http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/constraints/query20.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query20.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query20.q.out index da3e262..d3ecdac 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query20.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query20.q.out @@ -65,8 +65,7 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 8 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) @@ -79,23 +78,23 @@ Stage-0 limit:-1 Stage-1 Reducer 6 vectorized - File Output Operator [FS_86] - Limit [LIM_85] (rows=100 width=802) + File Output Operator [FS_81] + Limit [LIM_80] (rows=100 width=802) Number of rows:100 - Select Operator [SEL_84] (rows=138600 width=801) + Select Operator [SEL_79] (rows=138600 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_83] - Select Operator [SEL_82] (rows=138600 width=801) + SHUFFLE [RS_78] + Select Operator [SEL_77] (rows=138600 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_81] (rows=138600 width=689) + PTF Operator [PTF_76] (rows=138600 width=689) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST","partition by:":"_col1"}] - Select Operator [SEL_80] (rows=138600 width=689) + Select Operator [SEL_75] (rows=138600 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_79] + SHUFFLE [RS_74] PartitionCols:_col1 - Group By Operator [GBY_78] (rows=138600 width=689) + Group By Operator [GBY_73] (rows=138600 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] @@ -103,13 +102,13 @@ Stage-0 Group By Operator [GBY_16] (rows=138600 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col9, _col8, _col5, _col6, _col7 Merge Join Operator [MERGEJOIN_58] (rows=9551005 width=673) - Conds:RS_12._col1=RS_69._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9"] + Conds:RS_12._col1=RS_72._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9"] <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_69] + SHUFFLE [RS_72] PartitionCols:_col0 - Select Operator [SEL_68] (rows=138600 width=581) + Select Operator [SEL_71] (rows=138600 width=581) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_67] (rows=138600 width=581) + Filter Operator [FIL_70] (rows=138600 width=581) predicate:(i_category) IN ('Jewelry', 'Sports', 'Books') TableScan [TS_6] (rows=462000 width=581) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_class","i_category"] @@ -117,7 +116,7 @@ Stage-0 SHUFFLE [RS_12] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_57] (rows=31836679 width=110) - Conds:RS_77._col0=RS_61._col0(Inner),Output:["_col1","_col2"] + Conds:RS_69._col0=RS_61._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_61] PartitionCols:_col0 @@ -128,25 +127,14 @@ Stage-0 TableScan [TS_3] (rows=73049 width=98) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_77] + SHUFFLE [RS_69] PartitionCols:_col0 - Select Operator [SEL_76] (rows=286549727 width=119) + Select Operator [SEL_68] (rows=286549727 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_75] (rows=286549727 width=119) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) + Filter Operator [FIL_67] (rows=286549727 width=119) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null) TableScan [TS_0] (rows=287989836 width=119) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_sales_price"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_74] - Group By Operator [GBY_73] (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_72] - Group By Operator [GBY_71] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_70] (rows=138600 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_68] <-Reducer 8 [BROADCAST_EDGE] vectorized BROADCAST [RS_66] Group By Operator [GBY_65] (rows=1 width=12)
http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/constraints/query23.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query23.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query23.q.out index 292c920..7678363 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query23.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query23.q.out @@ -121,15 +121,15 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 31 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 1 <- Reducer 9 (BROADCAST_EDGE) Map 15 <- Reducer 27 (BROADCAST_EDGE) -Map 35 <- Reducer 7 (BROADCAST_EDGE) -Map 37 <- Reducer 34 (BROADCAST_EDGE) -Map 39 <- Reducer 14 (BROADCAST_EDGE), Reducer 33 (BROADCAST_EDGE) -Map 40 <- Reducer 13 (BROADCAST_EDGE) -Reducer 10 <- Map 39 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Map 33 <- Reducer 7 (BROADCAST_EDGE) +Map 35 <- Reducer 32 (BROADCAST_EDGE) +Map 37 <- Reducer 14 (BROADCAST_EDGE) +Map 38 <- Reducer 13 (BROADCAST_EDGE) +Reducer 10 <- Map 37 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) -Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 32 (ONE_TO_ONE_EDGE), Union 5 (CONTAINS) +Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 31 (ONE_TO_ONE_EDGE), Union 5 (CONTAINS) Reducer 13 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 26 (SIMPLE_EDGE) @@ -137,24 +137,22 @@ Reducer 17 <- Reducer 16 (SIMPLE_EDGE) Reducer 18 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) Reducer 19 <- Reducer 18 (CUSTOM_SIMPLE_EDGE), Reducer 21 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 20 <- Reducer 19 (CUSTOM_SIMPLE_EDGE), Reducer 36 (CUSTOM_SIMPLE_EDGE) +Reducer 20 <- Reducer 19 (CUSTOM_SIMPLE_EDGE), Reducer 34 (CUSTOM_SIMPLE_EDGE) Reducer 21 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) Reducer 22 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) Reducer 23 <- Reducer 22 (CUSTOM_SIMPLE_EDGE), Reducer 25 (CUSTOM_SIMPLE_EDGE) -Reducer 24 <- Reducer 23 (CUSTOM_SIMPLE_EDGE), Reducer 41 (CUSTOM_SIMPLE_EDGE) +Reducer 24 <- Reducer 23 (CUSTOM_SIMPLE_EDGE), Reducer 39 (CUSTOM_SIMPLE_EDGE) Reducer 25 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) Reducer 27 <- Map 26 (CUSTOM_SIMPLE_EDGE) -Reducer 28 <- Map 26 (SIMPLE_EDGE), Map 37 (SIMPLE_EDGE) -Reducer 29 <- Map 38 (SIMPLE_EDGE), Reducer 28 (SIMPLE_EDGE) +Reducer 28 <- Map 26 (SIMPLE_EDGE), Map 35 (SIMPLE_EDGE) +Reducer 29 <- Map 36 (SIMPLE_EDGE), Reducer 28 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) Reducer 30 <- Reducer 29 (SIMPLE_EDGE) -Reducer 31 <- Reducer 30 (CUSTOM_SIMPLE_EDGE) -Reducer 32 <- Reducer 29 (SIMPLE_EDGE) -Reducer 33 <- Reducer 32 (CUSTOM_SIMPLE_EDGE) -Reducer 34 <- Map 26 (CUSTOM_SIMPLE_EDGE) -Reducer 36 <- Map 35 (SIMPLE_EDGE) +Reducer 31 <- Reducer 29 (SIMPLE_EDGE) +Reducer 32 <- Map 26 (CUSTOM_SIMPLE_EDGE) +Reducer 34 <- Map 33 (SIMPLE_EDGE) +Reducer 39 <- Map 38 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 30 (ONE_TO_ONE_EDGE), Union 5 (CONTAINS) -Reducer 41 <- Map 40 (SIMPLE_EDGE) Reducer 6 <- Union 5 (CUSTOM_SIMPLE_EDGE) Reducer 7 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) @@ -164,10 +162,10 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_532] - Limit [LIM_531] (rows=1 width=112) + File Output Operator [FS_527] + Limit [LIM_526] (rows=1 width=112) Number of rows:100 - Group By Operator [GBY_530] (rows=1 width=112) + Group By Operator [GBY_525] (rows=1 width=112) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Union 5 [CUSTOM_SIMPLE_EDGE] <-Reducer 12 [CONTAINS] @@ -177,64 +175,7 @@ Stage-0 Select Operator [SEL_451] (rows=52 width=112) Output:["_col0"] Merge Join Operator [MERGEJOIN_450] (rows=52 width=2) - Conds:RS_192._col1=RS_538._col0(Inner),Output:["_col3","_col4"] - <-Reducer 32 [ONE_TO_ONE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_538] - PartitionCols:_col0 - Select Operator [SEL_537] (rows=745 width=4) - Output:["_col0"] - Filter Operator [FIL_536] (rows=745 width=12) - predicate:(_col1 > 4L) - Group By Operator [GBY_535] (rows=2235 width=12) - Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 - <-Reducer 29 [SIMPLE_EDGE] - SHUFFLE [RS_182] - PartitionCols:_col0 - Group By Operator [GBY_83] (rows=2235 width=12) - Output:["_col0","_col1"],aggregations:["count()"],keys:_col4 - Merge Join Operator [MERGEJOIN_431] (rows=19646398 width=4) - Conds:RS_79._col1=RS_483._col0(Inner),Output:["_col4"] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_483] - PartitionCols:_col0 - Select Operator [SEL_482] (rows=462000 width=188) - Output:["_col0"] - TableScan [TS_74] (rows=462000 width=4) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk"] - <-Reducer 28 [SIMPLE_EDGE] - SHUFFLE [RS_79] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_430] (rows=19646398 width=4) - Conds:RS_481._col0=RS_471._col0(Inner),Output:["_col1"] - <-Map 26 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_471] - PartitionCols:_col0 - Select Operator [SEL_468] (rows=2609 width=4) - Output:["_col0"] - Filter Operator [FIL_467] (rows=2609 width=8) - predicate:(d_year) IN (1999, 2000, 2001, 2002) - TableScan [TS_9] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Map 37 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_481] - PartitionCols:_col0 - Select Operator [SEL_480] (rows=550076554 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_479] (rows=550076554 width=7) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_77_date_dim_d_date_sk_min) AND DynamicValue(RS_77_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_77_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) - TableScan [TS_68] (rows=575995635 width=7) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] - <-Reducer 34 [BROADCAST_EDGE] vectorized - BROADCAST [RS_478] - Group By Operator [GBY_477] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_476] - Group By Operator [GBY_474] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_472] (rows=2609 