http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/constraints/query95.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query95.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query95.q.out index 4dc9cd8..0b0c9c5 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query95.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query95.q.out @@ -75,20 +75,18 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE) -Map 17 <- Reducer 10 (BROADCAST_EDGE) -Map 20 <- Reducer 10 (BROADCAST_EDGE) +Map 1 <- Reducer 13 (BROADCAST_EDGE) +Map 15 <- Reducer 10 (BROADCAST_EDGE) +Map 18 <- Reducer 10 (BROADCAST_EDGE) Reducer 10 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) -Reducer 19 <- Map 21 (SIMPLE_EDGE), Reducer 18 (ONE_TO_ONE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 18 (SIMPLE_EDGE) +Reducer 17 <- Map 19 (SIMPLE_EDGE), Reducer 16 (ONE_TO_ONE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) -Reducer 3 <- Map 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 18 (ONE_TO_ONE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 19 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) +Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 16 (ONE_TO_ONE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 17 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 7 (CUSTOM_SIMPLE_EDGE) Reducer 9 <- Reducer 8 (SIMPLE_EDGE) @@ -98,22 +96,22 @@ Stage-0 limit:-1 Stage-1 Reducer 9 vectorized - File Output Operator [FS_273] - Limit [LIM_272] (rows=1 width=240) + File Output Operator [FS_263] + Limit [LIM_262] (rows=1 width=240) Number of rows:100 - Select Operator [SEL_271] (rows=1 width=240) + Select Operator [SEL_261] (rows=1 width=240) Output:["_col0","_col1","_col2"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_270] - Select Operator [SEL_269] (rows=1 width=240) + SHUFFLE [RS_260] + Select Operator [SEL_259] (rows=1 width=240) Output:["_col1","_col2","_col3"] - Group By Operator [GBY_268] (rows=1 width=232) + Group By Operator [GBY_258] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_267] - Group By Operator [GBY_266] (rows=1 width=232) + PARTITION_ONLY_SHUFFLE [RS_257] + Group By Operator [GBY_256] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(_col0)","sum(_col1)","sum(_col2)"] - Group By Operator [GBY_265] (rows=38111880083 width=228) + Group By Operator [GBY_255] (rows=38111880083 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_101] @@ -122,14 +120,14 @@ Stage-0 Output:["_col0","_col2","_col3"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col3 Merge Join Operator [MERGEJOIN_227] (rows=83469759007 width=227) Conds:RS_47._col3=RS_48._col0(Inner),Output:["_col3","_col4","_col5"] - <-Reducer 19 [ONE_TO_ONE_EDGE] + <-Reducer 17 [ONE_TO_ONE_EDGE] FORWARD [RS_48] PartitionCols:_col0 Select Operator [SEL_34] (rows=1384229738 width=4) Output:["_col0"] Merge Join Operator [MERGEJOIN_221] (rows=1384229738 width=4) - Conds:RS_31._col0=RS_264.wr_order_number(Inner),Output:["_col14"] - <-Reducer 18 [ONE_TO_ONE_EDGE] + Conds:RS_31._col0=RS_254.wr_order_number(Inner),Output:["_col14"] + <-Reducer 16 [ONE_TO_ONE_EDGE] FORWARD [RS_31] PartitionCols:_col0 Select Operator [SEL_29] (rows=1411940834 width=4) @@ -137,19 +135,19 @@ Stage-0 Filter Operator [FIL_28] (rows=1411940834 width=11) predicate:(_col0 <> _col2) Merge Join Operator [MERGEJOIN_220] (rows=1411940834 width=11) - Conds:RS_260._col1=RS_263._col1(Inner),Output:["_col0","_col1","_col2"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_260] + Conds:RS_250._col1=RS_253._col1(Inner),Output:["_col0","_col1","_col2"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_250] PartitionCols:_col1 - Select Operator [SEL_259] (rows=144002668 width=7) + Select Operator [SEL_249] (rows=144002668 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_258] (rows=144002668 width=7) + Filter Operator [FIL_248] (rows=144002668 width=7) predicate:(in_bloom_filter(ws_order_number, DynamicValue(RS_44_ws1_ws_order_number_bloom_filter)) and ws_order_number BETWEEN DynamicValue(RS_44_ws1_ws_order_number_min) AND DynamicValue(RS_44_ws1_ws_order_number_max)) TableScan [TS_21] (rows=144002668 width=7) default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_256] - Group By Operator [GBY_255] (rows=1 width=12) + BROADCAST [RS_246] + Group By Operator [GBY_245] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] SHUFFLE [RS_179] @@ -158,13 +156,13 @@ Stage-0 Select Operator [SEL_177] (rows=5022875 width=8) Output:["_col0"] Merge Join Operator [MERGEJOIN_224] (rows=5022875 width=227) - Conds:RS_41._col2=RS_246._col0(Inner),Output:["_col3","_col4","_col5"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_246] + Conds:RS_41._col2=RS_244._col0(Inner),Output:["_col3","_col4","_col5"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_244] PartitionCols:_col0 - Select Operator [SEL_245] (rows=12 