http://git-wip-us.apache.org/repos/asf/hive/blob/244ca8e5/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 c82dcf7..d60751c 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query85.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query85.q.out @@ -175,7 +175,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 15 + Map 13 Map Operator Tree: TableScan alias: reason @@ -212,21 +212,21 @@ STAGE PLANS: Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: int) - 1 _col2 (type: int) + 0 _col10 (type: int) + 1 _col0 (type: int) Local Work: Map Reduce Local Work Stage: Stage-1 Spark Edges: - Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 20), Map 14 (PARTITION-LEVEL SORT, 20) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 90), Map 8 (PARTITION-LEVEL SORT, 90) - Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 17), Reducer 2 (PARTITION-LEVEL SORT, 17) - Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 19), Reducer 3 (PARTITION-LEVEL SORT, 19) - Reducer 5 <- Reducer 13 (PARTITION-LEVEL SORT, 35), Reducer 4 (PARTITION-LEVEL SORT, 35) - Reducer 6 <- Reducer 5 (GROUP, 2) - Reducer 7 <- Reducer 6 (SORT, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 28), Map 9 (PARTITION-LEVEL SORT, 28) + Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 98), Reducer 2 (PARTITION-LEVEL SORT, 98) + Reducer 4 <- Map 12 (PARTITION-LEVEL SORT, 5), Reducer 3 (PARTITION-LEVEL SORT, 5) + Reducer 5 <- Map 14 (PARTITION-LEVEL SORT, 11), Reducer 4 (PARTITION-LEVEL SORT, 11) + Reducer 6 <- Map 15 (PARTITION-LEVEL SORT, 7), Reducer 5 (PARTITION-LEVEL SORT, 7) + Reducer 7 <- Reducer 6 (GROUP, 7) + Reducer 8 <- Reducer 7 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -242,61 +242,32 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) + key expressions: _col0 (type: int), _col5 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col5 (type: int) Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) Map 10 Map Operator Tree: TableScan - alias: cd2 - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + alias: customer_address + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and cd_demo_sk is not null and cd_education_status is not null and cd_marital_status 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: 10000000 Data size: 10148798821 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 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10000000 Data size: 10148798821 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string), _col0 (type: int), _col1 (type: string) - sort order: +++ - Map-reduce partition columns: _col2 (type: string), _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10000000 Data size: 10148798821 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Map 12 Map Operator Tree: TableScan - alias: web_sales - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - Filter Operator - 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 - Statistics: Num rows: 16000296 Data size: 2175577518 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col1, _col2, _col4, _col5, _col6, _col7 - input vertices: - 0 Map 11 - Statistics: Num rows: 17600325 Data size: 2393135321 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: 17600325 Data size: 2393135321 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) - Local Work: - Map Reduce Local Work - Map 14 - Map Operator Tree: - TableScan alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -311,28 +282,28 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Map 8 + Map 14 Map Operator Tree: TableScan - alias: customer_address - Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + alias: cd1 + 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: 10000000 Data size: 10148798821 Basic stats: COMPLETE Column stats: NONE + predicate: (((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and cd_demo_sk is not null and cd_education_status is not null and cd_marital_status 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: 10000000 Data size: 10148798821 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: 10000000 Data size: 10148798821 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Map 9 + Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string) + Map 15 Map Operator Tree: TableScan - alias: cd1 + alias: cd2 Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and cd_demo_sk is not null and cd_education_status is not null and cd_marital_status is not null) (type: boolean) @@ -342,145 +313,173 @@ STAGE PLANS: 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) + 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: _col1 (type: string), _col2 (type: string) - Reducer 13 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col2, _col4, _col5, _col6, _col7 - Statistics: Num rows: 19360357 Data size: 2632448910 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) - outputColumnNames: _col4, _col6, _col7, _col8, _col9 - Statistics: Num rows: 19360357 Data size: 2632448910 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: int), _col6 (type: int) - sort order: ++ - Map-reduce partition columns: _col4 (type: int), _col6 (type: int) - Statistics: Num rows: 19360357 Data size: 2632448910 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: int), _col8 (type: decimal(7,2)), _col9 (type: decimal(7,2)) + Map 9 + Map Operator Tree: + TableScan + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Filter Operator + 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 + 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)) Reducer 2 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col9 - Statistics: Num rows: 15838314 Data size: 1457713633 Basic stats: COMPLETE Column stats: NONE + 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 + Statistics: Num rows: 17600325 Data size: 2393135321 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: _col2 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 15838314 Data size: 1457713633 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col9 (type: string) + Map-reduce partition columns: _col2 (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)) Reducer 3 + Local Work: + Map Reduce Local Work 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: _col0, _col3, _col4, _col5, _col6, _col7, _col9, _col12, _col13 - Statistics: Num rows: 17422145 Data size: 1603485031 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col13 (type: string), _col3 (type: int), _col12 (type: string) - sort order: +++ - Map-reduce partition columns: _col13 (type: string), _col3 (type: int), _col12 (type: string) - Statistics: Num rows: 17422145 Data size: 1603485031 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col9 (type: string) + outputColumnNames: _col1, _col3, _col4, _col6, _col7, _col8, _col10, _col12, _col13, _col14, _col16 + Statistics: Num rows: 19360357 Data size: 2632448910 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: 3226725 Data size: 438741326 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: 3549397 Data size: 482615469 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: 3549397 Data size: 482615469 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)) Reducer 4 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col13 (type: string), _col3 (type: int), _col12 (type: string) - 1 _col2 (type: string), _col0 (type: int), _col1 (type: string) - outputColumnNames: _col0, _col4, _col5, _col6, _col7, _col9, _col12, _col13 - Statistics: Num rows: 19164359 Data size: 1763833572 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col5 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col5 (type: int) - Statistics: Num rows: 19164359 Data size: 1763833572 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col9 (type: string), _col12 (type: string), _col13 (type: string) + 0 _col8 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4, _col6, _col7, _col12, _col13 + Statistics: Num rows: 3904336 Data size: 530877027 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, _col3, _col6, _col7, _col12, _col13, _col22 + input vertices: + 1 Map 13 + Statistics: Num rows: 4294769 Data size: 583964742 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: 4294769 Data size: 583964742 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) Reducer 5 - Local Work: - Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int), _col5 (type: int) - 1 _col4 (type: int), _col6 (type: int) - outputColumnNames: _col4, _col6, _col7, _col9, _col12, _col13, _col24, _col25, _col26 - Statistics: Num rows: 21296393 Data size: 2895693863 Basic stats: COMPLETE Column stats: NONE + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col6, _col7, _col12, _col13, _col22, _col24, _col25 + Statistics: Num rows: 4724246 Data size: 642361230 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((_col12 = 'M') and (_col13 = '4 yr Degree') and _col25 BETWEEN 100 AND 150) or ((_col12 = 'D') and (_col13 = 'Primary') and _col25 BETWEEN 50 AND 100) or ((_col12 = 'U') and (_col13 = 'Advanced Degree') and _col25 BETWEEN 150 AND 200)) and (((_col9) IN ('KY', 'GA', 'NM') and _col26 BETWEEN 100 AND 200) or ((_col9) IN ('MT', 'OR', 'IN') and _col26 BETWEEN 150 AND 300) or ((_col9) IN ('WI', 'MO', 'WV') and _col26 BETWEEN 50 AND 250))) (type: boolean) - Statistics: Num rows: 295782 Data size: 40217802 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: _col6, _col7, _col24, _col28 - input vertices: - 1 Map 15 - Statistics: Num rows: 325360 Data size: 44239583 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col24), count(_col24), sum(_col7), count(_col7), sum(_col6), count(_col6) - keys: _col28 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 325360 Data size: 44239583 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: 325360 Data size: 44239583 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) + 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: 393687 Data size: 53530079 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: int), _col24 (type: string), _col25 (type: string) + sort order: +++ + Map-reduce partition columns: _col3 (type: int), _col24 (type: string), _col25 (type: string) + Statistics: Num rows: 393687 Data size: 53530079 Basic stats: COMPLETE Column stats: NONE + value expressions: _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col22 (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) + 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) + Reducer 7 + Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), sum(VALUE._col4), count(VALUE._col5) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 162680 Data size: 22119791 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023990 Data size: 394452395 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (_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: 162680 Data size: 22119791 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023990 Data size: 394452395 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: 162680 Data size: 22119791 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023990 Data size: 394452395 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 - Reducer 7 + Reducer 8 Reduce Operator Tree: 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: 162680 Data size: 22119791 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1023990 Data size: 394452395 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 38500 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 38500 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/244ca8e5/ql/src/test/results/clientpositive/perf/spark/query88.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query88.q.out b/ql/src/test/results/clientpositive/perf/spark/query88.q.out index f8f2b70..be44719 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query88.