http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query23.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query23.q.out b/ql/src/test/results/clientpositive/perf/tez/query23.q.out index 7784792..059195a 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query23.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query23.q.out @@ -1,7 +1,7 @@ -Warning: Shuffle Join MERGEJOIN[593][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product -Warning: Shuffle Join MERGEJOIN[594][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product -Warning: Shuffle Join MERGEJOIN[596][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product -Warning: Shuffle Join MERGEJOIN[597][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product +Warning: Shuffle Join MERGEJOIN[583][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product +Warning: Shuffle Join MERGEJOIN[584][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product +Warning: Shuffle Join MERGEJOIN[586][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product +Warning: Shuffle Join MERGEJOIN[587][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product PREHOOK: query: explain with frequent_ss_items as (select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date solddate,count(*) cnt @@ -166,399 +166,391 @@ Stage-0 limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_699] - Limit [LIM_698] (rows=1 width=112) + File Output Operator [FS_689] + Limit [LIM_688] (rows=1 width=112) Number of rows:100 - Group By Operator [GBY_697] (rows=1 width=112) + Group By Operator [GBY_687] (rows=1 width=112) Output:["_col0"],aggregations:["sum(VALUE._col0)"] <-Union 5 [CUSTOM_SIMPLE_EDGE] <-Reducer 12 [CONTAINS] - Reduce Output Operator [RS_608] - Group By Operator [GBY_607] (rows=1 width=112) + Reduce Output Operator [RS_598] + Group By Operator [GBY_597] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_605] (rows=1 width=112) + Select Operator [SEL_595] (rows=1 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_604] (rows=1 width=116) - Conds:RS_248._col2=RS_249._col0(Inner),Output:["_col3","_col4"] + Merge Join Operator [MERGEJOIN_594] (rows=1 width=116) + Conds:RS_240._col2=RS_241._col0(Inner),Output:["_col3","_col4"] <-Reducer 11 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_248] + PARTITION_ONLY_SHUFFLE [RS_240] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_592] (rows=155 width=0) - Conds:RS_245._col1=RS_642._col0(Inner),Output:["_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_582] (rows=155 width=0) + Conds:RS_237._col1=RS_632._col0(Inner),Output:["_col2","_col3","_col4"] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_642] + SHUFFLE [RS_632] PartitionCols:_col0 - Group By Operator [GBY_639] (rows=2235 width=4) + Group By Operator [GBY_629] (rows=2235 width=4) Output:["_col0"],keys:_col1 - Select Operator [SEL_638] (rows=6548799 width=12) + Select Operator [SEL_628] (rows=6548799 width=290) Output:["_col1"] - Filter Operator [FIL_637] (rows=6548799 width=12) + Filter Operator [FIL_627] (rows=6548799 width=290) predicate:(_col3 > 4L) - Select Operator [SEL_636] (rows=19646398 width=12) - Output:["_col0","_col3"] - Group By Operator [GBY_635] (rows=19646398 width=290) + Select Operator [SEL_626] (rows=19646398 width=290) + Output:["_col1","_col3"] + Group By Operator [GBY_625] (rows=19646398 width=290) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 17 [SIMPLE_EDGE] - SHUFFLE [RS_24] + SHUFFLE [RS_23] PartitionCols:_col0 - Group By Operator [GBY_23] (rows=19646398 width=290) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 - Select Operator [SEL_21] (rows=19646398 width=282) - Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_577] (rows=19646398 width=282) - Conds:RS_18._col1=RS_634._col0(Inner),Output:["_col3","_col5","_col6"] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_634] - PartitionCols:_col0 - Select Operator [SEL_633] (rows=462000 width=188) - Output:["_col0","_col1"] - Filter Operator [FIL_632] (rows=462000 width=188) - predicate:i_item_sk is not null - TableScan [TS_12] (rows=462000 width=188) - default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc"] - <-Reducer 16 [SIMPLE_EDGE] - SHUFFLE [RS_18] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_576] (rows=19646398 width=98) - Conds:RS_631._col0=RS_623._col0(Inner),Output:["_col1","_col3"] - <-Map 21 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_623] - PartitionCols:_col0 - Select Operator [SEL_622] (rows=2609 width=102) - Output:["_col0","_col1"] - Filter Operator [FIL_621] (rows=2609 width=102) - predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) - TableScan [TS_9] (rows=73049 width=102) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_year"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_631] - PartitionCols:_col0 - Select Operator [SEL_630] (rows=550076554 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_629] (rows=550076554 width=7) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_6] (rows=575995635 width=7) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] - <-Reducer 22 [BROADCAST_EDGE] vectorized - BROADCAST [RS_628] - Group By Operator [GBY_627] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_626] - Group By Operator [GBY_625] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_624] (rows=2609 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_622] + Group By Operator [GBY_22] (rows=19646398 width=290) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col3, _col5 + Merge Join Operator [MERGEJOIN_567] (rows=19646398 width=282) + Conds:RS_18._col1=RS_624._col0(Inner),Output:["_col3","_col4","_col5"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_624] + PartitionCols:_col0 + Select Operator [SEL_623] (rows=462000 width=188) + Output:["_col0","_col1"] + Filter Operator [FIL_622] (rows=462000 width=188) + predicate:i_item_sk is not null + TableScan [TS_12] (rows=462000 width=188) + default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_18] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_566] (rows=19646398 width=98) + Conds:RS_621._col0=RS_613._col0(Inner),Output:["_col1","_col3"] + <-Map 21 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_613] + PartitionCols:_col0 + Select Operator [SEL_612] (rows=2609 width=98) + Output:["_col0","_col1"] + Filter Operator [FIL_611] (rows=2609 width=102) + predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) + TableScan [TS_9] (rows=73049 width=102) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_year"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_621] + PartitionCols:_col0 + Select Operator [SEL_620] (rows=550076554 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_619] (rows=550076554 width=7) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_16_date_dim_d_date_sk_min) AND DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_6] (rows=575995635 width=7) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"] + <-Reducer 22 [BROADCAST_EDGE] vectorized + BROADCAST [RS_618] + Group By Operator [GBY_617] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_616] + Group By Operator [GBY_615] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_614] (rows=2609 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_612] <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_245] + SHUFFLE [RS_237] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_583] (rows=3941102 width=122) - Conds:RS_706._col0=RS_613._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_573] (rows=3941102 width=122) + Conds:RS_696._col0=RS_603._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_613] + PARTITION_ONLY_SHUFFLE [RS_603] PartitionCols:_col0 - Select Operator [SEL_610] (rows=50 width=12) + Select Operator [SEL_600] (rows=50 width=4) Output:["_col0"] - Filter Operator [FIL_609] (rows=50 width=12) + Filter Operator [FIL_599] (rows=50 width=12) predicate:((d_moy = 1) and (d_year = 1999) and d_date_sk is not null) TableScan [TS_3] (rows=73049 width=12) default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"] <-Map 44 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_706] + SHUFFLE [RS_696] PartitionCols:_col0 - Select Operator [SEL_705] (rows=143930993 width=127) + Select Operator [SEL_695] (rows=143930993 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_704] (rows=143930993 width=127) - predicate:((ws_item_sk BETWEEN DynamicValue(RS_246_item_i_item_sk_min) AND DynamicValue(RS_246_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_246_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_243_date_dim_d_date_sk_min) AND DynamicValue(RS_243_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_243_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_126] (rows=144002668 width=127) + Filter Operator [FIL_694] (rows=143930993 width=127) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_238_item_i_item_sk_min) AND DynamicValue(RS_238_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_238_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_235_date_dim_d_date_sk_min) AND DynamicValue(RS_235_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_235_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_122] (rows=144002668 width=127) default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_quantity","ws_list_price"] <-Reducer 14 [BROADCAST_EDGE] vectorized - BROADCAST [RS_701] - Group By Operator [GBY_700] (rows=1 width=12) + BROADCAST [RS_691] + Group By Operator [GBY_690] (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_618] - Group By Operator [GBY_616] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_608] + Group By Operator [GBY_606] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_614] (rows=50 width=4) + Select Operator [SEL_604] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_610] + Please refer to the previous Select Operator [SEL_600] <-Reducer 20 [BROADCAST_EDGE] vectorized - BROADCAST [RS_703] - Group By Operator [GBY_702] (rows=1 width=12) + BROADCAST [RS_693] + Group By Operator [GBY_692] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_647] - Group By Operator [GBY_645] (rows=1 width=12) + SHUFFLE [RS_637] + Group By Operator [GBY_635] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_643] (rows=2235 width=4) + Select Operator [SEL_633] (rows=2235 width=4) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_639] + Please refer to the previous Group By Operator [GBY_629] <-Reducer 34 [SIMPLE_EDGE] - SHUFFLE [RS_249] + SHUFFLE [RS_241] PartitionCols:_col0 - Select