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_468] + Conds:RS_192._col1=RS_552._col0(Inner),Output:["_col3","_col4"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_192] PartitionCols:_col1 @@ -244,7 +185,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_189] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_432] (rows=3941102 width=122) - Conds:RS_546._col0=RS_459._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Conds:RS_532._col0=RS_459._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_459] PartitionCols:_col0 @@ -254,18 +195,18 @@ Stage-0 predicate:((d_moy = 1) and (d_year = 1999)) TableScan [TS_3] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 39 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_546] + <-Map 37 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_532] PartitionCols:_col0 - Select Operator [SEL_545] (rows=143930993 width=127) + Select Operator [SEL_531] (rows=143930993 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_544] (rows=143930993 width=127) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_193_item_i_item_sk_min) AND DynamicValue(RS_193_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_193_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_187_date_dim_d_date_sk_min) AND DynamicValue(RS_187_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_187_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + Filter Operator [FIL_530] (rows=143930993 width=127) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_187_date_dim_d_date_sk_min) AND DynamicValue(RS_187_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_187_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) TableScan [TS_98] (rows=144002668 width=127) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_quantity","ws_list_price"] <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_534] - Group By Operator [GBY_533] (rows=1 width=12) + BROADCAST [RS_529] + Group By Operator [GBY_528] (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_464] @@ -274,17 +215,6 @@ Stage-0 Select Operator [SEL_460] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_456] - <-Reducer 33 [BROADCAST_EDGE] vectorized - BROADCAST [RS_543] - Group By Operator [GBY_542] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_541] - Group By Operator [GBY_540] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_539] (rows=745 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_537] <-Reducer 24 [SIMPLE_EDGE] SHUFFLE [RS_190] PartitionCols:_col0 @@ -299,22 +229,22 @@ Stage-0 Merge Join Operator [MERGEJOIN_440] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 22 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_552] - Select Operator [SEL_551] (rows=1 width=8) - Filter Operator [FIL_550] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_538] + Select Operator [SEL_537] (rows=1 width=8) + Filter Operator [FIL_536] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_549] (rows=1 width=8) + Group By Operator [GBY_535] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_548] (rows=1 width=8) - Group By Operator [GBY_547] (rows=1 width=8) + Select Operator [SEL_534] (rows=1 width=8) + Group By Operator [GBY_533] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_512] - Group By Operator [GBY_508] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_496] + Group By Operator [GBY_492] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_504] (rows=50562 width=112) + Select Operator [SEL_488] (rows=50562 width=112) Output:["_col0"] - Group By Operator [GBY_501] (rows=50562 width=112) + Group By Operator [GBY_485] (rows=50562 width=112) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_17] @@ -322,60 +252,65 @@ Stage-0 Group By Operator [GBY_16] (rows=455058 width=112) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col1 Merge Join Operator [MERGEJOIN_428] (rows=18762463 width=112) - Conds:RS_500._col0=RS_469._col0(Inner),Output:["_col1","_col2"] + Conds:RS_484._col0=RS_472._col0(Inner),Output:["_col1","_col2"] <-Map 26 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_469] + PARTITION_ONLY_SHUFFLE [RS_472] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_468] + Select Operator [SEL_471] (rows=2609 width=4) + Output:["_col0"] + Filter Operator [FIL_470] (rows=2609 width=8) + predicate:(d_year) IN (1999, 2000, 2001, 2002) + TableScan [TS_9] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_500] + SHUFFLE [RS_484] PartitionCols:_col0 - Select Operator [SEL_499] (rows=525327388 width=119) + Select Operator [SEL_483] (rows=525327388 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_498] (rows=525327388 width=118) + Filter Operator [FIL_482] (rows=525327388 width=118) predicate:((ss_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(ss_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) TableScan [TS_6] (rows=575995635 width=118) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"] <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_497] - Group