http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query24.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query24.q.out b/ql/src/test/results/clientpositive/perf/tez/query24.q.out index 68a1504..9fcec42 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query24.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query24.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[154][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 8' is a cross product +Warning: Shuffle Join MERGEJOIN[286][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 8' is a cross product PREHOOK: query: explain with ssales as (select c_last_name @@ -100,20 +100,32 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Map 18 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 16 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 19 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Map 20 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 23 (BROADCAST_EDGE), Reducer 26 (BROADCAST_EDGE), Reducer 27 (BROADCAST_EDGE) +Map 31 <- Reducer 16 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE), Reducer 24 (BROADCAST_EDGE), Reducer 28 (BROADCAST_EDGE), Reducer 29 (BROADCAST_EDGE) +Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) +Reducer 11 <- Map 9 (SIMPLE_EDGE), Reducer 20 (SIMPLE_EDGE) +Reducer 12 <- Map 25 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 13 <- Map 30 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) Reducer 14 <- Reducer 13 (SIMPLE_EDGE) Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Reducer 16 <- Map 9 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 17 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE) +Reducer 20 <- Map 22 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE) +Reducer 21 <- Map 17 (CUSTOM_SIMPLE_EDGE) +Reducer 23 <- Map 22 (CUSTOM_SIMPLE_EDGE) +Reducer 24 <- Map 22 (CUSTOM_SIMPLE_EDGE) +Reducer 26 <- Map 25 (CUSTOM_SIMPLE_EDGE) +Reducer 27 <- Map 25 (CUSTOM_SIMPLE_EDGE) +Reducer 28 <- Map 25 (CUSTOM_SIMPLE_EDGE) +Reducer 29 <- Map 25 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Map 17 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 18 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 19 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Map 20 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 4 <- Map 22 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 25 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Map 30 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 1 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) Stage-0 Fetch Operator @@ -125,166 +137,281 @@ Stage-0 Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_89] (rows=77303902 width=321) predicate:(_col3 > _col4) - Merge Join Operator [MERGEJOIN_154] (rows=231911707 width=321) + Merge Join Operator [MERGEJOIN_286] (rows=231911707 width=321) Conds:(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 15 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_192] - Select Operator [SEL_191] (rows=1 width=232) + PARTITION_ONLY_SHUFFLE [RS_376] + Select Operator [SEL_375] (rows=1 width=232) Output:["_col0"] - Group By Operator [GBY_190] (rows=1 width=232) + Group By Operator [GBY_374] (rows=1 width=232) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"] <-Reducer 14 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_189] - Group By Operator [GBY_188] (rows=1 width=232) + PARTITION_ONLY_SHUFFLE [RS_373] + Group By Operator [GBY_372] (rows=1 width=232) Output:["_col0","_col1"],aggregations:["sum(_col10)","count(_col10)"] - Select Operator [SEL_187] (rows=463823414 width=88) + Select Operator [SEL_371] (rows=463823414 width=88) Output:["_col10"] - Group By Operator [GBY_186] (rows=463823414 width=88) + Group By Operator [GBY_370] (rows=463823414 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9 <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_78] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Group By Operator [GBY_77] (rows=927646829 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col4)"],keys:_col11, _col12, _col6, _col8, _col15, _col16, _col17, _col18, _col19, _col22 - Merge Join Operator [MERGEJOIN_153] (rows=927646829 width=88) - Conds:RS_73._col9, _col13=RS_180._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col8","_col11","_col12","_col15","_col16","_col17","_col18","_col19","_col22"] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_180] + Merge Join Operator [MERGEJOIN_285] (rows=927646829 width=88) + Conds:RS_73._col9, _col13=RS_351._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col8","_col11","_col12","_col15","_col16","_col17","_col18","_col19","_col22"] + <-Map 30 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_351] PartitionCols:_col1, upper(_col2) - Select Operator [SEL_178] (rows=40000000 width=1014) + Select Operator [SEL_349] (rows=40000000 width=1014) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_177] (rows=40000000 width=1014) + Filter Operator [FIL_348] (rows=40000000 width=1014) predicate:(ca_zip is not null and upper(ca_country) is not null) TableScan [TS_15] (rows=40000000 width=1014) default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_state","ca_zip","ca_country"] <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_73] PartitionCols:_col9, _col13 - Merge Join Operator [MERGEJOIN_152] (rows=843315281 width=88) - Conds:RS_70._col0, _col3=RS_176._col0, _col1(Inner),Output:["_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"] - <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_176] + Merge Join Operator [MERGEJOIN_284] (rows=843315281 width=88) + Conds:RS_70._col0, _col3=RS_330._col0, _col1(Inner),Output:["_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_330] PartitionCols:_col0, _col1 - Select Operator [SEL_174] (rows=57591150 width=77) + Select Operator [SEL_326] (rows=57591150 width=77) Output:["_col0","_col1"] - Filter Operator [FIL_173] (rows=57591150 width=77) + Filter Operator [FIL_325] (rows=57591150 width=77) predicate:(sr_item_sk is not null and sr_ticket_number is not null) TableScan [TS_12] (rows=57591150 width=77) default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_70] PartitionCols:_col0, _col3 - Merge Join Operator [MERGEJOIN_151] (rows=766650239 width=88) - Conds:RS_67._col0=RS_164._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_164] + Merge Join Operator [MERGEJOIN_283] (rows=766650239 width=88) + Conds:RS_67._col0=RS_293._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_293] PartitionCols:_col0 - Select Operator [SEL_162] (rows=462000 width=1436) + Select Operator [SEL_290] (rows=462000 width=1436) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_160] (rows=462000 width=1436) + Filter Operator [FIL_288] (rows=462000 width=1436) predicate:i_item_sk is not null TableScan [TS_3] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"] - <-Reducer 10 [SIMPLE_EDGE] + <-Reducer 20 [SIMPLE_EDGE] SHUFFLE [RS_67] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_150] (rows=696954748 width=88) - Conds:RS_64._col1=RS_172._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13"] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_172] + Merge Join Operator [MERGEJOIN_282] (rows=696954748 width=88) + Conds:RS_64._col1=RS_317._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_317] PartitionCols:_col0 - Select Operator [SEL_170] (rows=80000000 width=860) + Select Operator [SEL_314] (rows=80000000 width=860) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_169] (rows=80000000 width=860) + Filter Operator [FIL_313] (rows=80000000 width=860) predicate:(c_birth_country is not null and c_customer_sk is not null) TableScan [TS_9] (rows=80000000 width=860) default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name","c_birth_country"] - <-Reducer 9 [SIMPLE_EDGE] + <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_64] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_149] (rows=633595212 width=88) - Conds:RS_158._col2=RS_168._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col8","_col9"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_158] - PartitionCols:_col2 - Select Operator [SEL_156] (rows=575995635 width=88) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_155] (rows=575995635 width=88) - predicate:(ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] + Merge Join Operator [MERGEJOIN_281] (rows=633595212 width=88) + Conds:RS_369._col2=RS_305._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col8","_col9"] <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_168] + SHUFFLE [RS_305] PartitionCols:_col0 - Select Operator [SEL_166] (rows=852 width=1910) + Select Operator [SEL_302] (rows=852 width=1910) Output:["_col0","_col1","_col3","_col4"] - Filter Operator [FIL_165] (rows=852 width=1910) + Filter Operator [FIL_301] (rows=852 width=1910) predicate:((s_market_id = 7) and s_store_sk is not null and s_zip is not null) TableScan [TS_6] (rows=1704 width=1910) default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"] + <-Map 31 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_369] + PartitionCols:_col2 + Select Operator [SEL_368] (rows=575995635 width=88) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_367] (rows=575995635 width=88) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_65_customer_c_customer_sk_min) AND DynamicValue(RS_65_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_65_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_68_item_i_item_sk_min) AND DynamicValue(RS_68_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_68_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_71_store_returns_sr_item_sk_min) AND DynamicValue(RS_71_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_71_store_returns_sr_item_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_62_store_s_store_sk_min) AND DynamicValue(RS_62_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_62_store_s_store_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_71_store_returns_sr_ticket_number_min) AND DynamicValue(RS_71_stor e_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_71_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_43] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_362] + Group By Operator [GBY_361] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_298] + Group By Operator [GBY_296] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_294] (rows=462000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_290] + <-Reducer 