http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/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 0a0cfcc..bd45617 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query25.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query25.q.out @@ -109,20 +109,16 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 12 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Map 18 <- Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) -Reducer 10 <- Map 18 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 12 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 19 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 9 (BROADCAST_EDGE) +Map 14 <- Reducer 12 (BROADCAST_EDGE) +Reducer 10 <- Map 14 (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 15 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 20 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 21 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 16 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 17 (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) @@ -132,14 +128,14 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_263] - Limit [LIM_262] (rows=100 width=808) + File Output Operator [FS_253] + Limit [LIM_252] (rows=100 width=808) Number of rows:100 - Select Operator [SEL_261] (rows=4248052806 width=808) + Select Operator [SEL_251] (rows=4248052806 width=808) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_260] - Group By Operator [GBY_259] (rows=4248052806 width=808) + SHUFFLE [RS_250] + Group By Operator [GBY_249] (rows=4248052806 width=808) 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] @@ -149,13 +145,13 @@ Stage-0 Top N Key Operator [TNK_95] (rows=4248052806 width=807) keys:_col19, _col20, _col22, _col23,sort order:++++,top n:100 Merge Join Operator [MERGEJOIN_214] (rows=4248052806 width=807) - Conds:RS_44._col3=RS_258._col0(Inner),Output:["_col5","_col10","_col16","_col19","_col20","_col22","_col23"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_258] + Conds:RS_44._col3=RS_248._col0(Inner),Output:["_col5","_col10","_col16","_col19","_col20","_col22","_col23"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_248] PartitionCols:_col0 - Select Operator [SEL_257] (rows=1704 width=192) + Select Operator [SEL_247] (rows=1704 width=192) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_256] (rows=1704 width=192) + Filter Operator [FIL_246] (rows=1704 width=192) predicate:s_store_sk is not null TableScan [TS_32] (rows=1704 width=192) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] @@ -163,13 +159,13 @@ Stage-0 SHUFFLE [RS_44] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_213] (rows=4248052806 width=623) - Conds:RS_41._col1=RS_255._col0(Inner),Output:["_col3","_col5","_col10","_col16","_col19","_col20"] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_255] + Conds:RS_41._col1=RS_245._col0(Inner),Output:["_col3","_col5","_col10","_col16","_col19","_col20"] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_245] PartitionCols:_col0 - Select Operator [SEL_254] (rows=462000 width=288) + Select Operator [SEL_244] (rows=462000 width=288) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_253] (rows=462000 width=288) + Filter Operator [FIL_243] (rows=462000 width=288) predicate:i_item_sk is not null TableScan [TS_29] (rows=462000 width=288) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] @@ -184,10 +180,10 @@ Stage-0 Merge Join Operator [MERGEJOIN_211] (rows=1893811716 width=235) Conds:RS_25._col2, _col1=RS_26._col1, _col2(Inner),Output:["_col3","_col6","_col7","_col8","_col9"] <-Reducer 10 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_25] + SHUFFLE [RS_25] PartitionCols:_col2, _col1 Merge Join Operator [MERGEJOIN_209] (rows=54418158 width=119) - Conds:RS_245._col0=RS_223._col0(Inner),Output:["_col1","_col2","_col3"] + Conds:RS_239._col0=RS_223._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_223] PartitionCols:_col0 @@ -197,59 +193,19 @@ Stage-0 predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) TableScan [TS_3] (rows=73049 width=12) default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_245] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_239] PartitionCols:_col0 - Select Operator [SEL_244] (rows=285117831 width=123) + Select Operator [SEL_238] (rows=285117831 width=123) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_243] (rows=285117831 width=123) - 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_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) + Filter Operator [FIL_237] (rows=285117831 width=123) + predicate:((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=123) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_net_profit"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_237] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_236] Group By Operator [GBY_235] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_108] - Group By Operator [GBY_107] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_106] (rows=9402909 width=8) - Output:["_col0"] - Merge Join Operator [MERGEJOIN_210] (rows=9402909 width=100) - Conds:RS_234._col0=RS_225._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_225] - PartitionCols:_col0 - Select Operator [SEL_220] (rows=351 width=4) - Output:["_col0"] - Filter Operator [FIL_217] (rows=351 width=12) - 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 19 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_234] - PartitionCols:_col0 - Select Operator [SEL_233] (rows=53632139 width=123) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_232] (rows=53632139 width=123) - 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=123) - default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_net_loss"] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_242] - Group By Operator [GBY_240] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 15 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_123] - Group By Operator [GBY_122] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_121] (rows=9402909 width=6) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_210] - <-Reducer 14 [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 8 [CUSTOM_SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_229] Group By Operator [GBY_227] (rows=1 width=12) @@ -257,15 +213,33 @@ Stage-0 Select Operator [SEL_224] (rows=351 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_219] - <-Reducer 15 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_26] + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_26] PartitionCols:_col1, _col2 - Please refer to the previous Merge Join Operator [MERGEJOIN_210] + Merge Join Operator [MERGEJOIN_210] (rows=9402909 width=100) + Conds:RS_242._col0=RS_225._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_225] + PartitionCols:_col0 + Select Operator [SEL_220] (rows=351 width=4) + Output:["_col0"] + Filter Operator [FIL_217] (rows=351 width=12) + 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 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_242] + PartitionCols:_col0 + Select Operator [SEL_241] (rows=53632139 width=123) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_240] (rows=53632139 width=123) + 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=123) + default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_net_loss"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:_col1, _col2, _col4 Merge Join Operator [MERGEJOIN_208] (rows=13737330 width=8) - Conds:RS_252._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + Conds:RS_234._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_221] PartitionCols:_col0 @@ -275,42 +249,14 @@ Stage-0 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_252] + SHUFFLE [RS_234] PartitionCols:_col0 - Select Operator [SEL_251] (rows=501694138 width=126) + Select Operator [SEL_233] (rows=501694138 width=126) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_250] (rows=501694138 width=126) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_25_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_25_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_25_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_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(ss_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_25_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_25_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_catalog_sales_cs_item_sk_bloom_filter))) and (ss_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(ss_item_sk, DynamicValue(RS_26_store_returns_sr_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_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_232] (rows=501694138 width=126) + predicate:((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_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=126) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_net_profit"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_236] - Please refer to the previous Group By Operator [GBY_235] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_241] - Please refer to the previous Group By Operator [GBY_240] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_247] - Group By Operator [GBY_246] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 10 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_113] - Group By Operator [GBY_112] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_111] (rows=54418158 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_209] - <-Reducer 13 [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=1000000)"] - <-Reducer 10 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_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=54418158 width=7) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_209] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_231] Group By Operator [GBY_230] (rows=1 width=12)