Operator [SEL_241] (rows=471875 width=4) + Select Operator [SEL_233] (rows=471875 width=4) Output:["_col0"] - Filter Operator [FIL_240] (rows=471875 width=228) + Filter Operator [FIL_232] (rows=471875 width=228) predicate:(_col3 > (0.95 * _col1)) - Merge Join Operator [MERGEJOIN_597] (rows=1415625 width=228) + Merge Join Operator [MERGEJOIN_587] (rows=1415625 width=228) Conds:(Inner),Output:["_col1","_col2","_col3"] <-Reducer 33 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_237] - Merge Join Operator [MERGEJOIN_596] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_229] + Merge Join Operator [MERGEJOIN_586] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_712] - Select Operator [SEL_711] (rows=1 width=8) - Filter Operator [FIL_710] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_702] + Select Operator [SEL_701] (rows=1 width=8) + Filter Operator [FIL_700] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_709] (rows=1 width=8) + Group By Operator [GBY_699] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_708] (rows=1 width=8) - Group By Operator [GBY_707] (rows=1 width=8) + Select Operator [SEL_698] (rows=1 width=8) + Group By Operator [GBY_697] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_680] - Group By Operator [GBY_676] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_670] + Group By Operator [GBY_666] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_672] (rows=11859 width=116) + Select Operator [SEL_662] (rows=11859 width=116) Output:["_col0"] - Group By Operator [GBY_669] (rows=11859 width=116) + Group By Operator [GBY_659] (rows=11859 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 26 [SIMPLE_EDGE] - SHUFFLE [RS_51] + SHUFFLE [RS_49] PartitionCols:_col0 - Group By Operator [GBY_50] (rows=11859 width=116) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_48] (rows=18762463 width=4) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_579] (rows=18762463 width=4) - Conds:RS_45._col1=RS_667._col0(Inner),Output:["_col2","_col3","_col6"] - <-Map 41 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_667] - PartitionCols:_col0 - Select Operator [SEL_665] (rows=80000000 width=4) - Output:["_col0"] - Filter Operator [FIL_664] (rows=80000000 width=4) - predicate:c_customer_sk is not null - TableScan [TS_96] (rows=80000000 width=4) - default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk"] - <-Reducer 25 [SIMPLE_EDGE] - SHUFFLE [RS_45] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_578] (rows=18762463 width=0) - Conds:RS_663._col0=RS_655._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 36 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_655] - PartitionCols:_col0 - Select Operator [SEL_654] (rows=2609 width=8) - Output:["_col0"] - Filter Operator [FIL_653] (rows=2609 width=8) - predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) - TableScan [TS_36] (rows=73049 width=8) - default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] - <-Map 24 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_663] - PartitionCols:_col0 - Select Operator [SEL_662] (rows=525327388 width=118) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_661] (rows=525327388 width=118) - predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_43_date_dim_d_date_sk_min) AND DynamicValue(RS_43_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_33] (rows=575995635 width=118) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"] - <-Reducer 37 [BROADCAST_EDGE] vectorized - BROADCAST [RS_660] - Group By Operator [GBY_659] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Map 36 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_658] - Group By Operator [GBY_657] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_656] (rows=2609 width=4) - Output:["_col0"] - Please refer to the previous Select Operator [SEL_654] + Group By Operator [GBY_48] (rows=106731 width=116) + Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 + Merge Join Operator [MERGEJOIN_569] (rows=18762463 width=116) + Conds:RS_44._col1=RS_657._col0(Inner),Output:["_col2","_col4"] + <-Map 41 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_657] + PartitionCols:_col0 + Select Operator [SEL_655] (rows=80000000 width=4) + Output:["_col0"] + Filter Operator [FIL_654] (rows=80000000 width=4) + predicate:c_customer_sk is not null + TableScan [TS_93] (rows=80000000 width=4) + default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk"] + <-Reducer 25 [SIMPLE_EDGE] + SHUFFLE [RS_44] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_568] (rows=18762463 width=112) + Conds:RS_653._col0=RS_645._col0(Inner),Output:["_col1","_col2"] + <-Map 36 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_645] + PartitionCols:_col0 + Select Operator [SEL_644] (rows=2609 width=4) + Output:["_col0"] + Filter Operator [FIL_643] (rows=2609 width=8) + predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null) + TableScan [TS_35] (rows=73049 width=8) + default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"] + <-Map 24 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_653] + PartitionCols:_col0 + Select Operator [SEL_652] (rows=525327388 width=119) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_651] (rows=525327388 