http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query44.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query44.q.out b/ql/src/test/results/clientpositive/perf/tez/query44.q.out index 1a360e7..0dbce70 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query44.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query44.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[131][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Stage 'Reducer 9' is a cross product +Warning: Shuffle Join MERGEJOIN[141][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Stage 'Reducer 9' is a cross product PREHOOK: query: explain select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing from(select * @@ -87,126 +87,126 @@ Stage-0 limit:100 Stage-1 Reducer 4 vectorized - File Output Operator [FS_178] - Limit [LIM_177] (rows=100 width=185) + File Output Operator [FS_188] + Limit [LIM_187] (rows=100 width=185) Number of rows:100 - Select Operator [SEL_176] (rows=1393898919384048 width=185) + Select Operator [SEL_186] (rows=1393898919384048 width=185) Output:["_col0","_col1","_col2"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_101] Select Operator [SEL_100] (rows=1393898919384048 width=185) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_135] (rows=1393898919384048 width=185) + Merge Join Operator [MERGEJOIN_145] (rows=1393898919384048 width=185) Conds:RS_97._col3=RS_98._col3(Inner),Output:["_col1","_col3","_col5"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_97] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_132] (rows=1267180808338276 width=185) - Conds:RS_138._col0=RS_170._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_142] (rows=1267180808338276 width=185) + Conds:RS_148._col0=RS_180._col0(Inner),Output:["_col1","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_138] + SHUFFLE [RS_148] PartitionCols:_col0 - Select Operator [SEL_137] (rows=462000 width=1436) + Select Operator [SEL_147] (rows=462000 width=1436) Output:["_col0","_col1"] - Filter Operator [FIL_136] (rows=462000 width=1436) + Filter Operator [FIL_146] (rows=462000 width=1436) predicate:i_item_sk is not null TableScan [TS_0] (rows=462000 width=1436) default@item,i1,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_product_name"] <-Reducer 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_170] + SHUFFLE [RS_180] PartitionCols:_col0 - Select Operator [SEL_169] (rows=1151982528066248 width=185) + Select Operator [SEL_179] (rows=1151982528066248 width=185) Output:["_col0","_col1"] - Filter Operator [FIL_168] (rows=1151982528066248 width=185) + Filter Operator [FIL_178] (rows=1151982528066248 width=185) predicate:((rank_window_0 < 11) and _col2 is not null) - PTF Operator [PTF_167] (rows=3455947584198744 width=185) + PTF Operator [PTF_177] (rows=3455947584198744 width=185) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 ASC NULLS FIRST","partition by:":"0"}] - Select Operator [SEL_166] (rows=3455947584198744 width=185) + Select Operator [SEL_176] (rows=3455947584198744 width=185) Output:["_col2","_col3"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_38] PartitionCols:0 Filter Operator [FIL_37] (rows=3455947584198744 width=185) predicate:(_col3 > (0.9 * _col1)) - Merge Join Operator [MERGEJOIN_131] (rows=10367842752596232 width=185) + Merge Join Operator [MERGEJOIN_141] (rows=10367842752596232 width=185) Conds:(Inner),(Inner),Output:["_col1","_col2","_col3"] <-Reducer 13 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_158] - Select Operator [SEL_157] (rows=71999454 width=88) + PARTITION_ONLY_SHUFFLE [RS_168] + Select Operator [SEL_167] (rows=71999454 width=88) Output:["_col0"] - Group By Operator [GBY_156] (rows=71999454 width=88) + Group By Operator [GBY_166] (rows=71999454 width=88) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_155] + SHUFFLE [RS_165] PartitionCols:_col0 - Group By Operator [GBY_154] (rows=143998908 width=88) + Group By Operator [GBY_164] (rows=143998908 width=88) Output:["_col0","_col1","_col2"],aggregations:["sum(_col1)","count(_col1)"],keys:410 - Select Operator [SEL_153] (rows=143998908 width=88) + Select Operator [SEL_163] (rows=143998908 width=88) Output:["_col1"] - Filter Operator [FIL_152] (rows=143998908 width=88) + Filter Operator [FIL_162] (rows=143998908 width=88) predicate:((ss_store_sk = 410) and ss_hdemo_sk is null) TableScan [TS_18] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_hdemo_sk","ss_store_sk","ss_net_profit"] <-Reducer 15 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_165] - Select Operator [SEL_164] (rows=143998908 width=88) + PARTITION_ONLY_SHUFFLE [RS_175] + Select Operator [SEL_174] (rows=143998908 width=88) Output:["_col0","_col1"] - Group By Operator [GBY_163] (rows=143998908 width=88) + Group By Operator [GBY_173] (rows=143998908 width=88) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_162] + SHUFFLE [RS_172] PartitionCols:_col0 - Group By Operator [GBY_161] (rows=287997817 width=88) + Group By Operator [GBY_171] (rows=287997817 width=88) Output:["_col0","_col1","_col2"],aggregations:["sum(ss_net_profit)","count(ss_net_profit)"],keys:ss_item_sk - Select Operator [SEL_160] (rows=287997817 width=88) + Select Operator [SEL_170] (rows=287997817 width=88) Output:["ss_item_sk","ss_net_profit"] - Filter Operator [FIL_159] (rows=287997817 width=88) + Filter Operator [FIL_169] (rows=287997817 width=88) predicate:(ss_store_sk = 410) TableScan [TS_26] (rows=575995635 width=88) default@store_sales,ss1,Tbl:COMPLETE,Col:NONE,Output:["ss_item_sk","ss_store_sk","ss_net_profit"] <-Reducer 8 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_151] - Select Operator [SEL_150] (rows=1 width=8) - Filter Operator [FIL_149] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_161] + Select Operator [SEL_160] (rows=1 width=8) + Filter Operator [FIL_159] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_148] (rows=1 width=8) + Group By Operator [GBY_158] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_147] - Group By Operator [GBY_146] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_157] + Group By Operator [GBY_156] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_145] (rows=71999454 width=88) - Group By Operator [GBY_144] (rows=71999454 width=88) + Select Operator [SEL_155] (rows=71999454 width=88) + Group By Operator [GBY_154] (rows=71999454 width=88) Output:["_col0"],keys:KEY._col0 <-Map 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_143] + SHUFFLE [RS_153] PartitionCols:_col0 - Group By Operator [GBY_142] (rows=143998908 width=88) + Group By Operator [GBY_152] (rows=143998908 width=88) Output:["_col0"],keys:410 - Select Operator [SEL_141] (rows=143998908 width=88) - Filter Operator [FIL_140] (rows=143998908 width=88) + Select Operator [SEL_151] (rows=143998908 width=88) + Filter Operator [FIL_150] (rows=143998908 width=88) predicate:((ss_store_sk = 410) and ss_hdemo_sk is null) TableScan [TS_3] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_hdemo_sk","ss_store_sk"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_98] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_134] (rows=1267180808338276 width=185) - Conds:RS_139._col0=RS_175._col0(Inner),Output:["_col1","_col3"] + Merge Join Operator [MERGEJOIN_144] (rows=1267180808338276 width=185) + Conds:RS_149._col0=RS_185._col0(Inner),Output:["_col1","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_139] + SHUFFLE [RS_149] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_137] + Please refer to the previous Select Operator [SEL_147] <-Reducer 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_175] + SHUFFLE [RS_185] PartitionCols:_col0 - Select Operator [SEL_174] (rows=1151982528066248 width=185) + Select Operator [SEL_184] (rows=1151982528066248 width=185) Output:["_col0","_col1"] - Filter Operator [FIL_173] (rows=1151982528066248 width=185) + Filter Operator [FIL_183] (rows=1151982528066248 width=185) predicate:((rank_window_0 < 11) and _col2 is not null) - PTF Operator [PTF_172] (rows=3455947584198744 width=185) + PTF Operator [PTF_182] (rows=3455947584198744 width=185) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 DESC NULLS LAST","partition by:":"0"}] - Select Operator [SEL_171] (rows=3455947584198744 width=185) + Select Operator [SEL_181] (rows=3455947584198744 width=185) Output:["_col2","_col3"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_83]
http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query45.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query45.q.out b/ql/src/test/results/clientpositive/perf/tez/query45.q.out index 704af01..c9d820b 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query45.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query45.