By Operator [GBY_496] (rows=1 width=12) + BROADCAST [RS_481] + Group By Operator [GBY_480] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_475] - Group By Operator [GBY_473] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_478] + Group By Operator [GBY_476] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_470] (rows=2609 width=4) + Select Operator [SEL_473] (rows=2609 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_468] + Please refer to the previous Select Operator [SEL_471] <-Reducer 25 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_554] - Group By Operator [GBY_553] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_540] + Group By Operator [GBY_539] (rows=1 width=112) Output:["_col0"],aggregations:["max(VALUE._col0)"] <-Reducer 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_513] - Group By Operator [GBY_509] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_497] + Group By Operator [GBY_493] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_505] (rows=50562 width=112) + Select Operator [SEL_489] (rows=50562 width=112) Output:["_col1"] - Please refer to the previous Group By Operator [GBY_501] - <-Reducer 41 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_562] - Group By Operator [GBY_561] (rows=1415626 width=115) + Please refer to the previous Group By Operator [GBY_485] + <-Reducer 39 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_548] + Group By Operator [GBY_547] (rows=1415626 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Map 40 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_560] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_546] PartitionCols:_col0 - Group By Operator [GBY_559] (rows=550080312 width=115) + Group By Operator [GBY_545] (rows=550080312 width=115) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_558] (rows=550080312 width=114) + Select Operator [SEL_544] (rows=550080312 width=114) Output:["_col0","_col1"] - Filter Operator [FIL_557] (rows=550080312 width=114) + Filter Operator [FIL_543] (rows=550080312 width=114) predicate:((ss_customer_sk BETWEEN DynamicValue(RS_189_web_sales_ws_bill_customer_sk_min) AND DynamicValue(RS_189_web_sales_ws_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_189_web_sales_ws_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) TableScan [TS_150] (rows=575995635 width=114) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_556] - Group By Operator [GBY_555] (rows=1 width=12) + BROADCAST [RS_542] + Group By Operator [GBY_541] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 10 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_406] @@ -384,6 +319,58 @@ Stage-0 Select Operator [SEL_404] (rows=3941102 width=7) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_432] + <-Reducer 31 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_552] + PartitionCols:_col0 + Select Operator [SEL_551] (rows=745 width=4) + Output:["_col0"] + Filter Operator [FIL_550] (rows=745 width=12) + predicate:(_col1 > 4L) + Group By Operator [GBY_549] (rows=2235 width=12) + Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 + <-Reducer 29 [SIMPLE_EDGE] + SHUFFLE [RS_182] + PartitionCols:_col0 + Group By Operator [GBY_83] (rows=2235 width=12) + Output:["_col0","_col1"],aggregations:["count()"],keys:_col4 + Merge Join Operator [MERGEJOIN_431] (rows=19646398 width=4) + Conds:RS_79._col1=RS_520._col0(Inner),Output:["_col4"] + <-Map 36 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_520] + PartitionCols:_col0 + Select Operator [SEL_519] (rows=462000 width=188) + Output:["_col0"] + TableScan [TS_74] (rows=462000 width=4) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk"] + <-Reducer 28 [SIMPLE_EDGE] + SHUFFLE [RS_79] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_430] (rows=19646398 width=4) + Conds:RS_518._col0=RS_474._col0(Inner),Output:["_col1"] + <-Map 26 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_474] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_471] + <-Map 35 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_518] + PartitionCols:_col0 + Select Operator [SEL_517] (rows=550076554 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_516] (rows=550076554 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_77_date_dim_d_date_sk_min) AND DynamicValue(RS_77_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_77_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) + TableScan [TS_68] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] + <-Reducer 32 [BROADCAST_EDGE] vectorized + BROADCAST [RS_515] + Group By Operator [GBY_514] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_479] + Group By Operator [GBY_477] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_475] (rows=2609 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_471] <-Reducer 4 [CONTAINS] Reduce Output Operator [RS_449] Group By Operator [GBY_448] (rows=1 width=112) @@ -391,20 +378,7 @@ Stage-0 Select Operator [SEL_446] (rows=102 width=112) Output:["_col0"] Merge Join Operator [MERGEJOIN_445] (rows=102 width=1) - Conds:RS_94._col2=RS_487._col0(Inner),Output:["_col3","_col4"] - <-Reducer 30 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_487] - PartitionCols:_col0 - Select Operator [SEL_486] (rows=745 width=4) - Output:["_col0"] - Filter Operator [FIL_485] (rows=745 width=12) - predicate:(_col1 > 4L) - Group By Operator [GBY_484] (rows=2235 width=12) - Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 - <-Reducer 29 [SIMPLE_EDGE] - SHUFFLE [RS_84] - PartitionCols:_col0 - Please refer to the previous Group By Operator [GBY_83] + Conds:RS_94._col2=RS_524._col0(Inner),Output:["_col3","_col4"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_94] PartitionCols:_col2 @@ -414,31 +388,20 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_91] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_427] (rows=7751875 width=101) - Conds:RS_495._col0=RS_457._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Conds:RS_469._col0=RS_457._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_457] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_456] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_495] + SHUFFLE [RS_469] PartitionCols:_col0 - Select Operator [SEL_494] (rows=285117831 width=127) + Select Operator [SEL_468] (rows=285117831 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_493] (rows=285117831 width=127) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_95_item_i_item_sk_min) AND DynamicValue(RS_95_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_95_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_89_date_dim_d_date_sk_min) AND DynamicValue(RS_89_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_89_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null) + Filter Operator [FIL_467] (rows=285117831 width=127) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_89_date_dim_d_date_sk_min) AND DynamicValue(RS_89_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_89_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_0] (rows=287989836 width=127) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity","cs_list_price"] - <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_492] - Group By Operator [GBY_491] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 30 [CUSTOM_SIMPLE_EDGE] vectorized - FORWARD [RS_490] - Group By Operator [GBY_489] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_488] (rows=745 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_486] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_466] Group By Operator [GBY_465] (rows=1 width=12) @@ -464,51 +427,51 @@ Stage-0 Merge Join Operator [MERGEJOIN_437] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_519] - Select Operator [SEL_518] (rows=1 width=8) - Filter Operator [FIL_517] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_503] + Select Operator [SEL_502] (rows=1 width=8) + Filter Operator [FIL_501] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_516] (rows=1 width=8) + Group By Operator [GBY_500] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_515] (rows=1 width=8) - Group By Operator [GBY_514] (rows=1 width=8) + Select Operator [SEL_499] (rows=1 width=8) + Group By Operator [GBY_498] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_510] - Group By Operator [GBY_506] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_494] + Group By Operator [GBY_490] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_502] (rows=50562 width=112) + Select Operator [SEL_486] (rows=50562 width=112) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_501] + Please refer to the previous Group By Operator [GBY_485] <-Reducer 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_521] - Group By Operator [GBY_520] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_505] + Group By Operator [GBY_504] (rows=1 width=112) Output:["_col0"],aggregations:["max(VALUE._col0)"] <-Reducer 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_511] - Group By Operator [GBY_507] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_495] + Group By Operator [GBY_491] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_503] (rows=50562 width=112) + Select Operator [SEL_487] (rows=50562 width=112) Output:["_col1"] - Please refer to the previous Group By Operator [GBY_501] - <-Reducer 36 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_529] - Group By Operator [GBY_528] (rows=1415626 width=115) + Please refer to the previous Group By Operator [GBY_485] + <-Reducer 34 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_513] + Group By Operator [GBY_512] (rows=1415626 width=115) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Map 35 