width=118) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_42_date_dim_d_date_sk_min) AND DynamicValue(RS_42_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_42_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_32] (rows=575995635 width=118) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"] + <-Reducer 37 [BROADCAST_EDGE] vectorized + BROADCAST [RS_650] + Group By Operator [GBY_649] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 36 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_648] + Group By Operator [GBY_647] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_646] (rows=2609 width=4) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_644] <-Reducer 35 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_714] - Group By Operator [GBY_713] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_704] + Group By Operator [GBY_703] (rows=1 width=112) Output:["_col0"],aggregations:["max(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_681] - Group By Operator [GBY_677] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_671] + Group By Operator [GBY_667] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_673] (rows=11859 width=116) + Select Operator [SEL_663] (rows=11859 width=116) Output:["_col1"] - Please refer to the previous Group By Operator [GBY_669] + Please refer to the previous Group By Operator [GBY_659] <-Reducer 43 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_721] - Group By Operator [GBY_720] (rows=1415625 width=116) + PARTITION_ONLY_SHUFFLE [RS_711] + Group By Operator [GBY_710] (rows=1415625 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 42 [SIMPLE_EDGE] - SHUFFLE [RS_231] + SHUFFLE [RS_223] PartitionCols:_col0 - Group By Operator [GBY_230] (rows=550080312 width=116) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_228] (rows=550080312 width=114) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_590] (rows=550080312 width=114) - Conds:RS_719._col0=RS_668._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 41 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_668] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_665] - <-Map 45 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_719] - PartitionCols:_col0 - Select Operator [SEL_718] (rows=550080312 width=114) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_717] (rows=550080312 width=114) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_248_web_sales_ws_bill_customer_sk_min) AND DynamicValue(RS_248_web_sales_ws_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_248_web_sales_ws_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) - TableScan [TS_219] (rows=575995635 width=114) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] - <-Reducer 13 [BROADCAST_EDGE] vectorized - BROADCAST [RS_716] - Group By Operator [GBY_715] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 11 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_570] - Group By Operator [GBY_569] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_568] (rows=155 width=0) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_592] + Group By Operator [GBY_222] (rows=80000000 width=116) + Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col2 + Merge Join Operator [MERGEJOIN_580] (rows=550080312 width=116) + Conds:RS_709._col0=RS_658._col0(Inner),Output:["_col1","_col2"] + <-Map 41 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_658] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_655] + <-Map 45 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_709] + PartitionCols:_col0 + Select Operator [SEL_708] (rows=550080312 width=115) + Output:["_col0","_col1"] + Filter Operator [FIL_707] (rows=550080312 width=114) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_240_web_sales_ws_bill_customer_sk_min) AND DynamicValue(RS_240_web_sales_ws_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_240_web_sales_ws_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) + TableScan [TS_212] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] + <-Reducer 13 [BROADCAST_EDGE] vectorized + BROADCAST [RS_706] + Group By Operator [GBY_705] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 11 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_560] + Group By Operator [GBY_559] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_558] (rows=155 width=0) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_582] <-Reducer 4 [CONTAINS] - Reduce Output Operator [RS_603] - Group By Operator [GBY_602] (rows=1 width=112) + Reduce Output Operator [RS_593] + Group By Operator [GBY_592] (rows=1 width=112) Output:["_col0"],aggregations:["sum(_col0)"] - Select Operator [SEL_600] (rows=1 width=112) + Select Operator [SEL_590] (rows=1 width=112) Output:["_col0"] - Merge Join Operator [MERGEJOIN_599] (rows=1 width=116) - Conds:RS_122._col1=RS_123._col0(Inner),Output:["_col3","_col4"] + Merge Join Operator [MERGEJOIN_589] (rows=1 width=116) + Conds:RS_118._col1=RS_119._col0(Inner),Output:["_col3","_col4"] <-Reducer 3 [SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_122] + PARTITION_ONLY_SHUFFLE [RS_118] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_591] (rows=304 width=0) - Conds:RS_119._col2=RS_640._col0(Inner),Output:["_col1","_col3","_col4"] + Merge Join Operator [MERGEJOIN_581] (rows=304 