http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/perf/tez/query40.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query40.q.out b/ql/src/test/results/clientpositive/perf/tez/query40.q.out index 9920ad3..a3b6c03 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query40.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query40.q.out @@ -71,115 +71,117 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_135] - Limit [LIM_134] (rows=100 width=135) + File Output Operator [FS_136] + Limit [LIM_135] (rows=100 width=135) Number of rows:100 - Select Operator [SEL_133] (rows=210822976 width=135) + Select Operator [SEL_134] (rows=210822976 width=135) Output:["_col0","_col1","_col2","_col3"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_132] - Group By Operator [GBY_131] (rows=210822976 width=135) + SHUFFLE [RS_133] + Group By Operator [GBY_132] (rows=210822976 width=135) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0, _col1 Group By Operator [GBY_29] (rows=421645953 width=135) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col0, _col1 - Select Operator [SEL_27] (rows=421645953 width=135) - Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_100] (rows=421645953 width=135) - Conds:RS_24._col1=RS_119._col0(Inner),Output:["_col4","_col7","_col9","_col11","_col14"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_119] - PartitionCols:_col0 - Select Operator [SEL_118] (rows=27 width=1029) - Output:["_col0","_col1"] - Filter Operator [FIL_117] (rows=27 width=1029) - predicate:w_warehouse_sk is not null - TableScan [TS_12] (rows=27 width=1029) - default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_state"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_24] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_99] (rows=383314495 width=135) - Conds:RS_21._col2=RS_111._col0(Inner),Output:["_col1","_col4","_col7","_col9","_col11"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_111] - PartitionCols:_col0 - Select Operator [SEL_110] (rows=51333 width=1436) - Output:["_col0","_col1"] - Filter Operator [FIL_109] (rows=51333 width=1436) - predicate:(i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) - TableScan [TS_9] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_current_price"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_21] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_98] (rows=348467716 width=135) - Conds:RS_18._col0=RS_103._col0(Inner),Output:["_col1","_col2","_col4","_col7","_col9"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_103] - PartitionCols:_col0 - Select Operator [SEL_102] (rows=8116 width=1119) - Output:["_col0","_col1"] - Filter Operator [FIL_101] (rows=8116 width=1119) - predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-09 00:00:00' AND TIMESTAMP'1998-05-08 00:00:00' and d_date_sk is not null) - TableScan [TS_6] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_18] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_97] (rows=316788826 width=135) - Conds:RS_127._col2, _col3=RS_130._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col7"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_127] - PartitionCols:_col2, _col3 - Select Operator [SEL_126] (rows=287989836 width=135) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_125] (rows=287989836 width=135) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_22_item_i_item_sk_min) AND DynamicValue(RS_22_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_22_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (cs_warehouse_sk BETWEEN DynamicValue(RS_25_warehouse_w_warehouse_sk_min) AND DynamicValue(RS_25_warehouse_w_warehouse_sk_max) and in_bloom_filter(cs_warehouse_sk, DynamicValue(RS_25_warehouse_w_warehouse_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null and cs_warehouse_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_warehouse_sk","cs_item_sk","cs_order_number","cs_sales_price"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_108] - Group By Operator [GBY_107] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_106] - Group By Operator [GBY_105] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_104] (rows=8116 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_102] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_116] - Group By Operator [GBY_115] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_114] - Group By Operator [GBY_113] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_112] (rows=51333 width=1436) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_110] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_124] - Group By Operator [GBY_123] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_122] - Group By Operator [GBY_121] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_120] (rows=27 width=1029) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_118] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_130] - PartitionCols:_col0, _col1 - Select Operator [SEL_129] (rows=28798881 width=106) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_128] (rows=28798881 width=106) - predicate:cr_item_sk is not null - TableScan [TS_3] (rows=28798881 width=106) - default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash"] + Top N Key Operator [TNK_55] (rows=421645953 width=135) + keys:_col0, _col1,sort order:++,top n:100 + Select Operator [SEL_27] (rows=421645953 width=135) + Output:["_col0","_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_101] (rows=421645953 