21 [BROADCAST_EDGE] vectorized + BROADCAST [RS_358] + Group By Operator [GBY_357] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_310] + Group By Operator [GBY_308] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_306] (rows=852 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_302] + <-Reducer 24 [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=80000000)"] + <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_322] + Group By Operator [GBY_320] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] + Select Operator [SEL_318] (rows=80000000 width=860) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_314] + <-Reducer 28 [BROADCAST_EDGE] vectorized + BROADCAST [RS_364] + Group By Operator [GBY_363] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] + <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_339] + Group By Operator [GBY_335] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] + Select Operator [SEL_331] (rows=57591150 width=77) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_326] + <-Reducer 29 [BROADCAST_EDGE] vectorized + BROADCAST [RS_366] + Group By Operator [GBY_365] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] + <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_340] + Group By Operator [GBY_336] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] + Select Operator [SEL_332] (rows=57591150 width=77) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_326] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_185] - Select Operator [SEL_184] (rows=231911707 width=88) + PARTITION_ONLY_SHUFFLE [RS_356] + Select Operator [SEL_355] (rows=231911707 width=88) Output:["_col0","_col1","_col2","_col3"] - Group By Operator [GBY_183] (rows=231911707 width=88) + Group By Operator [GBY_354] (rows=231911707 width=88) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col9)"],keys:_col1, _col2, _col7 - Select Operator [SEL_182] (rows=463823414 width=88) + Select Operator [SEL_353] (rows=463823414 width=88) Output:["_col1","_col2","_col7","_col9"] - Group By Operator [GBY_181] (rows=463823414 width=88) + Group By Operator [GBY_352] (rows=463823414 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_34] (rows=927646829 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col17, _col18, _col12, _col22, _col6, _col7, _col9, _col10, _col14 - Merge Join Operator [MERGEJOIN_148] (rows=927646829 width=88) - Conds:RS_30._col15, _col19=RS_179._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col17","_col18","_col22"] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_179] + Merge Join Operator [MERGEJOIN_280] (rows=927646829 width=88) + Conds:RS_30._col15, _col19=RS_350._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col17","_col18","_col22"] + <-Map 30 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_350] PartitionCols:_col1, upper(_col2) - Please refer to the previous Select Operator [SEL_178] + Please refer to the previous Select Operator [SEL_349] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col15, _col19 - Merge Join Operator [MERGEJOIN_147] (rows=843315281 width=88) - Conds:RS_27._col0, _col3=RS_175._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"] - <-Map 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_175] + Merge Join Operator [MERGEJOIN_279] (rows=843315281 width=88) + Conds:RS_27._col0, _col3=RS_327._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"] + <-Map 25 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_327] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_174] + Please refer to the previous Select Operator [SEL_326] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col0, _col3 - Merge Join Operator [MERGEJOIN_146] (rows=766650239 width=88) - Conds:RS_24._col1=RS_171._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_171] + Merge Join Operator [MERGEJOIN_278] (rows=766650239 width=88) + Conds:RS_24._col1=RS_315._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_315] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_170] + Please refer to the previous Select Operator [SEL_314] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_145] (rows=696954748 width=88) - Conds:RS_21._col2=RS_167._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15"] + Merge Join Operator [MERGEJOIN_277] (rows=696954748 width=88) + Conds:RS_21._col2=RS_303._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15"] <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_167] + SHUFFLE [RS_303] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_166] + Please refer to the previous Select Operator [SEL_302] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_144] (rows=633595212 width=88) - Conds:RS_157._col0=RS_163._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col10"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_157] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_156] - <-Map 16 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_163] + Merge Join Operator [MERGEJOIN_276] (rows=633595212 width=88) + Conds:RS_347._col0=RS_291._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col10"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_291] PartitionCols:_col0 - Select Operator [SEL_161] (rows=231000 width=1436) + Select Operator [SEL_289] (rows=231000 width=1436) Output:["_col0","_col1","_col2","_col4","_col5"] - Filter Operator [FIL_159] (rows=231000 width=1436) + Filter Operator [FIL_287] (rows=231000 width=1436) predicate:((i_color = 'orchid') and i_item_sk is not null) Please refer to the previous TableScan [TS_3] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_347] + PartitionCols:_col0 + Select Operator [SEL_346] (rows=575995635 width=88) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_345] (rows=575995635 width=88) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_25_customer_c_customer_sk_min) AND DynamicValue(RS_25_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_25_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_19_item_i_item_sk_min) AND DynamicValue(RS_19_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_19_item_i_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_28_store_returns_sr_item_sk_min) AND DynamicValue(RS_28_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_28_store_returns_sr_item_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_ticket_number BETWEEN DynamicValue(RS_28_store_returns_sr_ticket_number_min) AND DynamicValue(RS_28_store_re turns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_28_store_returns_sr_ticket_number_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + TableScan [TS_0] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_300] + Group By Operator [GBY_299] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_297] + Group By Operator [GBY_295] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_292] (rows=231000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_289] + <-Reducer 18 [BROADCAST_EDGE] vectorized + BROADCAST [RS_312] + Group By Operator [GBY_311] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 17 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_309] + Group By Operator [GBY_307] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_304] (rows=852 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_302] + <-Reducer 23 [BROADCAST_EDGE] vectorized + BROADCAST [RS_324] + Group By Operator [GBY_323] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=80000000)"] + <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_321] + Group By Operator [GBY_319] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=80000000)"] + Select Operator [SEL_316] (rows=80000000 width=860) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_314] + <-Reducer 26 [BROADCAST_EDGE] vectorized + BROADCAST [RS_342] + Group By Operator [GBY_341] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] + <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_337] + Group By Operator [GBY_333] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] + Select Operator [SEL_328] (rows=57591150 width=77) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_326] + <-Reducer 27 [BROADCAST_EDGE] vectorized + BROADCAST [RS_344] + Group By Operator [GBY_343] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=57591152)"] + <-Map 25 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_338] + Group By Operator [GBY_334] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=57591152)"] + Select Operator [SEL_329] (rows=57591150 width=77) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_326]
http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query25.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query25.q.out b/ql/src/test/results/clientpositive/perf/tez/query25.q.out index 9af27f8..a885cf3 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query25.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query25.q.out @@ -95,135 +95,212 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Reducer 11 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 13 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Map 1 <- Reducer 19 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 16 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE) +Reducer 10 <- Map 16 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) +Reducer 12 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Map 17 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 14 <- Reducer 13 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Reducer 13 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 15 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE) +Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 18 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 20 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_130] - Limit [LIM_129] (rows=100 width=88) + File Output Operator [FS_259] + Limit [LIM_258] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_128] (rows=421657640 width=88) + Select Operator [SEL_257] (rows=421657640 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_127] - Group By Operator [GBY_126] (rows=421657640 width=88) + SHUFFLE [RS_256] + Group By Operator [GBY_255] (rows=421657640 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_48] (rows=843315281 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col5)","sum(_col20)","sum(_col12)"],keys:_col25, _col26, _col28, _col29 - Merge Join Operator [MERGEJOIN_101] (rows=843315281 