http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query33.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query33.q.out b/ql/src/test/results/clientpositive/perf/tez/query33.q.out index ad922e7..30871e5 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query33.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query33.q.out @@ -149,213 +149,324 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Reducer 2 (SIMPLE_EDGE), Reducer 21 (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 22 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 23 (SIMPLE_EDGE) -Reducer 19 <- Map 22 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 13 (ONE_TO_ONE_EDGE) -Reducer 20 <- Map 17 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE) -Reducer 21 <- Map 22 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) -Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +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) Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) Reducer 6 <- Union 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 19 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 9 <- Reducer 8 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 2 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_226] - Limit [LIM_225] (rows=100 width=108) + File Output Operator [FS_370] + Limit [LIM_369] (rows=100 width=108) Number of rows:100 - Select Operator [SEL_224] (rows=335408073 width=108) + Select Operator [SEL_368] (rows=335408073 width=108) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_223] - Group By Operator [GBY_222] (rows=335408073 width=108) + SHUFFLE [RS_367] + Group By Operator [GBY_366] (rows=335408073 width=108) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Union 5 [SIMPLE_EDGE] - <-Reducer 11 [CONTAINS] vectorized - Reduce Output Operator [RS_238] + <-Reducer 10 [CONTAINS] vectorized + Reduce Output Operator [RS_382] PartitionCols:_col0 - Group By Operator [GBY_237] (rows=670816147 width=108) + Group By Operator [GBY_381] (rows=670816147 width=108) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_236] (rows=95833781 width=135) + Group By Operator [GBY_380] (rows=191657247 width=135) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_109] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_71] PartitionCols:_col0 - Group By Operator [GBY_108] (rows=191667562 width=135) + Group By Operator [GBY_70] (rows=383314495 width=135) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_184] (rows=191667562 width=135) - Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"] + Merge Join Operator [MERGEJOIN_303] (rows=383314495 width=135) + Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_104] + SHUFFLE [RS_66] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_173] (rows=508200 width=1436) - Conds:RS_199._col1=RS_205._col0(Inner),Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_293] (rows=508200 width=1436) + Conds:RS_319._col1=RS_325._col0(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_199] + SHUFFLE [RS_319] PartitionCols:_col1 - Select Operator [SEL_198] (rows=462000 width=1436) + Select Operator [SEL_318] (rows=462000 width=1436) Output:["_col0","_col1"] - Filter Operator [FIL_197] (rows=462000 width=1436) + Filter Operator [FIL_317] (rows=462000 width=1436) predicate:(i_item_sk is not null and i_manufact_id is not null) TableScan [TS_0] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_manufact_id"] - <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_205] + <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_325] PartitionCols:_col0 - Group By Operator [GBY_204] (rows=115500 width=1436) + Group By Operator [GBY_324] (rows=115500 width=1436) Output:["_col0"],keys:KEY._col0 - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_203] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_323] PartitionCols:_col0 - Group By Operator [GBY_202] (rows=231000 width=1436) + Group By Operator [GBY_322] (rows=231000 width=1436) Output:["_col0"],keys:i_manufact_id - Select Operator [SEL_201] (rows=231000 width=1436) + Select Operator [SEL_321] (rows=231000 width=1436) Output:["i_manufact_id"] - Filter Operator [FIL_200] (rows=231000 width=1436) + Filter Operator [FIL_320] (rows=231000 width=1436) predicate:((i_category = 'Books') and i_manufact_id is not null) TableScan [TS_3] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_category","i_manufact_id"] - <-Reducer 21 [SIMPLE_EDGE] - SHUFFLE [RS_105] - PartitionCols:_col3 - Select Operator [SEL_100] (rows=174243235 width=135) - Output:["_col3","_col5"] - Merge Join Operator [MERGEJOIN_181] (rows=174243235 width=135) - Conds:RS_97._col2=RS_218._col0(Inner),Output:["_col1","_col3"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_218] + <-Reducer 23 [SIMPLE_EDGE] + SHUFFLE [RS_67] + PartitionCols:_col4 + Select Operator [SEL_62] (rows=348467716 width=135) + Output:["_col4","_col5"] + Merge Join Operator [MERGEJOIN_298] (rows=348467716 width=135) + Conds:RS_59._col1=RS_346._col0(Inner),Output:["_col2","_col3"] + <-Map 28 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_346] PartitionCols:_col0 - Select Operator [SEL_215] (rows=20000000 width=1014) + Select Operator [SEL_343] (rows=20000000 width=1014) Output:["_col0"] - Filter