width=4) + Select Operator [SEL_243] (rows=12 width=4) Output:["_col0"] - Filter Operator [FIL_244] (rows=12 width=92) + Filter Operator [FIL_242] (rows=12 width=92) predicate:(web_company_name = 'pri') TableScan [TS_9] (rows=84 width=92) default@web_site,web_site,Tbl:COMPLETE,Col:COMPLETE,Output:["web_site_sk","web_company_name"] @@ -172,13 +170,13 @@ Stage-0 SHUFFLE [RS_41] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_223] (rows=15673790 width=231) - Conds:RS_38._col1=RS_238._col0(Inner),Output:["_col2","_col3","_col4","_col5"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_238] + Conds:RS_38._col1=RS_230._col0(Inner),Output:["_col2","_col3","_col4","_col5"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_230] PartitionCols:_col0 - Select Operator [SEL_237] (rows=784314 width=4) + Select Operator [SEL_229] (rows=784314 width=4) Output:["_col0"] - Filter Operator [FIL_236] (rows=784314 width=90) + Filter Operator [FIL_228] (rows=784314 width=90) predicate:(ca_state = 'TX') TableScan [TS_6] (rows=40000000 width=90) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] @@ -186,72 +184,50 @@ Stage-0 SHUFFLE [RS_38] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_222] (rows=15987241 width=235) - Conds:RS_254._col0=RS_230._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_230] - PartitionCols:_col0 - Select Operator [SEL_229] (rows=8116 width=98) - Output:["_col0"] - Filter Operator [FIL_228] (rows=8116 width=98) - predicate:CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' - TableScan [TS_3] (rows=73049 width=98) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + Conds:RS_238._col0=RS_241._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_254] + SHUFFLE [RS_238] PartitionCols:_col0 - Select Operator [SEL_253] (rows=143895019 width=239) + Select Operator [SEL_237] (rows=143895019 width=239) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_252] (rows=143895019 width=239) - predicate:((ws_ship_addr_sk BETWEEN DynamicValue(RS_39_customer_address_ca_address_sk_min) AND DynamicValue(RS_39_customer_address_ca_address_sk_max) and in_bloom_filter(ws_ship_addr_sk, DynamicValue(RS_39_customer_address_ca_address_sk_bloom_filter))) and (ws_ship_date_sk BETWEEN DynamicValue(RS_36_date_dim_d_date_sk_min) AND DynamicValue(RS_36_date_dim_d_date_sk_max) and in_bloom_filter(ws_ship_date_sk, DynamicValue(RS_36_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_42_web_site_web_site_sk_min) AND DynamicValue(RS_42_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_42_web_site_web_site_sk_bloom_filter))) and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) + Filter Operator [FIL_236] (rows=143895019 width=239) + predicate:((ws_ship_addr_sk BETWEEN DynamicValue(RS_39_customer_address_ca_address_sk_min) AND DynamicValue(RS_39_customer_address_ca_address_sk_max) and in_bloom_filter(ws_ship_addr_sk, DynamicValue(RS_39_customer_address_ca_address_sk_bloom_filter))) and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) TableScan [TS_0] (rows=144002668 width=239) default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_ship_date_sk","ws_ship_addr_sk","ws_web_site_sk","ws_order_number","ws_ext_ship_cost","ws_net_profit"] - <-Reducer 12 [BROADCAST_EDGE] vectorized + <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_235] Group By Operator [GBY_234] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_233] Group By Operator [GBY_232] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_231] (rows=8116 width=4) + Select Operator [SEL_231] (rows=784314 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_229] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_243] - Group By Operator [GBY_242] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_241] - Group By Operator [GBY_240] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_239] (rows=784314 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_237] - <-Reducer 16 [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=1000000)"] - <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_249] - Group By Operator [GBY_248] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_247] (rows=12 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_245] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_263] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_241] + PartitionCols:_col0 + Select Operator [SEL_240] (rows=8116 width=98) + Output:["_col0"] + Filter Operator [FIL_239] (rows=8116 width=98) + predicate:CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_253] PartitionCols:_col1 - Select Operator [SEL_262] (rows=144002668 width=7) + Select Operator [SEL_252] (rows=144002668 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_261] (rows=144002668 width=7) + Filter Operator [FIL_251] (rows=144002668 width=7) predicate:(in_bloom_filter(ws_order_number, DynamicValue(RS_44_ws1_ws_order_number_bloom_filter)) and