width=0) + Conds:RS_115._col2=RS_630._col0(Inner),Output:["_col1","_col3","_col4"] <-Reducer 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_640] + SHUFFLE [RS_630] PartitionCols:_col0 - Please refer to the previous Group By Operator [GBY_639] + Please refer to the previous Group By Operator [GBY_629] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_119] + SHUFFLE [RS_115] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_575] (rows=7751875 width=101) - Conds:RS_652._col0=RS_611._col0(Inner),Output:["_col1","_col2","_col3","_col4"] + Merge Join Operator [MERGEJOIN_565] (rows=7751875 width=101) + Conds:RS_642._col0=RS_601._col0(Inner),Output:["_col1","_col2","_col3","_col4"] <-Map 8 [SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_611] + PARTITION_ONLY_SHUFFLE [RS_601] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_610] + Please refer to the previous Select Operator [SEL_600] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_652] + SHUFFLE [RS_642] PartitionCols:_col0 - Select Operator [SEL_651] (rows=285117831 width=127) + Select Operator [SEL_641] (rows=285117831 width=127) Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_650] (rows=285117831 width=127) - predicate:((cs_item_sk BETWEEN DynamicValue(RS_120_item_i_item_sk_min) AND DynamicValue(RS_120_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_120_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_117_date_dim_d_date_sk_min) AND DynamicValue(RS_117_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_117_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) + Filter Operator [FIL_640] (rows=285117831 width=127) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_116_item_i_item_sk_min) AND DynamicValue(RS_116_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_116_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_113_date_dim_d_date_sk_min) AND DynamicValue(RS_113_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_113_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) TableScan [TS_0] (rows=287989836 width=127) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity","cs_list_price"] <-Reducer 19 [BROADCAST_EDGE] vectorized - BROADCAST [RS_649] - Group By Operator [GBY_648] (rows=1 width=12) + BROADCAST [RS_639] + Group By Operator [GBY_638] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] <-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_646] - Group By Operator [GBY_644] (rows=1 width=12) + SHUFFLE [RS_636] + Group By Operator [GBY_634] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_641] (rows=2235 width=4) + Select Operator [SEL_631] (rows=2235 width=4) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_639] + Please refer to the previous Group By Operator [GBY_629] <-Reducer 9 [BROADCAST_EDGE] vectorized - BROADCAST [RS_620] - Group By Operator [GBY_619] (rows=1 width=12) + BROADCAST [RS_610] + Group By Operator [GBY_609] (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_617] - Group By Operator [GBY_615] (rows=1 width=12) + PARTITION_ONLY_SHUFFLE [RS_607] + Group By Operator [GBY_605] (rows=1 width=12) Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_612] (rows=50 width=4) + Select Operator [SEL_602] (rows=50 width=4) Output:["_col0"] - Please refer to the previous Select Operator [SEL_610] + Please refer to the previous Select Operator [SEL_600] <-Reducer 30 [SIMPLE_EDGE] - SHUFFLE [RS_123] + SHUFFLE [RS_119] PartitionCols:_col0 - Select Operator [SEL_115] (rows=471875 width=4) + Select Operator [SEL_111] (rows=471875 width=4) Output:["_col0"] - Filter Operator [FIL_114] (rows=471875 width=228) + Filter Operator [FIL_110] (rows=471875 width=228) predicate:(_col3 > (0.95 * _col1)) - Merge Join Operator [MERGEJOIN_594] (rows=1415625 width=228) + Merge Join Operator [MERGEJOIN_584] (rows=1415625 width=228) Conds:(Inner),Output:["_col1","_col2","_col3"] <-Reducer 29 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_111] - Merge Join Operator [MERGEJOIN_593] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_107] + Merge Join Operator [MERGEJOIN_583] (rows=1 width=112) Conds:(Inner),Output:["_col1"] <-Reducer 28 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_687] - Select Operator [SEL_686] (rows=1 width=8) - Filter Operator [FIL_685] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_677] + Select Operator [SEL_676] (rows=1 width=8) + Filter Operator [FIL_675] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_684] (rows=1 width=8) + Group By Operator [GBY_674] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_683] (rows=1 width=8) - Group By Operator [GBY_682] (rows=1 width=8) + Select Operator [SEL_673] (rows=1 width=8) + Group By Operator [GBY_672] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_678] - Group By Operator [GBY_674] (rows=1 width=8) + PARTITION_ONLY_SHUFFLE [RS_668] + Group By Operator [GBY_664] (rows=1 width=8) Output:["_col0"],aggregations:["count(_col0)"] - Select Operator [SEL_670] (rows=11859 width=116) + Select Operator [SEL_660] (rows=11859 width=116) Output:["_col0"] - Please refer to the previous Group By Operator [GBY_669] + Please refer to the previous Group By Operator [GBY_659] <-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_689] - Group By Operator [GBY_688] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_679] + Group By Operator [GBY_678] (rows=1 width=112) Output:["_col0"],aggregations:["max(VALUE._col0)"] <-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_679] - Group By Operator [GBY_675] (rows=1 width=112) + PARTITION_ONLY_SHUFFLE [RS_669] + Group By Operator [GBY_665] (rows=1 width=112) Output:["_col0"],aggregations:["max(_col1)"] - Select Operator [SEL_671] (rows=11859 width=116) + Select Operator [SEL_661] (rows=11859 width=116) Output:["_col1"] - Please refer to the previous Group By Operator [GBY_669] + Please refer to the previous Group By Operator [GBY_659] <-Reducer 40 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_696] - Group By Operator [GBY_695] (rows=1415625 width=116) + PARTITION_ONLY_SHUFFLE [RS_686] + Group By Operator [GBY_685] (rows=1415625 width=116) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 39 [SIMPLE_EDGE] - SHUFFLE [RS_105] + SHUFFLE [RS_101] PartitionCols:_col0 - Group By Operator [GBY_104] (rows=550080312 width=116) - Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0 - Select Operator [SEL_102] (rows=550080312 width=114) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_582] (rows=550080312 width=114) - Conds:RS_694._col0=RS_666._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 41 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_666] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_665] - <-Map 38 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_694] - PartitionCols:_col0 - Select Operator [SEL_693] (rows=550080312 width=114) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_692] (rows=550080312 width=114) - predicate:((ss_customer_sk BETWEEN DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) - TableScan [TS_93] (rows=575995635 width=114) - default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] - <-Reducer 7 [BROADCAST_EDGE] vectorized - BROADCAST [RS_691] - Group By Operator [GBY_690] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] - <-Reducer 3 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_464] - Group By Operator [GBY_463] (rows=1 width=12) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] - Select Operator [SEL_462] (rows=304 width=0) - Output:["_col0"] - Please refer to the previous Merge Join Operator [MERGEJOIN_591] + Group By Operator [GBY_100] (rows=80000000 width=116) + Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col2 + Merge Join Operator [MERGEJOIN_572] (rows=550080312 width=116) + Conds:RS_684._col0=RS_656._col0(Inner),Output:["_col1","_col2"] + <-Map 41 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_656] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_655] + <-Map 38 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_684] + PartitionCols:_col0 + Select Operator [SEL_683] (rows=550080312 width=115) + Output:["_col0","_col1"] + Filter Operator [FIL_682] (rows=550080312 width=114) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_118_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_118_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_118_catalog_sales_cs_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null) + TableScan [TS_90] (rows=575995635 width=114) + default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"] + <-Reducer 7 [BROADCAST_EDGE] vectorized + BROADCAST [RS_681] + Group By Operator [GBY_680] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_454] + Group By Operator [GBY_453] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_452] (rows=304 width=0) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_581]
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query24.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query24.q.out b/ql/src/test/results/clientpositive/perf/tez/query24.q.out index 43ece85..bd065ae 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query24.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query24.q.out @@ -166,9 +166,9 @@ Stage-0 SHUFFLE [RS_81] PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Group By Operator [GBY_80] (rows=576061174 width=932) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col18)"],keys:_col11, _col12, _col1, _col5, _col7, _col20, _col21, _col22, _col23, _col24 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col17)"],keys:_col10, _col11, _col1, _col5, _col6, _col19, _col20, _col21, _col22, _col23 Merge Join Operator [MERGEJOIN_300] (rows=589731269 width=928) - Conds:RS_76._col14, _col17=RS_332._col0, _col1(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col18","_col20","_col21","_col22","_col23","_col24"] + Conds:RS_76._col13, _col16=RS_332._col0, _col1(Inner),Output:["_col1","_col5","_col6","_col10","_col11","_col17","_col19","_col20","_col21","_col22","_col23"] <-Map 23 [SIMPLE_EDGE] vectorized SHUFFLE [RS_332] PartitionCols:_col0, _col1 @@ -180,9 +180,9 @@ Stage-0 default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"] <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_76] - PartitionCols:_col14, _col17 + PartitionCols:_col13, _col16 Merge Join Operator [MERGEJOIN_299] (rows=576061174 