width=135) + Conds:RS_24._col1=RS_120._col0(Inner),Output:["_col4","_col7","_col9","_col11","_col14"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_120] + PartitionCols:_col0 + Select Operator [SEL_119] (rows=27 width=1029) + Output:["_col0","_col1"] + Filter Operator [FIL_118] (rows=27 width=1029) + predicate:w_warehouse_sk is not null + TableScan [TS_12] (rows=27 width=1029) + default@warehouse,warehouse,Tbl:COMPLETE,Col:NONE,Output:["w_warehouse_sk","w_state"] + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_24] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_100] (rows=383314495 width=135) + Conds:RS_21._col2=RS_112._col0(Inner),Output:["_col1","_col4","_col7","_col9","_col11"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_112] + PartitionCols:_col0 + Select Operator [SEL_111] (rows=51333 width=1436) + Output:["_col0","_col1"] + Filter Operator [FIL_110] (rows=51333 width=1436) + predicate:(i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) + TableScan [TS_9] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_current_price"] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_21] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_99] (rows=348467716 width=135) + Conds:RS_18._col0=RS_104._col0(Inner),Output:["_col1","_col2","_col4","_col7","_col9"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_104] + PartitionCols:_col0 + Select Operator [SEL_103] (rows=8116 width=1119) + Output:["_col0","_col1"] + Filter Operator [FIL_102] (rows=8116 width=1119) + predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-09 00:00:00' AND TIMESTAMP'1998-05-08 00:00:00' and d_date_sk is not null) + TableScan [TS_6] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_98] (rows=316788826 width=135) + Conds:RS_128._col2, _col3=RS_131._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col7"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_128] + PartitionCols:_col2, _col3 + Select Operator [SEL_127] (rows=287989836 width=135) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_126] (rows=287989836 width=135) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_22_item_i_item_sk_min) AND DynamicValue(RS_22_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_22_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (cs_warehouse_sk BETWEEN DynamicValue(RS_25_warehouse_w_warehouse_sk_min) AND DynamicValue(RS_25_warehouse_w_warehouse_sk_max) and in_bloom_filter(cs_warehouse_sk, DynamicValue(RS_25_warehouse_w_warehouse_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null and cs_warehouse_sk is not null) + TableScan [TS_0] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_warehouse_sk","cs_item_sk","cs_order_number","cs_sales_price"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_109] + Group By Operator [GBY_108] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_107] + Group By Operator [GBY_106] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_105] (rows=8116 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_103] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_117] + Group By Operator [GBY_116] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_115] + Group By Operator [GBY_114] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_113] (rows=51333 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_111] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_125] + Group By Operator [GBY_124] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_123] + Group By Operator [GBY_122] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_121] (rows=27 width=1029) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_119] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_131] + PartitionCols:_col0, _col1 + Select Operator [SEL_130] (rows=28798881 width=106) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_129] (rows=28798881 width=106) + predicate:cr_item_sk is not null + TableScan [TS_3] (rows=28798881 width=106) + default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_refunded_cash"]
http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/perf/tez/query43.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query43.q.out b/ql/src/test/results/clientpositive/perf/tez/query43.q.out index 394f728..afa3363 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query43.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query43.q.out @@ -50,76 +50,78 @@ Stage-0 limit:100 Stage-1 Reducer 5 vectorized - File Output Operator [FS_78] - Limit [LIM_77] (rows=100 width=88) + File Output Operator [FS_79] + Limit [LIM_78] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_76] (rows=348477374 width=88) + Select Operator [SEL_77] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_75] - Group By Operator [GBY_74] (rows=348477374 width=88) + SHUFFLE [RS_76] + Group By Operator [GBY_75] (rows=348477374 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0, KEY._col1 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0, _col1 Group By Operator [GBY_17] (rows=696954748 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 - Select Operator [SEL_15] (rows=696954748 width=88) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_54] (rows=696954748 width=88) - Conds:RS_12._col1=RS_65._col0(Inner),Output:["_col2","_col5","_col7","_col8"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_65] - PartitionCols:_col0 - Select Operator [SEL_64] (rows=852 width=1910) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_63] (rows=852 width=1910) - predicate:((s_gmt_offset = -6) and s_store_sk is not null) - TableScan [TS_6] (rows=1704 width=1910) - default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name","s_gmt_offset"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_12] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_53] (rows=633595212 width=88) - Conds:RS_73._col0=RS_57._col0(Inner),Output:["_col1","_col2","_col5"] - <-Map 6 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_57] - PartitionCols:_col0 - Select Operator [SEL_56] (rows=36524 width=1119) - Output:["_col0","_col2"] - Filter Operator [FIL_55] (rows=36524 width=1119) - predicate:((d_year = 1998) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_day_name"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_73] - PartitionCols:_col0 - Select Operator [SEL_72] (rows=575995635 width=88) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_71] (rows=575995635 width=88) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_13_store_s_store_sk_min) AND DynamicValue(RS_13_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_13_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_62] - Group By Operator [GBY_61] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_60] - Group By Operator [GBY_59] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_58] (rows=36524 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_56] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_70] - Group By Operator [GBY_69] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_68] - Group By Operator [GBY_67] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_66] (rows=852 width=1910) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_64] + Top N Key Operator [TNK_33] (rows=696954748 width=88) + keys:_col0, _col1,sort order:++,top n:100 + Select Operator [SEL_15] (rows=696954748 width=88) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Merge Join Operator [MERGEJOIN_55] (rows=696954748 width=88) + Conds:RS_12._col1=RS_66._col0(Inner),Output:["_col2","_col5","_col7","_col8"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_66] + PartitionCols:_col0 + Select Operator [SEL_65] (rows=852 width=1910) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_64] (rows=852 width=1910) + predicate:((s_gmt_offset = -6) and s_store_sk is not null) + TableScan [TS_6] (rows=1704 width=1910) + default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name","s_gmt_offset"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_54] (rows=633595212 width=88) + Conds:RS_74._col0=RS_58._col0(Inner),Output:["_col1","_col2","_col5"] + <-Map 6 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_58] + PartitionCols:_col0 + Select Operator [SEL_57] (rows=36524 width=1119) + Output:["_col0","_col2"] + Filter Operator [FIL_56] (rows=36524 width=1119) + predicate:((d_year = 1998) and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_day_name"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_74] + PartitionCols:_col0 + Select Operator [SEL_73] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_72] (rows=575995635 width=88) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_13_store_s_store_sk_min) AND DynamicValue(RS_13_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_13_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_63] + Group By Operator [GBY_62] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_61] + Group By Operator [GBY_60] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_59] (rows=36524 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_57] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_71] + Group By Operator [GBY_70] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_69] + Group By Operator [GBY_68] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_67] (rows=852 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_65] http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/perf/tez/query45.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query45.q.out b/ql/src/test/results/clientpositive/perf/tez/query45.q.out index c9d820b..edb047d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query45.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query45.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[132][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[133][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product PREHOOK: query: explain select ca_zip, ca_county, sum(ws_sales_price) from web_sales, customer, customer_address, date_dim, item @@ -59,147 +59,149 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_172] - Limit [LIM_171] (rows=100 width=152) + File Output Operator [FS_173] + Limit [LIM_172] (rows=100 width=152) Number of rows:100 - Select Operator [SEL_170] (rows=95833781 width=152) + Select Operator [SEL_171] (rows=95833781 width=152) Output:["_col0","_col1","_col2"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_169] - Group By Operator [GBY_168] (rows=95833781 width=152) + SHUFFLE [RS_170] + Group By Operator [GBY_169] (rows=95833781 width=152) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_53] PartitionCols:_col0, _col1 Group By Operator [GBY_52] (rows=191667562 width=152) Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col8, _col7 - Select Operator [SEL_51] (rows=191667562 width=152) - Output:["_col3","_col7","_col8"] - Filter Operator [FIL_50] (rows=191667562 width=152) - predicate:((substr(_col8, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or CASE WHEN ((_col14 = 0L)) THEN (false) WHEN (_col17 is not null) THEN (true) WHEN (_col13 is null) THEN (null) WHEN ((_col15 < _col14)) THEN (null) ELSE (false) END) - Select Operator [SEL_49] (rows=191667562 width=152) - Output:["_col3","_col7","_col8","_col13","_col14","_col15","_col17"] - Merge Join Operator [MERGEJOIN_132] (rows=191667562 width=152) - Conds:(Inner),Output:["_col3","_col4","_col6","_col8","_col12","_col16","_col17"] - <-Reducer 13 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_167] - Group By Operator [GBY_166] (rows=1 width=16) - Output:["_col0","_col1"],aggregations:["count(VALUE._col0)","count(VALUE._col1)"] - <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_149] - Group By Operator [GBY_147] (rows=1 width=16) - Output:["_col0","_col1"],aggregations:["count()","count(i_item_id)"] - Select Operator [SEL_144] (rows=231000 width=1436) - Output:["i_item_id"] - Filter Operator [FIL_141] (rows=231000 width=1436) - predicate:(i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) - TableScan [TS_6] (rows=462000 width=1436) - default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_46] - Merge Join Operator [MERGEJOIN_131] (rows=191667562 width=135) - Conds:RS_43._col0=RS_44._col6(Inner),Output:["_col3","_col4","_col6","_col8","_col12"] - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_44] - PartitionCols:_col6 - Merge Join Operator [MERGEJOIN_130] (rows=174243235 width=135) - Conds:RS_29._col0=RS_30._col1(Inner),Output:["_col1","_col3","_col6","_col7"] - <-Reducer 9 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_29] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_128] (rows=508200 width=1436) - Conds:RS_145._col1=RS_152._col0(Left Outer),Output:["_col0","_col1","_col3"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_145] - PartitionCols:_col1 - Select Operator [SEL_142] (rows=462000 width=1436) - Output:["_col0","_col1"] - Filter Operator [FIL_139] (rows=462000 width=1436) - predicate:i_item_sk is not null - Please refer to the previous TableScan [TS_6] - <-Reducer 12 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_152] - PartitionCols:_col0 - Select Operator [SEL_151] (rows=115500 width=1436) - Output:["_col0","_col1"] - Group By Operator [GBY_150] (rows=115500 width=1436) - Output:["_col0"],keys:KEY._col0 - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_148] - PartitionCols:_col0 - Group By Operator [GBY_146] (rows=231000 width=1436) - Output:["_col0"],keys:i_item_id - Select Operator [SEL_143] (rows=231000 width=1436) - Output:["i_item_id"] - Filter Operator [FIL_140] (rows=231000 width=1436) - predicate:(i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) - Please refer to the previous TableScan [TS_6] - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_30] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_129] (rows=158402938 width=135) - Conds:RS_165._col0=RS_155._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_155] - PartitionCols:_col0 - Select Operator [SEL_154] (rows=18262 width=1119) - Output:["_col0"] - Filter Operator [FIL_153] (rows=18262 width=1119) - predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) - TableScan [TS_19] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_165] - PartitionCols:_col0 - Select Operator [SEL_164] (rows=144002668 width=135) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_163] (rows=144002668 width=135) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_29_item_i_item_sk_min) AND DynamicValue(RS_29_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_29_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_23_date_dim_d_date_sk_min) AND DynamicValue(RS_23_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_23_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_16] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_sales_price"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_162] - Group By Operator [GBY_161] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 9 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_114] - Group By Operator [GBY_113] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_112] (rows=508200 width=1436) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_128] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_160] - Group By Operator [GBY_159] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_158] - Group By Operator [GBY_157] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_156] (rows=18262 width=1119) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_154] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_43] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_127] (rows=88000001 width=860) - Conds:RS_135._col1=RS_138._col0(Inner),Output:["_col0","_col3","_col4"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_135] - PartitionCols:_col1 - Select Operator [SEL_134] (rows=80000000 width=860) - Output:["_col0","_col1"] - Filter Operator [FIL_133] (rows=80000000 width=860) - predicate:(c_current_addr_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_138] - PartitionCols:_col0 - Select Operator [SEL_137] (rows=40000000 width=1014) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_136] (rows=40000000 width=1014) - predicate:ca_address_sk is not null - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county","ca_zip"] + Top N Key Operator [TNK_82] (rows=191667562 width=152) + keys:_col8, _col7,sort order:++,top n:100 + Select Operator [SEL_51] (rows=191667562 width=152) + Output:["_col3","_col7","_col8"] + Filter Operator [FIL_50] (rows=191667562 width=152) + predicate:((substr(_col8, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or CASE WHEN ((_col14 = 0L)) THEN (false) WHEN (_col17 is not null) THEN (true) WHEN (_col13 is null) THEN (null) WHEN ((_col15 < _col14)) THEN (null) ELSE (false) END) + Select Operator [SEL_49] (rows=191667562 width=152) + Output:["_col3","_col7","_col8","_col13","_col14","_col15","_col17"] + Merge Join Operator [MERGEJOIN_133] (rows=191667562 width=152) + Conds:(Inner),Output:["_col3","_col4","_col6","_col8","_col12","_col16","_col17"] + <-Reducer 13 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_168] + Group By Operator [GBY_167] (rows=1 width=16) + Output:["_col0","_col1"],aggregations:["count(VALUE._col0)","count(VALUE._col1)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_150] + Group By Operator [GBY_148] (rows=1 width=16) + Output:["_col0","_col1"],aggregations:["count()","count(i_item_id)"] + Select Operator [SEL_145] (rows=231000 width=1436) + Output:["i_item_id"] + Filter Operator [FIL_142] (rows=231000 width=1436) + predicate:(i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) + TableScan [TS_6] (rows=462000 width=1436) + default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_46] + Merge Join Operator [MERGEJOIN_132] (rows=191667562 width=135) + Conds:RS_43._col0=RS_44._col6(Inner),Output:["_col3","_col4","_col6","_col8","_col12"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_44] + PartitionCols:_col6 + Merge Join Operator [MERGEJOIN_131] (rows=174243235 width=135) + Conds:RS_29._col0=RS_30._col1(Inner),Output:["_col1","_col3","_col6","_col7"] + <-Reducer 9 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_29] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_129] (rows=508200 width=1436) + Conds:RS_146._col1=RS_153._col0(Left Outer),Output:["_col0","_col1","_col3"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_146] + PartitionCols:_col1 + Select Operator [SEL_143] (rows=462000 width=1436) + Output:["_col0","_col1"] + Filter Operator [FIL_140] (rows=462000 width=1436) + predicate:i_item_sk is not null + Please refer to the previous TableScan [TS_6] + <-Reducer 12 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_153] + PartitionCols:_col0 + Select Operator [SEL_152] (rows=115500 width=1436) + Output:["_col0","_col1"] + Group By Operator [GBY_151] (rows=115500 width=1436) + Output:["_col0"],keys:KEY._col0 + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_149] + PartitionCols:_col0 + Group By Operator [GBY_147] (rows=231000 width=1436) + Output:["_col0"],keys:i_item_id + Select Operator [SEL_144] (rows=231000 width=1436) + Output:["i_item_id"] + Filter Operator [FIL_141] (rows=231000 width=1436) + predicate:(i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) + Please refer to the previous TableScan [TS_6] + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_30] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_130] (rows=158402938 width=135) + Conds:RS_166._col0=RS_156._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_156] + PartitionCols:_col0 + Select Operator [SEL_155] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_154] (rows=18262 width=1119) + predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) + TableScan [TS_19] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_166] + PartitionCols:_col0 + Select Operator [SEL_165] (rows=144002668 width=135) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_164] (rows=144002668 width=135) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_29_item_i_item_sk_min) AND DynamicValue(RS_29_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_29_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_23_date_dim_d_date_sk_min) AND DynamicValue(RS_23_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_23_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_16] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_sales_price"] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_163] + Group By Operator [GBY_162] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 9 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_115] + Group By Operator [GBY_114] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_113] (rows=508200 width=1436) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_129] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_161] + Group By Operator [GBY_160] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_159] + Group By Operator [GBY_158] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_157] (rows=18262 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_155] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_43] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_128] (rows=88000001 width=860) + Conds:RS_136._col1=RS_139._col0(Inner),Output:["_col0","_col3","_col4"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_136] + PartitionCols:_col1 + Select Operator [SEL_135] (rows=80000000 width=860) + Output:["_col0","_col1"] + Filter Operator [FIL_134] (rows=80000000 width=860) + predicate:(c_current_addr_sk is not null and c_customer_sk is not null) + TableScan [TS_0] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_139] + PartitionCols:_col0 + Select Operator [SEL_138] (rows=40000000 width=1014) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_137] (rows=40000000 width=1014) + predicate:ca_address_sk is not null + TableScan [TS_3] (rows=40000000 width=1014) + default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county","ca_zip"]
