http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query85.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query85.q.out b/ql/src/test/results/clientpositive/perf/spark/query85.q.out index 6bdbf7e..a7bf288 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query85.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query85.q.out @@ -182,8 +182,7 @@ POSTHOOK: Input: default@web_sales #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -191,47 +190,42 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 13 + Map 12 Map Operator Tree: TableScan - alias: reason - filterExpr: r_reason_sk is not null (type: boolean) - Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE + alias: web_page + filterExpr: wp_web_page_sk is not null (type: boolean) + Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: r_reason_sk is not null (type: boolean) - Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE + predicate: wp_web_page_sk is not null (type: boolean) + Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: r_reason_sk (type: int), r_reason_desc (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE + expressions: wp_web_page_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col4 (type: int) + 0 _col10 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - - Stage: Stage-3 - Spark -#### A masked pattern was here #### - Vertices: - Map 11 + Map 13 Map Operator Tree: TableScan - alias: web_page - filterExpr: wp_web_page_sk is not null (type: boolean) - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + alias: reason + filterExpr: r_reason_sk is not null (type: boolean) + Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: wp_web_page_sk is not null (type: boolean) - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + predicate: r_reason_sk is not null (type: boolean) + Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: wp_web_page_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + expressions: r_reason_sk (type: int), r_reason_desc (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col10 (type: int) + 0 _col4 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: @@ -241,11 +235,11 @@ STAGE PLANS: Spark Edges: Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 28), Map 9 (PARTITION-LEVEL SORT, 28) - Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 178), Reducer 2 (PARTITION-LEVEL SORT, 178) - Reducer 4 <- Map 12 (PARTITION-LEVEL SORT, 65), Reducer 3 (PARTITION-LEVEL SORT, 65) - Reducer 5 <- Map 14 (PARTITION-LEVEL SORT, 83), Reducer 4 (PARTITION-LEVEL SORT, 83) - Reducer 6 <- Map 15 (PARTITION-LEVEL SORT, 13), Reducer 5 (PARTITION-LEVEL SORT, 13) - Reducer 7 <- Reducer 6 (GROUP, 7) + Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 25), Reducer 2 (PARTITION-LEVEL SORT, 25) + Reducer 4 <- Map 11 (PARTITION-LEVEL SORT, 21), Reducer 3 (PARTITION-LEVEL SORT, 21) + Reducer 5 <- Map 14 (PARTITION-LEVEL SORT, 186), Reducer 4 (PARTITION-LEVEL SORT, 186) + Reducer 6 <- Map 15 (PARTITION-LEVEL SORT, 29), Reducer 5 (PARTITION-LEVEL SORT, 29) + Reducer 7 <- Reducer 6 (GROUP, 10) Reducer 8 <- Reducer 7 (SORT, 1) #### A masked pattern was here #### Vertices: @@ -272,24 +266,24 @@ STAGE PLANS: Map 10 Map Operator Tree: TableScan - alias: customer_address - filterExpr: ((ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and (ca_country = 'United States') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + alias: cd2 + filterExpr: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and ca_address_sk is not null) (type: boolean) - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + predicate: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ca_address_sk (type: int), ca_state (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + expressions: cd_demo_sk (type: int), cd_marital_status (type: string), cd_education_status (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1861800 Data size: 717186159 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: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Map 12 + Map 11 Map Operator Tree: TableScan alias: date_dim @@ -311,41 +305,42 @@ STAGE PLANS: Map 14 Map Operator Tree: TableScan - alias: cd1 - filterExpr: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + alias: customer_address + filterExpr: ((ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and (ca_country = 'United States') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + predicate: ((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cd_demo_sk (type: int), cd_marital_status (type: string), cd_education_status (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + expressions: ca_address_sk (type: int), (ca_state) IN ('KY', 'GA', 'NM') (type: boolean), (ca_state) IN ('MT', 'OR', 'IN') (type: boolean), (ca_state) IN ('WI', 'MO', 'WV') (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 20000000 Data size: 20297597642 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: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean) Execution mode: vectorized Map 15 Map Operator Tree: TableScan - alias: cd2 + alias: cd1 filterExpr: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cd_demo_sk (type: int), cd_marital_status (type: string), cd_education_status (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: cd_demo_sk (type: int), cd_marital_status (type: string), cd_education_status (type: string), (cd_marital_status = 'M') (type: boolean), (cd_education_status = '4 yr Degree') (type: boolean), (cd_marital_status = 'D') (type: boolean), (cd_education_status = 'Primary') (type: boolean), (cd_marital_status = 'U') (type: boolean), (cd_education_status = 'Advanced Degree') (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) sort order: +++ Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string) Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean) Execution mode: vectorized Map 9 Map Operator Tree: @@ -357,15 +352,15 @@ STAGE PLANS: predicate: ((ws_net_profit BETWEEN 100 AND 200 or ws_net_profit BETWEEN 150 AND 300 or ws_net_profit BETWEEN 50 AND 250) and (ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null and ws_web_page_sk is not null) (type: boolean) Statistics: Num rows: 16000296 Data size: 2175577518 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_web_page_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_sales_price (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_web_page_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_net_profit BETWEEN 100 AND 200 (type: boolean), ws_net_profit BETWEEN 150 AND 300 (type: boolean), ws_net_profit BETWEEN 50 AND 250 (type: boolean), ws_sales_price BETWEEN 100 AND 150 (type: boolean), ws_sales_price BETWEEN 50 AND 100 (type: boolean), ws_sales_price BETWEEN 150 AND 200 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 16000296 Data size: 2175577518 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int), _col3 (type: int) sort order: ++ Map-reduce partition columns: _col1 (type: int), _col3 (type: int) Statistics: Num rows: 16000296 Data size: 2175577518 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + value expressions: _col0 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean), _col10 (type: boolean) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -375,45 +370,30 @@ STAGE PLANS: keys: 0 _col0 (type: int), _col5 (type: int) 1 _col1 (type: int), _col3 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col6, _col7, _col8, _col10, _col12, _col13, _col14 + outputColumnNames: _col1, _col2, _col3, _col4, _col6, _col7, _col8, _col10, _col12, _col13, _col14, _col15, _col16, _col17, _col18 Statistics: Num rows: 17600325 Data size: 2393135321 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int) + key expressions: _col3 (type: int) sort order: + - Map-reduce partition columns: _col2 (type: int) + Map-reduce partition columns: _col3 (type: int) Statistics: Num rows: 17600325 Data size: 2393135321 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: int), _col10 (type: int), _col12 (type: int), _col13 (type: decimal(7,2)), _col14 (type: decimal(7,2)) + value expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: int), _col10 (type: int), _col12 (type: int), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean), _col18 (type: boolean) Reducer 3 - Local Work: - Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col3 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4, _col6, _col7, _col8, _col10, _col12, _col13, _col14, _col16 - Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((_col16) IN ('KY', 'GA', 'NM') and _col14 BETWEEN 100 AND 200) or ((_col16) IN ('MT', 'OR', 'IN') and _col14 BETWEEN 150 AND 300) or ((_col16) IN ('WI', 'MO', 'WV') and _col14 BETWEEN 50 AND 250)) (type: boolean) - Statistics: Num rows: 7333332 Data size: 7442451276 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col10 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4, _col6, _col7, _col8, _col12, _col13 - input vertices: - 1 Map 11 - Statistics: Num rows: 8066665 Data size: 8186696581 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col8 (type: int) - sort order: + - Map-reduce partition columns: _col8 (type: int) - Statistics: Num rows: 8066665 Data size: 8186696581 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col13 (type: decimal(7,2)) + outputColumnNames: _col1, _col2, _col4, _col6, _col7, _col8, _col10, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col20, _col21 + Statistics: Num rows: 19360357 Data size: 2632448910 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col8 (type: int) + sort order: + + Map-reduce partition columns: _col8 (type: int) + Statistics: Num rows: 19360357 Data size: 2632448910 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col10 (type: int), _col12 (type: int), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean), _col18 (type: boolean), _col20 (type: string), _col21 (type: string) Reducer 4 Local Work: Map Reduce Local Work @@ -424,65 +404,82 @@ STAGE PLANS: keys: 0 _col8 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col4, _col6, _col7, _col12, _col13 - Statistics: Num rows: 8873331 Data size: 9005366434 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1, _col2, _col4, _col6, _col7, _col10, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col20, _col21 + Statistics: Num rows: 21296393 Data size: 2895693863 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col4 (type: int) + 0 _col10 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col6, _col7, _col12, _col13, _col22 + outputColumnNames: _col1, _col2, _col4, _col6, _col7, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col20, _col21 input vertices: - 1 Map 13 - Statistics: Num rows: 9760664 Data size: 9905903292 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: 9760664 Data size: 9905903292 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col13 (type: decimal(7,2)), _col22 (type: string) + 1 Map 12 + Statistics: Num rows: 23426032 Data size: 3185263318 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col6, _col7, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col20, _col21, _col25 + input vertices: + 1 Map 13 + Statistics: Num rows: 25768635 Data size: 3503789725 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 25768635 Data size: 3503789725 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean), _col18 (type: boolean), _col20 (type: string), _col21 (type: string), _col25 (type: string) Reducer 5 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col3, _col6, _col7, _col12, _col13, _col22, _col24, _col25 - Statistics: Num rows: 10736730 Data size: 10896493857 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1, _col6, _col7, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col20, _col21, _col25, _col27, _col28, _col29 + Statistics: Num rows: 28345499 Data size: 3854168781 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((_col24 = 'D') and (_col25 = 'Primary') and _col13 BETWEEN 50 AND 100) or ((_col24 = 'M') and (_col25 = '4 yr Degree') and _col13 BETWEEN 100 AND 150) or ((_col24 = 'U') and (_col25 = 'Advanced Degree') and _col13 BETWEEN 150 AND 200)) (type: boolean) - Statistics: Num rows: 894726 Data size: 908039632 Basic stats: COMPLETE Column stats: NONE + predicate: ((_col27 and _col13) or (_col28 and _col14) or (_col29 and _col15)) (type: boolean) + Statistics: Num rows: 21259122 Data size: 2890626279 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col3 (type: int), _col24 (type: string), _col25 (type: string) + key expressions: _col1 (type: int), _col20 (type: string), _col21 (type: string) sort order: +++ - Map-reduce partition columns: _col3 (type: int), _col24 (type: string), _col25 (type: string) - Statistics: Num rows: 894726 Data size: 908039632 Basic stats: COMPLETE Column stats: NONE - value expressions: _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col22 (type: string) + Map-reduce partition columns: _col1 (type: int), _col20 (type: string), _col21 (type: string) + Statistics: Num rows: 21259122 Data size: 2890626279 Basic stats: COMPLETE Column stats: NONE + value expressions: _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col16 (type: boolean), _col17 (type: boolean), _col18 (type: boolean), _col25 (type: string) Reducer 6 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: int), _col24 (type: string), _col25 (type: string) + 0 _col1 (type: int), _col20 (type: string), _col21 (type: string) 1 _col0 (type: int), _col1 (type: string), _col2 (type: string) - outputColumnNames: _col6, _col7, _col12, _col22 - Statistics: Num rows: 2047980 Data size: 788904791 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col12), count(_col12), sum(_col7), count(_col7), sum(_col6), count(_col6) - keys: _col22 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 2047980 Data size: 788904791 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2047980 Data size: 788904791 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint) + outputColumnNames: _col6, _col7, _col12, _col16, _col17, _col18, _col25, _col33, _col34, _col35, _col36, _col37, _col38 + Statistics: Num rows: 23385034 Data size: 3179688975 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col33 and _col34 and _col16) or (_col35 and _col36 and _col17) or (_col37 and _col38 and _col18)) (type: boolean) + Statistics: Num rows: 8769387 Data size: 1192383263 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col25 (type: string) + outputColumnNames: _col6, _col7, _col12, _col25 + Statistics: Num rows: 8769387 Data size: 1192383263 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col12), count(_col12), sum(_col7), count(_col7), sum(_col6), count(_col6) + keys: _col25 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 8769387 Data size: 1192383263 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 8769387 Data size: 1192383263 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint) Reducer 7 Execution mode: vectorized Reduce Operator Tree: @@ -491,15 +488,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 1023990 Data size: 394452395 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4384693 Data size: 596191563 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(_col1) / _col2) (type: double), (_col3 / _col4) (type: decimal(37,22)), (_col5 / _col6) (type: decimal(37,22)), substr(_col0, 1, 20) (type: string) outputColumnNames: _col4, _col5, _col6, _col7 - Statistics: Num rows: 1023990 Data size: 394452395 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4384693 Data size: 596191563 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col7 (type: string), _col4 (type: double), _col5 (type: decimal(37,22)), _col6 (type: decimal(37,22)) sort order: ++++ - Statistics: Num rows: 1023990 Data size: 394452395 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4384693 Data size: 596191563 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reducer 8 Execution mode: vectorized @@ -507,13 +504,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: decimal(37,22)), KEY.reducesinkkey3 (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1023990 Data size: 394452395 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4384693 Data size: 596191563 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 38500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 38500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query86.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query86.q.out b/ql/src/test/results/clientpositive/perf/spark/query86.q.out index 3892340..835ac5c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query86.