488 width=843) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col13, _col14, _col21, _col6, _col7, _col9, _col10, _col17, _col23 + Merge Join Operator [MERGEJOIN_295] (rows=138508741 width=824) + Conds:RS_32._col0, _col3=RS_331._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col13","_col14","_col17","_col21","_col23"] <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_327] - PartitionCols:_col1, upper(_col2) - Please refer to the previous Select Operator [SEL_326] - <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_30] - PartitionCols:_col15, _col19 - Merge Join Operator [MERGEJOIN_283] (rows=92733777 width=910) - Conds:RS_27._col0, _col3=RS_323._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] - PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_322] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_27] - PartitionCols:_col0, _col3 - Merge Join Operator [MERGEJOIN_282] (rows=56246341 width=899) - Conds:RS_24._col1=RS_319._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_319] + SHUFFLE [RS_331] + PartitionCols:_col0, _col1 + Please refer to the previous Select Operator [SEL_330] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_32] + PartitionCols:_col0, _col3 + Merge Join Operator [MERGEJOIN_294] (rows=84010488 width=820) + Conds:RS_29._col1, _col2=RS_30._col0, _col9(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col9","_col10","_col13","_col14","_col17","_col21","_col23"] + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_30] + PartitionCols:_col0, _col9 + Select Operator [SEL_22] (rows=7276996 width=637) + Output:["_col0","_col2","_col3","_col6","_col9","_col10","_col12"] + Please refer to the previous Filter Operator [FIL_21] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_29] + PartitionCols:_col1, _col2 + Merge Join Operator [MERGEJOIN_291] (rows=76612563 width=382) + Conds:RS_328._col0=RS_306._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col10"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_306] + PartitionCols:_col0 + Select Operator [SEL_304] (rows=7000 width=385) + Output:["_col0","_col1","_col2","_col4","_col5"] + Filter Operator [FIL_302] (rows=7000 width=384) + predicate:((i_color = 'orchid') and i_item_sk is not null) + Please refer to the previous TableScan [TS_3] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_328] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_318] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_24] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_281] (rows=56246341 width=630) - Conds:RS_21._col2=RS_304._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_304] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_303] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_21] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_280] (rows=76612563 width=382) - Conds:RS_316._col0=RS_295._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col10"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_295] - PartitionCols:_col0 - Select Operator [SEL_293] (rows=7000 width=385) - Output:["_col0","_col1","_col2","_col4","_col5"] - Filter Operator [FIL_291] (rows=7000 width=384) - predicate:((i_color = 'orchid') and i_item_sk is not null) - Please refer to the previous TableScan [TS_3] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_316] - PartitionCols:_col0 - Select Operator [SEL_315] (rows=525333486 width=122) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_314] (rows=525333486 width=122) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_19_item_i_item_sk_min) AND DynamicValue(RS_19_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_19_item_i_item_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_0] (rows=575995635 width=122) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_301] - Group By Operator [GBY_300] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_299] - Group By Operator [GBY_298] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_296] (rows=7000 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_293] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_313] - Group By Operator [GBY_312] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_310] - Group By Operator [GBY_308] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_305] (rows=155 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_303] + Select Operator [SEL_327] (rows=525333486 width=122) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_326] (rows=525333486 width=122) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_30_customer_c_customer_sk_min) AND DynamicValue(RS_30_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_30_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_27_item_i_item_sk_min) AND DynamicValue(RS_27_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_27_item_i_item_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_30_store_s_store_sk_min) AND DynamicValue(RS_30_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_30_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_0] (rows=575995635 width=122) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_323] + Group By Operator [GBY_322] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=6636187)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_152] + Group By Operator [GBY_151] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=6636187)"] + Select Operator [SEL_150] (rows=7276996 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_22] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_325] + Group By Operator [GBY_324] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 15 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_157] + Group By Operator [GBY_156] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_155] (rows=7276996 width=8) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_22] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_312] + Group By Operator [GBY_311] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_310] + Group By Operator [GBY_309] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_307] (rows=7000 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_304] diff --git a/ql/src/test/results/clientpositive/perf/tez/query59.q.out b/ql/src/test/results/clientpositive/perf/tez/query59.q.out index 76b4a5e25d..2ac474ab0e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query59.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query59.q.out @@ -110,51 +110,51 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_210] - Limit [LIM_209] (rows=100 width=976) + File Output Operator [FS_208] + Limit [LIM_207] (rows=100 width=976) Number of rows:100 - Select Operator [SEL_208] (rows=1012347 width=976) + Select Operator [SEL_206] (rows=1012347 width=976) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_59] Select Operator [SEL_58] (rows=1012347 width=976) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Merge Join Operator [MERGEJOIN_185] (rows=1012347 width=1648) + Merge Join Operator [MERGEJOIN_183] (rows=1012347 width=1648) Conds:RS_55._col12, _col0=RS_56._col1, (_col0 - 52)(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13","_col16","_col17","_col18","_col19","_col20","_col21"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col1, (_col0 - 52) Select Operator [SEL_48] (rows=28847 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_184] (rows=28847 width=776) - Conds:RS_45._col1=RS_207._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col11"] + Merge Join Operator [MERGEJOIN_182] (rows=28847 width=776) + Conds:RS_45._col1=RS_205._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col11"] <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_207] + SHUFFLE [RS_205] PartitionCols:_col0 - Select Operator [SEL_206] (rows=1704 width=104) + Select Operator [SEL_204] (rows=1704 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_205] (rows=1704 width=104) + Filter Operator [FIL_203] (rows=1704 width=104) predicate:(s_store_id is not null and s_store_sk is not null) TableScan [TS_39] (rows=1704 width=104) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_183] (rows=28847 width=676) - Conds:RS_204._col0=RS_199._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Merge Join Operator [MERGEJOIN_181] (rows=28847 width=676) + Conds:RS_202._col0=RS_197._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_199] + SHUFFLE [RS_197] PartitionCols:_col1 - Select Operator [SEL_197] (rows=317 width=8) + Select Operator [SEL_195] (rows=317 width=8) Output:["_col1"] - Filter Operator [FIL_195] (rows=317 width=8) + Filter Operator [FIL_193] (rows=317 width=8) predicate:(d_month_seq BETWEEN 1197 AND 1208 and d_week_seq is not null) TableScan [TS_15] (rows=73049 width=8) default@date_dim,d,Tbl:COMPLETE,Col:COMPLETE,Output:["d_month_seq","d_week_seq"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_204] + SHUFFLE [RS_202] PartitionCols:_col0 - Group By Operator [GBY_203] (rows=1196832 width=679) + Group By Operator [GBY_201] (rows=1196832 width=679) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_33] @@ -163,57 +163,57 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)","sum(_col3)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 Select Operator [SEL_30] (rows=525329897 width=205) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_179] (rows=525329897 width=205) - Conds:RS_188._col0=RS_191._col0(Inner),Output:["_col1","_col2","_col4","_col5"] + Merge Join Operator [MERGEJOIN_177] (rows=525329897 width=205) + Conds:RS_186._col0=RS_189._col0(Inner),Output:["_col1","_col2","_col4","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_188] + SHUFFLE [RS_186] PartitionCols:_col0 - Select Operator [SEL_187] (rows=525329897 width=114) + Select Operator [SEL_185] (rows=525329897 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_186] (rows=525329897 width=114) + Filter Operator [FIL_184] (rows=525329897 width=114) predicate:(ss_sold_date_sk is not null and ss_store_sk is not null) TableScan [TS_0] (rows=575995635 width=114) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_191] + SHUFFLE [RS_189] PartitionCols:_col0 - Select Operator [SEL_190] (rows=73049 width=99) + Select Operator [SEL_188] (rows=73049 width=99) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_189] (rows=73049 width=99) + Filter Operator [FIL_187] (rows=73049 width=99) predicate:(d_date_sk is not