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[87][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[132][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product PREHOOK: query: explain select ca_zip, ca_county, sum(ws_sales_price) from web_sales, customer, customer_address, date_dim, item @@ -40,30 +40,33 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Reducer 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 8 (SIMPLE_EDGE) -Reducer 12 <- Map 8 (CUSTOM_SIMPLE_EDGE) -Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE) +Map 14 <- Reducer 11 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) +Reducer 10 <- Reducer 15 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) +Reducer 12 <- Map 8 (SIMPLE_EDGE) +Reducer 13 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 9 <- Map 8 (SIMPLE_EDGE), Reducer 11 (ONE_TO_ONE_EDGE) +Reducer 9 <- Map 8 (SIMPLE_EDGE), Reducer 12 (ONE_TO_ONE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_120] - Limit [LIM_119] (rows=100 width=152) + File Output Operator [FS_172] + Limit [LIM_171] (rows=100 width=152) Number of rows:100 - Select Operator [SEL_118] (rows=95833781 width=152) + Select Operator [SEL_170] (rows=95833781 width=152) Output:["_col0","_col1","_col2"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_117] - Group By Operator [GBY_116] (rows=95833781 width=152) + SHUFFLE [RS_169] + Group By Operator [GBY_168] (rows=95833781 width=152) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_53] @@ -76,104 +79,126 @@ Stage-0 predicate:((substr(_col8, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') or CASE WHEN ((_col14 = 0L)) THEN (false) WHEN (_col17 is not null) THEN (true) WHEN (_col13 is null) THEN (null) WHEN ((_col15 < _col14)) THEN (null) ELSE (false) END) Select Operator [SEL_49] (rows=191667562 width=152) Output:["_col3","_col7","_col8","_col13","_col14","_col15","_col17"] - Merge Join Operator [MERGEJOIN_87] (rows=191667562 width=152) + Merge Join Operator [MERGEJOIN_132] (rows=191667562 width=152) Conds:(Inner),Output:["_col3","_col4","_col6","_col8","_col12","_col16","_col17"] - <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_115] - Group By Operator [GBY_114] (rows=1 width=16) + <-Reducer 13 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_167] + Group By Operator [GBY_166] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)","count(VALUE._col1)"] <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_104] - Group By Operator [GBY_102] (rows=1 width=16) + SHUFFLE [RS_149] + Group By Operator [GBY_147] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["count()","count(i_item_id)"] - Select Operator [SEL_99] (rows=231000 width=1436) + Select Operator [SEL_144] (rows=231000 width=1436) Output:["i_item_id"] - Filter Operator [FIL_96] (rows=231000 width=1436) + Filter Operator [FIL_141] (rows=231000 width=1436) predicate:(i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) TableScan [TS_6] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_46] - Merge Join Operator [MERGEJOIN_86] (rows=191667562 width=135) + Merge Join Operator [MERGEJOIN_131] (rows=191667562 width=135) Conds:RS_43._col0=RS_44._col6(Inner),Output:["_col3","_col4","_col6","_col8","_col12"] <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_44] PartitionCols:_col6 - Merge Join Operator [MERGEJOIN_85] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_130] (rows=174243235 width=135) Conds:RS_29._col0=RS_30._col1(Inner),Output:["_col1","_col3","_col6","_col7"] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_30] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_84] (rows=158402938 width=135) - Conds:RS_110._col0=RS_113._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_110] - PartitionCols:_col0 - Select Operator [SEL_109] (rows=144002668 width=135) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_108] (rows=144002668 width=135) - predicate:(ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) - TableScan [TS_16] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_sales_price"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_113] - PartitionCols:_col0 - Select Operator [SEL_112] (rows=18262 width=1119) - Output:["_col0"] - Filter Operator [FIL_111] (rows=18262 width=1119) - predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) - TableScan [TS_19] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_29] + PARTITION_ONLY_SHUFFLE [RS_29] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_83] (rows=508200 width=1436) - Conds:RS_100._col1=RS_107._col0(Left Outer),Output:["_col0","_col1","_col3"] + Merge Join Operator [MERGEJOIN_128] (rows=508200 width=1436) + Conds:RS_145._col1=RS_152._col0(Left Outer),Output:["_col0","_col1","_col3"] <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_100] + SHUFFLE [RS_145] PartitionCols:_col1 - Select Operator [SEL_97] (rows=462000 width=1436) + Select Operator [SEL_142] (rows=462000 width=1436) Output:["_col0","_col1"] - Filter Operator [FIL_94] (rows=462000 width=1436) + Filter Operator [FIL_139] (rows=462000 width=1436) predicate:i_item_sk is not null Please refer to the previous TableScan [TS_6] - <-Reducer 11 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_107] + <-Reducer 12 