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query86.q.out @@ -154,10 +154,10 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col6, _col7 + outputColumnNames: _col2, _col5, _col6 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col7 (type: string), _col6 (type: string), _col2 (type: decimal(7,2)) + expressions: _col6 (type: string), _col5 (type: string), _col2 (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Group By Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query87.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query87.q.out b/ql/src/test/results/clientpositive/perf/spark/query87.q.out index daa725e..a74f1fa 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query87.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query87.q.out @@ -198,10 +198,10 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col3, _col6, _col7 + outputColumnNames: _col3, _col5, _col6 Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) + keys: _col6 (type: string), _col5 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE @@ -272,10 +272,10 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col3, _col6, _col7 + outputColumnNames: _col3, _col5, _col6 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) + keys: _col6 (type: string), _col5 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE @@ -346,10 +346,10 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col3, _col6, _col7 + outputColumnNames: _col3, _col5, _col6 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) + keys: _col6 (type: string), _col5 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query89.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query89.q.out b/ql/src/test/results/clientpositive/perf/spark/query89.q.out index 589dead..40a698a 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query89.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query89.q.out @@ -154,14 +154,14 @@ STAGE PLANS: Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int), d_moy (type: int) - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 36524 Data size: 40870356 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: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int) + value expressions: _col1 (type: int) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -189,7 +189,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col5, _col6, _col7, _col10 + outputColumnNames: _col2, _col3, _col5, _col6, _col7, _col9 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -197,13 +197,13 @@ STAGE PLANS: keys: 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col3, _col5, _col6, _col7, _col10, _col12, _col13 + outputColumnNames: _col3, _col5, _col6, _col7, _col9, _col11, _col12 input vertices: 1 Map 9 Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col3) - keys: _col5 (type: string), _col6 (type: string), _col7 (type: string), _col10 (type: int), _col12 (type: string), _col13 (type: string) + keys: _col5 (type: string), _col6 (type: string), _col7 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query9.q.out b/ql/src/test/results/clientpositive/perf/spark/query9.q.out index 6bb02a4..ce5e87a 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query9.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query9.q.out @@ -524,10 +524,14 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 + Select Operator + expressions: (_col0 > 7887297L) (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 Reducer 17 Execution mode: vectorized Local Work: @@ -574,10 +578,14 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 + Select Operator + expressions: (_col0 > 10872978L) (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 Reducer 23 Execution mode: vectorized Local Work: @@ -624,10 +632,14 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 + Select Operator + expressions: (_col0 > 43571537L) (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 Reducer 29 Execution mode: vectorized Local Work: @@ -656,10 +668,14 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 + Select Operator + expressions: (_col0 > 409437L) (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 Reducer 31 Execution mode: vectorized Local Work: @@ -724,10 +740,14 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 - 1 + Select Operator + expressions: (_col0 > 4595804L) (type: boolean) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 Stage: Stage-1 Spark @@ -895,7 +915,7 @@ STAGE PLANS: 1 Reducer 31 Statistics: Num rows: 36 Data size: 52380 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: CASE WHEN ((_col1 > 409437L)) THEN (_col2) ELSE (_col3) END (type: decimal(37,22)), CASE WHEN ((_col4 > 4595804L)) THEN (_col5) ELSE (_col6) END (type: decimal(37,22)), CASE WHEN ((_col7 > 7887297L)) THEN (_col8) ELSE (_col9) END (type: decimal(37,22)), CASE WHEN ((_col10 > 10872978L)) THEN (_col11) ELSE (_col12) END (type: decimal(37,22)), CASE WHEN ((_col13 > 43571537L)) THEN (_col14) ELSE (_col15) END (type: decimal(37,22)) + expressions: CASE WHEN (_col1) THEN (_col2) ELSE (_col3) END (type: decimal(37,22)), CASE WHEN (_col4) THEN (_col5) ELSE (_col6) END (type: decimal(37,22)), CASE WHEN (_col7) THEN (_col8) ELSE (_col9) END (type: decimal(37,22)), CASE WHEN (_col10) THEN (_col11) ELSE (_col12) END (type: decimal(37,22)), CASE WHEN (_col13) THEN (_col14) ELSE (_col15) END (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 36 Data size: 52380 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query91.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query91.q.out b/ql/src/test/results/clientpositive/perf/spark/query91.q.out index b9fa42f..be56486 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query91.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query91.q.out @@ -258,7 +258,7 @@ STAGE PLANS: keys: 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col3, _col8, _col9, _col10 + outputColumnNames: _col1, _col3, _col6, _col7, _col8 input vertices: 1 Map 12 Statistics: Num rows: 34846646 Data size: 3699254122 Basic stats: COMPLETE Column stats: NONE @@ -267,7 +267,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 34846646 Data size: 3699254122 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: decimal(7,2)), _col8 (type: string), _col9 (type: string), _col10 (type: string) + value expressions: _col3 (type: decimal(7,2)), _col6 (type: string), _col7 (type: string), _col8 (type: string) Reducer 2 Reduce Operator Tree: Join Operator @@ -310,7 +310,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col1 (type: int) - outputColumnNames: _col2, _col5, _col6, _col12, _col17, _col18, _col19 + outputColumnNames: _col2, _col5, _col6, _col11, _col14, _col15, _col16 Statistics: Num rows: 106480005 Data size: 91574956652 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -318,13 +318,13 @@ STAGE PLANS: keys: 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col5, _col6, _col12, _col17, _col18, _col19 + outputColumnNames: _col5, _col6, _col11, _col14, _col15, _col16 input vertices: 1 Map 13 Statistics: Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col12) - keys: _col5 (type: string), _col6 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: string) + aggregations: sum(_col11) + keys: _col5 (type: string), _col6 (type: string), _col14 (type: string), _col15 (type: string), _col16 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query92.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query92.q.out b/ql/src/test/results/clientpositive/perf/spark/query92.q.out index c7179e0..9aa135e 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query92.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query92.q.out @@ -228,10 +228,10 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col2 (type: int) - outputColumnNames: _col2, _col6 + outputColumnNames: _col2, _col5 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col2 > CAST( (1.3 * _col6) AS decimal(14,7))) (type: boolean) + predicate: (_col2 > _col5) (type: boolean) Statistics: Num rows: 58081078 Data size: 7897346909 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: decimal(7,2)) @@ -290,7 +290,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), (_col1 / _col2) (type: decimal(37,22)) + expressions: _col0 (type: int), CAST( (1.3 * (_col1 / _col2)) AS decimal(14,7)) (type: decimal(14,7)) outputColumnNames: _col0, _col1 Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -298,7 +298,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(37,22)) + value expressions: _col1 (type: decimal(14,7)) Reducer 8 Reduce Operator Tree: Join Operator @@ -314,7 +314,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col2 (type: int) Statistics: Num rows: 87121617 Data size: 11846020431 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(37,22)) + value expressions: _col1 (type: decimal(14,7)) Stage: Stage-0 Fetch Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query93.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query93.q.out b/ql/src/test/results/clientpositive/perf/spark/query93.q.out index 0263eb0..f393c13 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query93.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query93.q.out @@ -89,8 +89,8 @@ STAGE PLANS: predicate: (sr_item_sk is not null and sr_reason_sk is not null and sr_ticket_number is not null) (type: boolean) Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: sr_item_sk (type: int), sr_reason_sk (type: int), sr_ticket_number (type: int), sr_return_quantity (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: sr_item_sk (type: int), sr_reason_sk (type: int), sr_ticket_number (type: int), sr_return_quantity (type: int), sr_return_quantity is not null (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -98,7 +98,7 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col2, _col3 + outputColumnNames: _col0, _col2, _col3, _col4 input vertices: 1 Map 5 Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE @@ -107,7 +107,7 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: int), _col2 (type: int) Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int) + value expressions: _col3 (type: int), _col4 (type: boolean) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -121,15 +121,15 @@ STAGE PLANS: predicate: (ss_item_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_ticket_number (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ss_item_sk (type: int), ss_customer_sk (type: int), ss_ticket_number (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)), (CAST( ss_quantity AS decimal(10,0)) * ss_sales_price) (type: decimal(18,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col2 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col2 (type: int) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)) + value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)), _col5 (type: decimal(18,2)) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -139,10 +139,10 @@ STAGE PLANS: keys: 0 _col0 (type: int), _col2 (type: int) 1 _col0 (type: int), _col2 (type: int) - outputColumnNames: _col3, _col7, _col9, _col10 + outputColumnNames: _col3, _col4, _col7, _col9, _col10, _col11 Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col7 (type: int), CASE WHEN (_col3 is not null) THEN ((CAST( (_col9 - _col3) AS decimal(10,0)) * _col10)) ELSE ((CAST( _col9 AS decimal(10,0)) * _col10)) END (type: decimal(18,2)) + expressions: _col7 (type: int), CASE WHEN (_col4) THEN ((CAST( (_col9 - _col3) AS decimal(10,0)) * _col10)) ELSE (_col11) END (type: decimal(18,2)) outputColumnNames: _col0, _col1 Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Group By Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query98.