ws_order_number BETWEEN DynamicValue(RS_44_ws1_ws_order_number_min) AND DynamicValue(RS_44_ws1_ws_order_number_max)) TableScan [TS_23] (rows=144002668 width=7) default@web_sales,ws2,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"] <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_257] - Please refer to the previous Group By Operator [GBY_255] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_264] + BROADCAST [RS_247] + Please refer to the previous Group By Operator [GBY_245] + <-Map 19 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_254] PartitionCols:wr_order_number TableScan [TS_30] (rows=14398467 width=4) default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_order_number"] @@ -260,7 +236,7 @@ Stage-0 PartitionCols:_col3 Merge Join Operator [MERGEJOIN_226] (rows=482885639 width=227) Conds:RS_44._col3=RS_45._col0(Inner),Output:["_col3","_col4","_col5"] - <-Reducer 18 [ONE_TO_ONE_EDGE] + <-Reducer 16 [ONE_TO_ONE_EDGE] FORWARD [RS_45] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_29]
http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/constraints/query96.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query96.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query96.q.out index 8942a90..27c26aa 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query96.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query96.q.out @@ -41,12 +41,10 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 8 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) @@ -56,29 +54,29 @@ Stage-0 limit:-1 Stage-1 Reducer 6 vectorized - File Output Operator [FS_109] - Limit [LIM_108] (rows=1 width=16) + File Output Operator [FS_99] + Limit [LIM_98] (rows=1 width=16) Number of rows:100 - Select Operator [SEL_107] (rows=1 width=16) + Select Operator [SEL_97] (rows=1 width=16) Output:["_col0"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_106] - Select Operator [SEL_105] (rows=1 width=16) + SHUFFLE [RS_96] + Select Operator [SEL_95] (rows=1 width=16) Output:["_col1"] - Group By Operator [GBY_104] (rows=1 width=8) + Group By Operator [GBY_94] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_23] Group By Operator [GBY_22] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] Merge Join Operator [MERGEJOIN_76] (rows=1084713 width=8) - Conds:RS_18._col2=RS_95._col0(Inner) - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_95] + Conds:RS_18._col2=RS_93._col0(Inner) + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_93] PartitionCols:_col0 - Select Operator [SEL_94] (rows=155 width=4) + Select Operator [SEL_92] (rows=155 width=4) Output:["_col0"] - Filter Operator [FIL_93] (rows=155 width=92) + Filter Operator [FIL_91] (rows=155 width=92) predicate:(s_store_name = 'ese') TableScan [TS_9] (rows=1704 width=92) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name"] @@ -86,13 +84,13 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_75] (rows=1477476 width=0) - Conds:RS_15._col1=RS_87._col0(Inner),Output:["_col2"] + Conds:RS_15._col1=RS_90._col0(Inner),Output:["_col2"] <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_87] + SHUFFLE [RS_90] PartitionCols:_col0 - Select Operator [SEL_86] (rows=655 width=4) + Select Operator [SEL_89] (rows=655 width=4) Output:["_col0"] - Filter Operator [FIL_85] (rows=655 width=8) + Filter Operator [FIL_88] (rows=655 width=8) predicate:(hd_dep_count = 5) TableScan [TS_6] (rows=7200 width=8) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count"] @@ -100,7 +98,7 @@ Stage-0 SHUFFLE [RS_15] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_74] (rows=16240953 width=0) - Conds:RS_103._col0=RS_79._col0(Inner),Output:["_col1","_col2"] + Conds:RS_87._col0=RS_79._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_79] PartitionCols:_col0 @@ -111,36 +109,14 @@ Stage-0 TableScan [TS_3] (rows=86400 width=12) default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_hour","t_minute"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_103] + SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_102] (rows=501695814 width=11) + Select Operator [SEL_86] (rows=501695814 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_101] (rows=501695814 width=11) - predicate:((ss_hdemo_sk BETWEEN DynamicValue(RS_16_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_16_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_16_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_time_sk BETWEEN DynamicValue(RS_13_time_dim_t_time_sk_min) AND DynamicValue(RS_13_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_13_time_dim_t_time_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_19_store_s_store_sk_min) AND DynamicValue(RS_19_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_19_store_s_store_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) + Filter Operator [FIL_85] (rows=501695814 width=11) + predicate:((ss_sold_time_sk BETWEEN DynamicValue(RS_13_time_dim_t_time_sk_min) AND DynamicValue(RS_13_time_dim_t_time_sk_max) and in_bloom_filter(ss_sold_time_sk, DynamicValue(RS_13_time_dim_t_time_sk_bloom_filter))) and ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) TableScan [TS_0] (rows=575995635 width=11) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_time_sk","ss_hdemo_sk","ss_store_sk"] - <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_92] - Group By Operator [GBY_91] (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_90] - Group By Operator [GBY_89] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_88] (rows=655 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_86] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_100] - Group By Operator [GBY_99] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_98] - Group By Operator [GBY_97] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_96] (rows=155 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_94] <-Reducer 8 [BROADCAST_EDGE] vectorized BROADCAST [RS_84] Group By Operator [GBY_83] (rows=1 width=12) http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/constraints/query98.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query98.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query98.q.out index 3ffc379..d1e7d20 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query98.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query98.q.out @@ -71,8 +71,7 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE) +Map 1 <- Reducer 8 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) @@ -85,21 +84,21 @@ Stage-0 limit:-1 Stage-1 Reducer 6 vectorized - File Output Operator [FS_84] - Select Operator [SEL_83] (rows=138600 width=701) + File Output Operator [FS_79] + Select Operator [SEL_78] (rows=138600 width=701) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_82] - Select Operator [SEL_81] (rows=138600 width=801) + SHUFFLE [RS_77] + Select Operator [SEL_76] (rows=138600 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_80] (rows=138600 width=689) + PTF Operator [PTF_75] (rows=138600 width=689) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 ASC NULLS FIRST","partition by:":"_col1"}] - Select Operator [SEL_79] (rows=138600 width=689) + Select Operator [SEL_74] (rows=138600 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_78] + SHUFFLE [RS_73] PartitionCols:_col1 - Group By Operator [GBY_77] (rows=138600 width=689) + Group By Operator [GBY_72] (rows=138600 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_17] @@ -107,13 +106,13 @@ Stage-0 Group By Operator [GBY_16] (rows=138600 width=689) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col9, _col8, _col5, _col6, _col7 Merge Join Operator [MERGEJOIN_57] (rows=18334631 width=577) - Conds:RS_12._col1=RS_68._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9"] + Conds:RS_12._col1=RS_71._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9"] <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_68] + SHUFFLE [RS_71] PartitionCols:_col0 - Select Operator [SEL_67] (rows=138600 width=581) + Select Operator [SEL_70] (rows=138600 width=581) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_66] (rows=138600 width=581) + Filter Operator [FIL_69] (rows=138600 width=581) predicate:(i_category) IN ('Jewelry', 'Sports', 'Books') TableScan [TS_6] (rows=462000 width=581) default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_id","i_item_desc","i_current_price","i_class","i_category"] @@ -121,7 +120,7 @@ Stage-0 SHUFFLE [RS_12] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_56] (rows=61115434 width=70) - Conds:RS_76._col0=RS_60._col0(Inner),Output:["_col1","_col2"] + Conds:RS_68._col0=RS_60._col0(Inner),Output:["_col1","_col2"] <-Map 7 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_60] PartitionCols:_col0 @@ -132,25 +131,14 @@ Stage-0 TableScan [TS_3] (rows=73049 width=98) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_76] + SHUFFLE [RS_68] PartitionCols:_col0 - Select Operator [SEL_75] (rows=550076554 width=114) + Select Operator [SEL_67] (rows=550076554 width=114) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_74] (rows=550076554 width=114) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_13_item_i_item_sk_min) AND DynamicValue(RS_13_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_13_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null) + Filter Operator [FIL_66] (rows=550076554 width=114) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) 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 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_73] - Group By Operator [GBY_72] (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_71] - Group By Operator [GBY_70] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_69] (rows=138600 