http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/constraints/query56.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query56.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query56.q.out index 023ad3d..3524e43 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query56.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query56.q.out @@ -149,66 +149,60 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 17 <- Reducer 21 (BROADCAST_EDGE), Reducer 29 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Map 32 <- Reducer 11 (BROADCAST_EDGE), Reducer 24 (BROADCAST_EDGE), Reducer 30 (BROADCAST_EDGE) -Map 33 <- Reducer 14 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Reducer 31 (BROADCAST_EDGE) -Reducer 10 <- Reducer 9 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 11 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Reducer 2 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 14 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (SIMPLE_EDGE) -Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) -Reducer 19 <- Map 28 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 16 (ONE_TO_ONE_EDGE) -Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 22 <- Map 20 (SIMPLE_EDGE), Map 32 (SIMPLE_EDGE) -Reducer 23 <- Map 28 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) -Reducer 24 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 20 (SIMPLE_EDGE), Map 33 (SIMPLE_EDGE) -Reducer 26 <- Map 28 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) -Reducer 27 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 29 <- Map 28 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 19 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 30 <- Map 28 (CUSTOM_SIMPLE_EDGE) -Reducer 31 <- Map 28 (CUSTOM_SIMPLE_EDGE) +Map 14 <- Reducer 18 (BROADCAST_EDGE) +Map 26 <- Reducer 21 (BROADCAST_EDGE) +Map 27 <- Reducer 24 (BROADCAST_EDGE) +Reducer 10 <- Reducer 2 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 13 <- Map 12 (SIMPLE_EDGE) +Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 16 <- Map 25 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) +Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 17 (SIMPLE_EDGE), Map 26 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 13 (ONE_TO_ONE_EDGE) +Reducer 20 <- Map 25 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) +Reducer 21 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 22 <- Map 17 (SIMPLE_EDGE), Map 27 (SIMPLE_EDGE) +Reducer 23 <- Map 25 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) +Reducer 24 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 6 <- Union 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Reducer 2 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE), Union 5 (CONTAINS) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_366] - Limit [LIM_365] (rows=100 width=212) + File Output Operator [FS_353] + Limit [LIM_352] (rows=100 width=212) Number of rows:100 - Select Operator [SEL_364] (rows=355 width=212) + Select Operator [SEL_351] (rows=355 width=212) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_363] - Group By Operator [GBY_362] (rows=355 width=212) + SHUFFLE [RS_350] + Group By Operator [GBY_349] (rows=355 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] - <-Reducer 10 [CONTAINS] vectorized - Reduce Output Operator [RS_378] + <-Reducer 11 [CONTAINS] vectorized + Reduce Output Operator [RS_369] PartitionCols:_col0 - Group By Operator [GBY_377] (rows=355 width=212) + Group By Operator [GBY_368] (rows=355 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_376] (rows=355 width=212) + Group By Operator [GBY_367] (rows=355 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_69] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_106] PartitionCols:_col0 - Group By Operator [GBY_68] (rows=355 width=212) + Group By Operator [GBY_105] (rows=355 width=212) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_300] (rows=339151 width=100) - Conds:RS_64._col0=RS_65._col3(Inner),Output:["_col1","_col7"] + Merge Join Operator [MERGEJOIN_301] (rows=172427 width=188) + Conds:RS_101._col0=RS_102._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_64] + SHUFFLE [RS_101] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_290] (rows=15609 width=104) Conds:RS_315._col1=RS_321._col0(Inner),Output:["_col0","_col1"] @@ -219,12 +213,12 @@ Stage-0 Output:["_col0","_col1"] TableScan [TS_0] (rows=462000 width=104) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] - <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized + <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_321] PartitionCols:_col0 Group By Operator [GBY_320] (rows=10500 width=100) Output:["_col0"],keys:KEY._col0 - <-Map 15 [SIMPLE_EDGE] vectorized + <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_319] PartitionCols:_col0 Group By Operator [GBY_318] (rows=10500 width=100) @@ -236,28 +230,28 @@ Stage-0 TableScan [TS_2] (rows=462000 width=189) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_id","i_color"] <-Reducer 23 [SIMPLE_EDGE] - SHUFFLE [RS_65] - PartitionCols:_col3 - Select Operator [SEL_60] (rows=1550375 width=13) - Output:["_col3","_col4"] - Merge Join Operator [MERGEJOIN_295] (rows=1550375 width=13) - Conds:RS_57._col1=RS_342._col0(Inner),Output:["_col2","_col3"] - <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_342] + SHUFFLE [RS_102] + PartitionCols:_col2 + Select Operator [SEL_97] (rows=788222 width=110) + Output:["_col2","_col4"] + Merge Join Operator [MERGEJOIN_298] (rows=788222 width=110) + Conds:RS_94._col2=RS_345._col0(Inner),Output:["_col1","_col3"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_345] PartitionCols:_col0 - Select Operator [SEL_339] (rows=8000000 width=4) + Select Operator [SEL_342] (rows=8000000 width=4) Output:["_col0"] - Filter Operator [FIL_338] (rows=8000000 width=112) + Filter Operator [FIL_341] (rows=8000000 width=112) predicate:(ca_gmt_offset = -8) TableScan [TS_15] (rows=40000000 width=112) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] <-Reducer 22 [SIMPLE_EDGE] - SHUFFLE [RS_57] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_294] (rows=7751872 width=98) - Conds:RS_375._col0=RS_326._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_326] + SHUFFLE [RS_94] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_297] (rows=3941109 width=118) + Conds:RS_366._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 17 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_328] PartitionCols:_col0 Select Operator [SEL_323] (rows=50 width=4) Output:["_col0"] @@ -265,134 +259,32 @@ Stage-0 predicate:((d_moy = 1) and (d_year = 2000)) TableScan [TS_12] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 32 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_375] - PartitionCols:_col0 - Select Operator [SEL_374] (rows=285117733 width=123) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_373] (rows=285117733 width=123) - predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_58_customer_address_ca_address_sk_min) AND DynamicValue(RS_58_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_58_customer_address_ca_address_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_64_item_i_item_sk_min) AND DynamicValue(RS_64_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_64_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_55_date_dim_d_date_sk_min) AND DynamicValue(RS_55_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_55_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_45] (rows=287989836 width=123) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_372] - Group By Operator [GBY_371] (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] - SHUFFLE [RS_237] - Group By Operator [GBY_236] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_235] (rows=15609 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_290] - <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_368] - Group By Operator [GBY_367] (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 - PARTITION_ONLY_SHUFFLE [RS_334] - Group By Operator [GBY_331] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_327] (rows=50 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_323] - <-Reducer 30 [BROADCAST_EDGE] vectorized - BROADCAST [RS_370] - Group By Operator [GBY_369] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_350] - Group By Operator [GBY_347] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_343] (rows=8000000 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_339] - <-Reducer 13 [CONTAINS] vectorized - Reduce Output Operator [RS_390] - PartitionCols:_col0 - Group By Operator [GBY_389] (rows=355 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_388] (rows=355 width=212) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_106] - PartitionCols:_col0 - Group By Operator [GBY_105] (rows=355 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_301] (rows=172427 width=188) - Conds:RS_101._col0=RS_102._col2(Inner),Output:["_col1","_col7"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_101] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_290] - <-Reducer 26 [SIMPLE_EDGE] - SHUFFLE [RS_102] - PartitionCols:_col2 - Select Operator [SEL_97] (rows=788222 width=110) - Output:["_col2","_col4"] - Merge Join Operator [MERGEJOIN_298] (rows=788222 width=110) - Conds:RS_94._col2=RS_344._col0(Inner),Output:["_col1","_col3"] - <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_344] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_339] - <-Reducer 25 [SIMPLE_EDGE] - SHUFFLE [RS_94] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_297] (rows=3941109 width=118) - Conds:RS_387._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_328] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_323] - <-Map 33 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_387] + <-Map 27 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_366] PartitionCols:_col0 - Select Operator [SEL_386] (rows=143931246 width=123) + Select Operator [SEL_365] (rows=143931246 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_385] (rows=143931246 width=123) - predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_95_customer_address_ca_address_sk_min) AND DynamicValue(RS_95_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_95_customer_address_ca_address_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_101_item_i_item_sk_min) AND