http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/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 62bcbe8..da448c6 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query26.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query26.q.out @@ -53,12 +53,11 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 9 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (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 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 12 (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) @@ -68,16 +67,16 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_130] - Limit [LIM_129] (rows=100 width=444) + File Output Operator [FS_125] + Limit [LIM_124] (rows=100 width=444) Number of rows:100 - Select Operator [SEL_128] (rows=310774 width=444) + Select Operator [SEL_123] (rows=310774 width=444) Output:["_col0","_col1","_col2","_col3","_col4"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_127] - Select Operator [SEL_126] (rows=310774 width=444) + SHUFFLE [RS_122] + Select Operator [SEL_121] (rows=310774 width=444) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_125] (rows=310774 width=476) + Group By Operator [GBY_120] (rows=310774 width=476) 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] @@ -87,13 +86,13 @@ Stage-0 Top N Key Operator [TNK_55] (rows=809521 width=100) keys:_col12,sort order:+,top n:100 Merge Join Operator [MERGEJOIN_99] (rows=809521 width=100) - Conds:RS_24._col2=RS_124._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col12"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_124] + Conds:RS_24._col2=RS_119._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col12"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_119] PartitionCols:_col0 - Select Operator [SEL_123] (rows=462000 width=104) + Select Operator [SEL_118] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_122] (rows=462000 width=104) + Filter Operator [FIL_117] (rows=462000 width=104) predicate:i_item_sk is not null TableScan [TS_12] (rows=462000 width=104) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] @@ -101,13 +100,13 @@ Stage-0 SHUFFLE [RS_24] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_98] (rows=809521 width=4) - Conds:RS_21._col3=RS_121._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_121] + Conds:RS_21._col3=RS_116._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_116] PartitionCols:_col0 - Select Operator [SEL_120] (rows=2300 width=4) + Select Operator [SEL_115] (rows=2300 width=4) Output:["_col0"] - Filter Operator [FIL_119] (rows=2300 width=174) + Filter Operator [FIL_114] (rows=2300 width=174) predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) TableScan [TS_9] (rows=2300 width=174) default@promotion,promotion,Tbl:COMPLETE,Col:COMPLETE,Output:["p_promo_sk","p_channel_email","p_channel_event"] @@ -115,13 +114,13 @@ Stage-0 SHUFFLE [RS_21] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_97] (rows=809521 width=4) - Conds:RS_18._col0=RS_110._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7"] + Conds:RS_18._col0=RS_113._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_110] + SHUFFLE [RS_113] PartitionCols:_col0 - Select Operator [SEL_109] (rows=652 width=4) + Select Operator [SEL_112] (rows=652 width=4) Output:["_col0"] - Filter Operator [FIL_108] (rows=652 width=8) + Filter Operator [FIL_111] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=8) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] @@ -129,7 +128,7 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_96] (rows=2283326 width=135) - Conds:RS_118._col1=RS_102._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7"] + Conds:RS_110._col1=RS_102._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_102] PartitionCols:_col0 @@ -140,25 +139,14 @@ Stage-0 TableScan [TS_3] (rows=1861800 width=268) default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_118] + SHUFFLE [RS_110] PartitionCols:_col1 - Select Operator [SEL_117] (rows=283691050 width=354) + Select Operator [SEL_109] (rows=283691050 width=354) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_116] (rows=283691050 width=354) - 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_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) + Filter Operator [FIL_108] (rows=283691050 width=354) + 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_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=354) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,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_115] - Group By Operator [GBY_114] (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_113] - Group By Operator [GBY_112] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_111] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_109] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_107] Group By Operator [GBY_106] (rows=1 width=12) http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query27.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query27.q.out b/ql/src/test/results/clientpositive/perf/tez/query27.q.out index d7fd2ed..c9ab29f 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query27.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query27.q.out @@ -57,13 +57,11 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 9 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (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 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 12 (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) @@ -73,16 +71,16 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_136] - Limit [LIM_135] (rows=100 width=538) + File Output Operator [FS_126] + Limit [LIM_125] (rows=100 width=538) Number of rows:100 - Select Operator [SEL_134] (rows=4281825 width=538) + Select Operator [SEL_124] (rows=4281825 width=538) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_133] - Select Operator [SEL_132] (rows=4281825 width=538) + SHUFFLE [RS_123] + Select Operator [SEL_122] (rows=4281825 width=538) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Group By Operator [GBY_131] (rows=4281825 width=570) + Group By Operator [GBY_121] (rows=4281825 width=570) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],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, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_30] @@ -94,13 +92,13 @@ Stage-0 Select Operator [SEL_27] (rows=1427275 width=186) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] Merge Join Operator [MERGEJOIN_100] (rows=1427275 width=186) - Conds:RS_24._col1=RS_130._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col11","_col13"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_130] + Conds:RS_24._col1=RS_120._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col11","_col13"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_120] PartitionCols:_col0 - Select Operator [SEL_129] (rows=462000 width=104) + Select Operator [SEL_119] (rows=462000 width=104) Output:["_col0","_col1"] - Filter Operator [FIL_128] (rows=462000 width=104) + Filter Operator [FIL_118] (rows=462000 width=104) predicate:i_item_sk is not null TableScan [TS_12] (rows=462000 width=104) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id"] @@ -108,13 +106,13 @@ Stage-0 SHUFFLE [RS_24] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_99] (rows=1427275 width=90) - Conds:RS_21._col3=RS_119._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col11"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_119] + Conds:RS_21._col3=RS_117._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col11"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_117] PartitionCols:_col0 - Select Operator [SEL_118] (rows=209 width=90) + Select Operator [SEL_116] (rows=209 width=90) Output:["_col0","_col1"] - Filter Operator [FIL_117] (rows=209 width=90) + Filter Operator [FIL_115] (rows=209 width=90) predicate:((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') and s_store_sk is not null) TableScan [TS_9] (rows=1704 width=90) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"] @@ -122,13 +120,13 @@ Stage-0 SHUFFLE [RS_21] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_98] (rows=1441779 width=4) - Conds:RS_18._col0=RS_111._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] + Conds:RS_18._col0=RS_114._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_111] + SHUFFLE [RS_114] PartitionCols:_col0 - Select Operator [SEL_110] (rows=652 width=4) + Select Operator [SEL_113] (rows=652 width=4) Output:["_col0"] - Filter Operator [FIL_109] (rows=652 width=8) + Filter Operator [FIL_112] (rows=652 width=8) predicate:((d_year = 2001) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=8) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] @@ -136,7 +134,7 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_97] (rows=4037920 width=4) - Conds:RS_127._col2=RS_103._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] + Conds:RS_111._col2=RS_103._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_103] PartitionCols:_col0 @@ -147,36 +145,14 @@ Stage-0 TableScan [TS_3] (rows=1861800 width=268) default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_127] + SHUFFLE [RS_111] PartitionCols:_col2 - Select Operator [SEL_126] (rows=501690006 width=340) + Select Operator [SEL_110] (rows=501690006 width=340) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_125] (rows=501690006 width=340) - predicate:((ss_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(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (ss_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_cdemo_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) + Filter Operator [FIL_109] (rows=501690006 width=340) + predicate:((ss_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(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and ss_cdemo_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) TableScan [TS_0] (rows=575995635 width=340) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_cdemo_sk","ss_store_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"] - <-Reducer 11 [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 10 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_114] - Group By Operator [GBY_113] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_112] (rows=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_110] - <-Reducer 13 [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 12 [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=209 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_118] <-Reducer 9 [BROADCAST_EDGE] vectorized BROADCAST [RS_108] Group By Operator [GBY_107] (rows=1 width=12) http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query29.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query29.q.out b/ql/src/test/results/clientpositive/perf/tez/query29.q.out index 19f121e..71477d5 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query29.