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_527] + <-Map 33 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_511] PartitionCols:_col0 - Group By Operator [GBY_526] (rows=550080312 width=115) + Group By Operator [GBY_510] (rows=550080312 width=115) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_525] (rows=550080312 width=114) + Select Operator [SEL_509] (rows=550080312 width=114) Output:["_col0","_col1"] - Filter Operator [FIL_524] (rows=550080312 width=114) + Filter Operator [FIL_508] (rows=550080312 width=114) predicate:((ss_customer_sk BETWEEN DynamicValue(RS_91_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_91_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_91_catalog_sales_cs_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) TableScan [TS_52] (rows=575995635 width=114) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_523] - Group By Operator [GBY_522] (rows=1 width=12) + BROADCAST [RS_507] + Group By Operator [GBY_506] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_333] @@ -517,4 +480,17 @@ Stage-0 Select Operator [SEL_331] (rows=7751875 width=6) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_427] + <-Reducer 30 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_524] + PartitionCols:_col0 + Select Operator [SEL_523] (rows=745 width=4) + Output:["_col0"] + Filter Operator [FIL_522] (rows=745 width=12) + predicate:(_col1 > 4L) + Group By Operator [GBY_521] (rows=2235 width=12) + Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 + <-Reducer 29 [SIMPLE_EDGE] + SHUFFLE [RS_84] + PartitionCols:_col0 + Please refer to the previous Group By Operator [GBY_83] http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/constraints/query24.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query24.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query24.q.out index e782873..d5ff339 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query24.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query24.q.out @@ -116,24 +116,21 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 23 (BROADCAST_EDGE) -Map 24 <- Reducer 18 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE) -Reducer 10 <- Map 22 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Map 1 <- Reducer 20 (BROADCAST_EDGE) +Map 21 <- Reducer 16 (BROADCAST_EDGE) +Reducer 10 <- Map 19 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) Reducer 11 <- Reducer 10 (SIMPLE_EDGE) Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) -Reducer 15 <- Map 21 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 15 <- Map 18 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE) Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 23 <- Map 22 (CUSTOM_SIMPLE_EDGE) +Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 22 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 4 <- Map 19 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) -Reducer 8 <- Map 24 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 8 <- Map 21 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 9 <- Reducer 15 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 @@ -149,18 +146,18 @@ Stage-0 Merge Join Operator [MERGEJOIN_297] (rows=15392 width=492) Conds:(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_345] - Select Operator [SEL_344] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_339] + Select Operator [SEL_338] (rows=1 width=112) Output:["_col0"] - Group By Operator [GBY_343] (rows=1 width=120) + Group By Operator [GBY_337] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_342] - Group By Operator [GBY_341] (rows=1 width=120) + PARTITION_ONLY_SHUFFLE [RS_336] + Group By Operator [GBY_335] (rows=1 width=120) Output:["_col0","_col1"],aggregations:["sum(_col10)","count(_col10)"] - Select Operator [SEL_340] (rows=589731268 width=932) + Select Operator [SEL_334] (rows=589731268 width=932) Output:["_col10"] - Group By Operator [GBY_339] (rows=589731268 width=932) + Group By Operator [GBY_333] (rows=589731268 width=932) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9 <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_79] @@ -168,11 +165,11 @@ Stage-0 Group By Operator [GBY_78] (rows=589731268 width=932) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col4)"],keys:_col9, _col10, _col13, _col17, _col18, _col21, _col22, _col23, _col24, _col25 Merge Join Operator [MERGEJOIN_296] (rows=589731268 width=928) - Conds:RS_74._col0=RS_314._col0(Inner),Output:["_col4","_col9","_col10","_col13","_col17","_col18","_col21","_col22","_col23","_col24","_col25"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_314] + Conds:RS_74._col0=RS_301._col0(Inner),Output:["_col4","_col9","_col10","_col13","_col17","_col18","_col21","_col22","_col23","_col24","_col25"] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_301] PartitionCols:_col0 - Select Operator [SEL_312] (rows=462000 width=384) + Select