http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query15.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query15.q.out b/ql/src/test/results/clientpositive/perf/tez/query15.q.out index e4e0199..b593a2e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query15.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query15.q.out @@ -39,6 +39,8 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage +Map 7 <- Reducer 10 (BROADCAST_EDGE) +Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) @@ -50,14 +52,14 @@ Stage-0 limit:100 Stage-1 Reducer 5 vectorized - File Output Operator [FS_63] - Limit [LIM_62] (rows=100 width=135) + File Output Operator [FS_98] + Limit [LIM_97] (rows=100 width=135) Number of rows:100 - Select Operator [SEL_61] (rows=174233858 width=135) + Select Operator [SEL_96] (rows=174233858 width=135) Output:["_col0","_col1"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_60] - Group By Operator [GBY_59] (rows=174233858 width=135) + SHUFFLE [RS_95] + Group By Operator [GBY_94] (rows=174233858 width=135) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_25] @@ -68,52 +70,63 @@ Stage-0 Output:["_col4","_col7"] Filter Operator [FIL_22] (rows=348467716 width=135) predicate:((_col3) IN ('CA', 'WA', 'GA') or (_col7 > 500) or (substr(_col4, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792')) - Merge Join Operator [MERGEJOIN_46] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_76] (rows=348467716 width=135) Conds:RS_19._col0=RS_20._col1(Inner),Output:["_col3","_col4","_col7"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_19] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_44] (rows=88000001 width=860) - Conds:RS_49._col1=RS_52._col0(Inner),Output:["_col0","_col3","_col4"] + Merge Join Operator [MERGEJOIN_74] (rows=88000001 width=860) + Conds:RS_79._col1=RS_82._col0(Inner),Output:["_col0","_col3","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_49] + SHUFFLE [RS_79] PartitionCols:_col1 - Select Operator [SEL_48] (rows=80000000 width=860) + Select Operator [SEL_78] (rows=80000000 width=860) Output:["_col0","_col1"] - Filter Operator [FIL_47] (rows=80000000 width=860) + Filter Operator [FIL_77] (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 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_52] + SHUFFLE [RS_82] PartitionCols:_col0 - Select Operator [SEL_51] (rows=40000000 width=1014) + Select Operator [SEL_81] (rows=40000000 width=1014) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_50] (rows=40000000 width=1014) + Filter Operator [FIL_80] (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_state","ca_zip"] <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_20] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_45] (rows=316788826 width=135) - Conds:RS_55._col0=RS_58._col0(Inner),Output:["_col1","_col2"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_55] - PartitionCols:_col0 - Select Operator [SEL_54] (rows=287989836 width=135) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_53] (rows=287989836 width=135) - predicate:(cs_bill_customer_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_6] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_sales_price"] + Merge Join Operator [MERGEJOIN_75] (rows=316788826 width=135) + Conds:RS_93._col0=RS_85._col0(Inner),Output:["_col1","_col2"] <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_58] + SHUFFLE [RS_85] PartitionCols:_col0 - Select Operator [SEL_57] (rows=18262 width=1119) + Select Operator [SEL_84] (rows=18262 width=1119) Output:["_col0"] - Filter Operator [FIL_56] (rows=18262 width=1119) + Filter Operator [FIL_83] (rows=18262 width=1119) predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) TableScan [TS_9] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + <-Map 7 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_93] + PartitionCols:_col0 + Select Operator [SEL_92] (rows=287989836 width=135) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_91] (rows=287989836 width=135) + 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_bill_customer_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_6] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_sales_price"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_90] + Group By Operator [GBY_89] (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_88] + Group By Operator [GBY_87] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_86] (rows=18262 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_84]