Operator [FIL_214] (rows=20000000 width=1014) + Filter Operator [FIL_342] (rows=20000000 width=1014) predicate:((ca_gmt_offset = -6) and ca_address_sk is not null) TableScan [TS_16] (rows=40000000 width=1014) default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_gmt_offset"] - <-Reducer 20 [SIMPLE_EDGE] - SHUFFLE [RS_97] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_180] (rows=158402938 width=135) - Conds:RS_235._col0=RS_213._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_213] + <-Reducer 22 [SIMPLE_EDGE] + SHUFFLE [RS_59] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_297] (rows=316788826 width=135) + Conds:RS_379._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 20 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_330] PartitionCols:_col0 - Select Operator [SEL_210] (rows=18262 width=1119) + Select Operator [SEL_327] (rows=18262 width=1119) Output:["_col0"] - Filter Operator [FIL_209] (rows=18262 width=1119) + Filter Operator [FIL_326] (rows=18262 width=1119) predicate:((d_moy = 3) and (d_year = 1999) and d_date_sk is not null) TableScan [TS_13] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_235] + <-Map 32 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_379] PartitionCols:_col0 - Select Operator [SEL_234] (rows=144002668 width=135) + Select Operator [SEL_378] (rows=287989836 width=135) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_233] (rows=144002668 width=135) - predicate:(ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_85] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] - <-Reducer 4 [CONTAINS] vectorized - Reduce Output Operator [RS_221] + Filter Operator [FIL_377] (rows=287989836 width=135) + predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_60_customer_address_ca_address_sk_min) AND DynamicValue(RS_60_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_60_customer_address_ca_address_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_66_item_i_item_sk_min) AND DynamicValue(RS_66_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_66_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_57_date_dim_d_date_sk_min) AND DynamicValue(RS_57_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_57_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_47] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_376] + Group By Operator [GBY_375] (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_240] + Group By Operator [GBY_239] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_238] (rows=508200 width=1436) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_293] + <-Reducer 24 [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)"] + <-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=18262 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_327] + <-Reducer 30 [BROADCAST_EDGE] vectorized + BROADCAST [RS_374] + Group By Operator [GBY_373] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] + <-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=20000000)"] + Select Operator [SEL_347] (rows=20000000 width=1014) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_343] + <-Reducer 13 [CONTAINS] vectorized + Reduce Output Operator [RS_394] PartitionCols:_col0 - Group By Operator [GBY_220] (rows=670816147 width=108) + Group By Operator [GBY_393] (rows=670816147 width=108) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_219] (rows=383325119 width=88) + Group By Operator [GBY_392] (rows=95833781 width=135) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_34] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_109] PartitionCols:_col0 - Group By Operator [GBY_33] (rows=766650239 width=88) + Group By Operator [GBY_108] (rows=191667562 width=135) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_182] (rows=766650239 width=88) - Conds:RS_29._col0=RS_30._col3(Inner),Output:["_col1","_col8"] + Merge Join Operator [MERGEJOIN_304] (rows=191667562 width=135) + Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_29] + SHUFFLE [RS_104] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_173] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_30] + Please refer to the previous Merge Join Operator [MERGEJOIN_293] + <-Reducer 26 [SIMPLE_EDGE] + SHUFFLE [RS_105] PartitionCols:_col3 - Select Operator [SEL_25] (rows=696954748 width=88) + Select Operator [SEL_100] (rows=174243235 width=135) Output:["_col3","_col5"] - Merge Join Operator [MERGEJOIN_175] (rows=696954748 width=88) - Conds:RS_22._col2=RS_216._col0(Inner),Output:["_col1","_col3"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_216] + Merge Join Operator [MERGEJOIN_301] (rows=174243235 width=135) + Conds:RS_97._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_215] - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_22] + Please refer to the previous Select Operator [SEL_343] + <-Reducer 25 [SIMPLE_EDGE] + SHUFFLE [RS_97] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_174] (rows=633595212 width=88) - Conds:RS_208._col0=RS_211._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_211] + Merge Join Operator [MERGEJOIN_300] (rows=158402938 width=135) + Conds:RS_391._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 20 