width=88) - Conds:RS_44._col3=RS_125._col0(Inner),Output:["_col5","_col12","_col20","_col25","_col26","_col28","_col29"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_125] + Merge Join Operator [MERGEJOIN_205] (rows=843315281 width=88) + Conds:RS_44._col3=RS_234._col0(Inner),Output:["_col5","_col12","_col20","_col25","_col26","_col28","_col29"] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_234] PartitionCols:_col0 - Select Operator [SEL_124] (rows=1704 width=1910) + Select Operator [SEL_233] (rows=1704 width=1910) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_123] (rows=1704 width=1910) + Filter Operator [FIL_232] (rows=1704 width=1910) predicate:s_store_sk is not null TableScan [TS_32] (rows=1704 width=1910) default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_100] (rows=766650239 width=88) - Conds:RS_41._col1=RS_122._col0(Inner),Output:["_col3","_col5","_col12","_col20","_col25","_col26"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_122] + Merge Join Operator [MERGEJOIN_204] (rows=766650239 width=88) + Conds:RS_41._col1=RS_225._col0(Inner),Output:["_col3","_col5","_col12","_col20","_col25","_col26"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_225] PartitionCols:_col0 - Select Operator [SEL_121] (rows=462000 width=1436) + Select Operator [SEL_224] (rows=462000 width=1436) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_120] (rows=462000 width=1436) + Filter Operator [FIL_223] (rows=462000 width=1436) predicate:i_item_sk is not null TableScan [TS_29] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_99] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_203] (rows=696954748 width=88) Conds:RS_38._col1, _col2, _col4=RS_39._col8, _col9, _col10(Inner),Output:["_col1","_col3","_col5","_col12","_col20"] - <-Reducer 10 [SIMPLE_EDGE] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col8, _col9, _col10 - Merge Join Operator [MERGEJOIN_98] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_202] (rows=348467716 width=135) Conds:RS_25._col2, _col1=RS_26._col1, _col2(Inner),Output:["_col3","_col8","_col9","_col10","_col11"] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_26] + <-Reducer 13 [SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_26] PartitionCols:_col1, _col2 - Merge Join Operator [MERGEJOIN_97] (rows=63350266 width=77) - Conds:RS_119._col0=RS_113._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_201] (rows=63350266 width=77) + Conds:RS_247._col0=RS_216._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_113] + PARTITION_ONLY_SHUFFLE [RS_216] PartitionCols:_col0 - Select Operator [SEL_110] (rows=4058 width=1119) + Select Operator [SEL_211] (rows=4058 width=1119) Output:["_col0"] - Filter Operator [FIL_107] (rows=4058 width=1119) + Filter Operator [FIL_208] (rows=4058 width=1119) predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) TableScan [TS_3] (rows=73049 width=1119) default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_119] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_247] PartitionCols:_col0 - Select Operator [SEL_118] (rows=57591150 width=77) + Select Operator [SEL_246] (rows=57591150 width=77) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_117] (rows=57591150 width=77) + Filter Operator [FIL_245] (rows=57591150 width=77) predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) TableScan [TS_12] (rows=57591150 width=77) default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_net_loss"] - <-Reducer 9 [SIMPLE_EDGE] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col2, _col1 - Merge Join Operator [MERGEJOIN_96] (rows=316788826 width=135) - Conds:RS_116._col0=RS_112._col0(Inner),Output:["_col1","_col2","_col3"] + Merge Join Operator [MERGEJOIN_200] (rows=316788826 width=135) + Conds:RS_254._col0=RS_214._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] + PARTITION_ONLY_SHUFFLE [RS_214] PartitionCols:_col0 - Select Operator [SEL_109] (rows=4058 width=1119) + Select Operator [SEL_210] (rows=4058 width=1119) Output:["_col0"] - Filter Operator [FIL_106] (rows=4058 width=1119) + Filter Operator [FIL_207] (rows=4058 width=1119) predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) Please refer to the previous TableScan [TS_3] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_116] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_254] PartitionCols:_col0 - Select Operator [SEL_115] (rows=287989836 width=135) + Select Operator [SEL_253] (rows=287989836 width=135) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_114] (rows=287989836 width=135) - predicate:(cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + Filter Operator [FIL_252] (rows=287989836 width=135) + predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_42_item_i_item_sk_min) AND DynamicValue(RS_42_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_42_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_23_d3_d_date_sk_min) AND DynamicValue(RS_23_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_23_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) TableScan [TS_6] (rows=287989836 width=135) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_net_profit"] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_231] + Group