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query98.q.out b/ql/src/test/results/clientpositive/perf/spark/query98.q.out index 816da61..2931144 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query98.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query98.q.out @@ -168,11 +168,11 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: _col2, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col2) - keys: _col10 (type: string), _col9 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: decimal(7,2)) + keys: _col9 (type: string), _col8 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query99.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query99.q.out b/ql/src/test/results/clientpositive/perf/spark/query99.q.out index 6e656d4..220aae5 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query99.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query99.q.out @@ -103,7 +103,7 @@ STAGE PLANS: Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: @@ -118,12 +118,12 @@ STAGE PLANS: predicate: w_warehouse_sk is not null (type: boolean) Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string) + expressions: w_warehouse_sk (type: int), substr(w_warehouse_name, 1, 20) (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col4 (type: int) + 0 _col3 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: @@ -143,7 +143,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col3 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: @@ -167,15 +167,15 @@ STAGE PLANS: predicate: (cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_sk is not null) (type: boolean) Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cs_sold_date_sk (type: int), cs_ship_date_sk (type: int), cs_call_center_sk (type: int), cs_ship_mode_sk (type: int), cs_warehouse_sk (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: cs_ship_date_sk (type: int), cs_call_center_sk (type: int), cs_ship_mode_sk (type: int), cs_warehouse_sk (type: int), CASE WHEN (((cs_ship_date_sk - cs_sold_date_sk) <= 30)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((cs_ship_date_sk - cs_sold_date_sk) > 30) and ((cs_ship_date_sk - cs_sold_date_sk) <= 60))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((cs_ship_date_sk - cs_sold_date_sk) > 60) and ((cs_ship_date_sk - cs_sold_date_sk) <= 90))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((cs_ship_date_sk - cs_sold_date_sk) > 90) and ((cs_ship_date_sk - cs_sold_date_sk) <= 120))) THEN (1) ELSE (0) END (type: int), CASE WHEN (((cs_ship_date_sk - cs_sold_date_sk) > 120)) THEN (1) ELSE (0) END (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 287989836 Data size: 38999608952 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) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col8 (type: int) Execution mode: vectorized Map 5 Map Operator Tree: @@ -204,17 +204,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col8 + outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11 input vertices: 1 Map 6 Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE @@ -222,9 +222,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col4 (type: int) + 0 _col3 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col8, _col10 + outputColumnNames: _col2, _col4, _col5, _col6, _col7, _col8, _col11, _col13 input vertices: 1 Map 7 Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE @@ -232,29 +232,25 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col8, _col10, _col12 + outputColumnNames: _col4, _col5, _col6, _col7, _col8, _col11, _col13, _col15 input vertices: 1 Map 8 Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: substr(_col10, 1, 20) (type: string), _col12 (type: string), _col8 (type: string), CASE WHEN (((_col1 - _col0) <= 30)) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col1 - _col0) > 30) and ((_col1 - _col0) <= 60))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col1 - _col0) > 60) and ((_col1 - _col0) <= 90))) THEN (1) ELSE (0) END (type: int), CASE WHEN ((((_col1 - _col0) > 90) and ((_col1 - _col0) <= 120))) THEN (1) ELSE (0) END (type: int), CASE WHEN (((_col1 - _col0) > 120)) THEN (1) ELSE (0) END (type: int) + Group By Operator + aggregations: sum(_col4), sum(_col5), sum(_col6), sum(_col7), sum(_col8) + keys: _col13 (type: string), _col15 (type: string), _col11 (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: PARTIAL Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint) Reducer 3 Execution mode: vectorized Reduce Operator Tree: http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/cbo_query1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query1.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query1.q.out index 295ba99..9d0fa3a 100644 --- a/ql/src/test/results/clientpositive/perf/tez/cbo_query1.