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query29.q.out @@ -107,38 +107,33 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 9 (BROADCAST_EDGE) -Map 10 <- Reducer 16 (BROADCAST_EDGE), Reducer 18 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) -Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE) -Reducer 13 <- Map 22 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 14 <- Map 23 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) -Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 15 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) -Reducer 18 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 20 <- Reducer 17 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Map 1 <- Reducer 7 (BROADCAST_EDGE) +Map 8 <- Reducer 14 (BROADCAST_EDGE) +Reducer 10 <- Reducer 15 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Map 17 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) +Reducer 12 <- Map 18 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 13 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 3 <- Reducer 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 13 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 5 vectorized - File Output Operator [FS_254] - Limit [LIM_253] (rows=100 width=496) + File Output Operator [FS_244] + Limit [LIM_243] (rows=100 width=496) Number of rows:100 - Select Operator [SEL_252] (rows=21091879 width=496) + Select Operator [SEL_242] (rows=21091879 width=496) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_251] - Group By Operator [GBY_250] (rows=21091879 width=496) + SHUFFLE [RS_241] + Group By Operator [GBY_240] (rows=21091879 width=496) 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 3 [SIMPLE_EDGE] SHUFFLE [RS_49] @@ -149,81 +144,47 @@ Stage-0 keys:_col6, _col7, _col22, _col23,sort order:++++,top n:100 Merge Join Operator [MERGEJOIN_205] (rows=4156223234 width=483) Conds:RS_44._col2, _col1=RS_45._col11, _col12(Inner),Output:["_col3","_col6","_col7","_col13","_col19","_col22","_col23"] - <-Reducer 2 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_44] - PartitionCols:_col2, _col1 - Merge Join Operator [MERGEJOIN_199] (rows=7638375 width=10) - Conds:RS_216._col0=RS_208._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_208] - PartitionCols:_col0 - Select Operator [SEL_207] (rows=1957 width=4) - Output:["_col0"] - Filter Operator [FIL_206] (rows=1957 width=8) - predicate:((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=8) - default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_216] - PartitionCols:_col0 - Select Operator [SEL_215] (rows=285117831 width=15) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_214] (rows=285117831 width=15) - predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_42_d3_d_date_sk_min) AND DynamicValue(RS_42_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_42_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_0] (rows=287989836 width=15) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] - <-Reducer 9 [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 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_211] - Group By Operator [GBY_210] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_209] (rows=1957 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_207] - <-Reducer 14 [SIMPLE_EDGE] + <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_45] PartitionCols:_col11, _col12 Select Operator [SEL_40] (rows=21091879 width=484) Output:["_col1","_col2","_col8","_col11","_col12","_col14","_col17","_col18"] Merge Join Operator [MERGEJOIN_204] (rows=21091879 width=484) - Conds:RS_37._col3=RS_249._col0(Inner),Output:["_col5","_col8","_col9","_col11","_col14","_col15","_col17","_col18"] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_249] + Conds:RS_37._col3=RS_239._col0(Inner),Output:["_col5","_col8","_col9","_col11","_col14","_col15","_col17","_col18"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_239] PartitionCols:_col0 - Select Operator [SEL_248] (rows=1704 width=192) + Select Operator [SEL_238] (rows=1704 width=192) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_247] (rows=1704 width=192) + Filter Operator [FIL_237] (rows=1704 width=192) predicate:s_store_sk is not null TableScan [TS_25] (rows=1704 width=192) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"] - <-Reducer 13 [SIMPLE_EDGE] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_37] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_203] (rows=21091879 width=298) - Conds:RS_34._col1=RS_246._col0(Inner),Output:["_col3","_col5","_col8","_col9","_col11","_col14","_col15"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_246] + Conds:RS_34._col1=RS_236._col0(Inner),Output:["_col3","_col5","_col8","_col9","_col11","_col14","_col15"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_236] PartitionCols:_col0 - Select Operator [SEL_245] (rows=462000 width=288) + Select Operator [SEL_235] (rows=462000 width=288) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_244] (rows=462000 width=288) + Filter Operator [FIL_234] (rows=462000 width=288) predicate:i_item_sk is not null TableScan [TS_22] (rows=462000 width=288) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc"] - <-Reducer 12 [SIMPLE_EDGE] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_202] (rows=21091879 width=18) Conds:RS_31._col1, _col2, _col4=RS_32._col1, _col2, _col3(Inner),Output:["_col1","_col3","_col5","_col8","_col9","_col11"] - <-Reducer 17 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_32] + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_32] PartitionCols:_col1, _col2, _col3 Merge Join Operator [MERGEJOIN_201] (rows=5384572 width=13) - Conds:RS_230._col0=RS_223._col0(Inner),Output:["_col1","_col2","_col3","_col4"] - <-Map 15 [SIMPLE_EDGE] vectorized + Conds:RS_233._col0=RS_223._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_223] PartitionCols:_col0 Select Operator [SEL_220] (rows=201 width=4) @@ -232,21 +193,21 @@ Stage-0 predicate:((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) TableScan [TS_9] (rows=73049 width=12) default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_230] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_233] PartitionCols:_col0 - Select Operator [SEL_229] (rows=53632139 width=19) + Select Operator [SEL_232] (rows=53632139 width=19) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_228] (rows=53632139 width=19) + Filter Operator [FIL_231] (rows=53632139 width=19) 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=19) default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_return_quantity"] - <-Reducer 11 [SIMPLE_EDGE] + <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_31] PartitionCols:_col1, _col2, _col4 Merge Join Operator [MERGEJOIN_200] (rows=13737330 width=8) - Conds:RS_243._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 15 [SIMPLE_EDGE] vectorized + Conds:RS_230._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] + <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_221] PartitionCols:_col0 Select Operator [SEL_219] (rows=50 width=4) @@ -254,79 +215,58 @@ Stage-0 Filter Operator [FIL_217] (rows=50 width=12) predicate:((d_moy = 4) and (d_year = 1999) and d_date_sk is not null) Please refer to the previous TableScan [TS_9] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_243] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_230] PartitionCols:_col0 - Select Operator [SEL_242] (rows=501694138 width=23) + Select Operator [SEL_229] (rows=501694138 width=23) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_241] (rows=501694138 width=23) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_32_store_returns_sr_customer_sk_min) AND DynamicValue(RS_32_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_32_store_returns_sr_customer_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_44_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_44_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_44_catalog_sales_cs_bill_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_32_store_returns_sr_item_sk_min) AND DynamicValue(RS_32_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_32_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_44_catalog_sales_cs_item_sk_min) AND DynamicValue(RS_44_catalog_sales_cs_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_44_catalog_sales_cs_item_sk_bloom_filter))) and (ss_sold_da te_sk BETWEEN DynamicValue(RS_29_d1_d_date_sk_min) AND DynamicValue(RS_29_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_29_d1_d_date_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_32_store_returns_sr_ticket_number_min) AND DynamicValue(RS_32_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_32_store_returns_sr_ticket_number_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) + Filter Operator [FIL_228] (rows=501694138 width=23) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_29_d1_d_date_sk_min) AND DynamicValue(RS_29_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_29_d1_d_date_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_6] (rows=575995635 width=23) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_quantity"] - <-Reducer 16 [BROADCAST_EDGE] vectorized + <-Reducer 14 [BROADCAST_EDGE] vectorized BROADCAST [RS_227] Group By Operator [GBY_226] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_225] Group By Operator [GBY_224] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] Select Operator [SEL_222] (rows=50 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_219] - <-Reducer 18 [BROADCAST_EDGE] vectorized - BROADCAST [RS_232] - Group By Operator [GBY_231] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 17 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_121] - Group By Operator [GBY_120] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_119] (rows=5384572 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_201] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_234] - Group By Operator [GBY_233] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 17 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_126] - Group By Operator [GBY_125] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_124] (rows=5384572 width=5) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_201] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_236] - Group By Operator [GBY_235] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=3507020)"] - <-Reducer 17 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_131] - Group By Operator [GBY_130] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=3507020)"] - Select Operator [SEL_129] (rows=5384572 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_201] - <-Reducer 6 [BROADCAST_EDGE] vectorized - BROADCAST [RS_238] - Group By Operator [GBY_237] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_146] - Group By Operator [GBY_145] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_144] (rows=7638375 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_199] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_240] - Group By Operator [GBY_239] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_151] - Group