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_152] PartitionCols:_col0 - Select Operator [SEL_106] (rows=115500 width=1436) + Select Operator [SEL_151] (rows=115500 width=1436) Output:["_col0","_col1"] - Group By Operator [GBY_105] (rows=115500 width=1436) + Group By Operator [GBY_150] (rows=115500 width=1436) Output:["_col0"],keys:KEY._col0 <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_103] + SHUFFLE [RS_148] PartitionCols:_col0 - Group By Operator [GBY_101] (rows=231000 width=1436) + Group By Operator [GBY_146] (rows=231000 width=1436) Output:["_col0"],keys:i_item_id - Select Operator [SEL_98] (rows=231000 width=1436) + Select Operator [SEL_143] (rows=231000 width=1436) Output:["i_item_id"] - Filter Operator [FIL_95] (rows=231000 width=1436) + Filter Operator [FIL_140] (rows=231000 width=1436) predicate:(i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) Please refer to the previous TableScan [TS_6] + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_30] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_129] (rows=158402938 width=135) + Conds:RS_165._col0=RS_155._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_155] + PartitionCols:_col0 + Select Operator [SEL_154] (rows=18262 width=1119) + Output:["_col0"] + Filter Operator [FIL_153] (rows=18262 width=1119) + predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null) + TableScan [TS_19] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_qoy"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_165] + PartitionCols:_col0 + Select Operator [SEL_164] (rows=144002668 width=135) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_163] (rows=144002668 width=135) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_29_item_i_item_sk_min) AND DynamicValue(RS_29_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_29_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_23_date_dim_d_date_sk_min) AND DynamicValue(RS_23_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_23_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) + TableScan [TS_16] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_sales_price"] + <-Reducer 11 [BROADCAST_EDGE] vectorized + BROADCAST [RS_162] + Group By Operator [GBY_161] (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] + PARTITION_ONLY_SHUFFLE [RS_114] + Group By Operator [GBY_113] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_112] (rows=508200 width=1436) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_128] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_160] + Group By Operator [GBY_159] (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_158] + Group By Operator [GBY_157] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_156] (rows=18262 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_154] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_82] (rows=88000001 width=860) - Conds:RS_90._col1=RS_93._col0(Inner),Output:["_col0","_col3","_col4"] + Merge Join Operator [MERGEJOIN_127] (rows=88000001 width=860) + Conds:RS_135._col1=RS_138._col0(Inner),Output:["_col0","_col3","_col4"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_90] + SHUFFLE [RS_135] PartitionCols:_col1 - Select Operator [SEL_89] (rows=80000000 width=860) + Select Operator [SEL_134] (rows=80000000 width=860) Output:["_col0","_col1"] - Filter Operator [FIL_88] (rows=80000000 width=860) + Filter Operator [FIL_133] (rows=80000000 width=860) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) TableScan [TS_0] (rows=80000000 width=860) default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_93] + SHUFFLE [RS_138] PartitionCols:_col0 - Select Operator [SEL_92] (rows=40000000 width=1014) + Select Operator [SEL_137] (rows=40000000 width=1014) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_91] (rows=40000000 width=1014) + Filter Operator [FIL_136] (rows=40000000 width=1014) predicate:ca_address_sk is not null TableScan [TS_3] (rows=40000000 width=1014) default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_county","ca_zip"] http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query46.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query46.q.out b/ql/src/test/results/clientpositive/perf/tez/query46.q.out index 29795b2..708a852 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query46.