null and d_week_seq is not null) TableScan [TS_3] (rows=73049 width=99) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_week_seq","d_day_name"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col12, _col0 - Merge Join Operator [MERGEJOIN_181] (rows=28847 width=976) - Conds:RS_52._col1=RS_202._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13"] + Merge Join Operator [MERGEJOIN_179] (rows=28847 width=976) + Conds:RS_52._col1=RS_200._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_202] + SHUFFLE [RS_200] PartitionCols:_col0 - Select Operator [SEL_201] (rows=1704 width=192) + Select Operator [SEL_199] (rows=1704 width=192) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_200] (rows=1704 width=192) + Filter Operator [FIL_198] (rows=1704 width=192) predicate:(s_store_id is not null and s_store_sk is not null) TableScan [TS_18] (rows=1704 width=192) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_180] (rows=28847 width=788) - Conds:RS_193._col0=RS_198._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_178] (rows=28847 width=788) + Conds:RS_191._col0=RS_196._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_198] + SHUFFLE [RS_196] PartitionCols:_col1 - Select Operator [SEL_196] (rows=317 width=8) + Select Operator [SEL_194] (rows=317 width=8) Output:["_col1"] - Filter Operator [FIL_194] (rows=317 width=8) + Filter Operator [FIL_192] (rows=317 width=8) predicate:(d_month_seq BETWEEN 1185 AND 1196 and d_week_seq is not null) Please refer to the previous TableScan [TS_15] <-Reducer 3 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_193] + SHUFFLE [RS_191] PartitionCols:_col0 - Group By Operator [GBY_192] (rows=1196832 width=791) + Group By Operator [GBY_190] (rows=1196832 width=791) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] @@ -222,5 +222,5 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 Select Operator [SEL_9] (rows=525329897 width=205) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Please refer to the previous Merge Join Operator [MERGEJOIN_179] + Please refer to the previous Merge Join Operator [MERGEJOIN_177] diff --git a/ql/src/test/results/clientpositive/perf/tez/query95.q.out b/ql/src/test/results/clientpositive/perf/tez/query95.q.out index a88c534409..49e8e868c6 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query95.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query95.q.out @@ -104,123 +104,123 @@ Stage-0 limit:-1 Stage-1 Reducer 9 vectorized - File Output Operator [FS_296] - Limit [LIM_295] (rows=1 width=240) + File Output Operator [FS_302] + Limit [LIM_301] (rows=1 width=240) Number of rows:100 - Select Operator [SEL_294] (rows=1 width=240) + Select Operator [SEL_300] (rows=1 width=240) Output:["_col0","_col1","_col2"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_293] - Select Operator [SEL_292] (rows=1 width=240) + SHUFFLE [RS_299] + Select Operator [SEL_298] (rows=1 width=240) Output:["_col1","_col2","_col3"] - Group By Operator [GBY_291] (rows=1 width=232) + Group By Operator [GBY_297] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_290] - Group By Operator [GBY_289] (rows=1 width=232) + PARTITION_ONLY_SHUFFLE [RS_296] + Group By Operator [GBY_295] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(_col0)","sum(_col1)","sum(_col2)"] - Group By Operator [GBY_288] (rows=2511437 width=228) + Group By Operator [GBY_294] (rows=2511437 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_115] PartitionCols:_col0 Group By Operator [GBY_114] (rows=2511437 width=228) Output:["_col0","_col2","_col3"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col3 - Merge Join Operator [MERGEJOIN_235] (rows=5022875 width=227) - Conds:RS_61._col3=RS_287._col0(Inner),Output:["_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_241] (rows=5022875 width=227) + Conds:RS_61._col3=RS_293._col0(Inner),Output:["_col3","_col4","_col5"] <-Reducer 5 [ONE_TO_ONE_EDGE] FORWARD [RS_61] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_234] (rows=5022875 width=227) - Conds:RS_58._col3=RS_273._col0(Inner),Output:["_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_240] (rows=5022875 width=227) + Conds:RS_58._col3=RS_279._col0(Inner),Output:["_col3","_col4","_col5"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_58] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_230] (rows=5022875 width=227) - Conds:RS_55._col2=RS_254._col0(Inner),Output:["_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_236] (rows=5022875 width=227) + Conds:RS_55._col2=RS_260._col0(Inner),Output:["_col3","_col4","_col5"] <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_254] + SHUFFLE [RS_260] PartitionCols:_col0 - Select Operator [SEL_253] (rows=12 width=91) + Select Operator [SEL_259] (rows=12 width=91) Output:["_col0"] - Filter Operator [FIL_252] (rows=12 width=92) + Filter Operator [FIL_258] (rows=12 width=92) predicate:((web_company_name = 'pri') and web_site_sk is not null) TableScan [TS_9] (rows=84 width=92) default@web_site,web_site,Tbl:COMPLETE,Col:COMPLETE,Output:["web_site_sk","web_company_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_229] (rows=15673790 