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_332] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_210] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_208] + Please refer to the previous Select Operator [SEL_327] + <-Map 33 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_391] PartitionCols:_col0 - Select Operator [SEL_207] (rows=575995635 width=88) + Select Operator [SEL_390] (rows=144002668 width=135) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_206] (rows=575995635 width=88) - predicate:(ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_10] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] - <-Reducer 9 [CONTAINS] vectorized - Reduce Output Operator [RS_232] + Filter Operator [FIL_389] (rows=144002668 width=135) + predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_98_customer_address_ca_address_sk_min) AND DynamicValue(RS_98_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_98_customer_address_ca_address_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_104_item_i_item_sk_min) AND DynamicValue(RS_104_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_104_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_95_date_dim_d_date_sk_min) AND DynamicValue(RS_95_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_95_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_85] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"] + <-Reducer 14 [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=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_280] + Group By Operator [GBY_279] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_278] (rows=508200 width=1436) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_293] + <-Reducer 27 [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)"] + <-Map 20 [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=18262 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_327] + <-Reducer 31 [BROADCAST_EDGE] vectorized + BROADCAST [RS_386] + Group By Operator [GBY_385] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"] + <-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=20000000)"] + Select Operator [SEL_349] (rows=20000000 width=1014) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_343] + <-Reducer 4 [CONTAINS] vectorized + Reduce Output Operator [RS_365] PartitionCols:_col0 - Group By Operator [GBY_231] (rows=670816147 width=108) + Group By Operator [GBY_364] (rows=670816147 width=108) Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Group By Operator [GBY_230] (rows=191657247 width=135) + Group By Operator [GBY_363] (rows=383325119 width=88) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_71] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_34] PartitionCols:_col0 - Group By Operator [GBY_70] (rows=383314495 width=135) + Group By Operator [GBY_33] (rows=766650239 width=88) Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1 - Merge Join Operator [MERGEJOIN_183] (rows=383314495 width=135) - Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"] + Merge Join Operator [MERGEJOIN_302] (rows=766650239 width=88) + Conds:RS_29._col0=RS_30._col3(Inner),Output:["_col1","_col8"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_66] + SHUFFLE [RS_29] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_173] + Please refer to the previous Merge Join Operator [MERGEJOIN_293] <-Reducer 19 [SIMPLE_EDGE] - SHUFFLE [RS_67] - PartitionCols:_col4 - Select Operator [SEL_62] (rows=348467716 width=135) - Output:["_col4","_col5"] - Merge Join Operator [MERGEJOIN_178] (rows=348467716 width=135) - Conds:RS_59._col1=RS_217._col0(Inner),Output:["_col2","_col3"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_217] + SHUFFLE [RS_30] + PartitionCols:_col3 + Select Operator [SEL_25] (rows=696954748 width=88) + Output:["_col3","_col5"] + Merge Join Operator [MERGEJOIN_295] (rows=696954748 width=88) + Conds:RS_22._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_215] + Please refer to the previous Select Operator [SEL_343] <-Reducer 18 [SIMPLE_EDGE] - SHUFFLE [RS_59] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_177] (rows=316788826 width=135) - Conds:RS_229._col0=RS_212._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_212] + SHUFFLE [RS_22] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_294] (rows=633595212 width=88) + Conds:RS_362._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_210] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_229] + Please refer to the previous Select Operator [SEL_327] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_362] PartitionCols:_col0 - Select Operator [SEL_228] (rows=287989836 width=135) + Select Operator [SEL_361] (rows=575995635 width=88) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_227] (rows=287989836 width=135) - predicate:(cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_47] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"] + Filter Operator [FIL_360] (rows=575995635 width=88) + predicate:((ss_addr_sk BETWEEN DynamicValue(RS_23_customer_address_ca_address_sk_min) AND DynamicValue(RS_23_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_23_customer_address_ca_address_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_29_item_i_item_sk_min) AND DynamicValue(RS_29_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_29_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_10] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"] + <-Reducer 21 [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 + 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=18262 width=1119) + 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=20000000)"] + <-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=20000000)"] + Select Operator [SEL_345] (rows=20000000 width=1014) + 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) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_200] + Group By Operator [GBY_199] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_198] (rows=508200 width=1436) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_293]
