http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query89.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query89.q.out b/ql/src/test/results/clientpositive/perf/tez/query89.q.out index e79b9dd..8501822 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query89.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query89.q.out @@ -65,42 +65,41 @@ 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 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- 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_117] - Limit [LIM_116] (rows=100 width=801) + File Output Operator [FS_112] + Limit [LIM_111] (rows=100 width=801) Number of rows:100 - Select Operator [SEL_115] (rows=4804228 width=801) + Select Operator [SEL_110] (rows=4804228 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_114] - Select Operator [SEL_113] (rows=4804228 width=801) + SHUFFLE [RS_109] + Select Operator [SEL_108] (rows=4804228 width=801) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Filter Operator [FIL_112] (rows=4804228 width=689) + Filter Operator [FIL_107] (rows=4804228 width=689) predicate:CASE WHEN ((avg_window_0 <> 0)) THEN (((abs((_col6 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (null) END - Select Operator [SEL_111] (rows=9608456 width=577) + Select Operator [SEL_106] (rows=9608456 width=577) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_110] (rows=9608456 width=577) + PTF Operator [PTF_105] (rows=9608456 width=577) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 ASC NULLS FIRST, _col0 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST","partition by:":"_col2, _col0, _col4, _col5"}] - Select Operator [SEL_109] (rows=9608456 width=577) + Select Operator [SEL_104] (rows=9608456 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_108] + SHUFFLE [RS_103] PartitionCols:_col2, _col0, _col4, _col5 - Group By Operator [GBY_107] (rows=9608456 width=577) + Group By Operator [GBY_102] (rows=9608456 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_23] @@ -108,13 +107,13 @@ Stage-0 Group By Operator [GBY_22] (rows=27308180 width=577) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col7, _col9, _col11, _col12 Merge Join Operator [MERGEJOIN_84] (rows=27308180 width=480) - Conds:RS_18._col2=RS_106._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col9","_col11","_col12"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_106] + Conds:RS_18._col2=RS_101._col0(Inner),Output:["_col3","_col5","_col6","_col7","_col9","_col11","_col12"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_101] PartitionCols:_col0 - Select Operator [SEL_105] (rows=1704 width=183) + Select Operator [SEL_100] (rows=1704 width=183) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_104] (rows=1704 width=183) + Filter Operator [FIL_99] (rows=1704 width=183) predicate:s_store_sk is not null TableScan [TS_9] (rows=1704 width=183) default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_company_name"] @@ -122,13 +121,13 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_83] (rows=27308180 width=301) - Conds:RS_15._col0=RS_95._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col7","_col9"] - <-Map 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_95] + Conds:RS_15._col0=RS_87._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col7","_col9"] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_87] PartitionCols:_col0 - Select Operator [SEL_94] (rows=652 width=8) + Select Operator [SEL_86] (rows=652 width=8) Output:["_col0","_col1"] - Filter Operator [FIL_93] (rows=652 width=12) + Filter Operator [FIL_85] (rows=652 width=12) predicate:((d_year = 2000) and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] @@ -136,45 +135,34 @@ Stage-0 SHUFFLE [RS_15] PartitionCols:_col0 Merge Join Operator [MERGEJOIN_82] (rows=76480702 width=364) - Conds:RS_103._col1=RS_87._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6","_col7"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_87] - PartitionCols:_col0 - Select Operator [SEL_86] (rows=6988 width=286) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_85] (rows=6988 width=286) - predicate:((((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and (i_category) IN ('Home', 'Books', 'Electronics', 'Shoes', 'Jewelry', 'Men') and (i_class) IN ('wallpaper', 'parenting', 'musical', 'womens', 'birdal', 'pants') and i_item_sk is not null) - TableScan [TS_3] (rows=462000 width=286) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_class","i_category"] + Conds:RS_95._col1=RS_98._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6","_col7"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_103] + SHUFFLE [RS_95] PartitionCols:_col1 - Select Operator [SEL_102] (rows=525329897 width=118) + Select Operator [SEL_94] (rows=525329897 width=118) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_101] (rows=525329897 width=118) - 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_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_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + Filter Operator [FIL_93] (rows=525329897 width=118) + 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_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=118) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] - <-Reducer 11 [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 10 [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=652 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_94] - <-Reducer 9 [BROADCAST_EDGE] vectorized + <-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 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_90] + <-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=6988 width=4) + Select Operator [SEL_88] (rows=652 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_86] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_98] + PartitionCols:_col0 + Select Operator [SEL_97] (rows=6988 width=286) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_96] (rows=6988 width=286) + predicate:((((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and (i_category) IN ('Home', 'Books', 'Electronics', 'Shoes', 'Jewelry', 'Men') and (i_class) IN ('wallpaper', 'parenting', 'musical', 'womens', 'birdal', 'pants') and i_item_sk is not null) + TableScan [TS_3] (rows=462000 width=286) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_brand","i_class","i_category"]
http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query90.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query90.q.out b/ql/src/test/results/clientpositive/perf/tez/query90.q.out index 916a232..0ba2b2a 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query90.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query90.q.out @@ -54,34 +54,27 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 16 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) -Map 21 <- Reducer 14 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE) -Reducer 10 <- Map 21 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 11 <- Map 15 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 12 <- Map 18 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 17 <- Map 15 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 20 <- Map 18 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Map 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 18 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Map 1 <- Reducer 14 (BROADCAST_EDGE) +Reducer 10 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 9 <- Map 13 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_209] - Limit [LIM_208] (rows=1 width=112) + File Output Operator [FS_180] + Limit [LIM_179] (rows=1 width=112) Number of rows:100 - Select Operator [SEL_207] (rows=1 width=112) + Select Operator [SEL_178] (rows=1 width=112) Output:["_col0"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_56] @@ -89,171 +82,102 @@ Stage-0 Output:["_col0"] Merge Join Operator [MERGEJOIN_152] (rows=1 width=16) Conds:(Inner),Output:["_col0","_col1"] - <-Reducer 13 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_206] - Group By Operator [GBY_205] (rows=1 width=8) + <-Reducer 10 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_177] + Group By Operator [GBY_176] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 12 [CUSTOM_SIMPLE_EDGE] + <-Reducer 9 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_49] Group By Operator [GBY_48] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] Merge Join Operator [MERGEJOIN_151] (rows=153010 width=8) - Conds:RS_44._col1=RS_183._col0(Inner) - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_183] + Conds:RS_44._col1=RS_157._col0(Inner) + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_157] PartitionCols:_col0 - Select Operator [SEL_180] (rows=655 width=4) + Select Operator [SEL_154] (rows=655 width=4) Output:["_col0"] - Filter Operator [FIL_179] (rows=655 width=8) + Filter Operator [FIL_153] (rows=655 width=8) predicate:((hd_dep_count = 8) and hd_demo_sk is not null) TableScan [TS_9] (rows=7200 width=8) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count"] - <-Reducer 11 [SIMPLE_EDGE] + <-Reducer 8 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_150] (rows=1681936 width=3) - Conds:RS_41._col0=RS_171._col0(Inner),Output:["_col1"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_171] + Conds:RS_41._col0=RS_173._col0(Inner),Output:["_col1"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_173] PartitionCols:_col0 - Select Operator [SEL_168] (rows=9095 width=4) + Select Operator [SEL_171] (rows=9095 width=4) Output:["_col0"] - Filter Operator [FIL_166] (rows=9095 width=8) + Filter Operator [FIL_169] (rows=9095 width=8) predicate:(t_hour BETWEEN 14 AND 15 and t_time_sk is not null) TableScan [TS_6] (rows=86400 width=8) default@time_dim,time_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["t_time_sk","t_hour"] - <-Reducer 10 [SIMPLE_EDGE] + <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_41] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_149] (rows=15977923 width=7) - Conds:RS_204._col2=RS_157._col0(Inner),Output:["_col0","_col1"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_157] - PartitionCols:_col0 - Select Operator [SEL_154] (rows=511 width=4) - Output:["_col0"] - Filter Operator [FIL_153] (rows=511 width=7) - predicate:(wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) - TableScan [TS_3] (rows=4602 width=7) - default@web_page,web_page,Tbl:COMPLETE,Col:COMPLETE,Output:["wp_web_page_sk","wp_char_count"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_204] + Merge Join Operator [MERGEJOIN_146] (rows=15977923 width=7) + Conds:RS_164._col2=RS_167._col0(Inner),Output:["_col0","_col1"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_164] PartitionCols:_col2 - Select Operator [SEL_203] (rows=143895111 width=11) + Select Operator [SEL_163] (rows=143895111 width=11) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_202] (rows=143895111 width=11) - predicate:((ws_ship_hdemo_sk BETWEEN DynamicValue(RS_45_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_45_household_demographics_hd_demo_sk_max) and in_bloom_filter(ws_ship_hdemo_sk, DynamicValue(RS_45_household_demographics_hd_demo_sk_bloom_filter))) and (ws_sold_time_sk BETWEEN DynamicValue(RS_42_time_dim_t_time_sk_min) AND DynamicValue(RS_42_time_dim_t_time_sk_max) and in_bloom_filter(ws_sold_time_sk, DynamicValue(RS_42_time_dim_t_time_sk_bloom_filter))) and (ws_web_page_sk BETWEEN DynamicValue(RS_39_web_page_wp_web_page_sk_min) AND DynamicValue(RS_39_web_page_wp_web_page_sk_max) and in_bloom_filter(ws_web_page_sk, DynamicValue(RS_39_web_page_wp_web_page_sk_bloom_filter))) and ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) - TableScan [TS_26] (rows=144002668 width=11) + Filter Operator [FIL_162] (rows=143895111 width=11) + predicate:((ws_ship_hdemo_sk BETWEEN DynamicValue(RS_19_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_19_household_demographics_hd_demo_sk_max) and in_bloom_filter(ws_ship_hdemo_sk, DynamicValue(RS_19_household_demographics_hd_demo_sk_bloom_filter))) and ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) + TableScan [TS_0] (rows=144002668 width=11) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_time_sk","ws_ship_hdemo_sk","ws_web_page_sk"] <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_197] - Group By Operator [GBY_196] (rows=1 width=12) + BROADCAST [RS_161] + Group By Operator [GBY_160] (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_162] - Group By Operator [GBY_160] (rows=1 width=12) + <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_159] + Group By Operator [GBY_158] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_158] (rows=511 width=4) + Select Operator [SEL_156] (rows=655 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_154] - <-Reducer 17 [BROADCAST_EDGE] vectorized - BROADCAST [RS_199] - Group By Operator [GBY_198] (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_176] - Group By Operator [GBY_174] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_172] (rows=9095 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_168] - <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_201] - Group By Operator [GBY_200] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_188] - Group By Operator [GBY_186] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_184] (rows=655 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_180] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_167] + PartitionCols:_col0 + Select Operator [SEL_166] (rows=511 width=4) + Output:["_col0"] + Filter Operator [FIL_165] (rows=511 width=7) + predicate:(wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) + TableScan [TS_3] (rows=4602 width=7) + default@web_page,web_page,Tbl:COMPLETE,Col:COMPLETE,Output:["wp_web_page_sk","wp_char_count"] <-Reducer 5 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_195] - Group By Operator [GBY_194] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_175] + Group By Operator [GBY_174] (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_148] (rows=153010 width=8) - Conds:RS_18._col1=RS_181._col0(Inner) - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_181] + Conds:RS_18._col1=RS_155._col0(Inner) + <-Map 13 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_155] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_180] + Please refer to the previous Select Operator [SEL_154] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_147] (rows=1681936 width=3) - Conds:RS_15._col0=RS_169._col0(Inner),Output:["_col1"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_169] + Conds:RS_15._col0=RS_172._col0(Inner),Output:["_col1"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_172] PartitionCols:_col0 - Select Operator [SEL_167] (rows=9095 width=4) + Select Operator [SEL_170] (rows=9095 width=4) Output:["_col0"] - Filter Operator [FIL_165] (rows=9095 width=8) + Filter Operator [FIL_168] (rows=9095 width=8) predicate:(t_hour BETWEEN 6 AND 7 and t_time_sk is not null) Please refer to the previous TableScan [TS_6] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_15] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_146] (rows=15977923 width=7) - Conds:RS_193._col2=RS_155._col0(Inner),Output:["_col0","_col1"] - <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_155] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_154] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_193] - PartitionCols:_col2 - Select Operator [SEL_192] (rows=143895111 width=11) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_191] (rows=143895111 width=11) - predicate:((ws_ship_hdemo_sk BETWEEN DynamicValue(RS_19_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_19_household_demographics_hd_demo_sk_max) and in_bloom_filter(ws_ship_hdemo_sk, DynamicValue(RS_19_household_demographics_hd_demo_sk_bloom_filter))) and (ws_sold_time_sk BETWEEN DynamicValue(RS_16_time_dim_t_time_sk_min) AND DynamicValue(RS_16_time_dim_t_time_sk_max) and in_bloom_filter(ws_sold_time_sk, DynamicValue(RS_16_time_dim_t_time_sk_bloom_filter))) and (ws_web_page_sk BETWEEN DynamicValue(RS_13_web_page_wp_web_page_sk_min) AND DynamicValue(RS_13_web_page_wp_web_page_sk_max) and in_bloom_filter(ws_web_page_sk, DynamicValue(RS_13_web_page_wp_web_page_sk_bloom_filter))) and ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) - TableScan [TS_0] (rows=144002668 width=11) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_time_sk","ws_ship_hdemo_sk","ws_web_page_sk"] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_178] - Group By Operator [GBY_177] (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_175] - Group By Operator [GBY_173] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_170] (rows=9095 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_167] - <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_190] - Group By Operator [GBY_189] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_187] - Group By Operator [GBY_185] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_182] (rows=655 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_180] - <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_164] - Group By Operator [GBY_163] (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_161] - Group By Operator [GBY_159] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_156] (rows=511 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_154] + Please refer to the previous Merge Join Operator [MERGEJOIN_146] http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query92.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query92.q.out b/ql/src/test/results/clientpositive/perf/tez/query92.q.out index 1f837dd..3989d9e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query92.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query92.q.out @@ -67,35 +67,33 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Reducer 15 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) -Map 13 <- Reducer 12 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE) -Reducer 10 <- Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 14 (SIMPLE_EDGE), Reducer 10 (ONE_TO_ONE_EDGE) -Reducer 12 <- Map 7 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 3 <- Reducer 11 (ONE_TO_ONE_EDGE), Reducer 2 (SIMPLE_EDGE) +Map 1 <- Reducer 10 (BROADCAST_EDGE) +Map 11 <- Reducer 13 (BROADCAST_EDGE) +Reducer 10 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (ONE_TO_ONE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) -Reducer 9 <- Map 13 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 7 <- Map 11 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Map 12 (SIMPLE_EDGE), Reducer 8 (ONE_TO_ONE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 Reducer 5 vectorized - File Output Operator [FS_147] - Limit [LIM_146] (rows=1 width=224) + File Output Operator [FS_136] + Limit [LIM_135] (rows=1 width=224) Number of rows:100 - Select Operator [SEL_145] (rows=1 width=224) + Select Operator [SEL_134] (rows=1 width=224) Output:["_col0"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_144] - Select Operator [SEL_143] (rows=1 width=224) + SHUFFLE [RS_133] + Select Operator [SEL_132] (rows=1 width=224) Output:["_col1"] - Group By Operator [GBY_142] (rows=1 width=112) + Group By Operator [GBY_131] (rows=1 width=112) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_36] @@ -107,115 +105,90 @@ Stage-0 predicate:(_col2 > _col5) Merge Join Operator [MERGEJOIN_107] (rows=7434 width=112) Conds:RS_30._col1=RS_31._col2(Inner),Output:["_col2","_col5"] - <-Reducer 2 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_30] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_104] (rows=15995224 width=115) - Conds:RS_131._col0=RS_110._col0(Inner),Output:["_col1","_col2"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_110] - PartitionCols:_col0 - Select Operator [SEL_109] (rows=8116 width=4) - Output:["_col0"] - Filter Operator [FIL_108] (rows=8116 width=98) - predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) - 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_131] - PartitionCols:_col0 - Select Operator [SEL_130] (rows=143966864 width=119) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_129] (rows=143966864 