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query46.q.out @@ -69,24 +69,30 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 14 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Map 10 <- Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 5 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) +Reducer 12 <- Map 16 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 13 <- Map 18 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 6 <- Map 5 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) -Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Map 6 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Map 6 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 4 vectorized - File Output Operator [FS_110] - Limit [LIM_109] (rows=100 width=88) + File Output Operator [FS_192] + Limit [LIM_191] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_108] (rows=463823414 width=88) + Select Operator [SEL_190] (rows=463823414 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_46] @@ -94,98 +100,153 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] Filter Operator [FIL_44] (rows=463823414 width=88) predicate:(_col5 <> _col8) - Merge Join Operator [MERGEJOIN_85] (rows=463823414 width=88) - Conds:RS_41._col0=RS_107._col1(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9","_col10"] + Merge Join Operator [MERGEJOIN_145] (rows=463823414 width=88) + Conds:RS_41._col0=RS_189._col1(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9","_col10"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_41] + PARTITION_ONLY_SHUFFLE [RS_41] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_80] (rows=88000001 width=860) - Conds:RS_88._col1=RS_91._col0(Inner),Output:["_col0","_col2","_col3","_col5"] - <-Map 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_91] + Merge Join Operator [MERGEJOIN_140] (rows=88000001 width=860) + Conds:RS_148._col1=RS_151._col0(Inner),Output:["_col0","_col2","_col3","_col5"] + <-Map 6 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_151] PartitionCols:_col0 - Select Operator [SEL_90] (rows=40000000 width=1014) + Select Operator [SEL_150] (rows=40000000 width=1014) Output:["_col0","_col1"] - Filter Operator [FIL_89] (rows=40000000 width=1014) + Filter Operator [FIL_149] (rows=40000000 width=1014) predicate:ca_address_sk is not null TableScan [TS_3] (rows=40000000 width=1014) default@customer_address,current_addr,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_city"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_88] + SHUFFLE [RS_148] PartitionCols:_col1 - Select Operator [SEL_87] (rows=80000000 width=860) + Select Operator [SEL_147] (rows=80000000 width=860) Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_86] (rows=80000000 width=860) + Filter Operator [FIL_146] (rows=80000000 width=860) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) TableScan [TS_0] (rows=80000000 width=860) default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name"] - <-Reducer 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_107] + <-Reducer 8 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_189] PartitionCols:_col1 - Select Operator [SEL_106] (rows=421657640 width=88) + Select Operator [SEL_188] (rows=421657640 width=88) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_105] (rows=421657640 width=88) + Group By Operator [GBY_187] (rows=421657640 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3 - <-Reducer 6 [SIMPLE_EDGE] + <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_35] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_34] (rows=843315281 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","sum(_col7)"],keys:_col1, _col17, _col3, _col5 - Merge Join Operator [MERGEJOIN_84] (rows=843315281 width=88) - Conds:RS_30._col3=RS_92._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col17"] - <-Map 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_92] + Merge Join Operator [MERGEJOIN_144] (rows=843315281 width=88) + Conds:RS_30._col3=RS_152._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7","_col17"] + <-Map 6 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_152] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_90] - <-Reducer 11 [SIMPLE_EDGE] + Please refer to the previous Select Operator [SEL_150] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_83] (rows=766650239 width=88) - Conds:RS_27._col2=RS_104._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_104] + Merge Join Operator [MERGEJOIN_143] (rows=766650239 width=88) + Conds:RS_27._col2=RS_174._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col7"] + <-Map 18 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_174] PartitionCols:_col0 - Select Operator [SEL_103] (rows=7200 width=107) + Select Operator [SEL_173] (rows=7200 width=107) Output:["_col0"] - Filter Operator [FIL_102] (rows=7200 width=107) + Filter Operator [FIL_172] (rows=7200 width=107) predicate:(((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) TableScan [TS_15] (rows=7200 