By Operator [GBY_150] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_149] (rows=7638375 width=6) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_199] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_44] + PartitionCols:_col2, _col1 + Merge Join Operator [MERGEJOIN_199] (rows=7638375 width=10) + Conds:RS_216._col0=RS_208._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 6 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_208] + PartitionCols:_col0 + Select Operator [SEL_207] (rows=1957 width=4) + Output:["_col0"] + Filter Operator [FIL_206] (rows=1957 width=8) + predicate:((d_year) IN (1999, 2000, 2001) and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_216] + PartitionCols:_col0 + Select Operator [SEL_215] (rows=285117831 width=15) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_214] (rows=285117831 width=15) + predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_42_d3_d_date_sk_min) AND DynamicValue(RS_42_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_42_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_0] (rows=287989836 width=15) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity"] + <-Reducer 7 [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 6 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_211] + Group By Operator [GBY_210] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_209] (rows=1957 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_207] http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query3.q.out b/ql/src/test/results/clientpositive/perf/tez/query3.q.out index e31c994..a647ab5 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query3.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query3.q.out @@ -49,27 +49,26 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 7 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 1 <- Reducer 7 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 5 vectorized - File Output Operator [FS_77] - Limit [LIM_76] (rows=100 width=220) + File Output Operator [FS_72] + Limit [LIM_71] (rows=100 width=220) Number of rows:100 - Select Operator [SEL_75] (rows=274400 width=220) + Select Operator [SEL_70] (rows=274400 width=220) Output:["_col0","_col1","_col2","_col3"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_74] - Group By Operator [GBY_73] (rows=274400 width=220) + SHUFFLE [RS_69] + Group By Operator [GBY_68] (rows=274400 width=220) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] @@ -77,13 +76,13 @@ Stage-0 Group By Operator [GBY_16] (rows=274400 width=220) Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col7, _col4, _col5 Merge Join Operator [MERGEJOIN_53] (rows=589741 width=108) - Conds:RS_12._col0=RS_64._col0(Inner),Output:["_col2","_col4","_col5","_col7"] + Conds:RS_12._col0=RS_67._col0(Inner),Output:["_col2","_col4","_col5","_col7"] <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_64] + SHUFFLE [RS_67] PartitionCols:_col0 - Select Operator [SEL_63] (rows=5619 width=8) + Select Operator [SEL_66] (rows=5619 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_62] (rows=5619 width=12) + Filter Operator [FIL_65] (rows=5619 width=12) predicate:((d_moy = 12) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=12) default@date_dim,dt,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] @@ -91,7 +90,7 @@ Stage-0 SHUFFLE [RS_12] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_52] (rows=7666836 width=104) - Conds:RS_72._col1=RS_56._col0(Inner),Output:["_col0","_col2","_col4","_col5"] + Conds:RS_64._col1=RS_56._col0(Inner),Output:["_col0","_col2","_col4","_col5"] <-Map 6 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_56] PartitionCols:_col0 @@ -102,12 +101,12 @@ Stage-0 TableScan [TS_3] (rows=462000 width=111) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand_id","i_brand","i_manufact_id"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_72] + SHUFFLE [RS_64] PartitionCols:_col1 - Select Operator [SEL_71] (rows=550076554 width=114) + Select Operator [SEL_63] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_70] (rows=550076554 width=114) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_10_item_i_item_sk_min) AND DynamicValue(RS_10_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_10_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_13_dt_d_date_sk_min) AND DynamicValue(RS_13_dt_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_dt_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) + Filter Operator [FIL_62] (rows=550076554 width=114) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_10_item_i_item_sk_min) AND DynamicValue(RS_10_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_10_item_i_item_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) TableScan [TS_0] (rows=575995635 width=114) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] <-Reducer 7 [BROADCAST_EDGE] vectorized @@ -121,15 +120,4 @@ Stage-0 Select Operator [SEL_57] (rows=669 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_55] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_69] - Group By Operator [GBY_68] (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_67] - Group By Operator [GBY_66] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_65] (rows=5619 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_63]