width=119) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_0] (rows=144002668 width=119) - default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_discount_amt"] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_127] - Group By Operator [GBY_126] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_125] - Group By Operator [GBY_124] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_123] (rows=669 width=4) - Output:["_col0"] - Select Operator [SEL_121] (rows=669 width=4) - Output:["_col0"] - Filter Operator [FIL_120] (rows=669 width=7) - predicate:((i_manufact_id = 269) and i_item_sk is not null) - TableScan [TS_20] (rows=462000 width=7) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_manufact_id"] - <-Reducer 8 [BROADCAST_EDGE] vectorized - BROADCAST [RS_119] - Group By Operator [GBY_118] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_116] - Group By Operator [GBY_114] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_111] (rows=8116 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_109] - <-Reducer 11 [ONE_TO_ONE_EDGE] + <-Reducer 9 [ONE_TO_ONE_EDGE] FORWARD [RS_31] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_106] (rows=97 width=116) - Conds:RS_141._col0=RS_122._col0(Inner),Output:["_col1","_col2"] - <-Map 14 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_122] + Conds:RS_125._col0=RS_114._col0(Inner),Output:["_col1","_col2"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_114] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_121] - <-Reducer 10 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_141] + Select Operator [SEL_113] (rows=669 width=4) + Output:["_col0"] + Filter Operator [FIL_112] (rows=669 width=7) + predicate:((i_manufact_id = 269) and i_item_sk is not null) + TableScan [TS_20] (rows=462000 width=7) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_manufact_id"] + <-Reducer 8 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_125] PartitionCols:_col0 - Select Operator [SEL_140] (rows=6951 width=116) + Select Operator [SEL_124] (rows=6951 width=116) Output:["_col0","_col1"] - Group By Operator [GBY_139] (rows=6951 width=124) + Group By Operator [GBY_123] (rows=6951 width=124) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 - <-Reducer 9 [SIMPLE_EDGE] + <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_17] PartitionCols:_col0 Group By Operator [GBY_16] (rows=55608 width=124) Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1 Merge Join Operator [MERGEJOIN_105] (rows=15995224 width=115) - Conds:RS_138._col0=RS_112._col0(Inner),Output:["_col1","_col2"] - <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] + Conds:RS_122._col0=RS_111._col0(Inner),Output:["_col1","_col2"] + <-Map 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_111] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_109] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_138] + Select Operator [SEL_109] (rows=8116 width=4) + Output:["_col0"] + Filter Operator [FIL_108] (rows=8116 width=98) + predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_122] PartitionCols:_col0 - Select Operator [SEL_137] (rows=143966864 width=119) + Select Operator [SEL_121] (rows=143966864 width=119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_136] (rows=143966864 width=119) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_30_web_sales_ws_item_sk_min) AND DynamicValue(RS_30_web_sales_ws_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_30_web_sales_ws_item_sk_bloom_filter))) and (ws_sold_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(ws_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) + Filter Operator [FIL_120] (rows=143966864 width=119) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) TableScan [TS_6] (rows=144002668 width=119) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_discount_amt"] - <-Reducer 15 [BROADCAST_EDGE] vectorized - BROADCAST [RS_128] - Please refer to the previous Group By Operator [GBY_126] - <-Reducer 12 [BROADCAST_EDGE] vectorized - BROADCAST [RS_133] - Group By Operator [GBY_132] (rows=1 width=12) + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_119] + Group By Operator [GBY_118] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized SHUFFLE [RS_117] - Group By Operator [GBY_115] (rows=1 width=12) + Group By Operator [GBY_116] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_113] (rows=8116 width=4) + Select Operator [SEL_115] (rows=669 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_109] - <-Reducer 6 [BROADCAST_EDGE] vectorized - BROADCAST [RS_135] - Group By Operator [GBY_134] (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_94] - Group By Operator [GBY_93] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_92] (rows=15995224 width=8) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_104] + Please refer to the previous Select Operator [SEL_113] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_30] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_104] (rows=15995224 width=115) + Conds:RS_130._col0=RS_110._col0(Inner),Output:["_col1","_col2"] + <-Map 