http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query16.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query16.q.out b/ql/src/test/results/clientpositive/perf/tez/query16.q.out index 7df8385..28cf571 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query16.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query16.q.out @@ -61,12 +61,16 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 15 <- Map 14 (SIMPLE_EDGE) +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Map 17 (SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) -Reducer 3 <- Map 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 15 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) +Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 16 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 18 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 7 (CUSTOM_SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) @@ -76,22 +80,22 @@ Stage-0 limit:-1 Stage-1 Reducer 9 vectorized - File Output Operator [FS_114] - Limit [LIM_113] (rows=1 width=344) + File Output Operator [FS_174] + Limit [LIM_173] (rows=1 width=344) Number of rows:100 - Select Operator [SEL_112] (rows=1 width=344) + Select Operator [SEL_172] (rows=1 width=344) Output:["_col0","_col1","_col2"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_111] - Select Operator [SEL_110] (rows=1 width=344) + SHUFFLE [RS_171] + Select Operator [SEL_170] (rows=1 width=344) Output:["_col1","_col2","_col3"] - Group By Operator [GBY_109] (rows=1 width=344) + Group By Operator [GBY_169] (rows=1 width=344) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_108] - Group By Operator [GBY_107] (rows=1 width=344) + PARTITION_ONLY_SHUFFLE [RS_168] + Group By Operator [GBY_167] (rows=1 width=344) Output:["_col0","_col1","_col2"],aggregations:["count(_col0)","sum(_col1)","sum(_col2)"] - Group By Operator [GBY_106] (rows=231905279 width=135) + Group By Operator [GBY_166] (rows=231905279 width=135) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_74] @@ -102,21 +106,21 @@ Stage-0 Output:["_col4","_col5","_col6"] Filter Operator [FIL_41] (rows=231905279 width=135) predicate:_col14 is null - Merge Join Operator [MERGEJOIN_83] (rows=463810558 width=135) - Conds:RS_38._col4=RS_105._col0(Left Outer),Output:["_col4","_col5","_col6","_col14"] - <-Reducer 15 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_105] + Merge Join Operator [MERGEJOIN_128] (rows=463810558 width=135) + Conds:RS_38._col4=RS_165._col0(Left Outer),Output:["_col4","_col5","_col6","_col14"] + <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_165] PartitionCols:_col0 - Select Operator [SEL_104] (rows=14399440 width=106) + Select Operator [SEL_164] (rows=14399440 width=106) Output:["_col0","_col1"] - Group By Operator [GBY_103] (rows=14399440 width=106) + Group By Operator [GBY_163] (rows=14399440 width=106) Output:["_col0"],keys:KEY._col0 - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_102] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_162] PartitionCols:_col0 - Group By Operator [GBY_101] (rows=28798881 width=106) + Group By Operator [GBY_161] (rows=28798881 width=106) Output:["_col0"],keys:cr_order_number - Filter Operator [FIL_100] (rows=28798881 width=106) + Filter Operator [FIL_160] (rows=28798881 width=106) predicate:cr_order_number is not null TableScan [TS_25] (rows=28798881 width=106) default@catalog_returns,cr1,Tbl:COMPLETE,Col:NONE,Output:["cr_order_number"] @@ -125,68 +129,101 @@ Stage-0 PartitionCols:_col4 Select Operator [SEL_37] (rows=421645953 width=135) Output:["_col4","_col5","_col6"] - Merge Join Operator [MERGEJOIN_82] (rows=421645953 width=135) - Conds:RS_34._col4=RS_99._col0(Left Semi),Output:["_col3","_col4","_col5","_col6","_col14"],residual filter predicates:{(_col3 <> _col14)} - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_99] + Merge Join Operator [MERGEJOIN_127] (rows=421645953 width=135) + Conds:RS_34._col4=RS_159._col0(Left Semi),Output:["_col3","_col4","_col5","_col6","_col14"],residual filter predicates:{(_col3 <> _col14)} + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_159] PartitionCols:_col0 - Group By Operator [GBY_98] (rows=287989836 width=135) + Group By Operator [GBY_158] (rows=287989836 width=135) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_97] (rows=287989836 width=135) + Select Operator [SEL_157] (rows=287989836 width=135) Output:["_col0","_col1"] - Filter Operator [FIL_96] (rows=287989836 width=135) + Filter Operator [FIL_156] (rows=287989836 width=135) predicate:(cs_order_number is not null and cs_warehouse_sk is not null) TableScan [TS_22] (rows=287989836 width=135) default@catalog_sales,cs2,Tbl:COMPLETE,Col:NONE,Output:["cs_warehouse_sk","cs_order_number"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_81] (rows=383314495 width=135) - Conds:RS_18._col2=RS_95._col0(Inner),Output:["_col3","_col4","_col5","_col6"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_95] + Merge Join Operator [MERGEJOIN_126] (rows=383314495 width=135) + Conds:RS_18._col2=RS_147._col0(Inner),Output:["_col3","_col4","_col5","_col6"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_147] PartitionCols:_col0 - Select Operator [SEL_94] (rows=30 width=2045) + Select Operator [SEL_146] (rows=30 width=2045) Output:["_col0"] - Filter Operator [FIL_93] (rows=30 width=2045) + Filter Operator [FIL_145] (rows=30 width=2045) predicate:((cc_county) IN ('Ziebach County', 'Levy County', 'Huron County', 'Franklin Parish', 'Daviess County') and cc_call_center_sk is not null) TableScan [TS_9] (rows=60 width=2045) default@call_center,call_center,Tbl:COMPLETE,Col:NONE,Output:["cc_call_center_sk","cc_county"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_80] (rows=348467716 width=135) - Conds:RS_15._col1=RS_92._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_92] + Merge