By Operator [GBY_229] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_228] + Group By Operator [GBY_227] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_226] (rows=462000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_224] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_244] + Group By Operator [GBY_243] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_220] + Group By Operator [GBY_218] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_215] (rows=4058 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_210] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_249] + Group By Operator [GBY_248] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + <-Reducer 13 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_137] + Group By Operator [GBY_136] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] + Select Operator [SEL_135] (rows=63350266 width=77) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_201] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_251] + Group By Operator [GBY_250] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"] + <-Reducer 13 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_142] + Group By Operator [GBY_141] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"] + Select Operator [SEL_140] (rows=63350266 width=77) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_201] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col1, _col2, _col4 - Merge Join Operator [MERGEJOIN_95] (rows=633595212 width=88) - Conds:RS_104._col0=RS_111._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Merge Join Operator [MERGEJOIN_199] (rows=633595212 width=88) + Conds:RS_242._col0=RS_212._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_111] + PARTITION_ONLY_SHUFFLE [RS_212] PartitionCols:_col0 - Select Operator [SEL_108] (rows=18262 width=1119) + Select Operator [SEL_209] (rows=18262 width=1119) Output:["_col0"] - Filter Operator [FIL_105] (rows=18262 width=1119) + Filter Operator [FIL_206] (rows=18262 width=1119) predicate:((d_moy = 4) and (d_year = 2000) and d_date_sk is not null) Please refer to the previous TableScan [TS_3] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_104] + SHUFFLE [RS_242] PartitionCols:_col0 - Select Operator [SEL_103] (rows=575995635 width=88) + Select Operator [SEL_241] (rows=575995635 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_102] (rows=575995635 width=88) - predicate:(ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) + Filter Operator [FIL_240] (rows=575995635 width=88) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_42_item_i_item_sk_min) AND DynamicValue(RS_42_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_42_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_36_d1_d_date_sk_min) AND DynamicValue(RS_36_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_36_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_45_store_s_store_sk_min) AND DynamicValue(RS_45_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_45_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) TableScan [TS_0] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_net_profit"] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_230] + Please refer to the previous Group By Operator [GBY_229] + <-Reducer 21 [BROADCAST_EDGE] vectorized + BROADCAST [RS_239] + Group By Operator [GBY_238] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_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=1704 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_233] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_222] + Group By Operator [GBY_221] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_219] + Group By Operator [GBY_217] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_213] (rows=18262 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_209] http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query26.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query26.q.out b/ql/src/test/results/clientpositive/perf/tez/query26.q.out index f113113..0c6c0f8 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query26.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query26.q.out @@ -41,94 +41,143 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage +Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 9 (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), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 11 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) +Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_79] - Limit [LIM_78] (rows=100 width=135) + File Output Operator [FS_139] + Limit [LIM_138] (rows=100 width=135) Number of rows:100 - Select Operator [SEL_77] (rows=210822976 width=135) + Select Operator [SEL_137] (rows=210822976 width=135) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_76] - Select Operator [SEL_75] (rows=210822976 width=135) + SHUFFLE [RS_136] + Select Operator [SEL_135] (rows=210822976 width=135) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_74] (rows=210822976 width=135) + Group By Operator [GBY_134] (rows=210822976 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)"],keys:KEY._col0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col0 Group By Operator [GBY_28] (rows=421645953 width=135) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col18 - Merge Join Operator [MERGEJOIN_58] (rows=421645953 width=135) - Conds:RS_24._col2=RS_73._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_73] + Merge Join Operator [MERGEJOIN_98] (rows=421645953 width=135) + Conds:RS_24._col2=RS_125._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_125] PartitionCols:_col0 - Select Operator [SEL_72] (rows=462000 width=1436) + Select Operator [SEL_124] (rows=462000 width=1436) Output:["_col0","_col1"] - Filter Operator [FIL_71] (rows=462000 width=1436) + Filter Operator [FIL_123] (rows=462000 width=1436) predicate:i_item_sk is not null TableScan [TS_12] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_57] (rows=383314495 width=135) - Conds:RS_21._col3=RS_70._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_70] + Merge Join Operator [MERGEJOIN_97] (rows=383314495 width=135) + Conds:RS_21._col3=RS_117._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_117] PartitionCols:_col0 - Select Operator [SEL_69] (rows=2300 width=1179) + Select Operator [SEL_116] (rows=2300 width=1179) Output:["_col0"] - Filter Operator [FIL_68] (rows=2300 width=1179) + Filter Operator [FIL_115] (rows=2300 width=1179) predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) TableScan [TS_9] (rows=2300 width=1179) default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_email","p_channel_event"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_21] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_56] (rows=348467716 width=135) - Conds:RS_18._col0=RS_67._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_67] + Merge Join Operator [MERGEJOIN_96] (rows=348467716 width=135) + Conds:RS_18._col0=RS_109._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_109] PartitionCols:_col0 - Select Operator [SEL_66] (rows=36524 width=1119) + Select Operator [SEL_108] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_65] (rows=36524 width=1119) + Filter Operator [FIL_107] (rows=36524 width=1119) predicate:((d_year = 1998) 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"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_55] (rows=316788826 width=135) - Conds:RS_61._col1=RS_64._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_61] - PartitionCols:_col1 - Select Operator [SEL_60] (rows=287989836 width=135) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_59] (rows=287989836 width=135) - predicate:(cs_bill_cdemo_sk is not null and cs_item_sk is not null and cs_promo_sk is not null and cs_sold_date_sk is not null) - TableScan [TS_0] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_cdemo_sk","cs_item_sk","cs_promo_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt"] + Merge Join Operator [MERGEJOIN_95] (rows=316788826 width=135) + Conds:RS_133._col1=RS_101._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_64] + PARTITION_ONLY_SHUFFLE [RS_101] PartitionCols:_col0 - Select Operator [SEL_63] (rows=232725 width=385) + Select Operator [SEL_100] (rows=232725 width=385) Output:["_col0"] - Filter Operator [FIL_62] (rows=232725 width=385) + Filter Operator [FIL_99] (rows=232725 width=385) predicate:((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) TableScan [TS_3] (rows=1861800 width=385) default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_133] + PartitionCols:_col1 + Select Operator [SEL_132] (rows=287989836 width=135) + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + Filter Operator [FIL_131] (rows=287989836 width=135) + predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (cs_promo_sk BETWEEN DynamicValue(RS_22_promotion_p_promo_sk_min) AND DynamicValue(RS_22_promotion_p_promo_sk_max) and in_bloom_filter(cs_promo_sk, DynamicValue(RS_22_promotion_p_promo_sk_bloom_filter))) and (cs_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(cs_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_item_sk is not null and cs_promo_sk is not null and cs_sold_date_sk is not null) + TableScan [TS_0] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_cdemo_sk","cs_item_sk","cs_promo_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt"] + <-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=36524 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_108] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_122] + Group By Operator [GBY_121] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_120] + Group By Operator [GBY_119] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_118] (rows=2300 width=1179) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_116] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_130] + Group By Operator [GBY_129] (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_128] + Group By Operator [GBY_127] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_126] (rows=462000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_124] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_106] + Group By Operator [GBY_105] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_104] + Group By Operator [GBY_103] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_102] (rows=232725 width=385) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_100]