width=936) - Conds:RS_73._col14=RS_308._col0(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col14","_col17","_col18","_col20","_col21","_col22","_col23","_col24"] + Conds:RS_73._col13=RS_308._col0(Inner),Output:["_col1","_col5","_col6","_col10","_col11","_col13","_col16","_col17","_col19","_col20","_col21","_col22","_col23"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_308] PartitionCols:_col0 @@ -194,16 +194,16 @@ Stage-0 default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"] <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_73] - PartitionCols:_col14 + PartitionCols:_col13 Merge Join Operator [MERGEJOIN_298] (rows=576061174 width=555) - Conds:RS_70._col9, _col4=RS_344._col1, _col2(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col14","_col17","_col18"] + Conds:RS_70._col8, _col4=RS_344._col1, _col2(Inner),Output:["_col1","_col5","_col6","_col10","_col11","_col13","_col16","_col17"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_70] - PartitionCols:_col9, _col4 - Filter Operator [FIL_21] (rows=7276996 width=637) - predicate:(_col13 <> upper(_col3)) - Merge Join Operator [MERGEJOIN_293] (rows=7276996 width=637) - Conds:RS_18._col0=RS_321._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col9","_col11","_col12","_col13"] + PartitionCols:_col8, _col4 + Filter Operator [FIL_21] (rows=7276996 width=724) + predicate:(_col12 <> _col3) + Merge Join Operator [MERGEJOIN_293] (rows=7276996 width=724) + Conds:RS_18._col0=RS_321._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col8","_col10","_col11","_col12"] <-Map 22 [SIMPLE_EDGE] vectorized SHUFFLE [RS_321] PartitionCols:_col1 @@ -216,12 +216,12 @@ Stage-0 <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_18] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_292] (rows=611379 width=365) - Conds:RS_315._col2=RS_318._col4(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col7"] + Merge Join Operator [MERGEJOIN_292] (rows=611379 width=452) + Conds:RS_315._col2=RS_318._col3(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_315] PartitionCols:_col2 - Select Operator [SEL_314] (rows=40000000 width=276) + Select Operator [SEL_314] (rows=40000000 width=363) Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_313] (rows=40000000 width=276) predicate:(ca_address_sk is not null and ca_zip is not null) @@ -229,9 +229,9 @@ Stage-0 default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_zip","ca_country"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_318] - PartitionCols:_col4 - Select Operator [SEL_317] (rows=155 width=271) - Output:["_col0","_col1","_col3","_col4"] + PartitionCols:_col3 + Select Operator [SEL_317] (rows=155 width=267) + Output:["_col0","_col1","_col2","_col3"] Filter Operator [FIL_316] (rows=155 width=271) predicate:((s_market_id = 7) and s_store_sk is not null and s_zip is not null) TableScan [TS_9] (rows=1704 width=270) @@ -281,9 +281,9 @@ Stage-0 SHUFFLE [RS_37] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_36] (rows=84010488 width=843) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col13, _col14, _col21, _col6, _col7, _col9, _col10, _col17, _col23 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col12, _col13, _col20, _col6, _col7, _col8, _col9, _col16, _col21 Merge Join Operator [MERGEJOIN_295] (rows=138508741 width=824) - Conds:RS_32._col0, _col3=RS_331._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col13","_col14","_col17","_col21","_col23"] + Conds:RS_32._col0, _col3=RS_331._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col8","_col9","_col12","_col13","_col16","_col20","_col21"] <-Map 23 [SIMPLE_EDGE] vectorized SHUFFLE [RS_331] PartitionCols:_col0, _col1 @@ -292,23 +292,23 @@ Stage-0 SHUFFLE [RS_32] PartitionCols:_col0, _col3 Merge Join Operator [MERGEJOIN_294] (rows=84010488 width=820) - Conds:RS_29._col1, _col2=RS_30._col0, _col9(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col9","_col10","_col13","_col14","_col17","_col21","_col23"] + Conds:RS_29._col1, _col2=RS_30._col0, _col9(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col8","_col9","_col12","_col13","_col16","_col20","_col21"] <-Reducer 15 [SIMPLE_EDGE] SHUFFLE [RS_30] PartitionCols:_col0, _col9 - Select Operator [SEL_22] (rows=7276996 width=637) - Output:["_col0","_col2","_col3","_col6","_col9","_col10","_col12"] + Select Operator [SEL_22] (rows=7276996 width=724) + Output:["_col0","_col2","_col3","_col6","_col9","_col10","_col11"] Please refer to the previous Filter Operator [FIL_21] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_29] PartitionCols:_col1, _col2 Merge Join Operator [MERGEJOIN_291] (rows=76612563 width=382) - Conds:RS_328._col0=RS_306._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col10"] + Conds:RS_328._col0=RS_306._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9"] <-Map 7 [SIMPLE_EDGE] vectorized SHUFFLE [RS_306] PartitionCols:_col0 - Select Operator [SEL_304] (rows=7000 width=385) - Output:["_col0","_col1","_col2","_col4","_col5"] + Select Operator [SEL_304] (rows=7000 width=295) + Output:["_col0","_col1","_col2","_col3","_col4"] Filter Operator [FIL_302] (rows=7000 width=384) predicate:((i_color = 'orchid') and i_item_sk is not null) Please refer to the previous TableScan [TS_3] http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query25.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query25.q.out b/ql/src/test/results/clientpositive/perf/tez/query25.q.out index 5d1c9fc..0a0cfcc 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query25.