Join Operator [MERGEJOIN_125] (rows=348467716 width=135) + Conds:RS_15._col1=RS_139._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_139] PartitionCols:_col0 - Select Operator [SEL_91] (rows=20000000 width=1014) + Select Operator [SEL_138] (rows=20000000 width=1014) Output:["_col0"] - Filter Operator [FIL_90] (rows=20000000 width=1014) + Filter Operator [FIL_137] (rows=20000000 width=1014) predicate:((ca_state = 'NY') and ca_address_sk is not null) TableScan [TS_6] (rows=40000000 width=1014) default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_79] (rows=316788826 width=135) - Conds:RS_86._col0=RS_89._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_86] - PartitionCols:_col0 - Select Operator [SEL_85] (rows=287989836 width=135) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_84] (rows=287989836 width=135) - predicate:(cs_call_center_sk is not null and cs_order_number is not null and cs_ship_addr_sk is not null and cs_ship_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,cs1,Tbl:COMPLETE,Col:NONE,Output:["cs_ship_date_sk","cs_ship_addr_sk","cs_call_center_sk","cs_warehouse_sk","cs_order_number","cs_ext_ship_cost","cs_net_profit"] + Merge Join Operator [MERGEJOIN_124] (rows=316788826 width=135) + Conds:RS_155._col0=RS_131._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_89] + SHUFFLE [RS_131] PartitionCols:_col0 - Select Operator [SEL_88] (rows=8116 width=1119) + Select Operator [SEL_130] (rows=8116 width=1119) Output:["_col0"] - Filter Operator [FIL_87] (rows=8116 width=1119) + Filter Operator [FIL_129] (rows=8116 width=1119) predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-04-01 00:00:00.0' AND TIMESTAMP'2001-05-31 01:00:00.0' 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_date"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_155] + PartitionCols:_col0 + Select Operator [SEL_154] (rows=287989836 width=135) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Filter Operator [FIL_153] (rows=287989836 width=135) + predicate:((cs_call_center_sk BETWEEN DynamicValue(RS_19_call_center_cc_call_center_sk_min) AND DynamicValue(RS_19_call_center_cc_call_center_sk_max) and in_bloom_filter(cs_call_center_sk, DynamicValue(RS_19_call_center_cc_call_center_sk_bloom_filter))) and (cs_ship_addr_sk BETWEEN DynamicValue(RS_16_customer_address_ca_address_sk_min) AND DynamicValue(RS_16_customer_address_ca_address_sk_max) and in_bloom_filter(cs_ship_addr_sk, DynamicValue(RS_16_customer_address_ca_address_sk_bloom_filter))) and (cs_ship_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_ship_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and cs_call_center_sk is not null and cs_order_number is not null and cs_ship_addr_sk is not null and cs_ship_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=135) + default@catalog_sales,cs1,Tbl:COMPLETE,Col:NONE,Output:["cs_ship_date_sk","cs_ship_addr_sk","cs_call_center_sk","cs_warehouse_sk","cs_order_number","cs_ext_ship_cost","cs_net_profit"] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_136] + Group By Operator [GBY_135] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_134] + Group By Operator [GBY_133] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_132] (rows=8116 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_130] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_144] + Group By Operator [GBY_143] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_142] + Group By Operator [GBY_141] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"] + Select Operator [SEL_140] (rows=20000000 width=1014) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_138] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_152] + Group By Operator [GBY_151] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_150] + Group By Operator [GBY_149] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_148] (rows=30 width=2045) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_146] http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query17.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query17.q.out b/ql/src/test/results/clientpositive/perf/tez/query17.q.out index 0551653..2e5e254 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query17.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query17.q.out @@ -89,31 +89,39 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Reducer 11 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 14 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Map 1 <- Reducer 17 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 18 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE) +Reducer 10 <- Map 18 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) +Reducer 12 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Map 19 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 14 <- Reducer 13 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Reducer 13 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 15 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Map 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 20 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 13 