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_67] <-Reducer 8 [BROADCAST_EDGE] vectorized BROADCAST [RS_65] Group By Operator [GBY_64] (rows=1 width=12) http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out index e76bb8e..5f84036 100644 --- a/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query99.q.out @@ -81,31 +81,30 @@ 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 10 (BROADCAST_EDGE) +Reducer 10 <- Map 9 (CUSTOM_SIMPLE_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 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (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) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 7 vectorized - File Output Operator [FS_125] - Limit [LIM_124] (rows=100 width=590) + File Output Operator [FS_120] + Limit [LIM_119] (rows=100 width=590) Number of rows:100 - Select Operator [SEL_123] (rows=3869553 width=590) + Select Operator [SEL_118] (rows=3869553 width=590) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_122] - Select Operator [SEL_121] (rows=3869553 width=590) + SHUFFLE [RS_117] + Select Operator [SEL_116] (rows=3869553 width=590) Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Group By Operator [GBY_120] (rows=3869553 width=406) + Group By Operator [GBY_115] (rows=3869553 width=406) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_26] @@ -115,11 +114,11 @@ Stage-0 Top N Key Operator [TNK_53] (rows=15478212 width=386) keys:_col13, _col11, _col15,sort order:+++,top n:100 Merge Join Operator [MERGEJOIN_97] (rows=15478212 width=386) - Conds:RS_21._col1=RS_119._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col8","_col11","_col13","_col15"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_119] + Conds:RS_21._col1=RS_114._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col8","_col11","_col13","_col15"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_114] PartitionCols:_col0 - Select Operator [SEL_118] (rows=60 width=102) + Select Operator [SEL_113] (rows=60 width=102) Output:["_col0","_col1"] TableScan [TS_10] (rows=60 width=102) default@call_center,call_center,Tbl:COMPLETE,Col:COMPLETE,Output:["cc_call_center_sk","cc_name"] @@ -127,11 +126,11 @@ Stage-0 SHUFFLE [RS_21] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_96] (rows=15478212 width=291) - Conds:RS_18._col3=RS_117._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_117] + Conds:RS_18._col3=RS_112._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col8","_col11","_col13"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_112] PartitionCols:_col0 - Select Operator [SEL_116] (rows=27 width=188) + Select Operator [SEL_111] (rows=27 width=188) Output:["_col0","_col1"] TableScan [TS_8] (rows=27 width=104) default@warehouse,warehouse,Tbl:COMPLETE,Col:COMPLETE,Output:["w_warehouse_sk","w_warehouse_name"] @@ -139,11 +138,11 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_95] (rows=15478212 width=111) - Conds:RS_15._col2=RS_107._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_107] + Conds:RS_15._col2=RS_99._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col11"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_99] PartitionCols:_col0 - Select Operator [SEL_106] (rows=1 width=88) + Select Operator [SEL_98] (rows=1 width=88) Output:["_col0","_col1"] TableScan [TS_6] (rows=1 width=88) default@ship_mode,ship_mode,Tbl:COMPLETE,Col:COMPLETE,Output:["sm_ship_mode_sk","sm_type"] @@ -151,45 +150,34 @@ Stage-0 SHUFFLE [RS_15] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_94] (rows=46434637 width=31) - Conds:RS_115._col0=RS_100._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_100] - PartitionCols:_col0 - Select Operator [SEL_99] (rows=317 width=4) - Output:["_col0"] - Filter Operator [FIL_98] (rows=317 width=8) - predicate:d_month_seq BETWEEN 1212 AND 1223 - TableScan [TS_3] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] + Conds:RS_107._col0=RS_110._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_115] + SHUFFLE [RS_107] PartitionCols:_col0 - Select Operator [SEL_114] (rows=282273729 width=35) + Select Operator [SEL_106] (rows=282273729 width=35) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_113] (rows=282273729 width=19) - predicate:((cs_ship_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(cs_ship_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and (cs_ship_mode_sk BETWEEN DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_bloom_filter))) and cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_sk is not null) + Filter Operator [FIL_105] (rows=282273729 width=19) + predicate:((cs_ship_mode_sk BETWEEN DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_min) AND DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_max) and in_bloom_filter(cs_ship_mode_sk, DynamicValue(RS_16_ship_mode_sm_ship_mode_sk_bloom_filter))) and