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query25.q.out @@ -145,11 +145,11 @@ Stage-0 SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2, _col3 Group By Operator [GBY_48] (rows=4248052806 width=808) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col5)","sum(_col20)","sum(_col12)"],keys:_col25, _col26, _col28, _col29 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col5)","sum(_col16)","sum(_col10)"],keys:_col19, _col20, _col22, _col23 Top N Key Operator [TNK_95] (rows=4248052806 width=807) - keys:_col25, _col26, _col28, _col29,sort order:++++,top n:100 + keys:_col19, _col20, _col22, _col23,sort order:++++,top n:100 Merge Join Operator [MERGEJOIN_214] (rows=4248052806 width=807) - Conds:RS_44._col3=RS_258._col0(Inner),Output:["_col5","_col12","_col20","_col25","_col26","_col28","_col29"] + Conds:RS_44._col3=RS_258._col0(Inner),Output:["_col5","_col10","_col16","_col19","_col20","_col22","_col23"] <-Map 21 [SIMPLE_EDGE] vectorized SHUFFLE [RS_258] PartitionCols:_col0 @@ -163,7 +163,7 @@ Stage-0 SHUFFLE [RS_44] PartitionCols:_col3 Merge Join Operator [MERGEJOIN_213] (rows=4248052806 width=623) - Conds:RS_41._col1=RS_255._col0(Inner),Output:["_col3","_col5","_col12","_col20","_col25","_col26"] + Conds:RS_41._col1=RS_255._col0(Inner),Output:["_col3","_col5","_col10","_col16","_col19","_col20"] <-Map 20 [SIMPLE_EDGE] vectorized SHUFFLE [RS_255] PartitionCols:_col0 @@ -177,12 +177,12 @@ Stage-0 SHUFFLE [RS_41] PartitionCols:_col1 Merge Join Operator [MERGEJOIN_212] (rows=4248052806 width=343) - Conds:RS_38._col1, _col2, _col4=RS_39._col8, _col9, _col10(Inner),Output:["_col1","_col3","_col5","_col12","_col20"] + Conds:RS_38._col1, _col2, _col4=RS_39._col6, _col7, _col8(Inner),Output:["_col1","_col3","_col5","_col10","_col16"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_39] - PartitionCols:_col8, _col9, _col10 + PartitionCols:_col6, _col7, _col8 Merge Join Operator [MERGEJOIN_211] (rows=1893811716 width=235) - Conds:RS_25._col2, _col1=RS_26._col1, _col2(Inner),Output:["_col3","_col8","_col9","_col10","_col11"] + Conds:RS_25._col2, _col1=RS_26._col1, _col2(Inner),Output:["_col3","_col6","_col7","_col8","_col9"] <-Reducer 10 [SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_25] PartitionCols:_col2, _col1 @@ -191,7 +191,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_223] PartitionCols:_col0 - Select Operator [SEL_219] (rows=351 width=12) + Select Operator [SEL_219] (rows=351 width=4) Output:["_col0"] Filter Operator [FIL_216] (rows=351 width=12) predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) @@ -221,7 +221,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_225] PartitionCols:_col0 - Select Operator [SEL_220] (rows=351 width=12) + Select Operator [SEL_220] (rows=351 width=4) Output:["_col0"] Filter Operator [FIL_217] (rows=351 width=12) predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) @@ -269,7 +269,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_221] PartitionCols:_col0 - Select Operator [SEL_218] (rows=50 width=12) + Select Operator [SEL_218] (rows=50 width=4) Output:["_col0"] Filter Operator [FIL_215] (rows=50 width=12) predicate:((d_moy = 4) and (d_year = 2000) and d_date_sk is not null) http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query26.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query26.q.out b/ql/src/test/results/clientpositive/perf/tez/query26.q.out index 7c42069..62bcbe8 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query26.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query26.q.out @@ -83,11 +83,11 @@ Stage-0 SHUFFLE [RS_29] PartitionCols:_col0 Group By Operator [GBY_28] (rows=462000 width=476) - Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col18 + Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col12 Top N Key Operator [TNK_55] (rows=809521 width=100) - keys:_col18,sort order:+,top n:100 + keys:_col12,sort order:+,top n:100 Merge Join Operator [MERGEJOIN_99] (rows=809521 width=100) - Conds:RS_24._col2=RS_124._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"] + Conds:RS_24._col2=RS_124._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col12"] <-Map 13 [SIMPLE_EDGE] vectorized SHUFFLE [RS_124] PartitionCols:_col0 @@ -105,7 +105,7 @@ Stage-0 <-Map 12 [SIMPLE_EDGE] vectorized SHUFFLE [RS_121] PartitionCols:_col0 - Select Operator [SEL_120] (rows=2300 width=174) + Select Operator [SEL_120] (rows=2300 width=4) Output:["_col0"] Filter Operator [FIL_119] (rows=2300 width=174) predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) @@ -119,7 +119,7 @@ Stage-0 <-Map 10 [SIMPLE_EDGE] vectorized SHUFFLE [RS_110] PartitionCols:_col0 - Select Operator [SEL_109] (rows=652 width=8) + Select Operator [SEL_109] (rows=652 width=4) Output:["_col0"] Filter Operator [FIL_108] (rows=652 width=8) predicate:((d_year = 1998) and d_date_sk is not null) @@ -133,7 +133,7 @@ Stage-0 <-Map 8 [SIMPLE_EDGE] vectorized PARTITION_ONLY_SHUFFLE [RS_102] PartitionCols:_col0 - Select Operator [SEL_101] (rows=14776 width=265) + Select Operator [SEL_101] (rows=14776 width=4) Output:["_col0"] Filter Operator [FIL_100] (rows=14776 width=268) predicate:((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null)