width=107) default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_dep_count","hd_vehicle_count"] - <-Reducer 10 [SIMPLE_EDGE] + <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_82] (rows=696954748 width=88) - Conds:RS_24._col4=RS_101._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_101] + Merge Join Operator [MERGEJOIN_142] (rows=696954748 width=88) + Conds:RS_24._col4=RS_166._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col7"] + <-Map 16 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_166] PartitionCols:_col0 - Select Operator [SEL_100] (rows=852 width=1910) + Select Operator [SEL_165] (rows=852 width=1910) Output:["_col0"] - Filter Operator [FIL_99] (rows=852 width=1910) + Filter Operator [FIL_164] (rows=852 width=1910) predicate:((s_city) IN ('Cedar Grove', 'Wildwood', 'Union', 'Salem', 'Highland Park') and s_store_sk is not null) TableScan [TS_12] (rows=1704 width=1910) default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_city"] - <-Reducer 9 [SIMPLE_EDGE] + <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_81] (rows=633595212 width=88) - Conds:RS_95._col0=RS_98._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_98] + Merge Join Operator [MERGEJOIN_141] (rows=633595212 width=88) + Conds:RS_186._col0=RS_158._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 14 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_158] PartitionCols:_col0 - Select Operator [SEL_97] (rows=18263 width=1119) + Select Operator [SEL_157] (rows=18263 width=1119) Output:["_col0"] - Filter Operator [FIL_96] (rows=18263 width=1119) + Filter Operator [FIL_156] (rows=18263 width=1119) predicate:((d_dow) IN (6, 0) and (d_year) IN (1998, 1999, 2000) and d_date_sk is not null) TableScan [TS_9] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_dow"] - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_95] + <-Map 10 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_186] PartitionCols:_col0 - Select Operator [SEL_94] (rows=575995635 width=88) + Select Operator [SEL_185] (rows=575995635 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Filter Operator [FIL_93] (rows=575995635 width=88) - predicate:(ss_addr_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) + Filter Operator [FIL_184] (rows=575995635 width=88) + predicate:((ss_addr_sk BETWEEN DynamicValue(RS_31_customer_address_ca_address_sk_min) AND DynamicValue(RS_31_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_31_customer_address_ca_address_sk_bloom_filter))) and (ss_customer_sk BETWEEN DynamicValue(RS_41_customer_c_customer_sk_min) AND DynamicValue(RS_41_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_41_customer_c_customer_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_28_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_28_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_28_household_demographics_hd_demo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN Dy namicValue(RS_25_store_s_store_sk_min) AND DynamicValue(RS_25_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_25_store_s_store_sk_bloom_filter))) and ss_addr_sk is not null and ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) TableScan [TS_6] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_ticket_number","ss_coupon_amt","ss_net_profit"] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_163] + Group By Operator [GBY_162] (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_161] + Group By Operator [GBY_160] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_159] (rows=18263 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_157] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_171] + Group By Operator [GBY_170] (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_169] + Group By Operator [GBY_168] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_167] (rows=852 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_165] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_179] + Group By Operator [GBY_178] (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 + PARTITION_ONLY_SHUFFLE [RS_177] + Group By Operator [GBY_176] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_175] (rows=7200 width=107) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_173] + <-Reducer 5 [BROADCAST_EDGE] vectorized + BROADCAST [RS_183] + Group By Operator [GBY_182] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=88000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_117] + Group By Operator [GBY_116] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=88000000)"] + Select Operator [SEL_115] (rows=88000001 width=860) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_140] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_181] + Group By Operator [GBY_180] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=40000000)"] + <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_155] + Group By Operator [GBY_154] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=40000000)"] + Select Operator [SEL_153] (rows=40000000 width=1014) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_150] http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query47.