http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query34.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query34.q.out b/ql/src/test/results/clientpositive/perf/tez/query34.q.out index f5046e3..9b7b482 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query34.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query34.q.out @@ -61,67 +61,72 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Map 5 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 4 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 6 <- Map 10 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Map 11 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 7 (SIMPLE_EDGE) +Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Map 10 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) +Reducer 7 <- Map 12 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Map 14 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 3 vectorized - File Output Operator [FS_78] - Select Operator [SEL_77] (rows=88000001 width=860) + File Output Operator [FS_135] + Select Operator [SEL_134] (rows=88000001 width=860) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_35] Select Operator [SEL_34] (rows=88000001 width=860) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_60] (rows=88000001 width=860) - Conds:RS_63._col0=RS_76._col1(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col7"] + Merge Join Operator [MERGEJOIN_100] (rows=88000001 width=860) + Conds:RS_103._col0=RS_133._col1(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col7"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_63] + PARTITION_ONLY_SHUFFLE [RS_103] PartitionCols:_col0 - Select Operator [SEL_62] (rows=80000000 width=860) + Select Operator [SEL_102] (rows=80000000 width=860) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_61] (rows=80000000 width=860) + Filter Operator [FIL_101] (rows=80000000 width=860) predicate:c_customer_sk is not null TableScan [TS_0] (rows=80000000 width=860) default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag"] - <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_76] + <-Reducer 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_133] PartitionCols:_col1 - Filter Operator [FIL_75] (rows=42591679 width=88) + Filter Operator [FIL_132] (rows=42591679 width=88) predicate:_col2 BETWEEN 15 AND 20 - Select Operator [SEL_74] (rows=383325119 width=88) + Select Operator [SEL_131] (rows=383325119 width=88) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_73] (rows=383325119 width=88) + Group By Operator [GBY_130] (rows=383325119 width=88) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 - <-Reducer 7 [SIMPLE_EDGE] + <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_26] PartitionCols:_col0, _col1 Group By Operator [GBY_25] (rows=766650239 width=88) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col1, _col4 - Merge Join Operator [MERGEJOIN_59] (rows=766650239 width=88) - Conds:RS_21._col3=RS_72._col0(Inner),Output:["_col1","_col4"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_72] + Merge Join Operator [MERGEJOIN_99] (rows=766650239 width=88) + Conds:RS_21._col3=RS_119._col0(Inner),Output:["_col1","_col4"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_119] PartitionCols:_col0 - Select Operator [SEL_71] (rows=852 width=1910) + Select Operator [SEL_118] (rows=852 width=1910) Output:["_col0"] - Filter Operator [FIL_70] (rows=852 width=1910) + Filter Operator [FIL_117] (rows=852 width=1910) predicate:((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County', 'Fairfield County', 'Jackson County', 'Barrow County', 'Pennington County') and s_store_sk is not null) TableScan [TS_12] (rows=1704 width=1910) default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_county"] - <-Reducer 6 [SIMPLE_EDGE] + <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_58] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_98] (rows=696954748 width=88) Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col1","_col3","_col4"] - <-Map 10 [SIMPLE_EDGE] + <-Map 12 [SIMPLE_EDGE] SHUFFLE [RS_19] PartitionCols:_col0 Select Operator [SEL_11] (rows=1200 width=107) @@ -130,27 +135,71 @@ Stage-0 predicate:(((hd_buy_potential = '>10000') or (hd_buy_potential = 'unknown')) and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2D)) ELSE (null) END and hd_demo_sk is not null) TableScan [TS_9] (rows=7200 width=107) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential","hd_dep_count","hd_vehicle_count"] - <-Reducer 