6 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_110] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_109] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_130] + PartitionCols:_col0 + Select Operator [SEL_129] (rows=143966864 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_128] (rows=143966864 width=119) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_31_item_i_item_sk_min) AND DynamicValue(RS_31_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_31_item_i_item_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_0] (rows=144002668 width=119) + default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_discount_amt"] + <-Reducer 10 [BROADCAST_EDGE] vectorized + BROADCAST [RS_127] + Group By Operator [GBY_126] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 9 [CUSTOM_SIMPLE_EDGE] + FORWARD [RS_68] + Group By Operator [GBY_67] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_66] (rows=97 width=8) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_106] http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query93.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query93.q.out b/ql/src/test/results/clientpositive/perf/tez/query93.q.out index 45e6e9f..b5e6ba9 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query93.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query93.q.out @@ -43,27 +43,26 @@ POSTHOOK: Output: hdfs://### HDFS PATH ### Plan optimized by CBO. Vertex dependency in root stage -Map 9 <- Reducer 6 (BROADCAST_EDGE), Reducer 7 (BROADCAST_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) -Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Map 8 <- Reducer 6 (BROADCAST_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (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 6 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 5 vectorized - File Output Operator [FS_82] - Limit [LIM_81] (rows=100 width=112) + File Output Operator [FS_80] + Limit [LIM_79] (rows=100 width=112) Number of rows:100 - Select Operator [SEL_80] (rows=38308 width=112) + Select Operator [SEL_78] (rows=38308 width=112) Output:["_col0","_col1"] <-Reducer 4 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_79] - Group By Operator [GBY_78] (rows=38308 width=112) + SHUFFLE [RS_77] + Group By Operator [GBY_76] (rows=38308 width=112) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_18] @@ -73,7 +72,7 @@ Stage-0 Select Operator [SEL_15] (rows=15586502 width=119) Output:["_col0","_col1"] Merge Join Operator [MERGEJOIN_64] (rows=15586502 width=119) - Conds:RS_12._col0, _col2=RS_77._col0, _col2(Inner),Output:["_col3","_col4","_col7","_col9","_col10","_col11"] + Conds:RS_12._col0, _col2=RS_75._col0, _col2(Inner),Output:["_col3","_col4","_col7","_col9","_col10","_col11"] <-Reducer 2 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_12] PartitionCols:_col0, _col2 @@ -88,7 +87,7 @@ Stage-0 predicate:(sr_item_sk is not null and sr_reason_sk is not null and sr_ticket_number is not null) TableScan [TS_0] (rows=57591150 width=15) default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_reason_sk","sr_ticket_number","sr_return_quantity"] - <-Map 8 [SIMPLE_EDGE] vectorized + <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_70] PartitionCols:_col0 Select Operator [SEL_69] (rows=1 width=4) @@ -97,13 +96,13 @@ Stage-0 predicate:((r_reason_desc = 'Did not like the warranty') and r_reason_sk is not null) TableScan [TS_3] (rows=72 width=101) default@reason,reason,Tbl:COMPLETE,Col:COMPLETE,Output:["r_reason_sk","r_reason_desc"] - <-Map 9 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_77] + <-Map 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_75] PartitionCols:_col0, _col2 - Select Operator [SEL_76] (rows=575995635 width=234) + Select Operator [SEL_74] (rows=575995635 width=234) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_75] (rows=575995635 width=122) - predicate:((ss_item_sk BETWEEN DynamicValue(RS_12_store_returns_sr_item_sk_min) AND DynamicValue(RS_12_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_12_store_returns_sr_item_sk_bloom_filter))) and (ss_ticket_number BETWEEN DynamicValue(RS_12_store_returns_sr_ticket_number_min) AND DynamicValue(RS_12_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_12_store_returns_sr_ticket_number_bloom_filter))) and ss_item_sk is not null and ss_ticket_number is not null) + Filter Operator [FIL_73] (rows=575995635 width=122) + predicate:((ss_ticket_number BETWEEN DynamicValue(RS_12_store_returns_sr_ticket_number_min) AND DynamicValue(RS_12_store_returns_sr_ticket_number_max) and in_bloom_filter(ss_ticket_number, DynamicValue(RS_12_store_returns_sr_ticket_number_bloom_filter))) and ss_item_sk is not null and ss_ticket_number is not null) TableScan [TS_6] (rows=575995635 width=122) default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_ticket_number","ss_quantity","ss_sales_price"] <-Reducer 6 [BROADCAST_EDGE] vectorized @@ -111,17 +110,6 @@ Stage-0 Group By Operator [GBY_71] (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_55] - Group By Operator [GBY_54] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_53] (rows=1522298 width=4) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_63] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_74] - Group By Operator [GBY_73] (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_60] Group By Operator [GBY_59] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] http://git-wip-us.apache.org/repos/asf/hive/blob/e986fc56/ql/src/test/results/clientpositive/perf/tez/query94.