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_129] - Limit [LIM_128] (rows=100 width=88) + File Output Operator [FS_256] + Limit [LIM_255] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_127] (rows=421657640 width=88) + Select Operator [SEL_254] (rows=421657640 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] - Select Operator [SEL_125] (rows=421657640 width=88) + SHUFFLE [RS_253] + Select Operator [SEL_252] (rows=421657640 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - Group By Operator [GBY_124] (rows=421657640 width=88) + Group By Operator [GBY_251] (rows=421657640 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","count(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)","sum(VALUE._col7)","count(VALUE._col8)","sum(VALUE._col9)","sum(VALUE._col10)","sum(VALUE._col11)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_50] @@ -122,106 +130,172 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"],aggregations:["count(_col3)","sum(_col3)","sum(_col7)","sum(_col6)","count(_col4)","sum(_col4)","sum(_col9)","sum(_col8)","count(_col5)","sum(_col5)","sum(_col11)","sum(_col10)"],keys:_col0, _col1, _col2 Select Operator [SEL_47] (rows=843315281 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11"] - Merge Join Operator [MERGEJOIN_99] (rows=843315281 width=88) - Conds:RS_44._col3=RS_123._col0(Inner),Output:["_col5","_col9","_col10","_col14","_col21","_col25"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_123] + Merge Join Operator [MERGEJOIN_202] (rows=843315281 width=88) + Conds:RS_44._col3=RS_230._col0(Inner),Output:["_col5","_col9","_col10","_col14","_col21","_col25"] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_230] PartitionCols:_col0 - Select Operator [SEL_122] (rows=1704 width=1910) + Select Operator [SEL_229] (rows=1704 width=1910) Output:["_col0","_col1"] - Filter Operator [FIL_121] (rows=1704 width=1910) + Filter Operator [FIL_228] (rows=1704 width=1910) predicate:s_store_sk is not null TableScan [TS_32] (rows=1704 width=1910) default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_98] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_201] (rows=766650239 width=88) Conds:RS_41._col1, _col2, _col4=RS_42._col7, _col8, _col9(Inner),Output:["_col3","_col5","_col9","_col10","_col14","_col21"] - <-Reducer 10 [SIMPLE_EDGE] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col7, _col8, _col9 - Merge Join Operator [MERGEJOIN_97] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_200] (rows=348467716 width=135) Conds:RS_28._col2, _col1=RS_29._col1, _col2(Inner),Output:["_col3","_col7","_col8","_col9","_col10"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_29] + <-Reducer 13 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_29] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_96] (rows=63350266 width=77) - Conds:RS_120._col0=RS_111._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_199] (rows=63350266 width=77) + Conds:RS_243._col0=RS_213._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_111] + PARTITION_ONLY_SHUFFLE [RS_213] PartitionCols:_col0 - Select Operator [SEL_108] (rows=36525 width=1119) + Select Operator [SEL_208] (rows=36525 width=1119) Output:["_col0"] - Filter Operator [FIL_105] (rows=36525 width=1119) + Filter Operator [FIL_205] (rows=36525 width=1119) predicate:((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=1119) default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_quarter_name"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_120] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_243] PartitionCols:_col0 - Select Operator [SEL_119] (rows=57591150 width=77) + Select Operator [SEL_242] (rows=57591150 width=77) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_118] (rows=57591150 width=77) + Filter Operator [FIL_241] (rows=57591150 width=77) predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) TableScan [TS_15] (rows=57591150 width=77) default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] - <-Reducer 9 [SIMPLE_EDGE] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_28] PartitionCols:_col2, _col1 - Merge Join Operator [MERGEJOIN_95] (rows=316788826 width=135) - Conds:RS_117._col0=RS_110._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_198] (rows=316788826 width=135) + Conds:RS_250._col0=RS_211._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_110] + PARTITION_ONLY_SHUFFLE [RS_211] PartitionCols:_col0 - Select Operator [SEL_107] (rows=36525 width=1119) + Select Operator [SEL_207] (rows=36525 width=1119) Output:["_col0"] - Filter Operator [FIL_104] (rows=36525 width=1119) + Filter Operator [FIL_204] (rows=36525 width=1119) predicate:((d_quarter_name) IN ('2000Q1', '2000Q2', '2000Q3') and d_date_sk is not null) Please refer to the previous TableScan [TS_3] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_117] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_250] PartitionCols:_col0 - Select Operator [SEL_116] (rows=287989836 width=135) + Select Operator [SEL_249] (rows=287989836 width=135) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_115] (rows=287989836 width=135) - predicate:(cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + Filter Operator [FIL_248] (rows=287989836 width=135) + predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_29_store_returns_sr_customer_sk_min) AND DynamicValue(RS_29_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_29_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_29_store_returns_sr_item_sk_min) AND DynamicValue(RS_29_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_29_store_returns_sr_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_26_d3_d_date_sk_min) AND DynamicValue(RS_26_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_26_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) TableScan [TS_9] (rows=287989836 width=135) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_240] + Group By Operator [GBY_239] (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_217] + Group By Operator [GBY_215] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_212] (rows=36525 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_207] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_245] + Group By Operator [GBY_244] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + <-Reducer 13 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_141] + Group By Operator [GBY_140] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] + Select Operator [SEL_139] (rows=63350266 width=77) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_199] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_247] + Group By Operator [GBY_246] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + <-Reducer 13 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_146] + Group By Operator [GBY_145] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] + Select Operator [SEL_144] (rows=63350266 width=77) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_199] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col1, _col2, _col4 - Merge Join Operator [MERGEJOIN_94] (rows=696954748 width=88) - Conds:RS_38._col1=RS_114._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col9","_col10"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_114] + Merge Join Operator [MERGEJOIN_197] (rows=696954748 width=88) + Conds:RS_38._col1=RS_222._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col9","_col10"] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_222] PartitionCols:_col0 - Select Operator [SEL_113] (rows=462000 width=1436) + Select Operator [SEL_221] (rows=462000 width=1436) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_112] (rows=462000 width=1436) + Filter Operator [FIL_220] (rows=462000 width=1436) predicate:i_item_sk is not null TableScan [TS_6] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_93] (rows=633595212 width=88) - Conds:RS_102._col0=RS_109._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_196] (rows=633595212 width=88) + Conds:RS_238._col0=RS_209._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_109] + PARTITION_ONLY_SHUFFLE [RS_209] PartitionCols:_col0 - Select Operator [SEL_106] (rows=36524 width=1119) + Select Operator [SEL_206] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_103] (rows=36524 width=1119) + Filter Operator [FIL_203] (rows=36524 width=1119) predicate:((d_quarter_name = '2000Q1') and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_102] + SHUFFLE [RS_238] PartitionCols:_col0 - Select Operator [SEL_101] (rows=575995635 width=88) + Select Operator [SEL_237] (rows=575995635 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_100] (rows=575995635 width=88) - predicate:(ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + Filter Operator [FIL_236] (rows=575995635 width=88) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_39_item_i_item_sk_min) AND DynamicValue(RS_39_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_39_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_36_d1_d_date_sk_min) AND DynamicValue(RS_36_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_36_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_45_store_s_store_sk_min) AND DynamicValue(RS_45_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_45_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number 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_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_227] + Group By Operator [GBY_226] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_225] + Group By Operator [GBY_224] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_223] (rows=462000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_221] + <-Reducer 21 [BROADCAST_EDGE] vectorized + BROADCAST [RS_235] + Group By Operator [GBY_234] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_233] + Group By Operator [GBY_232] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_231] (rows=1704 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_229] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_219] + Group By Operator [GBY_218] (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_216] + Group By Operator [GBY_214] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_210] (rows=36524 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_206] http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query18.