5 [SIMPLE_EDGE] + <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_57] (rows=633595212 width=88) - Conds:RS_66._col0=RS_69._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_66] + Merge Join Operator [MERGEJOIN_97] (rows=633595212 width=88) + Conds:RS_129._col0=RS_109._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_109] PartitionCols:_col0 - Select Operator [SEL_65] (rows=575995635 width=88) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_64] (rows=575995635 width=88) - predicate:(ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_3] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_store_sk","ss_ticket_number"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_69] - PartitionCols:_col0 - Select Operator [SEL_68] (rows=8116 width=1119) + Select Operator [SEL_108] (rows=8116 width=1119) Output:["_col0"] - Filter Operator [FIL_67] (rows=8116 width=1119) + Filter Operator [FIL_107] (rows=8116 width=1119) predicate:((d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and (d_year) IN (2000, 2001, 2002) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_dom"] + <-Map 5 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_129] + PartitionCols:_col0 + Select Operator [SEL_128] (rows=575995635 width=88) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_127] (rows=575995635 width=88) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_31_customer_c_customer_sk_min) AND DynamicValue(RS_31_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_31_customer_c_customer_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_19_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_19_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_19_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_da te_sk is not null and ss_store_sk is not null) + TableScan [TS_3] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_store_sk","ss_ticket_number"] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_114] + Group By Operator [GBY_113] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_112] + Group By Operator [GBY_111] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_110] (rows=8116 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_108] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_116] + Group By Operator [GBY_115] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_69] + Group By Operator [GBY_68] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_67] (rows=1200 width=107) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_11] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_124] + Group By Operator [GBY_123] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_122] + Group By Operator [GBY_121] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_120] (rows=852 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_118] + <-Reducer 4 [BROADCAST_EDGE] vectorized + BROADCAST [RS_126] + Group By Operator [GBY_125] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] + <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_106] + Group By Operator [GBY_105] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] + Select Operator [SEL_104] (rows=80000000 width=860) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_102] http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query35.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query35.q.out b/ql/src/test/results/clientpositive/perf/tez/query35.q.out index 772f994..4fe3856 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query35.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query35.q.out @@ -113,32 +113,39 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Map 11 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) -Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Map 11 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Map 10 <- Reducer 13 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) +Map 20 <- Reducer 16 (BROADCAST_EDGE) +Map 21 <- Reducer 19 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 12 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) Reducer 15 <- Reducer 14 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 13 (ONE_TO_ONE_EDGE), Reducer 15 (ONE_TO_ONE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 16 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 12 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) +Reducer 18 <- Reducer 17 (SIMPLE_EDGE) +Reducer 19 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 11 (SIMPLE_EDGE), Reducer 15 (ONE_TO_ONE_EDGE), Reducer 18 (ONE_TO_ONE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 6 vectorized - File Output Operator [FS_144] - Limit [LIM_143] (rows=100 width=88) + File Output Operator [FS_225] + Limit [LIM_224] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_142] (rows=1045432122 width=88) + Select Operator [SEL_223] (rows=1045432122 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_141] - Select Operator [SEL_140] (rows=1045432122 width=88) + SHUFFLE [RS_222] + Select Operator [SEL_221] (rows=1045432122 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col14","_col15","_col16","_col17"] - Group By Operator [GBY_139] (rows=1045432122 width=88) + Group By Operator [GBY_220] (rows=1045432122 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","count(VALUE._col2)","max(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","max(VALUE._col6)","sum(VALUE._col7)","count(VALUE._col8)","max(VALUE._col9)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_63] @@ -149,124 +156,168 @@ Stage-0 Output:["_col4","_col6","_col7","_col8","_col9","_col10"] Filter Operator [FIL_60] (rows=2090864244 width=88) predicate:(_col12 is not null or _col14 is not null) - Merge Join Operator [MERGEJOIN_109] (rows=2090864244 width=88) - Conds:RS_55._col0=RS_56._col0(Left Semi),RS_55._col0=RS_132._col0(Left Outer),RS_55._col0=RS_138._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14"] - <-Reducer 10 [SIMPLE_EDGE] + Merge Join Operator [MERGEJOIN_173] (rows=2090864244 width=88) + Conds:RS_55._col0=RS_56._col0(Left Semi),RS_55._col0=RS_211._col0(Left Outer),RS_55._col0=RS_219._col0(Left Outer),Output:["_col4","_col6","_col7","_col8","_col9","_col10","_col12","_col14"] + <-Reducer 3 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_55] + PartitionCols:_col0 + Merge Join Operator [MERGEJOIN_169] (rows=96800003 width=860) + Conds:RS_50._col1=RS_182._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_182] + PartitionCols:_col0 + Select Operator [SEL_181] (rows=1861800 width=385) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_180] (rows=1861800 width=385) + predicate:cd_demo_sk is not null + TableScan [TS_6] (rows=1861800 width=385) + default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_dep_count","cd_dep_employed_count","cd_dep_college_count"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_50] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_168] (rows=88000001 width=860) + Conds:RS_176._col2=RS_179._col0(Inner),Output:["_col0","_col1","_col4"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_176] + PartitionCols:_col2 + Select Operator [SEL_175] (rows=80000000 width=860) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_174] (rows=80000000 width=860) + predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) + TableScan [TS_0] (rows=80000000 width=860) + default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_179] + PartitionCols:_col0 + Select Operator [SEL_178] (rows=40000000 width=1014) + Output:["_col0","_col1"] + Filter Operator [FIL_177] (rows=40000000 width=1014) + predicate:ca_address_sk is not null + TableScan [TS_3] (rows=40000000 width=1014) + default@customer_address,ca,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col0 Group By Operator [GBY_54] (rows=633595212 width=88) Output:["_col0"],keys:_col0 Select Operator [SEL_18] (rows=633595212 width=88) Output:["_col0"] - Merge Join Operator [MERGEJOIN_106] (rows=633595212 width=88) - Conds:RS_121._col0=RS_124._col0(Inner),Output:["_col1"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_124] + Merge Join Operator [MERGEJOIN_170] (rows=633595212 width=88) + Conds:RS_203._col0=RS_185._col0(Inner),Output:["_col1"] + <-Map 12 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_185] PartitionCols:_col0 - Select Operator [SEL_123] (rows=12174 width=1119) + Select Operator [SEL_184] (rows=12174 width=1119) Output:["_col0"] - Filter Operator [FIL_122] (rows=12174 width=1119) + Filter Operator [FIL_183] (rows=12174 width=1119) predicate:((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) TableScan [TS_12] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_121] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_203] PartitionCols:_col0 - Select Operator [SEL_120] (rows=575995635 width=88) + Select Operator [SEL_202] (rows=575995635 width=88) Output:["_col0","_col1"] - Filter Operator [FIL_119] (rows=575995635 width=88) - predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null) + Filter Operator [FIL_201] (rows=575995635 width=88) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_55_c_c_customer_sk_min) AND DynamicValue(RS_55_c_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_55_c_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) TableScan [TS_9] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] - <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_132] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_198] + Group By Operator [GBY_197] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_194] + Group By Operator [GBY_191] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_186] (rows=12174 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_184] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_200] + Group By Operator [GBY_199] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=96800000)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_136] + Group By Operator [GBY_135] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=96800000)"] + Select Operator [SEL_134] (rows=96800003 width=860) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_169] + <-Reducer 15 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_211] PartitionCols:_col0 - Select Operator [SEL_131] (rows=79201469 width=135) + Select Operator [SEL_210] (rows=79201469 width=135) Output:["_col0","_col1"] - Group By Operator [GBY_130] (rows=79201469 width=135) + Group By Operator [GBY_209] (rows=79201469 