Operator [SEL_299] (rows=462000 width=384) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] TableScan [TS_22] (rows=462000 width=384) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"] @@ -189,13 +186,13 @@ Stage-0 Filter Operator [FIL_20] (rows=7276996 width=724) predicate:(_col12 <> _col3) Merge Join Operator [MERGEJOIN_289] (rows=7276996 width=724) - Conds:RS_17._col0=RS_306._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col8","_col10","_col11","_col12"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_306] + Conds:RS_17._col0=RS_322._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col8","_col10","_col11","_col12"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_322] PartitionCols:_col1 - Select Operator [SEL_305] (rows=80000000 width=280) + Select Operator [SEL_321] (rows=80000000 width=280) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_304] (rows=80000000 width=280) + Filter Operator [FIL_320] (rows=80000000 width=280) predicate:c_current_addr_sk is not null TableScan [TS_11] (rows=80000000 width=280) default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name","c_birth_country"] @@ -203,22 +200,22 @@ Stage-0 SHUFFLE [RS_17] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_288] (rows=611379 width=452) - Conds:RS_300._col2=RS_303._col3(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6"] + Conds:RS_316._col2=RS_319._col3(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6"] <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_300] + SHUFFLE [RS_316] PartitionCols:_col2 - Select Operator [SEL_299] (rows=40000000 width=363) + Select Operator [SEL_315] (rows=40000000 width=363) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_298] (rows=40000000 width=276) + Filter Operator [FIL_314] (rows=40000000 width=276) predicate:ca_zip is not null TableScan [TS_5] (rows=40000000 width=276) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_zip","ca_country"] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_303] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_319] PartitionCols:_col3 - Select Operator [SEL_302] (rows=155 width=267) + Select Operator [SEL_318] (rows=155 width=267) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_301] (rows=155 width=271) + Filter Operator [FIL_317] (rows=155 width=271) predicate:((s_market_id = 7) and s_zip is not null) TableScan [TS_8] (rows=1704 width=270) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"] @@ -226,37 +223,26 @@ Stage-0 SHUFFLE [RS_71] PartitionCols:_col2, _col1 Merge Join Operator [MERGEJOIN_292] (rows=537799798 width=118) - Conds:RS_338._col0, _col3=RS_326._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col4"] + Conds:RS_332._col0, _col3=RS_313._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_326] + SHUFFLE [RS_313] PartitionCols:_col0, _col1 - Select Operator [SEL_324] (rows=57591150 width=8) + Select Operator [SEL_311] (rows=57591150 width=8) Output:["_col0","_col1"] TableScan [TS_3] (rows=57591150 width=8) default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] - <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_338] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_332] PartitionCols:_col0, _col3 - Select Operator [SEL_337] (rows=525333486 width=122) + Select Operator [SEL_331] (rows=525333486 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_336] (rows=525333486 width=122) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_72_customer_c_customer_sk_min) AND DynamicValue(RS_72_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_72_customer_c_customer_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_72_store_s_store_sk_min) AND DynamicValue(RS_72_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_72_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_store_sk is not null) + Filter Operator [FIL_330] (rows=525333486 width=122) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_72_customer_c_customer_sk_min) AND DynamicValue(RS_72_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_72_customer_c_customer_sk_bloom_filter))) and ss_customer_sk is not null and ss_store_sk is not null) TableScan [TS_44] (rows=575995635 width=122) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] - <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_333] - Group By Operator [GBY_332] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_226] - Group By Operator [GBY_225] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_224] (rows=7276996 width=8) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_21] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_335] - Group By Operator [GBY_334] (rows=1 width=12) + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_329] + Group By Operator [GBY_328] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=6636187)"] <-Reducer 15 [CUSTOM_SIMPLE_EDGE] SHUFFLE [RS_231] @@ -266,14 +252,14 @@ Stage-0 Output:["_col0"] Please refer to the previous Select Operator [SEL_21] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_331] - Select Operator [SEL_330] (rows=15392 width=380) + PARTITION_ONLY_SHUFFLE [RS_327] + Select Operator [SEL_326] (rows=15392 width=380) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_329] (rows=15392 width=380) + Group By Operator [GBY_325] (rows=15392 width=380) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col9)"],keys:_col0, _col1, _col3 - Select Operator [SEL_328] (rows=86004082 width=843) + Select Operator [SEL_324] (rows=86004082 width=843) Output:["_col0","_col1","_col3","_col9"] - Group By Operator [GBY_327] (rows=86004082 width=843) + Group By Operator [GBY_323] (rows=86004082 width=843) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_36] @@ -281,13 +267,13 @@ Stage-0 Group By Operator [GBY_35] (rows=86004082 width=843) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col9, _col10, _col17, _col13, _col18, _col21, _col22, _col23, _col24 Merge Join Operator [MERGEJOIN_291] (rows=86004082 width=813) - Conds:RS_31._col0=RS_315._col0(Inner),Output:["_col4","_col9","_col10","_col13","_col17","_col18","_col21","_col22","_col23","_col24"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_315] + Conds:RS_31._col0=RS_302._col0(Inner),Output:["_col4","_col9","_col10","_col13","_col17","_col18","_col21","_col22","_col23","_col24"] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_302] PartitionCols:_col0 - Select Operator [SEL_313] (rows=7000 width=295) + Select Operator [SEL_300] (rows=7000 width=295) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_311] (rows=7000 width=384) + Filter Operator [FIL_298] (rows=7000 width=384) predicate:(i_color = 'orchid') Please refer to the previous TableScan [TS_22] <-Reducer 3 [SIMPLE_EDGE] @@ -303,51 +289,29 @@ Stage-0 SHUFFLE [RS_28] PartitionCols:_col2, _col1 Merge Join Operator [MERGEJOIN_287] (rows=537799798 width=118) - Conds:RS_323._col0, _col3=RS_325._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col4"] + Conds:RS_310._col0, _col3=RS_312._col0, _col1(Inner),Output:["_col0","_col1","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_325] + SHUFFLE [RS_312] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_324] + Please refer to the previous Select Operator [SEL_311] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_323] + SHUFFLE [RS_310] PartitionCols:_col0, _col3 - Select Operator [SEL_322] (rows=525333486 width=122) + Select Operator [SEL_309] (rows=525333486 width=122) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_321] (rows=525333486 width=122) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_29_customer_c_customer_sk_min) AND DynamicValue(RS_29_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_29_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_32_item_i_item_sk_min) AND DynamicValue(RS_32_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_32_item_i_item_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_29_store_s_store_sk_min) AND DynamicValue(RS_29_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_29_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_store_sk is not null) + Filter Operator [FIL_308] (rows=525333486 width=122) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_32_item_i_item_sk_min) AND DynamicValue(RS_32_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_32_item_i_item_sk_bloom_filter))) and ss_customer_sk is not null and ss_store_sk is not null) TableScan [TS_0] (rows=575995635 width=122) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_308] - Group By Operator [GBY_307] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_153] - Group By Operator [GBY_152] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_151] (rows=7276996 width=8) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_21] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_310] - Group By Operator [GBY_309] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=6636187)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - 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=6636187)"] - Select Operator [SEL_156] (rows=7276996 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_21] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_320] - Group By Operator [GBY_319] (rows=1 width=12) + <-Reducer 20 [BROADCAST_EDGE] vectorized + BROADCAST [RS_307] + Group By Operator [GBY_306] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_318] - Group By Operator [GBY_317] (rows=1 width=12) + <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_305] + Group By Operator [GBY_304] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_316] (rows=7000 width=4) + Select Operator [SEL_303] (rows=7000 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_313] + Please refer to the previous Select Operator [SEL_300]