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query47.q.out b/ql/src/test/results/clientpositive/perf/tez/query47.q.out index 2989fce..d034ea9 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query47.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query47.q.out @@ -101,11 +101,15 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage +Map 1 <- Reducer 13 (BROADCAST_EDGE), Reducer 15 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE) Reducer 10 <- Reducer 5 (SIMPLE_EDGE) Reducer 11 <- Reducer 10 (SIMPLE_EDGE) +Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE) +Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 12 (SIMPLE_EDGE) -Reducer 3 <- Map 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 3 <- Map 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 16 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) Reducer 5 <- Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 11 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) @@ -117,16 +121,16 @@ Stage-0 limit:-1 Stage-1 Reducer 8 vectorized - File Output Operator [FS_215] - Limit [LIM_214] (rows=100 width=88) + File Output Operator [FS_320] + Limit [LIM_319] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_213] (rows=843315280 width=88) + Select Operator [SEL_318] (rows=843315280 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 7 [SIMPLE_EDGE] SHUFFLE [RS_108] Select Operator [SEL_107] (rows=843315280 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_189] (rows=843315280 width=88) + Merge Join Operator [MERGEJOIN_279] (rows=843315280 width=88) Conds:RS_103._col0, _col1, _col2, _col3, (_col5 + 1)=RS_104._col0, _col1, _col2, _col3, _col8(Inner),RS_104._col0, _col1, _col2, _col3, _col8=RS_105._col0, _col1, _col2, _col3, (_col5 - 1)(Inner),Output:["_col4","_col6","_col10","_col11","_col12","_col13","_col19"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_104] @@ -144,72 +148,105 @@ Stage-0 Select Operator [SEL_64] (rows=383325119 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 10 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_211] + SHUFFLE [RS_316] PartitionCols:_col3, _col2, _col4, _col5 - Select Operator [SEL_210] (rows=383325119 width=88) + Select Operator [SEL_315] (rows=383325119 width=88) Output:["avg_window_0","_col0","_col1","_col2","_col3","_col4","_col5","_col6"] - PTF Operator [PTF_209] (rows=383325119 width=88) + PTF Operator [PTF_314] (rows=383325119 width=88) Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col3 ASC NULLS FIRST, _col2 ASC NULLS FIRST, _col4 ASC NULLS FIRST, _col5 ASC NULLS FIRST, _col0 ASC NULLS FIRST","partition by:":"_col3, _col2, _col4, _col5, _col0"}] - Select Operator [SEL_208] (rows=383325119 width=88) + Select Operator [SEL_313] (rows=383325119 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_205] + SHUFFLE [RS_310] PartitionCols:_col3, _col2, _col4, _col5, _col0 - Group By Operator [GBY_202] (rows=383325119 width=88) + Group By Operator [GBY_307] (rows=383325119 width=88) 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_93] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5 Group By Operator [GBY_92] (rows=766650239 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col3)"],keys:_col5, _col6, _col8, _col9, _col11, _col12 - Merge Join Operator [MERGEJOIN_188] (rows=766650239 width=88) - Conds:RS_88._col2=RS_201._col0(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col11","_col12"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_201] + Merge Join Operator [MERGEJOIN_278] (rows=766650239 width=88) + Conds:RS_88._col2=RS_298._col0(Inner),Output:["_col3","_col5","_col6","_col8","_col9","_col11","_col12"] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_298] PartitionCols:_col0 - Select Operator [SEL_200] (rows=1704 width=1910) + Select Operator [SEL_297] (rows=1704 width=1910) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_199] (rows=1704 width=1910) + Filter Operator [FIL_296] (rows=1704 width=1910) predicate:(s_company_name is not null and s_store_name is not null and s_store_sk is not null) TableScan [TS_79] (rows=1704 