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query1.q.out @@ -59,7 +59,7 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(c_customer_id=[$1]) - HiveJoin(condition=[AND(=($3, $8), >($4, $7))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($3, $7), >($4, $6))], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1]) HiveFilter(condition=[IS NOT NULL($0)]) @@ -71,10 +71,10 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(sr_returned_date_sk=[$0], sr_customer_sk=[$3], sr_store_sk=[$7], sr_fee=[$14]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($3))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject(s_store_sk=[$0], s_state=[CAST(_UTF-16LE'NM'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveProject(s_store_sk=[$0]) HiveFilter(condition=[AND(=($24, _UTF-16LE'NM'), IS NOT NULL($0))]) HiveTableScan(table=[[default, store]], table:alias=[store]) HiveProject(_o__c0=[*(/($1, $2), 1.2)], ctr_store_sk=[$0]) @@ -85,7 +85,7 @@ HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(sr_returned_date_sk=[$0], sr_customer_sk=[$3], sr_store_sk=[$7], sr_fee=[$14]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2000), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out index b226905..ccad67d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out @@ -154,7 +154,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$4], sort4=[$6], sort5= HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), BETWEEN(false, $8, 4, 7), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(ws_bill_customer_sk0=[$0], $f1=[true]) @@ -163,7 +163,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$4], sort4=[$6], sort5= HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4]) HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), BETWEEN(false, $8, 4, 7), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject(cs_ship_customer_sk0=[$0], $f1=[true]) @@ -172,7 +172,7 @@ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$4], sort4=[$6], sort5= HiveProject(cs_sold_date_sk=[$0], cs_ship_customer_sk=[$7]) HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($0))]) HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER], d_moy=[$8]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2002), BETWEEN(false, $8, 4, 7), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out index e09f7ec..de0783b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out @@ -159,65 +159,61 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### CBO PLAN: HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) HiveProject(c_preferred_cust_flag=[$1]) - HiveJoin(condition=[AND(=($0, $5), CASE(CAST(IS NOT NULL($6)):BOOLEAN, CASE(CAST(IS NOT NULL($8)):BOOLEAN, >(/($4, $8), /($2, $6)), >(null, /($2, $6))), CASE(CAST(IS NOT NULL($8)):BOOLEAN, >(/($4, $8), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($0, $5), CASE(CAST(IS NOT NULL($6)):BOOLEAN, CASE($9, >(/($4, $8), /($2, $6)), >(null, /($2, $6))), CASE($9, >(/($4, $8), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f4=[$3], $f9=[$7]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f9=[-($11, $10)]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_discount_amt=[$14], ss_ext_list_price=[$17]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) - HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], -=[-($17, $14)]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveJoin(condition=[=($2, $4)], joinType=[inner], algorithm=[none], cost=[not available]) HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject($f0=[$0], $f8=[$7]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[-($11, $10)]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], ws_ext_discount_amt=[$22], ws_ext_list_price=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER]) - HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], -=[-($25, $22)]) + HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) HiveProject($f0=[$0], $f9=[$7]) HiveFilter(condition=[>($7, 0)]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f9=[-($11, $10)]) - HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) - HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) - HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_discount_amt=[$14], ss_ext_list_price=[$17]) - HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) - HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) - HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) - HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) - HiveProject($f0=[$0], $f8=[$7]) - HiveFilter(condition=[>($7, 0)]) - HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) - HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[-($11, $10)]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) HiveTableScan(table=[[default, customer]], table:alias=[customer]) - HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) - HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], ws_ext_discount_amt=[$22], ws_ext_list_price=[$25]) - HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) - HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], -=[-($17, $14)]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(customer_id=[$0], year_total=[$7], CAST=[CAST(IS NOT NULL($7)):BOOLEAN]) + HiveFilter(condition=[>($7, 0)]) + HiveAggregate(group=[{1, 2, 3, 4, 5, 6, 7}], agg#0=[sum($10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], -=[-($25, $22)]) + HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out index dbfe6e7..cda7aa3 100644 --- a/ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out @@ -83,7 +83,7 @@ HiveProject(i_item_desc=[$0], i_category=[$1], i_class=[$2], i_current_price=[$3 HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_ext_sales_price=[$23]) HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) - HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveProject(d_date_sk=[$0]) HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 2001-01-12 00:00:00, 2001-02-11 00:00:00), IS NOT NULL($0))]) HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])