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query88.q.out @@ -204,18 +204,18 @@ STAGE PLANS: Map 10 Map Operator Tree: TableScan - alias: household_demographics - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hd_demo_sk (type: int) + expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -240,18 +240,18 @@ STAGE PLANS: Map 9 Map Operator Tree: TableScan - alias: store - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -294,9 +294,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1 + outputColumnNames: _col2 input vertices: 1 Map 14 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE @@ -304,7 +304,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) input vertices: 1 Map 15 @@ -346,9 +346,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1 + outputColumnNames: _col2 input vertices: 1 Map 19 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE @@ -356,7 +356,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) input vertices: 1 Map 20 @@ -398,9 +398,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1 + outputColumnNames: _col2 input vertices: 1 Map 24 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE @@ -408,7 +408,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) input vertices: 1 Map 25 @@ -450,9 +450,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1 + outputColumnNames: _col2 input vertices: 1 Map 29 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE @@ -460,7 +460,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) input vertices: 1 Map 30 @@ -502,9 +502,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1 + outputColumnNames: _col2 input vertices: 1 Map 34 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE @@ -512,7 +512,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) input vertices: 1 Map 35 @@ -554,9 +554,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1 + outputColumnNames: _col2 input vertices: 1 Map 39 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE @@ -564,7 +564,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) input vertices: 1 Map 40 @@ -606,9 +606,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1 + outputColumnNames: _col2 input vertices: 1 Map 9 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE @@ -616,7 +616,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) input vertices: 1 Map 10 @@ -791,36 +791,36 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: store - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work Map 5 Map Operator Tree: TableScan - alias: household_demographics - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hd_demo_sk (type: int) + expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -857,9 +857,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1 + outputColumnNames: _col2 input vertices: 1 Map 4 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE @@ -867,7 +867,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) input vertices: 1 Map 5 @@ -957,36 +957,36 @@ STAGE PLANS: Map 14 Map Operator Tree: TableScan - alias: store - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work Map 15 Map Operator Tree: TableScan - alias: household_demographics - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hd_demo_sk (type: int) + expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -1016,36 +1016,36 @@ STAGE PLANS: Map 19 Map Operator Tree: TableScan - alias: store - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work Map 20 Map Operator Tree: TableScan - alias: household_demographics - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hd_demo_sk (type: int) + expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -1075,36 +1075,36 @@ STAGE PLANS: Map 24 Map Operator Tree: TableScan - alias: store - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work Map 25 Map Operator Tree: TableScan - alias: household_demographics - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hd_demo_sk (type: int) + expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -1134,36 +1134,36 @@ STAGE PLANS: Map 29 Map Operator Tree: TableScan - alias: store - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work Map 30 Map Operator Tree: TableScan - alias: household_demographics - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hd_demo_sk (type: int) + expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -1193,36 +1193,36 @@ STAGE PLANS: Map 34 Map Operator Tree: TableScan - alias: store - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work Map 35 Map Operator Tree: TableScan - alias: household_demographics - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hd_demo_sk (type: int) + expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -1252,36 +1252,36 @@ STAGE PLANS: Map 39 Map Operator Tree: TableScan - alias: store - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s_store_sk (type: int) + expressions: hd_demo_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work Map 40 Map Operator Tree: TableScan - alias: household_demographics - Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hd_demo_sk (type: int) + expressions: s_store_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work http://git-wip-us.apache.org/repos/asf/hive/blob/244ca8e5/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 815c55d..c933fe1 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query89.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query89.q.out @@ -185,47 +185,47 @@ STAGE PLANS: Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col3) - keys: _col12 (type: string), _col13 (type: string), _col10 (type: int), _col5 (type: string), _col6 (type: string), _col7 (type: string) + keys: _col5 (type: string), _col6 (type: string), _col7 (type: string), _col10 (type: int), _col12 (type: string), _col13 (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 Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: string) + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE value expressions: _col6 (type: decimal(17,2)) Reducer 4 Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int), KEY._col4 (type: string), KEY._col5 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col5 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string) + key expressions: _col2 (type: string), _col0 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++ - Map-reduce partition columns: _col5 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string) + Map-reduce partition columns: _col2 (type: string), _col0 (type: string), _col4 (type: string), _col5 (type: string) Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: string), _col6 (type: decimal(17,2)) + value expressions: _col1 (type: string), _col3 (type: int), _col6 (type: decimal(17,2)) Reducer 5 Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col2 (type: decimal(17,2)) + expressions: KEY.reducesinkkey1 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col2 (type: decimal(17,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE PTF Operator Function definitions: Input definition input alias: ptf_0 - output shape: _col0: string, _col1: string, _col2: int, _col3: string, _col4: string, _col5: string, _col6: decimal(17,2) + output shape: _col0: string, _col1: string, _col2: string, _col3: int, _col4: string, _col5: string, _col6: decimal(17,2) type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col5 ASC NULLS FIRST, _col3 ASC NULLS FIRST, _col0 ASC NULLS FIRST, _col1 ASC NULLS FIRST - partition by: _col5, _col3, _col0, _col1 + order by: _col2 ASC NULLS FIRST, _col0 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST + partition by: _col2, _col0, _col4, _col5 raw input shape: window functions: window function definition @@ -236,14 +236,14 @@ STAGE PLANS: window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2)) + expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string), _col6 (type: decimal(17,2)) outputColumnNames: avg_window_0, _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: CASE WHEN ((avg_window_0 <> 0)) THEN (((abs((_col6 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (null) END (type: boolean) Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col5 (type: string), _col4 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: int), _col6 (type: decimal(17,2)), avg_window_0 (type: decimal(21,6)), (_col6 - avg_window_0) (type: decimal(22,6)) + expressions: _col2 (type: string), _col1 (type: string), _col0 (type: string), _col4 (type: string), _col5 (type: string), _col3 (type: int), _col6 (type: decimal(17,2)), avg_window_0 (type: decimal(21,6)), (_col6 - avg_window_0) (type: decimal(22,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/244ca8e5/ql/src/test/results/clientpositive/perf/spark/query90.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query90.q.out b/ql/src/test/results/clientpositive/perf/spark/query90.q.out index 9978b10..115a2cc 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query90.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query90.q.out @@ -56,18 +56,18 @@ STAGE PLANS: Map 10 Map Operator Tree: TableScan - alias: web_page - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + alias: time_dim + Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE + predicate: (t_hour BETWEEN 14 AND 15 and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: wp_web_page_sk (type: int) + expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -92,18 +92,18 @@ STAGE PLANS: Map 9 Map Operator Tree: TableScan - alias: time_dim - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + alias: web_page + Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (t_hour BETWEEN 14 AND 15 and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE + predicate: (wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) (type: boolean) + Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: t_time_sk (type: int) + expressions: wp_web_page_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -130,9 +130,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col1 input vertices: 1 Map 9 Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE @@ -140,7 +140,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 input vertices: @@ -187,36 +187,36 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: time_dim - Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + alias: web_page + Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (t_hour BETWEEN 6 AND 7 and t_time_sk is not null) (type: boolean) - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE + predicate: (wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) (type: boolean) + Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: t_time_sk (type: int) + expressions: wp_web_page_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work Map 5 Map Operator Tree: TableScan - alias: web_page - Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE + alias: time_dim + Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE + predicate: (t_hour BETWEEN 6 AND 7 and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: wp_web_page_sk (type: int) + expressions: t_time_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -262,9 +262,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col1 input vertices: 1 Map 4 Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE @@ -272,7 +272,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col2 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 input vertices: http://git-wip-us.apache.org/repos/asf/hive/blob/244ca8e5/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 0ad330f..b4f0650 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query91.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query91.q.out @@ -234,14 +234,14 @@ STAGE PLANS: Statistics: Num rows: 106480005 Data size: 91574956652 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col4, _col9, _col10 + outputColumnNames: _col2, _col7, _col8 Statistics: Num rows: 106480005 Data size: 91574956652 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: int) + key expressions: _col2 (type: int) sort order: + - Map-reduce partition columns: _col4 (type: int) + Map-reduce partition columns: _col2 (type: int) Statistics: Num rows: 106480005 Data size: 91574956652 Basic stats: COMPLETE Column stats: NONE - value expressions: _col9 (type: string), _col10 (type: string) + value expressions: _col7 (type: string), _col8 (type: string) Reducer 2 Local Work: Map Reduce Local Work @@ -277,12 +277,12 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col1 (type: int) - 1 _col4 (type: int) - outputColumnNames: _col3, _col8, _col9, _col10, _col20, _col21 + 1 _col2 (type: int) + outputColumnNames: _col3, _col8, _col9, _col10, _col18, _col19 Statistics: Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col3) - keys: _col8 (type: string), _col9 (type: string), _col10 (type: string), _col20 (type: string), _col21 (type: string) + keys: _col8 (type: string), _col9 (type: string), _col10 (type: string), _col18 (type: string), _col19 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE