http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query73.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query73.q.out b/ql/src/test/results/clientpositive/perf/tez/query73.q.out index a3ec378..352c724 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query73.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query73.q.out @@ -67,15 +67,13 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 4 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE) +Map 4 <- Reducer 10 (BROADCAST_EDGE) Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) Reducer 6 <- Map 11 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Map 13 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 7 <- Map 12 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Stage-0 @@ -83,15 +81,15 @@ Stage-0 limit:-1 Stage-1 Reducer 3 vectorized - File Output Operator [FS_136] - Select Operator [SEL_135] (rows=5 width=364) + File Output Operator [FS_126] + Select Operator [SEL_125] (rows=5 width=364) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_35] Select Operator [SEL_34] (rows=5 width=364) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_100] (rows=5 width=364) - Conds:RS_103._col0=RS_134._col1(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col7"] + Conds:RS_103._col0=RS_124._col1(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col7"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_103] PartitionCols:_col0 @@ -102,13 +100,13 @@ Stage-0 TableScan [TS_0] (rows=80000000 width=356) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_134] + SHUFFLE [RS_124] PartitionCols:_col1 - Filter Operator [FIL_133] (rows=5 width=12) + Filter Operator [FIL_123] (rows=5 width=12) predicate:_col2 BETWEEN 1 AND 5 - Select Operator [SEL_132] (rows=788766 width=12) + Select Operator [SEL_122] (rows=788766 width=12) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_131] (rows=788766 width=12) + Group By Operator [GBY_121] (rows=788766 width=12) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_26] @@ -116,13 +114,13 @@ Stage-0 Group By Operator [GBY_25] (rows=788766 width=12) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 Merge Join Operator [MERGEJOIN_99] (rows=788766 width=4) - Conds:RS_21._col3=RS_122._col0(Inner),Output:["_col1","_col4"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_122] + Conds:RS_21._col3=RS_120._col0(Inner),Output:["_col1","_col4"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_120] PartitionCols:_col0 - Select Operator [SEL_121] (rows=56 width=4) + Select Operator [SEL_119] (rows=56 width=4) Output:["_col0"] - Filter Operator [FIL_120] (rows=56 width=102) + Filter Operator [FIL_118] (rows=56 width=102) predicate:((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County') and s_store_sk is not null) TableScan [TS_12] (rows=1704 width=102) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_county"] @@ -130,13 +128,13 @@ Stage-0 SHUFFLE [RS_21] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_98] (rows=2973700 width=4) - Conds:RS_18._col2=RS_114._col0(Inner),Output:["_col1","_col3","_col4"] + Conds:RS_18._col2=RS_117._col0(Inner),Output:["_col1","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_114] + SHUFFLE [RS_117] PartitionCols:_col0 - Select Operator [SEL_113] (rows=480 width=4) + Select Operator [SEL_116] (rows=480 width=4) Output:["_col0"] - Filter Operator [FIL_112] (rows=480 width=104) + Filter Operator [FIL_115] (rows=480 width=104) predicate:((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0D)) ELSE (null) END and hd_demo_sk is not null) TableScan [TS_9] (rows=7200 width=104) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] @@ -144,7 +142,7 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_97] (rows=44605486 width=10) - Conds:RS_130._col0=RS_106._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Conds:RS_114._col0=RS_106._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_106] PartitionCols:_col0 @@ -155,12 +153,12 @@ Stage-0 TableScan [TS_6] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dom"] <-Map 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_130] + SHUFFLE [RS_114] PartitionCols:_col0 - Select Operator [SEL_129] (rows=479121995 width=19) + Select Operator [SEL_113] (rows=479121995 width=19) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_128] (rows=479121995 width=19) - predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_19_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_19_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_19_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + Filter Operator [FIL_112] (rows=479121995 width=19) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) TableScan [TS_3] (rows=575995635 width=19) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_store_sk","ss_ticket_number"] <-Reducer 10 [BROADCAST_EDGE] vectorized @@ -174,26 +172,4 @@ Stage-0 Select Operator [SEL_107] (rows=170 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_105] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_119] - Group By Operator [GBY_118] (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_117] - Group By Operator [GBY_116] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_115] (rows=480 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_113] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_127] - Group By Operator [GBY_126] (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_125] - Group By Operator [GBY_124] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_123] (rows=56 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_121]
http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query75.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query75.q.out b/ql/src/test/results/clientpositive/perf/tez/query75.q.out index f4bd046..4019788 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query75.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query75.q.out @@ -157,45 +157,39 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 12 (BROADCAST_EDGE), Reducer 38 (BROADCAST_EDGE) -Map 45 <- Reducer 16 (BROADCAST_EDGE), Reducer 39 (BROADCAST_EDGE) -Map 47 <- Reducer 20 (BROADCAST_EDGE), Reducer 40 (BROADCAST_EDGE) -Map 49 <- Reducer 28 (BROADCAST_EDGE), Reducer 41 (BROADCAST_EDGE) -Map 50 <- Reducer 32 (BROADCAST_EDGE), Reducer 42 (BROADCAST_EDGE) -Map 51 <- Reducer 36 (BROADCAST_EDGE), Reducer 43 (BROADCAST_EDGE) +Map 1 <- Reducer 12 (BROADCAST_EDGE) +Map 39 <- Reducer 16 (BROADCAST_EDGE) +Map 41 <- Reducer 20 (BROADCAST_EDGE) +Map 43 <- Reducer 28 (BROADCAST_EDGE) +Map 44 <- Reducer 32 (BROADCAST_EDGE) +Map 45 <- Reducer 36 (BROADCAST_EDGE) Reducer 10 <- Reducer 9 (SIMPLE_EDGE) Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 11 (SIMPLE_EDGE), Map 45 (SIMPLE_EDGE) +Reducer 13 <- Map 11 (SIMPLE_EDGE), Map 39 (SIMPLE_EDGE) Reducer 14 <- Map 37 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) -Reducer 15 <- Map 46 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 15 <- Map 40 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 16 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 11 (SIMPLE_EDGE), Map 47 (SIMPLE_EDGE) +Reducer 17 <- Map 11 (SIMPLE_EDGE), Map 41 (SIMPLE_EDGE) Reducer 18 <- Map 37 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) -Reducer 19 <- Map 48 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE), Union 7 (CONTAINS) +Reducer 19 <- Map 42 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE), Union 7 (CONTAINS) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) Reducer 20 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 21 <- Map 11 (SIMPLE_EDGE), Map 49 (SIMPLE_EDGE) +Reducer 21 <- Map 11 (SIMPLE_EDGE), Map 43 (SIMPLE_EDGE) Reducer 22 <- Map 37 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 23 <- Map 44 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE), Union 24 (CONTAINS) +Reducer 23 <- Map 38 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE), Union 24 (CONTAINS) Reducer 25 <- Union 24 (SIMPLE_EDGE), Union 26 (CONTAINS) Reducer 27 <- Union 26 (SIMPLE_EDGE) Reducer 28 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 29 <- Map 11 (SIMPLE_EDGE), Map 50 (SIMPLE_EDGE) +Reducer 29 <- Map 11 (SIMPLE_EDGE), Map 44 (SIMPLE_EDGE) Reducer 3 <- Map 37 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 30 <- Map 37 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE) -Reducer 31 <- Map 46 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE), Union 24 (CONTAINS) +Reducer 31 <- Map 40 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE), Union 24 (CONTAINS) Reducer 32 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 33 <- Map 11 (SIMPLE_EDGE), Map 51 (SIMPLE_EDGE) +Reducer 33 <- Map 11 (SIMPLE_EDGE), Map 45 (SIMPLE_EDGE) Reducer 34 <- Map 37 (SIMPLE_EDGE), Reducer 33 (SIMPLE_EDGE) -Reducer 35 <- Map 48 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE), Union 26 (CONTAINS) +Reducer 35 <- Map 42 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE), Union 26 (CONTAINS) Reducer 36 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 38 <- Map 37 (CUSTOM_SIMPLE_EDGE) -Reducer 39 <- Map 37 (CUSTOM_SIMPLE_EDGE) -Reducer 4 <- Map 44 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 40 <- Map 37 (CUSTOM_SIMPLE_EDGE) -Reducer 41 <- Map 37 (CUSTOM_SIMPLE_EDGE) -Reducer 42 <- Map 37 (CUSTOM_SIMPLE_EDGE) -Reducer 43 <- Map 37 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Map 38 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS) Reducer 8 <- Union 7 (SIMPLE_EDGE) Reducer 9 <- Reducer 27 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) @@ -205,12 +199,12 @@ Stage-0 limit:-1 Stage-1 Reducer 10 vectorized - File Output Operator [FS_638] - Select Operator [SEL_637] (rows=100 width=160) + File Output Operator [FS_618] + Select Operator [SEL_617] (rows=100 width=160) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Limit [LIM_636] (rows=100 width=152) + Limit [LIM_616] (rows=100 width=152) Number of rows:100 - Select Operator [SEL_635] (rows=3422897230256 width=151) + Select Operator [SEL_615] (rows=3422897230256 width=151) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_175] @@ -219,21 +213,21 @@ Stage-0 Filter Operator [FIL_173] (rows=3422897230256 width=255) predicate:((CAST( _col10 AS decimal(17,2)) / CAST( _col4 AS decimal(17,2))) < 0.9) Merge Join Operator [MERGEJOIN_518] (rows=10268691690770 width=255) - Conds:RS_631._col0, _col1, _col2, _col3=RS_634._col0, _col1, _col2, _col3(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col10","_col11"] + Conds:RS_611._col0, _col1, _col2, _col3=RS_614._col0, _col1, _col2, _col3(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col10","_col11"] <-Reducer 27 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_634] + SHUFFLE [RS_614] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_633] (rows=84235776 width=135) + Group By Operator [GBY_613] (rows=84235776 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 - Group By Operator [GBY_632] (rows=736356923 width=131) + Group By Operator [GBY_612] (rows=736356923 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Union 26 [SIMPLE_EDGE] <-Reducer 25 [CONTAINS] vectorized - Reduce Output Operator [RS_670] + Reduce Output Operator [RS_644] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_669] (rows=736356923 width=131) + Group By Operator [GBY_643] (rows=736356923 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_668] (rows=621178955 width=131) + Group By Operator [GBY_642] (rows=621178955 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Union 24 [SIMPLE_EDGE] <-Reducer 23 [CONTAINS] @@ -244,13 +238,13 @@ Stage-0 Select Operator [SEL_539] (rows=170474971 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_538] (rows=170474971 width=234) - Conds:RS_103._col1, _col2=RS_625._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] - <-Map 44 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_625] + Conds:RS_103._col1, _col2=RS_605._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_605] PartitionCols:_col0, _col1 - Select Operator [SEL_623] (rows=28798881 width=121) + Select Operator [SEL_603] (rows=28798881 width=121) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_622] (rows=28798881 width=121) + Filter Operator [FIL_602] (rows=28798881 width=121) predicate:cr_item_sk is not null TableScan [TS_9] (rows=28798881 width=121) default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["cr_item_sk","cr_order_number","cr_return_quantity","cr_return_amount"] @@ -260,11 +254,11 @@ Stage-0 Merge Join Operator [MERGEJOIN_510] (rows=96821196 width=138) Conds:RS_100._col1=RS_599._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_599] + SHUFFLE [RS_599] PartitionCols:_col0 - Select Operator [SEL_592] (rows=45745 width=19) + Select Operator [SEL_595] (rows=45745 width=19) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_591] (rows=45745 width=109) + Filter Operator [FIL_594] (rows=45745 width=109) predicate:((i_category = 'Sports') and i_brand_id is not null and i_category_id is not null and i_class_id is not null and i_item_sk is not null and i_manufact_id is not null) TableScan [TS_6] (rows=462000 width=109) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_class_id","i_category_id","i_category","i_manufact_id"] @@ -272,7 +266,7 @@ Stage-0 SHUFFLE [RS_100] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_509] (rows=101592102 width=122) - Conds:RS_667._col0=RS_571._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Conds:RS_641._col0=RS_571._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_571] PartitionCols:_col0 @@ -282,18 +276,18 @@ Stage-0 predicate:((d_year = 2002) and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=8) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Map 49 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_667] + <-Map 43 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_641] PartitionCols:_col0 - Select Operator [SEL_666] (rows=286549727 width=127) + Select Operator [SEL_640] (rows=286549727 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_665] (rows=286549727 width=127) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_101_item_i_item_sk_min) AND DynamicValue(RS_101_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_101_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_98_date_dim_d_date_sk_min) AND DynamicValue(RS_98_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_98_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) + Filter Operator [FIL_639] (rows=286549727 width=127) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_98_date_dim_d_date_sk_min) AND DynamicValue(RS_98_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_98_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) TableScan [TS_85] (rows=287989836 width=127) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_ext_sales_price"] <-Reducer 28 [BROADCAST_EDGE] vectorized - BROADCAST [RS_662] - Group By Operator [GBY_661] (rows=1 width=12) + BROADCAST [RS_638] + Group By Operator [GBY_637] (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 PARTITION_ONLY_SHUFFLE [RS_586] @@ -302,17 +296,6 @@ Stage-0 Select Operator [SEL_572] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_562] - <-Reducer 41 [BROADCAST_EDGE] vectorized - BROADCAST [RS_664] - Group By Operator [GBY_663] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 37 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_614] - Group By Operator [GBY_608] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_600] (rows=45745 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_592] <-Reducer 31 [CONTAINS] Reduce Output Operator [RS_551] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 @@ -321,13 +304,13 @@ Stage-0 Select Operator [SEL_548] (rows=450703984 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_547] (rows=450703984 width=204) - Conds:RS_125._col1, _col2=RS_649._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] - <-Map 46 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_649] + Conds:RS_125._col1, _col2=RS_627._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] + <-Map 40 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_627] PartitionCols:_col0, _col1 - Select Operator [SEL_647] (rows=57591150 width=119) + Select Operator [SEL_625] (rows=57591150 width=119) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_646] (rows=57591150 width=119) + Filter Operator [FIL_624] (rows=57591150 width=119) predicate:sr_item_sk is not null TableScan [TS_31] (rows=57591150 width=119) default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number","sr_return_quantity","sr_return_amt"] @@ -335,16 +318,16 @@ Stage-0 SHUFFLE [RS_125] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_513] (rows=187186493 width=124) - Conds:RS_122._col1=RS_601._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] + Conds:RS_122._col1=RS_600._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_601] + SHUFFLE [RS_600] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_592] + Please refer to the previous Select Operator [SEL_595] <-Reducer 29 [SIMPLE_EDGE] SHUFFLE [RS_122] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_512] (rows=196410188 width=109) - Conds:RS_677._col0=RS_573._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Conds:RS_649._col0=RS_573._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_573] PartitionCols:_col0 @@ -353,18 +336,18 @@ Stage-0 Filter Operator [FIL_559] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] - <-Map 50 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_677] + <-Map 44 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_649] PartitionCols:_col0 - Select Operator [SEL_676] (rows=550076554 width=122) + Select Operator [SEL_648] (rows=550076554 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_675] (rows=550076554 width=122) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_123_item_i_item_sk_min) AND DynamicValue(RS_123_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_123_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_120_date_dim_d_date_sk_min) AND DynamicValue(RS_120_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_120_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) + Filter Operator [FIL_647] (rows=550076554 width=122) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_120_date_dim_d_date_sk_min) AND DynamicValue(RS_120_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_120_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) TableScan [TS_107] (rows=575995635 width=122) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_ext_sales_price"] <-Reducer 32 [BROADCAST_EDGE] vectorized - BROADCAST [RS_672] - Group By Operator [GBY_671] (rows=1 width=12) + BROADCAST [RS_646] + Group By Operator [GBY_645] (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 PARTITION_ONLY_SHUFFLE [RS_587] @@ -373,17 +356,6 @@ Stage-0 Select Operator [SEL_574] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_563] - <-Reducer 42 [BROADCAST_EDGE] vectorized - BROADCAST [RS_674] - Group By Operator [GBY_673] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 37 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_615] - Group By Operator [GBY_609] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_602] (rows=45745 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_592] <-Reducer 35 [CONTAINS] Reduce Output Operator [RS_556] PartitionCols:_col0, _col1, _col2, _col3 @@ -392,13 +364,13 @@ Stage-0 Select Operator [SEL_553] (rows=115177968 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_552] (rows=115177968 width=220) - Conds:RS_154._col1, _col2=RS_660._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] - <-Map 48 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_660] + Conds:RS_154._col1, _col2=RS_636._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] + <-Map 42 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_636] PartitionCols:_col0, _col1 - Select Operator [SEL_658] (rows=14398467 width=118) + Select Operator [SEL_634] (rows=14398467 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_657] (rows=14398467 width=118) + Filter Operator [FIL_633] (rows=14398467 width=118) predicate:wr_item_sk is not null TableScan [TS_60] (rows=14398467 width=118) default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_item_sk","wr_order_number","wr_return_quantity","wr_return_amt"] @@ -406,16 +378,16 @@ Stage-0 SHUFFLE [RS_154] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_516] (rows=48990732 width=139) - Conds:RS_151._col1=RS_603._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] + Conds:RS_151._col1=RS_601._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_603] + SHUFFLE [RS_601] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_592] + Please refer to the previous Select Operator [SEL_595] <-Reducer 33 [SIMPLE_EDGE] SHUFFLE [RS_151] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_515] (rows=51404771 width=123) - Conds:RS_684._col0=RS_575._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Conds:RS_654._col0=RS_575._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_575] PartitionCols:_col0 @@ -424,18 +396,18 @@ Stage-0 Filter Operator [FIL_560] (rows=652 width=8) predicate:((d_year = 2002) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] - <-Map 51 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_684] + <-Map 45 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_654] PartitionCols:_col0 - Select Operator [SEL_683] (rows=143966864 width=127) + Select Operator [SEL_653] (rows=143966864 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_682] (rows=143966864 width=127) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_152_item_i_item_sk_min) AND DynamicValue(RS_152_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_152_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_149_date_dim_d_date_sk_min) AND DynamicValue(RS_149_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_149_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) + Filter Operator [FIL_652] (rows=143966864 width=127) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_149_date_dim_d_date_sk_min) AND DynamicValue(RS_149_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_149_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) TableScan [TS_136] (rows=144002668 width=127) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_ext_sales_price"] <-Reducer 36 [BROADCAST_EDGE] vectorized - BROADCAST [RS_679] - Group By Operator [GBY_678] (rows=1 width=12) + BROADCAST [RS_651] + Group By Operator [GBY_650] (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 PARTITION_ONLY_SHUFFLE [RS_588] @@ -444,23 +416,12 @@ Stage-0 Select Operator [SEL_576] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_564] - <-Reducer 43 [BROADCAST_EDGE] vectorized - BROADCAST [RS_681] - Group By Operator [GBY_680] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 37 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_616] - Group By Operator [GBY_610] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_604] (rows=45745 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_592] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_631] + SHUFFLE [RS_611] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_630] (rows=84235776 width=135) + Group By Operator [GBY_610] (rows=84235776 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col0, _col1, _col2, _col3 - Group By Operator [GBY_629] (rows=736356923 width=131) + Group By Operator [GBY_609] (rows=736356923 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Union 7 [SIMPLE_EDGE] <-Reducer 19 [CONTAINS] @@ -471,25 +432,25 @@ Stage-0 Select Operator [SEL_534] (rows=115177968 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_533] (rows=115177968 width=220) - Conds:RS_69._col1, _col2=RS_659._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] - <-Map 48 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_659] + Conds:RS_69._col1, _col2=RS_635._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] + <-Map 42 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_635] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_658] + Please refer to the previous Select Operator [SEL_634] <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_69] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_507] (rows=48990732 width=139) - Conds:RS_66._col1=RS_597._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] + Conds:RS_66._col1=RS_598._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_597] + SHUFFLE [RS_598] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_592] + Please refer to the previous Select Operator [SEL_595] <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_66] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_506] (rows=51404771 width=123) - Conds:RS_656._col0=RS_569._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Conds:RS_632._col0=RS_569._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_569] PartitionCols:_col0 @@ -498,18 +459,18 @@ Stage-0 Filter Operator [FIL_557] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] - <-Map 47 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_656] + <-Map 41 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_632] PartitionCols:_col0 - Select Operator [SEL_655] (rows=143966864 width=127) + Select Operator [SEL_631] (rows=143966864 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_654] (rows=143966864 width=127) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_67_item_i_item_sk_min) AND DynamicValue(RS_67_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_67_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_64_date_dim_d_date_sk_min) AND DynamicValue(RS_64_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_64_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) + Filter Operator [FIL_630] (rows=143966864 width=127) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_64_date_dim_d_date_sk_min) AND DynamicValue(RS_64_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_64_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) TableScan [TS_51] (rows=144002668 width=127) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_order_number","ws_quantity","ws_ext_sales_price"] <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_651] - Group By Operator [GBY_650] (rows=1 width=12) + BROADCAST [RS_629] + Group By Operator [GBY_628] (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 PARTITION_ONLY_SHUFFLE [RS_585] @@ -518,23 +479,12 @@ Stage-0 Select Operator [SEL_570] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_561] - <-Reducer 40 [BROADCAST_EDGE] vectorized - BROADCAST [RS_653] - Group By Operator [GBY_652] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 37 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_613] - Group By Operator [GBY_607] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_598] (rows=45745 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_592] <-Reducer 6 [CONTAINS] vectorized - Reduce Output Operator [RS_628] + Reduce Output Operator [RS_608] PartitionCols:_col0, _col1, _col2, _col3 - Group By Operator [GBY_627] (rows=736356923 width=131) + Group By Operator [GBY_607] (rows=736356923 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:_col0, _col1, _col2, _col3, _col4, _col5 - Group By Operator [GBY_626] (rows=621178955 width=131) + Group By Operator [GBY_606] (rows=621178955 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Union 5 [SIMPLE_EDGE] <-Reducer 15 [CONTAINS] @@ -545,41 +495,41 @@ Stage-0 Select Operator [SEL_529] (rows=450703984 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_528] (rows=450703984 width=204) - Conds:RS_40._col1, _col2=RS_648._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] - <-Map 46 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_648] + Conds:RS_40._col1, _col2=RS_626._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] + <-Map 40 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_626] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_647] + Please refer to the previous Select Operator [SEL_625] <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_504] (rows=187186493 width=124) - Conds:RS_37._col1=RS_595._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] + Conds:RS_37._col1=RS_597._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_595] + SHUFFLE [RS_597] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_592] + Please refer to the previous Select Operator [SEL_595] <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_503] (rows=196410188 width=109) - Conds:RS_645._col0=RS_567._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Conds:RS_623._col0=RS_567._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_567] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_561] - <-Map 45 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_645] + <-Map 39 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_623] PartitionCols:_col0 - Select Operator [SEL_644] (rows=550076554 width=122) + Select Operator [SEL_622] (rows=550076554 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_643] (rows=550076554 width=122) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_38_item_i_item_sk_min) AND DynamicValue(RS_38_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_38_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) + Filter Operator [FIL_621] (rows=550076554 width=122) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) TableScan [TS_22] (rows=575995635 width=122) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ticket_number","ss_quantity","ss_ext_sales_price"] <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_640] - Group By Operator [GBY_639] (rows=1 width=12) + BROADCAST [RS_620] + Group By Operator [GBY_619] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_584] @@ -588,17 +538,6 @@ Stage-0 Select Operator [SEL_568] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_561] - <-Reducer 39 [BROADCAST_EDGE] vectorized - BROADCAST [RS_642] - Group By Operator [GBY_641] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 37 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_612] - Group By Operator [GBY_606] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_596] (rows=45745 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_592] <-Reducer 4 [CONTAINS] Reduce Output Operator [RS_523] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 @@ -607,36 +546,36 @@ Stage-0 Select Operator [SEL_520] (rows=170474971 width=131) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_519] (rows=170474971 width=234) - Conds:RS_18._col1, _col2=RS_624._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] - <-Map 44 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_624] + Conds:RS_18._col1, _col2=RS_604._col0, _col1(Left Outer),Output:["_col3","_col4","_col7","_col8","_col9","_col10","_col13","_col14"] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_604] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_623] + Please refer to the previous Select Operator [SEL_603] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_501] (rows=96821196 width=138) - Conds:RS_15._col1=RS_593._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] + Conds:RS_15._col1=RS_596._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col10"] <-Map 37 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_593] + SHUFFLE [RS_596] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_592] + Please refer to the previous Select Operator [SEL_595] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_500] (rows=101592102 width=122) - Conds:RS_621._col0=RS_565._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Conds:RS_593._col0=RS_565._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 11 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_565] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_561] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_621] + SHUFFLE [RS_593] PartitionCols:_col0 - Select Operator [SEL_620] (rows=286549727 width=127) + Select Operator [SEL_592] (rows=286549727 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_619] (rows=286549727 width=127) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_16_item_i_item_sk_min) AND DynamicValue(RS_16_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_16_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) + Filter Operator [FIL_591] (rows=286549727 width=127) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) TableScan [TS_0] (rows=287989836 width=127) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_order_number","cs_quantity","cs_ext_sales_price"] <-Reducer 12 [BROADCAST_EDGE] vectorized @@ -650,15 +589,4 @@ Stage-0 Select Operator [SEL_566] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_561] - <-Reducer 38 [BROADCAST_EDGE] vectorized - BROADCAST [RS_618] - Group By Operator [GBY_617] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 37 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_611] - Group By Operator [GBY_605] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_594] (rows=45745 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_592] http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query79.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query79.q.out b/ql/src/test/results/clientpositive/perf/tez/query79.q.out index 877ff7b..ce5a8bc 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query79.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query79.q.out @@ -57,9 +57,8 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 4 <- Reducer 10 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE) +Map 4 <- Reducer 10 (BROADCAST_EDGE) Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) @@ -72,17 +71,17 @@ Stage-0 limit:-1 Stage-1 Reducer 3 vectorized - File Output Operator [FS_131] - Limit [LIM_130] (rows=100 width=776) + File Output Operator [FS_126] + Limit [LIM_125] (rows=100 width=776) Number of rows:100 - Select Operator [SEL_129] (rows=43530621 width=776) + Select Operator [SEL_124] (rows=43530621 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_33] Select Operator [SEL_32] (rows=43530621 width=776) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] Merge Join Operator [MERGEJOIN_100] (rows=43530621 width=685) - Conds:RS_103._col0=RS_128._col1(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col8"] + Conds:RS_103._col0=RS_123._col1(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col8"] <-Map 1 [SIMPLE_EDGE] vectorized SHUFFLE [RS_103] PartitionCols:_col0 @@ -93,11 +92,11 @@ Stage-0 TableScan [TS_0] (rows=80000000 width=184) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_first_name","c_last_name"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_128] + SHUFFLE [RS_123] PartitionCols:_col1 - Select Operator [SEL_127] (rows=43530621 width=507) + Select Operator [SEL_122] (rows=43530621 width=507) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Group By Operator [GBY_126] (rows=43530621 width=325) + Group By Operator [GBY_121] (rows=43530621 width=325) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_26] @@ -105,13 +104,13 @@ Stage-0 Group By Operator [GBY_25] (rows=43530621 width=325) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col3, _col5, _col10 Merge Join Operator [MERGEJOIN_99] (rows=43530621 width=214) - Conds:RS_21._col2=RS_114._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col10"] + Conds:RS_21._col2=RS_120._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col10"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_114] + SHUFFLE [RS_120] PartitionCols:_col0 - Select Operator [SEL_113] (rows=3055 width=4) + Select Operator [SEL_119] (rows=3055 width=4) Output:["_col0"] - Filter Operator [FIL_112] (rows=3055 width=12) + Filter Operator [FIL_118] (rows=3055 width=12) predicate:(((hd_dep_count = 8) or (hd_vehicle_count > 0)) and hd_demo_sk is not null) TableScan [TS_12] (rows=7200 width=12) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] @@ -119,13 +118,13 @@ Stage-0 SHUFFLE [RS_21] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_98] (rows=102592623 width=283) - Conds:RS_18._col4=RS_125._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col10"] + Conds:RS_18._col4=RS_117._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7","_col10"] <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_125] + SHUFFLE [RS_117] PartitionCols:_col0 - Select Operator [SEL_124] (rows=1704 width=97) + Select Operator [SEL_116] (rows=1704 width=97) Output:["_col0","_col1"] - Filter Operator [FIL_123] (rows=1704 width=100) + Filter Operator [FIL_115] (rows=1704 width=100) predicate:(s_number_employees BETWEEN 200 AND 295 and s_store_sk is not null) TableScan [TS_9] (rows=1704 width=100) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_number_employees","s_city"] @@ -133,7 +132,7 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col4 Merge Join Operator [MERGEJOIN_97] (rows=102592623 width=193) - Conds:RS_122._col0=RS_106._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Conds:RS_114._col0=RS_106._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 9 [SIMPLE_EDGE] vectorized SHUFFLE [RS_106] PartitionCols:_col0 @@ -144,12 +143,12 @@ Stage-0 TableScan [TS_6] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_dow"] <-Map 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_122] + SHUFFLE [RS_114] PartitionCols:_col0 - Select Operator [SEL_121] (rows=479121995 width=237) + Select Operator [SEL_113] (rows=479121995 width=237) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_120] (rows=479121995 width=237) - predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_22_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_22_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_22_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + Filter Operator [FIL_112] (rows=479121995 width=237) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) TableScan [TS_3] (rows=575995635 width=237) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_coupon_amt","ss_net_profit"] <-Reducer 10 [BROADCAST_EDGE] vectorized @@ -163,15 +162,4 @@ Stage-0 Select Operator [SEL_107] (rows=391 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_105] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_119] - Group By Operator [GBY_118] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_117] - Group By Operator [GBY_116] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_115] (rows=3055 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_113]