width=1910) default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_name","s_company_name"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_88] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_187] (rows=696954748 width=88) - Conds:RS_85._col1=RS_198._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_198] + Merge Join Operator [MERGEJOIN_277] (rows=696954748 width=88) + Conds:RS_85._col1=RS_290._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col8","_col9"] + <-Map 14 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_290] PartitionCols:_col0 - Select Operator [SEL_197] (rows=462000 width=1436) + Select Operator [SEL_289] (rows=462000 width=1436) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_196] (rows=462000 width=1436) + Filter Operator [FIL_288] (rows=462000 width=1436) predicate:(i_brand is not null and i_category is not null and i_item_sk is not null) TableScan [TS_76] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_category"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_85] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_186] (rows=633595212 width=88) - Conds:RS_192._col0=RS_195._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_192] - PartitionCols:_col0 - Select Operator [SEL_191] (rows=575995635 width=88) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_190] (rows=575995635 width=88) - predicate:(ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_70] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] + Merge Join Operator [MERGEJOIN_276] (rows=633595212 width=88) + Conds:RS_306._col0=RS_282._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"] <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_195] + SHUFFLE [RS_282] PartitionCols:_col0 - Select Operator [SEL_194] (rows=73048 width=1119) + Select Operator [SEL_281] (rows=73048 width=1119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_193] (rows=73048 width=1119) + Filter Operator [FIL_280] (rows=73048 width=1119) predicate:(((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) TableScan [TS_73] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_306] + PartitionCols:_col0 + Select Operator [SEL_305] (rows=575995635 width=88) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_304] (rows=575995635 width=88) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_86_item_i_item_sk_min) AND DynamicValue(RS_86_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_86_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_83_date_dim_d_date_sk_min) AND DynamicValue(RS_83_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_83_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_89_store_s_store_sk_min) AND DynamicValue(RS_89_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_89_store_s_store_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_70] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_sales_price"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_287] + Group By Operator [GBY_286] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_285] + Group By Operator [GBY_284] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_283] (rows=73048 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_281] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_295] + Group By Operator [GBY_294] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_293] + Group By Operator [GBY_292] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_291] (rows=462000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_289] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_303] + Group By Operator [GBY_302] (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 + SHUFFLE [RS_301] + Group By Operator [GBY_300] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_299] (rows=1704 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_297] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_105] PartitionCols:_col0, _col1, _col2, _col3, (_col5 - 1) @@ -222,9 +259,9 @@ Stage-0 Select Operator [SEL_97] (rows=383325119 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_203] + SHUFFLE [RS_308] PartitionCols:_col3, _col2, _col4, _col5 - Please refer to the previous Group By Operator [GBY_202] + Please refer to the previous Group By Operator [GBY_307] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_103] PartitionCols:_col0, _col1, _col2, _col3, (_col5 + 1) @@ -237,7 +274,7 @@ Stage-0 Select Operator [SEL_27] (rows=383325119 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] <-Reducer 5 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_204] + SHUFFLE [RS_309] PartitionCols:_col3, _col2, _col4, _col5 - Please refer to the previous Group By Operator [GBY_202] + Please refer to the previous Group By Operator [GBY_307]