cs_call_center_sk is not null and cs_ship_date_sk is not null and cs_ship_mode_sk is not null and cs_warehouse_sk is not null) TableScan [TS_0] (rows=287989836 width=19) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_date_sk","cs_call_center_sk","cs_ship_mode_sk","cs_warehouse_sk"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_112] - Group By Operator [GBY_111] (rows=1 width=12) + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_104] + Group By Operator [GBY_103] (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_110] - Group By Operator [GBY_109] (rows=1 width=12) + <-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_102] + Group By Operator [GBY_101] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_108] (rows=1 width=4) + Select Operator [SEL_100] (rows=1 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_106] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_105] - Group By Operator [GBY_104] (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_103] - Group By Operator [GBY_102] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_101] (rows=317 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_99] + Please refer to the previous Select Operator [SEL_98] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_110] + PartitionCols:_col0 + Select Operator [SEL_109] (rows=317 width=4) + Output:["_col0"] + Filter Operator [FIL_108] (rows=317 width=8) + predicate:d_month_seq BETWEEN 1212 AND 1223 + TableScan [TS_3] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"] http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query10.q.out b/ql/src/test/results/clientpositive/perf/tez/query10.q.out index 4fc8123..210144d 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query10.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query10.q.out @@ -133,24 +133,21 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 14 <- Reducer 11 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) -Map 24 <- Reducer 10 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE) -Map 25 <- Reducer 23 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 13 <- Reducer 16 (BROADCAST_EDGE) +Map 21 <- Reducer 10 (BROADCAST_EDGE) +Map 22 <- Reducer 9 (BROADCAST_EDGE) Reducer 10 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 16 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE) -Reducer 19 <- Reducer 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) -Reducer 20 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 21 <- Map 16 (SIMPLE_EDGE), Map 25 (SIMPLE_EDGE) -Reducer 22 <- Reducer 21 (SIMPLE_EDGE) -Reducer 23 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 19 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) -Reducer 6 <- Reducer 22 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) +Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 15 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) +Reducer 18 <- Reducer 17 (SIMPLE_EDGE) +Reducer 19 <- Map 15 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Reducer 20 <- Reducer 19 (SIMPLE_EDGE) +Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 18 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) +Reducer 6 <- Reducer 20 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) Reducer 8 <- Reducer 7 (SIMPLE_EDGE) Reducer 9 <- Reducer 5 (CUSTOM_SIMPLE_EDGE) @@ -160,16 +157,16 @@ Stage-0 limit:100 Stage-1 Reducer 8 vectorized - File Output Operator [FS_237] - Limit [LIM_236] (rows=1 width=419) + File Output Operator [FS_225] + Limit [LIM_224] (rows=1 width=419) Number of rows:100 - Select Operator [SEL_235] (rows=1 width=419) + Select Operator [SEL_223] (rows=1 width=419) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_234] - Select Operator [SEL_233] (rows=1 width=419) + SHUFFLE [RS_222] + Select Operator [SEL_221] (rows=1 width=419) Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col8","_col10","_col12"] - Group By Operator [GBY_232] (rows=1 width=379) + Group By Operator [GBY_220] (rows=1 width=379) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_67] @@ -183,23 +180,61 @@ Stage-0 Filter Operator [FIL_64] (rows=58 width=379) predicate:(_col15 is not null or _col17 is not null) Merge Join Operator [MERGEJOIN_181] (rows=58 width=379) - Conds:RS_61._col0=RS_231._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col15","_col17"] + Conds:RS_61._col0=RS_219._col0(Left Outer),Output:["_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col15","_col17"] <-Reducer 5 [ONE_TO_ONE_EDGE] PARTITION_ONLY_SHUFFLE [RS_61] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_180] (rows=58 width=379) - Conds:RS_58._col0=RS_221._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col15"] + Conds:RS_58._col0=RS_211._col0(Left Outer),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col15"] <-Reducer 4 [ONE_TO_ONE_EDGE] FORWARD [RS_58] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_179] (rows=22703 width=375) Conds:RS_55._col0=RS_56._col0(Left Semi),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_56] + PartitionCols:_col0 + Group By Operator [GBY_54] (rows=155827 width=2) + Output:["_col0"],keys:_col0 + Select Operator [SEL_18] (rows=57825495 width=2) + Output:["_col0"] + Merge Join Operator [MERGEJOIN_176] (rows=57825495 width=2) + Conds:RS_203._col0=RS_193._col0(Inner),Output:["_col1"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_193] + PartitionCols:_col0 + Select Operator [SEL_192] (rows=201 width=4) + Output:["_col0"] + Filter Operator [FIL_191] (rows=201 width=12) + predicate:((d_year = 2002) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) + TableScan [TS_12] (rows=73049 width=12) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_203] + PartitionCols:_col0 + Select Operator [SEL_202] (rows=525327388 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_201] (rows=525327388 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_9] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_200] + Group By Operator [GBY_199] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_198] + Group By Operator [GBY_197] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_194] (rows=201 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_192] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_55] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_175] (rows=228127 width=375) Conds:RS_50._col1=RS_190._col0(Inner),Output:["_col0","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"] - <-Map 13 [SIMPLE_EDGE] vectorized + <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_190] PartitionCols:_col0 Select Operator [SEL_189] (rows=1861800 width=375) @@ -222,7 +257,7 @@ Stage-0 predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_customer_sk is not null) TableScan [TS_0] (rows=80000000 width=11) default@customer,c,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_addr_sk"] - <-Map 12 [SIMPLE_EDGE] vectorized + <-Map 11 [SIMPLE_EDGE] vectorized SHUFFLE [RS_187] PartitionCols:_col0 Select Operator [SEL_186] (rows=116550 width=102) @@ -231,85 +266,36 @@ Stage-0 predicate:((ca_county) IN ('Walker County', 'Richland County', 'Gaines County', 'Douglas County', 'Dona Ana County') and ca_address_sk is not null) TableScan [TS_3] (rows=40000000 width=102) default@customer_address,ca,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_county"] - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_56] - PartitionCols:_col0 - Group By Operator [GBY_54] (rows=155827 width=2) - Output:["_col0"],keys:_col0 - Select Operator [SEL_18] (rows=57825495 width=2) - Output:["_col0"] - Merge Join Operator [MERGEJOIN_176] (rows=57825495 width=2) - Conds:RS_211._col0=RS_193._col0(Inner),Output:["_col1"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_193] - PartitionCols:_col0 - Select Operator [SEL_192] (rows=201 width=4) - Output:["_col0"] - Filter Operator [FIL_191] (rows=201 width=12) - predicate:((d_year = 2002) and d_date_sk is not null and d_moy BETWEEN 4 AND 7) - TableScan [TS_12] (rows=73049 width=12) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_211] - PartitionCols:_col0 - Select Operator [SEL_210] (rows=525327388 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_209] (rows=525327388 width=7) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_55_c_c_customer_sk_min) AND DynamicValue(RS_55_c_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_55_c_c_customer_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_9] (rows=575995635 width=7) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk"] - <-Reducer 11 [BROADCAST_EDGE] vectorized - BROADCAST [RS_208] - Group By Operator [GBY_207] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - SHUFFLE [RS_136] - Group By Operator [GBY_135] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_134] (rows=228127 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_175] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_206] - Group By Operator [GBY_205] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_202] - Group By Operator [GBY_199] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_194] (rows=201 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_192] - <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_221] + <-Reducer 18 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_211] PartitionCols:_col0 - Select Operator [SEL_220] (rows=155827 width=7) + Select Operator [SEL_210] (rows=155827 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_219] (rows=155827 width=3) + Group By Operator [GBY_209] (rows=155827 width=3) Output:["_col0"],keys:KEY._col0 - <-Reducer 18 [SIMPLE_EDGE] + <-Reducer 17 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0 Group By Operator [GBY_29] (rows=155827 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_177] (rows=15843227 