DynamicValue(RS_101_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_101_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_92_date_dim_d_date_sk_min) AND DynamicValue(RS_92_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_92_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) + Filter Operator [FIL_364] (rows=143931246 width=123) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_92_date_dim_d_date_sk_min) AND DynamicValue(RS_92_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_92_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) TableScan [TS_82] (rows=144002668 width=123) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_384] - Group By Operator [GBY_383] (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] - SHUFFLE [RS_277] - Group By Operator [GBY_276] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_275] (rows=15609 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_290] - <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_380] - Group By Operator [GBY_379] (rows=1 width=12) + <-Reducer 24 [BROADCAST_EDGE] vectorized + BROADCAST [RS_363] + Group By Operator [GBY_362] (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 + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_335] Group By Operator [GBY_332] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] Select Operator [SEL_329] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_323] - <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_382] - Group By Operator [GBY_381] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_351] - Group By Operator [GBY_348] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_345] (rows=8000000 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_339] <-Reducer 4 [CONTAINS] vectorized - Reduce Output Operator [RS_361] + Reduce Output Operator [RS_348] PartitionCols:_col0 - Group By Operator [GBY_360] (rows=355 width=212) + Group By Operator [GBY_347] (rows=355 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_359] (rows=355 width=212) + Group By Operator [GBY_346] (rows=355 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_33] @@ -405,66 +297,102 @@ Stage-0 SHUFFLE [RS_28] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_290] - <-Reducer 19 [SIMPLE_EDGE] + <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col2 Select Operator [SEL_24] (rows=2876890 width=4) Output:["_col2","_col4"] Merge Join Operator [MERGEJOIN_292] (rows=2876890 width=4) - Conds:RS_21._col2=RS_340._col0(Inner),Output:["_col1","_col3"] - <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_340] + Conds:RS_21._col2=RS_343._col0(Inner),Output:["_col1","_col3"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_343] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_339] - <-Reducer 18 [SIMPLE_EDGE] + Please refer to the previous Select Operator [SEL_342] + <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_291] (rows=14384447 width=4) - Conds:RS_358._col0=RS_324._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] vectorized + Conds:RS_340._col0=RS_324._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 17 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_324] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_323] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_358] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_340] PartitionCols:_col0 - Select Operator [SEL_357] (rows=525327191 width=118) + Select Operator [SEL_339] (rows=525327191 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_356] (rows=525327191 width=118) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_22_customer_address_ca_address_sk_min) AND DynamicValue(RS_22_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_22_customer_address_ca_address_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_28_item_i_item_sk_min) AND DynamicValue(RS_28_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_28_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) + Filter Operator [FIL_338] (rows=525327191 width=118) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) TableScan [TS_9] (rows=575995635 width=118) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] - <-Reducer 21 [BROADCAST_EDGE] vectorized + <-Reducer 18 [BROADCAST_EDGE] vectorized BROADCAST [RS_337] Group By Operator [GBY_336] (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 + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_333] Group By Operator [GBY_330] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] Select Operator [SEL_325] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_323] - <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_353] - Group By Operator [GBY_352] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_349] - Group By Operator [GBY_346] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_341] (rows=8000000 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_339] - <-Reducer 8 [BROADCAST_EDGE] vectorized + <-Reducer 9 [CONTAINS] vectorized + Reduce Output Operator [RS_361] + PartitionCols:_col0 + Group By Operator [GBY_360] (rows=355 width=212) + Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 + Group By Operator [GBY_359] (rows=355 width=212) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_69] + PartitionCols:_col0 + Group By Operator [GBY_68] (rows=355 width=212) + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 + Merge Join Operator [MERGEJOIN_300] (rows=339151 width=100) + Conds:RS_64._col0=RS_65._col3(Inner),Output:["_col1","_col7"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_64] + PartitionCols:_col0 + Please refer to the previous Merge Join Operator [MERGEJOIN_290] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_65] + PartitionCols:_col3 + Select Operator [SEL_60] (rows=1550375 width=13) + Output:["_col3","_col4"] + Merge Join Operator [MERGEJOIN_295] (rows=1550375 width=13) + Conds:RS_57._col1=RS_344._col0(Inner),Output:["_col2","_col3"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_344] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_342] + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_57] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_294] (rows=7751872 width=98) + Conds:RS_358._col0=RS_326._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 17 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_326] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_323] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_358] + PartitionCols:_col0 + Select Operator [SEL_357] (rows=285117733 width=123) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_356] (rows=285117733 width=123) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_55_date_dim_d_date_sk_min) AND DynamicValue(RS_55_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_55_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_45] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] + <-Reducer 21 [BROADCAST_EDGE] vectorized BROADCAST [RS_355] Group By Operator [GBY_354] (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] - SHUFFLE [RS_197] - Group By Operator [GBY_196] (rows=1 width=12) + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_334] + Group By Operator [GBY_331] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_195] (rows=15609 width=4) + Select Operator [SEL_327] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_290] + Please refer to the previous Select Operator [SEL_323]
http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/constraints/query60.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query60.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query60.q.out index 5ba912a..4e68dca 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query60.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query60.q.out @@ -169,68 +169,62 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 17 <- Reducer 21 (BROADCAST_EDGE), Reducer 29 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Map 32 <- Reducer 11 (BROADCAST_EDGE), Reducer 24 (BROADCAST_EDGE), Reducer 30 (BROADCAST_EDGE) -Map 33 <- Reducer 14 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE), Reducer 31 (BROADCAST_EDGE) -Reducer 10 <- Reducer 9 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 11 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Reducer 2 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 14 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (SIMPLE_EDGE) -Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) -Reducer 19 <- Map 28 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 16 (ONE_TO_ONE_EDGE) -Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 22 <- Map 20 (SIMPLE_EDGE), Map 32 (SIMPLE_EDGE) -Reducer 23 <- Map 28 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) -Reducer 24 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 25 <- Map 20 (SIMPLE_EDGE), Map 33 (SIMPLE_EDGE) -Reducer 26 <- Map 28 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE) -Reducer 27 <- Map 20 (CUSTOM_SIMPLE_EDGE) -Reducer 29 <- Map 28 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 19 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 30 <- Map 28 (CUSTOM_SIMPLE_EDGE) -Reducer 31 <- Map 28 (CUSTOM_SIMPLE_EDGE) +Map 14 <- Reducer 18 (BROADCAST_EDGE) +Map 26 <- Reducer 21 (BROADCAST_EDGE) +Map 27 <- Reducer 24 (BROADCAST_EDGE) +Reducer 10 <- Reducer 2 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 13 <- Map 12 (SIMPLE_EDGE) +Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 16 <- Map 25 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) +Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 17 (SIMPLE_EDGE), Map 26 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 13 (ONE_TO_ONE_EDGE) +Reducer 20 <- Map 25 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) +Reducer 21 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 22 <- Map 17 (SIMPLE_EDGE), Map 27 (SIMPLE_EDGE) +Reducer 23 <- Map 25 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE) +Reducer 24 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 6 <- Union 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Reducer 2 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE), Union 5 (CONTAINS) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_371] - Limit [LIM_370] (rows=100 width=212) + File Output Operator [FS_358] + Limit [LIM_357] (rows=100 width=212) Number of rows:100 - Select Operator [SEL_369] (rows=1717 width=212) + Select Operator [SEL_356] (rows=1717 width=212) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_368] - Group By Operator [GBY_367] (rows=1717 width=212) + SHUFFLE [RS_355] + Group By Operator [GBY_354] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] - <-Reducer 10 [CONTAINS] vectorized - Reduce Output Operator [RS_384] + <-Reducer 11 [CONTAINS] vectorized + Reduce Output Operator [RS_376] PartitionCols:_col0 - Group By Operator [GBY_383] (rows=1717 width=212) + Group By Operator [GBY_375] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Top N Key Operator [TNK_382] (rows=5151 width=212) + Top N Key Operator [TNK_374] (rows=5151 width=212) keys:_col0,sort order:+,top n:100 - Group By Operator [GBY_381] (rows=1717 width=212) + Group By Operator [GBY_373] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_69] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_106] PartitionCols:_col0 - Group By Operator [GBY_68] (rows=1717 width=212) + Group By Operator [GBY_105] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_301] (rows=746132 width=100) - Conds:RS_64._col0=RS_65._col3(Inner),Output:["_col1","_col7"] + Merge Join Operator [MERGEJOIN_302] (rows=379339 width=201) + Conds:RS_101._col0=RS_102._col2(Inner),Output:["_col1","_col7"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_64] + SHUFFLE [RS_101] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_291] (rows=34340 width=104) Conds:RS_319._col1=RS_325._col0(Inner),Output:["_col0","_col1"] @@ -241,12 +235,12 @@ Stage-0 Output:["_col0","_col1"] TableScan [TS_0] (rows=462000 width=104) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] - <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized + <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized FORWARD [RS_325] PartitionCols:_col0 Group By Operator [GBY_324] (rows=23100 width=100) Output:["_col0"],keys:KEY._col0 - <-Map 15 [SIMPLE_EDGE] vectorized + <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_323] PartitionCols:_col0 Group By Operator [GBY_322] (rows=23100 width=100) @@ -258,28 +252,28 @@ Stage-0 TableScan [TS_2] (rows=462000 width=190) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_id","i_category"] <-Reducer 23 [SIMPLE_EDGE] - SHUFFLE [RS_65] - PartitionCols:_col3 - Select Operator [SEL_60] (rows=1550375 width=13) - Output:["_col3","_col4"] - Merge Join Operator [MERGEJOIN_296] (rows=1550375 width=13) - Conds:RS_57._col1=RS_346._col0(Inner),Output:["_col2","_col3"] - <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_346] + SHUFFLE [RS_102] + PartitionCols:_col2 + Select Operator [SEL_97] (rows=788222 width=110) + Output:["_col2","_col4"] + Merge Join Operator [MERGEJOIN_299] (rows=788222 width=110) + Conds:RS_94._col2=RS_349._col0(Inner),Output:["_col1","_col3"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_349] PartitionCols:_col0 - Select Operator [SEL_343] (rows=8000000 width=4) + Select Operator [SEL_346] (rows=8000000 width=4) Output:["_col0"] - Filter Operator [FIL_342] (rows=8000000 width=112) + Filter Operator [FIL_345] (rows=8000000 width=112) predicate:(ca_gmt_offset = -6) TableScan [TS_15] (rows=40000000 width=112) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_gmt_offset"] <-Reducer 22 [SIMPLE_EDGE] - SHUFFLE [RS_57] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_295] (rows=7751872 width=98) - Conds:RS_380._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_330] + SHUFFLE [RS_94] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_298] (rows=3941109 width=118) + Conds:RS_372._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 17 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_332] PartitionCols:_col0 Select Operator [SEL_327] (rows=50 width=4) Output:["_col0"] @@ -287,138 +281,34 @@ Stage-0 predicate:((d_moy = 9) and (d_year = 1999)) TableScan [TS_12] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 32 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_380] - PartitionCols:_col0 - Select Operator [SEL_379] (rows=285117733 width=123) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_378] (rows=285117733 width=123) - predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_58_customer_address_ca_address_sk_min) AND DynamicValue(RS_58_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_58_customer_address_ca_address_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_64_item_i_item_sk_min) AND DynamicValue(RS_64_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_64_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_55_date_dim_d_date_sk_min) AND DynamicValue(RS_55_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_55_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_45] (rows=287989836 width=123) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_377] - Group By Operator [GBY_376] (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] - SHUFFLE [RS_238] - Group By Operator [GBY_237] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_236] (rows=34340 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_291] - <-Reducer 24 [BROADCAST_EDGE] vectorized - BROADCAST [RS_373] - Group By Operator [GBY_372] (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 - PARTITION_ONLY_SHUFFLE [RS_338] - Group By Operator [GBY_335] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_331] (rows=50 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_327] - <-Reducer 30 [BROADCAST_EDGE] vectorized - BROADCAST [RS_375] - Group By Operator [GBY_374] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_354] - Group By Operator [GBY_351] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_347] (rows=8000000 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_343] - <-Reducer 13 [CONTAINS] vectorized - Reduce Output Operator [RS_397] - PartitionCols:_col0 - Group By Operator [GBY_396] (rows=1717 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Top N Key Operator [TNK_395] (rows=5151 width=212) - keys:_col0,sort order:+,top n:100 - Group By Operator [GBY_394] (rows=1717 width=212) - Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_106] - PartitionCols:_col0 - Group By Operator [GBY_105] (rows=1717 width=212) - Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 - Merge Join Operator [MERGEJOIN_302] (rows=379339 width=201) - Conds:RS_101._col0=RS_102._col2(Inner),Output:["_col1","_col7"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_101] - PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_291] - <-Reducer 26 [SIMPLE_EDGE] - SHUFFLE [RS_102] - PartitionCols:_col2 - Select Operator [SEL_97] (rows=788222 width=110) - Output:["_col2","_col4"] - Merge Join Operator [MERGEJOIN_299] (rows=788222 width=110) - Conds:RS_94._col2=RS_348._col0(Inner),Output:["_col1","_col3"] - <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_348] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_343] - <-Reducer 25 [SIMPLE_EDGE] - SHUFFLE [RS_94] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_298] (rows=3941109 width=118) - Conds:RS_393._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_332] + <-Map 27 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_372] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_327] - <-Map 33 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_393] - PartitionCols:_col0 - Select Operator [SEL_392] (rows=143931246 width=123) + Select Operator [SEL_371] (rows=143931246 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_391] (rows=143931246 width=123) - predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_95_customer_address_ca_address_sk_min) AND DynamicValue(RS_95_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_95_customer_address_ca_address_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_101_item_i_item_sk_min) AND DynamicValue(RS_101_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_101_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_92_date_dim_d_date_sk_min) AND DynamicValue(RS_92_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_92_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) + Filter Operator [FIL_370] (rows=143931246 width=123) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_92_date_dim_d_date_sk_min) AND DynamicValue(RS_92_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_92_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_sold_date_sk is not null) TableScan [TS_82] (rows=144002668 width=123) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_390] - Group By Operator [GBY_389] (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] - SHUFFLE [RS_278] - Group By Operator [GBY_277] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_276] (rows=34340 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_291] - <-Reducer 27 [BROADCAST_EDGE] vectorized - BROADCAST [RS_386] - Group By Operator [GBY_385] (rows=1 width=12) + <-Reducer 24 [BROADCAST_EDGE] vectorized + BROADCAST [RS_369] + Group By Operator [GBY_368] (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 + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_339] Group By Operator [GBY_336] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] Select Operator [SEL_333] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_327] - <-Reducer 31 [BROADCAST_EDGE] vectorized - BROADCAST [RS_388] - Group By Operator [GBY_387] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_355] - Group By Operator [GBY_352] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_349] (rows=8000000 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_343] <-Reducer 4 [CONTAINS] vectorized - Reduce Output Operator [RS_366] + Reduce Output Operator [RS_353] PartitionCols:_col0 - Group By Operator [GBY_365] (rows=1717 width=212) + Group By Operator [GBY_352] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Top N Key Operator [TNK_364] (rows=5151 width=212) + Top N Key Operator [TNK_351] (rows=5151 width=212) keys:_col0,sort order:+,top n:100 - Group By Operator [GBY_363] (rows=1717 width=212) + Group By Operator [GBY_350] (rows=1717 width=212) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_33] @@ -431,66 +321,104 @@ Stage-0 SHUFFLE [RS_28] PartitionCols:_col0 Please refer to the previous Merge Join Operator [MERGEJOIN_291] - <-Reducer 19 [SIMPLE_EDGE] + <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col2 Select Operator [SEL_24] (rows=2876890 width=4) Output:["_col2","_col4"] Merge Join Operator [MERGEJOIN_293] (rows=2876890 width=4) - Conds:RS_21._col2=RS_344._col0(Inner),Output:["_col1","_col3"] - <-Map 