width=231) - Conds:RS_52._col1=RS_246._col0(Inner),Output:["_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_235] (rows=15673790 width=231) + Conds:RS_52._col1=RS_252._col0(Inner),Output:["_col2","_col3","_col4","_col5"] <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_246] + SHUFFLE [RS_252] PartitionCols:_col0 - Select Operator [SEL_245] (rows=784314 width=90) + Select Operator [SEL_251] (rows=784314 width=90) Output:["_col0"] - Filter Operator [FIL_244] (rows=784314 width=90) + Filter Operator [FIL_250] (rows=784314 width=90) predicate:((ca_state = 'TX') and ca_address_sk is not null) TableScan [TS_6] (rows=40000000 width=90) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_228] (rows=15987241 width=235) - Conds:RS_262._col0=RS_238._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_234] (rows=15987241 width=235) + Conds:RS_268._col0=RS_244._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_238] + SHUFFLE [RS_244] PartitionCols:_col0 - Select Operator [SEL_237] (rows=8116 width=98) + Select Operator [SEL_243] (rows=8116 width=98) Output:["_col0"] - Filter Operator [FIL_236] (rows=8116 width=98) + Filter Operator [FIL_242] (rows=8116 width=98) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=98) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_262] + SHUFFLE [RS_268] PartitionCols:_col0 - Select Operator [SEL_261] (rows=143895019 width=239) + Select Operator [SEL_267] (rows=143895019 width=239) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_260] (rows=143895019 width=239) + Filter Operator [FIL_266] (rows=143895019 width=239) predicate:((ws_ship_addr_sk BETWEEN DynamicValue(RS_53_customer_address_ca_address_sk_min) AND DynamicValue(RS_53_customer_address_ca_address_sk_max) and in_bloom_filter(ws_ship_addr_sk, DynamicValue(RS_53_customer_address_ca_address_sk_bloom_filter))) and (ws_ship_date_sk BETWEEN DynamicValue(RS_50_date_dim_d_date_sk_min) AND DynamicValue(RS_50_date_dim_d_date_sk_max) and in_bloom_filter(ws_ship_date_sk, DynamicValue(RS_50_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_56_web_site_web_site_sk_min) AND DynamicValue(RS_56_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_56_web_site_web_site_sk_bloom_filter))) and ws_order_number is not null and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) TableScan [TS_0] (rows=144002668 width=239) default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_ship_date_sk","ws_ship_addr_sk","ws_web_site_sk","ws_order_number","ws_ext_ship_cost","ws_net_profit"] <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_243] - Group By Operator [GBY_242] (rows=1 width=12) + BROADCAST [RS_249] + Group By Operator [GBY_248] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_241] - Group By Operator [GBY_240] (rows=1 width=12) + SHUFFLE [RS_247] + Group By Operator [GBY_246] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_239] (rows=8116 width=4) + Select Operator [SEL_245] (rows=8116 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_237] + Please refer to the previous Select Operator [SEL_243] <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_251] - Group By Operator [GBY_250] (rows=1 width=12) + BROADCAST [RS_257] + Group By Operator [GBY_256] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_249] - Group By Operator [GBY_248] (rows=1 width=12) + SHUFFLE [RS_255] + Group By Operator [GBY_254] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_247] (rows=784314 width=4) + Select Operator [SEL_253] (rows=784314 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_245] + Please refer to the previous Select Operator [SEL_251] <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_259] - Group By Operator [GBY_258] (rows=1 width=12) + BROADCAST [RS_265] + Group By Operator [GBY_264] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_257] - Group By Operator [GBY_256] (rows=1 width=12) + SHUFFLE [RS_263] + Group By Operator [GBY_262] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_255] (rows=12 width=4) + Select Operator [SEL_261] (rows=12 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_253] + Please refer to the previous Select Operator [SEL_259] <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_273] + FORWARD [RS_279] PartitionCols:_col0 - Group By Operator [GBY_272] (rows=14686712 width=4) + Group By Operator [GBY_278] (rows=14686712 width=4) Output:["_col0"],keys:KEY._col0 <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_24] @@ -231,58 +231,58 @@ Stage-0 Output:["_col1"] Filter Operator [FIL_21] (rows=1411940834 width=11) predicate:(_col0 <> _col2) - Merge Join Operator [MERGEJOIN_231] (rows=1411940834 width=11) - Conds:RS_268._col1=RS_271._col1(Inner),Output:["_col0","_col1","_col2"] + Merge Join Operator [MERGEJOIN_237] (rows=1411940834 width=11) + Conds:RS_274._col1=RS_277._col1(Inner),Output:["_col0","_col1","_col2"] <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_268] + SHUFFLE [RS_274] PartitionCols:_col1 - Select Operator [SEL_267] (rows=144002668 width=7) + Select Operator [SEL_273] (rows=144002668 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_266] (rows=144002668 width=7) + Filter Operator [FIL_272] (rows=144002668 width=7) predicate:((ws_order_number