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query18.q.out b/ql/src/test/results/clientpositive/perf/tez/query18.q.out index 5fa9ad7..e858527 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query18.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query18.q.out @@ -67,30 +67,35 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Map 13 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 11 <- Map 14 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 15 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Map 10 <- Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) +Reducer 12 <- Map 16 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 13 <- Map 18 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_110] - Limit [LIM_109] (rows=100 width=135) + File Output Operator [FS_187] + Limit [LIM_186] (rows=100 width=135) Number of rows:100 - Select Operator [SEL_108] (rows=1054114882 width=135) + Select Operator [SEL_185] (rows=1054114882 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_107] - Select Operator [SEL_106] (rows=1054114882 width=135) + SHUFFLE [RS_184] + Select Operator [SEL_183] (rows=1054114882 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Group By Operator [GBY_105] (rows=1054114882 width=135) + Group By Operator [GBY_182] (rows=1054114882 width=135) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)","sum(VALUE._col8)","count(VALUE._col9)","sum(VALUE._col10)","count(VALUE._col11)","sum(VALUE._col12)","count(VALUE._col13)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_43] @@ -99,96 +104,140 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col6)","count(_col6)","sum(_col7)","count(_col7)","sum(_col8)","count(_col8)","sum(_col9)","count(_col9)","sum(_col10)","count(_col10)"],keys:_col0, _col1, _col2, _col3, 0L Select Operator [SEL_40] (rows=421645953 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"] - Merge Join Operator [MERGEJOIN_83] (rows=421645953 width=135) + Merge Join Operator [MERGEJOIN_143] (rows=421645953 width=135) Conds:RS_37._col0=RS_38._col3(Inner),Output:["_col4","_col6","_col7","_col8","_col11","_col16","_col17","_col18","_col19","_col20","_col26"] - <-Reducer 12 [SIMPLE_EDGE] + <-Reducer 3 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_37] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_139] (rows=48400001 width=860) + Conds:RS_34._col1=RS_152._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_152] + PartitionCols:_col0 + Select Operator [SEL_151] (rows=1861800 width=385) + Output:["_col0"] + Filter Operator [FIL_150] (rows=1861800 width=385) + predicate:cd_demo_sk is not null + TableScan [TS_6] (rows=1861800 width=385) + default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_138] (rows=44000000 width=860) + Conds:RS_146._col2=RS_149._col0(Inner),Output:["_col0","_col1","_col4","_col6","_col7","_col8"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_146] + PartitionCols:_col2 + Select Operator [SEL_145] (rows=40000000 width=860) + Output:["_col0","_col1","_col2","_col4"] + Filter Operator [FIL_144] (rows=40000000 width=860) + predicate:((c_birth_month) IN (9, 5, 12, 4, 1, 10) and c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) + TableScan [TS_0] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk","c_birth_month","c_birth_year"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_149] + PartitionCols:_col0 + Select Operator [SEL_148] (rows=20000000 width=1014) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_147] (rows=20000000 width=1014) + predicate:((ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') and 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_state","ca_country"] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col3 Select Operator [SEL_30] (rows=383314495 width=135) Output:["_col1","_col3","_col6","_col7","_col8","_col9","_col10","_col16"] - Merge Join Operator [MERGEJOIN_82] (rows=383314495 width=135) - Conds:RS_27._col3=RS_104._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col14","_col16"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_104] + Merge Join Operator [MERGEJOIN_142] (rows=383314495 width=135) + Conds:RS_27._col3=RS_171._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col14","_col16"] + <-Map 18 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_171] PartitionCols:_col0 - Select Operator [SEL_103] (rows=462000 width=1436) + Select Operator [SEL_170] (rows=462000 width=1436) Output:["_col0","_col1"] - Filter Operator [FIL_102] (rows=462000 width=1436) + Filter Operator [FIL_169] (rows=462000 width=1436) predicate:i_item_sk is not null TableScan [TS_18] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] - <-Reducer 11 [SIMPLE_EDGE] + <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_81] (rows=348467716 width=135) - Conds:RS_24._col2=RS_101._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col14"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_101] + Merge Join Operator [MERGEJOIN_141] (rows=348467716 width=135) + Conds:RS_24._col2=RS_163._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col14"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_163] PartitionCols:_col0 - Select Operator [SEL_100] (rows=465450 width=385) + Select Operator [SEL_162] (rows=465450 width=385) Output:["_col0","_col3"] - Filter Operator [FIL_99] (rows=465450 width=385) + Filter Operator [FIL_161] (rows=465450 width=385) predicate:((cd_education_status = 'College') and (cd_gender = 'M') and cd_demo_sk is not null) TableScan [TS_15] (rows=1861800 width=385) default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_education_status","cd_dep_count"] - <-Reducer 10 [SIMPLE_EDGE] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_80] (rows=316788826 width=135) - Conds:RS_95._col0=RS_98._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_98] + Merge Join Operator [MERGEJOIN_140] (rows=316788826 width=135) + Conds:RS_181._col0=RS_155._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 14 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_155] PartitionCols:_col0 - Select Operator [SEL_97] (rows=36524 width=1119) + Select Operator [SEL_154] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_96] (rows=36524 width=1119) + Filter Operator [FIL_153] (rows=36524 width=1119) predicate:((d_year = 2001) and d_date_sk is not null) TableScan [TS_12] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_95] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_181] PartitionCols:_col0 - Select Operator [SEL_94] (rows=287989836 width=135) + Select Operator [SEL_180] (rows=287989836 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_93] (rows=287989836 width=135) - predicate:(cs_bill_cdemo_sk is not null and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + Filter Operator [FIL_179] (rows=287989836 width=135) + predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_25_cd1_cd_demo_sk_min) AND DynamicValue(RS_25_cd1_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_25_cd1_cd_demo_sk_bloom_filter))) and (cs_bill_customer_sk BETWEEN DynamicValue(RS_37_customer_c_customer_sk_min) AND DynamicValue(RS_37_customer_c_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_37_customer_c_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_28_item_i_item_sk_min) AND DynamicValue(RS_28_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_28_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) TableScan [TS_9] (rows=287989836 width=135) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_bill_cdemo_sk","cs_item_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt","cs_net_profit"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_37] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_79] (rows=48400001 width=860) - Conds:RS_34._col1=RS_92._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_92] - PartitionCols:_col0 - Select Operator [SEL_91] (rows=1861800 width=385) - Output:["_col0"] - Filter Operator [FIL_90] (rows=1861800 width=385) - predicate:cd_demo_sk is not null - TableScan [TS_6] (rows=1861800 width=385) - default@customer_demographics,cd2,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_34] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_78] (rows=44000000 width=860) - Conds:RS_86._col2=RS_89._col0(Inner),Output:["_col0","_col1","_col4","_col6","_col7","_col8"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_86] - PartitionCols:_col2 - Select Operator [SEL_85] (rows=40000000 width=860) - Output:["_col0","_col1","_col2","_col4"] - Filter Operator [FIL_84] (rows=40000000 width=860) - predicate:((c_birth_month) IN (9, 5, 12, 4, 1, 10) and c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk","c_birth_month","c_birth_year"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_89] - PartitionCols:_col0 - Select Operator [SEL_88] (rows=20000000 width=1014) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_87] (rows=20000000 width=1014) - predicate:((ca_state) IN ('ND', 'WI', 'AL', 'NC', 'OK', 'MS', 'TN') and 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_state","ca_country"] + <-Reducer 15 [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 14 [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=36524 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_154] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_168] + Group By Operator [GBY_167] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_166] + Group By Operator [GBY_165] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_164] (rows=465450 width=385) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_162] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_176] + Group By Operator [GBY_175] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_174] + Group By Operator [GBY_173] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_172] (rows=462000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_170] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_178] + Group By Operator [GBY_177] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=48400000)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_120] + Group By Operator [GBY_119] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=48400000)"] + Select Operator [SEL_118] (rows=48400001 width=860) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_139]