width=135) Output:["_col0"],keys:KEY._col0 - <-Reducer 12 [SIMPLE_EDGE] + <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0 Group By Operator [GBY_29] (rows=158402938 width=135) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_107] (rows=158402938 width=135) - Conds:RS_129._col0=RS_125._col0(Inner),Output:["_col1"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_125] + Merge Join Operator [MERGEJOIN_171] (rows=158402938 width=135) + Conds:RS_208._col0=RS_187._col0(Inner),Output:["_col1"] + <-Map 12 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_187] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_123] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_129] + Please refer to the previous Select Operator [SEL_184] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_208] PartitionCols:_col0 - Select Operator [SEL_128] (rows=144002668 width=135) + Select Operator [SEL_207] (rows=144002668 width=135) Output:["_col0","_col1"] - Filter Operator [FIL_127] (rows=144002668 width=135) - predicate:(ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + Filter Operator [FIL_206] (rows=144002668 width=135) + predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_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_19] (rows=144002668 width=135) default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] - <-Reducer 15 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_138] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_205] + Group By Operator [GBY_204] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_195] + Group By Operator [GBY_192] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_188] (rows=12174 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_184] + <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_219] PartitionCols:_col0 - Select Operator [SEL_137] (rows=158394413 width=135) + Select Operator [SEL_218] (rows=158394413 width=135) Output:["_col0","_col1"] - Group By Operator [GBY_136] (rows=158394413 width=135) + Group By Operator [GBY_217] (rows=158394413 width=135) Output:["_col0"],keys:KEY._col0 - <-Reducer 14 [SIMPLE_EDGE] + <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col0 Group By Operator [GBY_43] (rows=316788826 width=135) Output:["_col0"],keys:_col1 - Merge Join Operator [MERGEJOIN_108] (rows=316788826 width=135) - Conds:RS_135._col0=RS_126._col0(Inner),Output:["_col1"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] + Merge Join Operator [MERGEJOIN_172] (rows=316788826 width=135) + Conds:RS_216._col0=RS_189._col0(Inner),Output:["_col1"] + <-Map 12 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_189] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_123] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_135] + Please refer to the previous Select Operator [SEL_184] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_216] PartitionCols:_col0 - Select Operator [SEL_134] (rows=287989836 width=135) + Select Operator [SEL_215] (rows=287989836 width=135) Output:["_col0","_col1"] - Filter Operator [FIL_133] (rows=287989836 width=135) - predicate:(cs_ship_customer_sk is not null and cs_sold_date_sk is not null) + Filter Operator [FIL_214] (rows=287989836 width=135) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_40_date_dim_d_date_sk_min) AND DynamicValue(RS_40_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) TableScan [TS_33] (rows=287989836 width=135) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_55] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_105] (rows=96800003 width=860) - Conds:RS_50._col1=RS_118._col0(Inner),Output:["_col0","_col4","_col6","_col7","_col8","_col9","_col10"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_118] - PartitionCols:_col0 - Select Operator [SEL_117] (rows=1861800 width=385) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_116] (rows=1861800 width=385) - predicate:cd_demo_sk is not null - TableScan [TS_6] (rows=1861800 width=385) - default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_dep_count","cd_dep_employed_count","cd_dep_college_count"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_50] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_104] (rows=88000001 width=860) - Conds:RS_112._col2=RS_115._col0(Inner),Output:["_col0","_col1","_col4"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] - PartitionCols:_col2 - Select Operator [SEL_111] (rows=80000000 width=860) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_110] (rows=80000000 width=860) - predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) - TableScan [TS_0] (rows=80000000 width=860) - default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_115] - PartitionCols:_col0 - Select Operator [SEL_114] (rows=40000000 width=1014) - Output:["_col0","_col1"] - Filter Operator [FIL_113] (rows=40000000 width=1014) - predicate:ca_address_sk is not null - TableScan [TS_3] (rows=40000000 width=1014) - default@customer_address,ca,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_213] + Group By Operator [GBY_212] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_196] + Group By Operator [GBY_193] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_190] (rows=12174 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_184]