width=3) - Conds:RS_218._col0=RS_195._col0(Inner),Output:["_col1"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_195] + Conds:RS_208._col0=RS_195._col0(Inner),Output:["_col1"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_195] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_192] - <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_218] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_208] PartitionCols:_col0 - Select Operator [SEL_217] (rows=143930993 width=7) + Select Operator [SEL_207] (rows=143930993 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_216] (rows=143930993 width=7) - predicate:((ws_bill_customer_sk BETWEEN DynamicValue(RS_58_c_c_customer_sk_min) AND DynamicValue(RS_58_c_c_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_58_c_c_customer_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_26_date_dim_d_date_sk_min) AND DynamicValue(RS_26_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_26_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) + Filter Operator [FIL_206] (rows=143930993 width=7) + predicate:((ws_bill_customer_sk BETWEEN DynamicValue(RS_58_c_c_customer_sk_min) AND DynamicValue(RS_58_c_c_customer_sk_max) and in_bloom_filter(ws_bill_customer_sk, DynamicValue(RS_58_c_c_customer_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null) TableScan [TS_19] (rows=144002668 width=7) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] <-Reducer 10 [BROADCAST_EDGE] vectorized - BROADCAST [RS_215] - Group By Operator [GBY_214] (rows=1 width=12) + BROADCAST [RS_205] + Group By Operator [GBY_204] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] FORWARD [RS_151] @@ -318,58 +304,36 @@ Stage-0 Select Operator [SEL_149] (rows=22703 width=4) Output:["_col0"] Please refer to the previous Merge Join Operator [MERGEJOIN_179] - <-Reducer 20 [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 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_203] - Group By Operator [GBY_200] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_196] (rows=201 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_192] - <-Reducer 22 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_231] + <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_219] PartitionCols:_col0 - Select Operator [SEL_230] (rows=154725 width=7) + Select Operator [SEL_218] (rows=154725 width=7) Output:["_col0","_col1"] - Group By Operator [GBY_229] (rows=154725 width=3) + Group By Operator [GBY_217] (rows=154725 width=3) Output:["_col0"],keys:KEY._col0 - <-Reducer 21 [SIMPLE_EDGE] + <-Reducer 19 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col0 Group By Operator [GBY_43] (rows=154725 width=3) Output:["_col0"],keys:_col1 Merge Join Operator [MERGEJOIN_178] (rows=31162251 width=3) - Conds:RS_228._col0=RS_197._col0(Inner),Output:["_col1"] - <-Map 16 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_197] + Conds:RS_216._col0=RS_196._col0(Inner),Output:["_col1"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_196] PartitionCols:_col0 Please refer to the previous Select Operator [SEL_192] - <-Map 25 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_228] + <-Map 22 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_216] PartitionCols:_col0 - Select Operator [SEL_227] (rows=285115246 width=7) + Select Operator [SEL_215] (rows=285115246 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_226] (rows=285115246 width=7) - predicate:((cs_ship_customer_sk BETWEEN DynamicValue(RS_61_c_c_customer_sk_min) AND DynamicValue(RS_61_c_c_customer_sk_max) and in_bloom_filter(cs_ship_customer_sk, DynamicValue(RS_61_c_c_customer_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_40_date_dim_d_date_sk_min) AND DynamicValue(RS_40_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_40_date_dim_d_date_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) + Filter Operator [FIL_214] (rows=285115246 width=7) + predicate:((cs_ship_customer_sk BETWEEN DynamicValue(RS_61_c_c_customer_sk_min) AND DynamicValue(RS_61_c_c_customer_sk_max) and in_bloom_filter(cs_ship_customer_sk, DynamicValue(RS_61_c_c_customer_sk_bloom_filter))) and cs_ship_customer_sk is not null and cs_sold_date_sk is not null) TableScan [TS_33] (rows=287989836 width=7) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ship_customer_sk"] - <-Reducer 23 [BROADCAST_EDGE] vectorized - BROADCAST [RS_223] - Group By Operator [GBY_222] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_204] - Group By Operator [GBY_201] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_198] (rows=201 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_192] <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_225] - Group By Operator [GBY_224] (rows=1 width=12) + 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)"] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_166]