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query94.q.out b/ql/src/test/results/clientpositive/perf/tez/query94.q.out index ada9f3b..e6ac653 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query94.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query94.q.out @@ -69,18 +69,16 @@ 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 1 <- Reducer 13 (BROADCAST_EDGE) +Map 15 <- 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 19 <- Map 18 (SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 16 (SIMPLE_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 <- Map 17 (SIMPLE_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 <- Map 15 (SIMPLE_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) @@ -90,22 +88,22 @@ Stage-0 limit:-1 Stage-1 Reducer 9 vectorized - File Output Operator [FS_178] - Limit [LIM_177] (rows=1 width=240) + File Output Operator [FS_168] + Limit [LIM_167] (rows=1 width=240) Number of rows:100 - Select Operator [SEL_176] (rows=1 width=240) + Select Operator [SEL_166] (rows=1 width=240) Output:["_col0","_col1","_col2"] <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_175] - Select Operator [SEL_174] (rows=1 width=240) + SHUFFLE [RS_165] + Select Operator [SEL_164] (rows=1 width=240) Output:["_col1","_col2","_col3"] - Group By Operator [GBY_173] (rows=1 width=232) + Group By Operator [GBY_163] (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_172] - Group By Operator [GBY_171] (rows=1 width=232) + PARTITION_ONLY_SHUFFLE [RS_162] + Group By Operator [GBY_161] (rows=1 width=232) Output:["_col0","_col1","_col2"],aggregations:["count(_col0)","sum(_col1)","sum(_col2)"] - Group By Operator [GBY_170] (rows=2511437 width=228) + Group By Operator [GBY_160] (rows=2511437 width=228) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0 <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_74] @@ -117,20 +115,20 @@ Stage-0 Filter Operator [FIL_41] (rows=5022875 width=229) predicate:_col14 is null Merge Join Operator [MERGEJOIN_130] (rows=10045750 width=229) - Conds:RS_38._col4=RS_169._col0(Left Outer),Output:["_col4","_col5","_col6","_col14"] - <-Reducer 19 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_169] + Conds:RS_38._col4=RS_159._col0(Left Outer),Output:["_col4","_col5","_col6","_col14"] + <-Reducer 17 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_159] PartitionCols:_col0 - Select Operator [SEL_168] (rows=8007986 width=8) + Select Operator [SEL_158] (rows=8007986 width=8) Output:["_col0","_col1"] - Group By Operator [GBY_167] (rows=8007986 width=4) + Group By Operator [GBY_157] (rows=8007986 width=4) Output:["_col0"],keys:KEY._col0 - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_166] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_156] PartitionCols:_col0 - Group By Operator [GBY_165] (rows=14398467 width=4) + Group By Operator [GBY_155] (rows=14398467 width=4) Output:["_col0"],keys:wr_order_number - Filter Operator [FIL_164] (rows=14398467 width=4) + Filter Operator [FIL_154] (rows=14398467 width=4) predicate:wr_order_number is not null TableScan [TS_25] (rows=14398467 width=4) default@web_returns,wr1,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_order_number"] @@ -140,18 +138,18 @@ Stage-0 Select Operator [SEL_37] (rows=5022875 width=231) Output:["_col4","_col5","_col6"] Merge Join Operator [MERGEJOIN_129] (rows=5022875 width=235) - Conds:RS_34._col4=RS_163._col0(Left Semi),Output:["_col3","_col4","_col5","_col6","_col14"],residual filter predicates:{(_col3 <> _col14)} + Conds:RS_34._col4=RS_153._col0(Left Semi),Output:["_col3","_col4","_col5","_col6","_col14"],residual filter predicates:{(_col3 <> _col14)} <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_34] PartitionCols:_col4 Merge Join Operator [MERGEJOIN_128] (rows=5022875 width=231) - Conds:RS_18._col2=RS_149._col0(Inner),Output:["_col3","_col4","_col5","_col6"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_149] + Conds:RS_18._col2=RS_147._col0(Inner),Output:["_col3","_col4","_col5","_col6"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_147] PartitionCols:_col0 - Select Operator [SEL_148] (rows=12 width=91) + Select Operator [SEL_146] (rows=12 width=91) Output:["_col0"] - Filter Operator [FIL_147] (rows=12 width=92) + Filter Operator [FIL_145] (rows=12 width=92) predicate:((web_company_name = 'pri') and web_site_sk is not null) TableScan [TS_9] (rows=84 width=92) default@web_site,web_site,Tbl:COMPLETE,Col:COMPLETE,Output:["web_site_sk","web_company_name"] @@ -159,13 +157,13 @@ Stage-0 SHUFFLE [RS_18] PartitionCols:_col2 Merge Join Operator [MERGEJOIN_127] (rows=15673790 width=235) - Conds:RS_15._col1=RS_141._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_141] + Conds:RS_15._col1=RS_133._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6"] + <-Map 12 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_133] PartitionCols:_col0 - Select Operator [SEL_140] (rows=784314 width=90) + Select Operator [SEL_132] (rows=784314 width=90) Output:["_col0"] - Filter Operator [FIL_139] (rows=784314 width=90) + Filter Operator [FIL_131] (rows=784314 width=90) predicate:((ca_state = 'TX') and ca_address_sk is not null) TableScan [TS_6] (rows=40000000 width=90) default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"] @@ -173,72 +171,50 @@ Stage-0 SHUFFLE [RS_15] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_126] (rows=15987241 width=239) - Conds:RS_157._col0=RS_133._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_133] - PartitionCols:_col0 - Select Operator [SEL_132] (rows=8116 width=98) - Output:["_col0"] - Filter Operator [FIL_131] (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' and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=98) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + Conds:RS_141._col0=RS_144._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_157] + SHUFFLE [RS_141] PartitionCols:_col0 - Select Operator [SEL_156] (rows=143895019 width=243) + Select Operator [SEL_140] (rows=143895019 width=243) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - Filter Operator [FIL_155] (rows=143895019 width=243) - predicate:((ws_ship_addr_sk BETWEEN DynamicValue(RS_16_customer_address_ca_address_sk_min) AND DynamicValue(RS_16_customer_address_ca_address_sk_max) and in_bloom_filter(ws_ship_addr_sk, DynamicValue(RS_16_customer_address_ca_address_sk_bloom_filter))) and (ws_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(ws_ship_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_19_web_site_web_site_sk_min) AND DynamicValue(RS_19_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_19_web_site_web_site_sk_bloom_filter))) and ws_order_number is not null 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_139] (rows=143895019 width=243) + predicate:((ws_ship_addr_sk BETWEEN DynamicValue(RS_16_customer_address_ca_address_sk_min) AND DynamicValue(RS_16_customer_address_ca_address_sk_max) and in_bloom_filter(ws_ship_addr_sk, DynamicValue(RS_16_customer_address_ca_address_sk_bloom_filter))) and ws_order_number is not null 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=243) default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_ship_date_sk","ws_ship_addr_sk","ws_web_site_sk","ws_warehouse_sk","ws_order_number","ws_ext_ship_cost","ws_net_profit"] - <-Reducer 12 [BROADCAST_EDGE] vectorized + <-Reducer 13 [BROADCAST_EDGE] vectorized BROADCAST [RS_138] Group By Operator [GBY_137] (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_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=8116 width=4) + Select Operator [SEL_134] (rows=784314 width=4) Output:["_col0"] Please refer to the previous Select Operator [SEL_132] - <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_146] - Group By Operator [GBY_145] (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_144] - Group By Operator [GBY_143] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_142] (rows=784314 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_140] - <-Reducer 16 [BROADCAST_EDGE] vectorized - BROADCAST [RS_154] - Group By Operator [GBY_153] (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_152] - Group By Operator [GBY_151] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_150] (rows=12 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_148] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_163] + <-Map 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_144] + PartitionCols:_col0 + Select Operator [SEL_143] (rows=8116 width=98) + Output:["_col0"] + Filter Operator [FIL_142] (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' and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=98) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_153] PartitionCols:_col0 - Group By Operator [GBY_162] (rows=143966743 width=7) + Group By Operator [GBY_152] (rows=143966743 width=7) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_161] (rows=143966743 width=7) + Select Operator [SEL_151] (rows=143966743 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_160] (rows=143966743 width=7) + Filter Operator [FIL_150] (rows=143966743 width=7) predicate:((ws_order_number BETWEEN DynamicValue(RS_34_ws1_ws_order_number_min) AND DynamicValue(RS_34_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_34_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null and ws_warehouse_sk is not null) TableScan [TS_22] (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_159] - Group By Operator [GBY_158] (rows=1 width=12) + BROADCAST [RS_149] + Group By Operator [GBY_148] (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_116]