BETWEEN DynamicValue(RS_58_ws1_ws_order_number_min) AND DynamicValue(RS_58_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_58_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null) TableScan [TS_12] (rows=144002668 width=7) default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_264] - Group By Operator [GBY_263] (rows=1 width=12) + BROADCAST [RS_270] + Group By Operator [GBY_269] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_183] - Group By Operator [GBY_182] (rows=1 width=12) + SHUFFLE [RS_193] + Group By Operator [GBY_192] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_181] (rows=5022875 width=8) + Select Operator [SEL_191] (rows=5022875 width=8) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_230] + Please refer to the previous Merge Join Operator [MERGEJOIN_236] <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_271] + SHUFFLE [RS_277] PartitionCols:_col1 - Select Operator [SEL_270] (rows=144002668 width=7) + Select Operator [SEL_276] (rows=144002668 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_269] (rows=144002668 width=7) + Filter Operator [FIL_275] (rows=144002668 width=7) predicate:((ws_order_number BETWEEN DynamicValue(RS_58_ws1_ws_order_number_min) AND DynamicValue(RS_58_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_58_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null) TableScan [TS_15] (rows=144002668 width=7) default@web_sales,ws2,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_265] - Please refer to the previous Group By Operator [GBY_263] + BROADCAST [RS_271] + Please refer to the previous Group By Operator [GBY_269] <-Reducer 25 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_287] + FORWARD [RS_293] PartitionCols:_col0 - Group By Operator [GBY_286] (rows=8007986 width=4) + Group By Operator [GBY_292] (rows=8007986 width=4) Output:["_col0"],keys:KEY._col0 <-Reducer 24 [SIMPLE_EDGE] SHUFFLE [RS_46] PartitionCols:_col0 Group By Operator [GBY_45] (rows=14398467 width=4) Output:["_col0"],keys:_col14 - Merge Join Operator [MERGEJOIN_233] (rows=1384229738 width=4) - Conds:RS_41._col0=RS_285._col13(Inner),Output:["_col14"] + Merge Join Operator [MERGEJOIN_239] (rows=1384229738 width=4) + Conds:RS_41._col0=RS_291._col13(Inner),Output:["_col14"] <-Map 27 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_285] + SHUFFLE [RS_291] PartitionCols:_col13 - Select Operator [SEL_284] (rows=14398467 width=272) + Select Operator [SEL_290] (rows=14398467 width=272) Output:["_col13"] - Filter Operator [FIL_283] (rows=14398467 width=4) + Filter Operator [FIL_289] (rows=14398467 width=4) predicate:wr_order_number is not null TableScan [TS_38] (rows=14398467 width=4) default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_order_number"] @@ -293,38 +293,38 @@ Stage-0 Output:["_col0"] Filter Operator [FIL_36] (rows=1411940834 width=11) predicate:(_col0 <> _col2) - Merge Join Operator [MERGEJOIN_232] (rows=1411940834 width=11) - Conds:RS_279._col1=RS_282._col1(Inner),Output:["_col0","_col1","_col2"] + Merge Join Operator [MERGEJOIN_238] (rows=1411940834 width=11) + Conds:RS_285._col1=RS_288._col1(Inner),Output:["_col0","_col1","_col2"] <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_279] + SHUFFLE [RS_285] PartitionCols:_col1 - Select Operator [SEL_278] (rows=144002668 width=7) + Select Operator [SEL_284] (rows=144002668 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_277] (rows=144002668 width=7) + Filter Operator [FIL_283] (rows=144002668 width=7) predicate:((ws_order_number BETWEEN DynamicValue(RS_61_ws1_ws_order_number_min) AND DynamicValue(RS_61_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_61_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null) TableScan [TS_27] (rows=144002668 width=7) default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_275] - Group By Operator [GBY_274] (rows=1 width=12) + BROADCAST [RS_281] + Group By Operator [GBY_280] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] - FORWARD [RS_202] - Group By Operator [GBY_201] (rows=1 width=12) + FORWARD [RS_212] + Group By Operator [GBY_211] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_200] (rows=5022875 width=8) + Select Operator [SEL_210] (rows=5022875 width=8) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_234] + Please refer to the previous Merge Join Operator [MERGEJOIN_240] <-Map 26 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_282] + SHUFFLE [RS_288] PartitionCols:_col1 - Select Operator [SEL_281] (rows=144002668 width=7) + Select Operator [SEL_287] (rows=144002668 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_280] (rows=144002668 width=7) + Filter Operator [FIL_286] (rows=144002668 width=7) predicate:((ws_order_number BETWEEN DynamicValue(RS_61_ws1_ws_order_number_min) AND DynamicValue(RS_61_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_61_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null) TableScan [TS_30] (rows=144002668 width=7) default@web_sales,ws2,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_276] - Please refer to the previous Group By Operator [GBY_274] + BROADCAST [RS_282] + Please refer to the previous Group By Operator [GBY_280]