28 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_344] + Conds:RS_21._col2=RS_347._col0(Inner),Output:["_col1","_col3"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_347] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_343] - <-Reducer 18 [SIMPLE_EDGE] + Please refer to the previous Select Operator [SEL_346] + <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_292] (rows=14384447 width=4) - Conds:RS_362._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 20 [SIMPLE_EDGE] vectorized + Conds:RS_344._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 17 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_328] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_327] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_362] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_344] PartitionCols:_col0 - Select Operator [SEL_361] (rows=525327191 width=118) + Select Operator [SEL_343] (rows=525327191 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_360] (rows=525327191 width=118) - predicate:((ss_addr_sk BETWEEN DynamicValue(RS_22_customer_address_ca_address_sk_min) AND DynamicValue(RS_22_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_22_customer_address_ca_address_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_28_item_i_item_sk_min) AND DynamicValue(RS_28_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_28_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) + Filter Operator [FIL_342] (rows=525327191 width=118) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_sold_date_sk is not null) TableScan [TS_9] (rows=575995635 width=118) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] - <-Reducer 21 [BROADCAST_EDGE] vectorized + <-Reducer 18 [BROADCAST_EDGE] vectorized BROADCAST [RS_341] Group By Operator [GBY_340] (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 + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_337] Group By Operator [GBY_334] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] Select Operator [SEL_329] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_327] - <-Reducer 29 [BROADCAST_EDGE] vectorized - BROADCAST [RS_357] - Group By Operator [GBY_356] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=8000000)"] - <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_353] - Group By Operator [GBY_350] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=8000000)"] - Select Operator [SEL_345] (rows=8000000 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_343] - <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_359] - Group By Operator [GBY_358] (rows=1 width=12) + <-Reducer 9 [CONTAINS] vectorized + Reduce Output Operator [RS_367] + PartitionCols:_col0 + Group By Operator [GBY_366] (rows=1717 width=212) + Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 + Top N Key Operator [TNK_365] (rows=5151 width=212) + keys:_col0,sort order:+,top n:100 + Group By Operator [GBY_364] (rows=1717 width=212) + Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_69] + PartitionCols:_col0 + Group By Operator [GBY_68] (rows=1717 width=212) + Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col1 + Merge Join Operator [MERGEJOIN_301] (rows=746132 width=100) + Conds:RS_64._col0=RS_65._col3(Inner),Output:["_col1","_col7"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_64] + PartitionCols:_col0 + Please refer to the previous Merge Join Operator [MERGEJOIN_291] + <-Reducer 20 [SIMPLE_EDGE] + SHUFFLE [RS_65] + PartitionCols:_col3 + Select Operator [SEL_60] (rows=1550375 width=13) + Output:["_col3","_col4"] + Merge Join Operator [MERGEJOIN_296] (rows=1550375 width=13) + Conds:RS_57._col1=RS_348._col0(Inner),Output:["_col2","_col3"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_348] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_346] + <-Reducer 19 [SIMPLE_EDGE] + SHUFFLE [RS_57] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_295] (rows=7751872 width=98) + Conds:RS_363._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 17 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_330] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_327] + <-Map 26 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_363] + PartitionCols:_col0 + Select Operator [SEL_362] (rows=285117733 width=123) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_361] (rows=285117733 width=123) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_55_date_dim_d_date_sk_min) AND DynamicValue(RS_55_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_55_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_45] (rows=287989836 width=123) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] + <-Reducer 21 [BROADCAST_EDGE] vectorized + BROADCAST [RS_360] + Group By Operator [GBY_359] (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] - SHUFFLE [RS_198] - Group By Operator [GBY_197] (rows=1 width=12) + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_338] + Group By Operator [GBY_335] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_196] (rows=34340 width=4) + Select Operator [SEL_331] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_291] + Please refer to the previous Select Operator [SEL_327]
