http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query58.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query58.q.out b/ql/src/test/results/clientpositive/perf/tez/query58.q.out index b2da513..b3f9bbb 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query58.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query58.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[265][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 18' is a cross product +Warning: Shuffle Join MERGEJOIN[403][tables = [$hdt$_4, $hdt$_5]] in Stage 'Reducer 24' is a cross product PREHOOK: query: explain with ss_items as (select i_item_id item_id @@ -130,32 +130,41 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Reducer 9 (SIMPLE_EDGE) -Reducer 11 <- Map 23 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 13 <- Reducer 12 (SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Reducer 20 (ONE_TO_ONE_EDGE) -Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) -Reducer 18 <- Map 21 (CUSTOM_SIMPLE_EDGE), Reducer 17 (CUSTOM_SIMPLE_EDGE) -Reducer 19 <- Map 21 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) +Map 1 <- Reducer 19 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) +Map 28 <- Reducer 12 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE) +Map 29 <- Reducer 16 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE) +Reducer 10 <- Reducer 18 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE) +Reducer 12 <- Map 7 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Map 29 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (SIMPLE_EDGE) +Reducer 16 <- Map 7 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Map 17 (SIMPLE_EDGE), Reducer 26 (ONE_TO_ONE_EDGE) +Reducer 19 <- Reducer 18 (CUSTOM_SIMPLE_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 20 <- Reducer 19 (SIMPLE_EDGE) -Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 20 <- Reducer 18 (CUSTOM_SIMPLE_EDGE) +Reducer 21 <- Reducer 18 (CUSTOM_SIMPLE_EDGE) +Reducer 23 <- Map 22 (CUSTOM_SIMPLE_EDGE) +Reducer 24 <- Map 27 (CUSTOM_SIMPLE_EDGE), Reducer 23 (CUSTOM_SIMPLE_EDGE) +Reducer 25 <- Map 27 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) +Reducer 26 <- Reducer 25 (SIMPLE_EDGE) +Reducer 3 <- Reducer 18 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 10 (ONE_TO_ONE_EDGE), Reducer 13 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) +Reducer 5 <- Reducer 11 (ONE_TO_ONE_EDGE), Reducer 15 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) -Reducer 8 <- Map 22 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) -Reducer 9 <- Reducer 15 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Map 28 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 6 vectorized - File Output Operator [FS_321] - Limit [LIM_320] (rows=100 width=88) + File Output Operator [FS_480] + Limit [LIM_479] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_319] (rows=1442 width=88) + Select Operator [SEL_478] (rows=1442 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_161] @@ -163,172 +172,238 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] Filter Operator [FIL_154] (rows=1442 width=88) predicate:(_col1 BETWEEN (0.9 * _col3) AND (1.1 * _col3) and _col1 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col3 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col3 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col5 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col5 BETWEEN (0.9 * _col3) AND (1.1 * _col3)) - Merge Join Operator [MERGEJOIN_279] (rows=766650239 width=88) - Conds:RS_308._col0=RS_313._col0(Inner),RS_308._col0=RS_318._col0(Inner),Output:["_col0","_col1","_col3","_col5"] - <-Reducer 10 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_313] + Merge Join Operator [MERGEJOIN_417] (rows=766650239 width=88) + Conds:RS_459._col0=RS_468._col0(Inner),RS_459._col0=RS_477._col0(Inner),Output:["_col0","_col1","_col3","_col5"] + <-Reducer 11 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_468] PartitionCols:_col0 - Group By Operator [GBY_312] (rows=348477374 width=88) + Group By Operator [GBY_467] (rows=348477374 width=88) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 9 [SIMPLE_EDGE] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_97] PartitionCols:_col0 Group By Operator [GBY_96] (rows=696954748 width=88) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_277] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_415] (rows=696954748 width=88) Conds:RS_92._col0=RS_93._col0(Inner),Output:["_col2","_col4"] - <-Reducer 15 [SIMPLE_EDGE] + <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_93] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_267] (rows=80353 width=1119) - Conds:RS_290._col1=RS_306._col0(Inner),Output:["_col0"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_290] + Merge Join Operator [MERGEJOIN_405] (rows=80353 width=1119) + Conds:RS_436._col1=RS_452._col0(Inner),Output:["_col0"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_436] PartitionCols:_col1 - Select Operator [SEL_289] (rows=73049 width=1119) + Select Operator [SEL_435] (rows=73049 width=1119) Output:["_col0","_col1"] - Filter Operator [FIL_288] (rows=73049 width=1119) + Filter Operator [FIL_434] (rows=73049 width=1119) predicate:(d_date is not null and d_date_sk is not null) TableScan [TS_6] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"] - <-Reducer 20 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_306] + <-Reducer 26 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_452] PartitionCols:_col0 - Group By Operator [GBY_305] (rows=40176 width=1119) + Group By Operator [GBY_451] (rows=40176 width=1119) Output:["_col0"],keys:KEY._col0 - <-Reducer 19 [SIMPLE_EDGE] + <-Reducer 25 [SIMPLE_EDGE] SHUFFLE [RS_32] PartitionCols:_col0 Group By Operator [GBY_31] (rows=80353 width=1119) Output:["_col0"],keys:_col2 - Merge Join Operator [MERGEJOIN_266] (rows=80353 width=1119) - Conds:RS_27._col1=RS_303._col1(Inner),Output:["_col2"] - <-Map 21 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_303] + Merge Join Operator [MERGEJOIN_404] (rows=80353 width=1119) + Conds:RS_27._col1=RS_449._col1(Inner),Output:["_col2"] + <-Map 27 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_449] PartitionCols:_col1 - Select Operator [SEL_301] (rows=73049 width=1119) + Select Operator [SEL_447] (rows=73049 width=1119) Output:["_col0","_col1"] - Filter Operator [FIL_299] (rows=73049 width=1119) + Filter Operator [FIL_445] (rows=73049 width=1119) predicate:(d_date is not null and d_week_seq is not null) TableScan [TS_21] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date","d_week_seq"] - <-Reducer 18 [SIMPLE_EDGE] + <-Reducer 24 [SIMPLE_EDGE] SHUFFLE [RS_27] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_265] (rows=36524 width=1128) + Merge Join Operator [MERGEJOIN_403] (rows=36524 width=1128) Conds:(Inner),Output:["_col1"] - <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized - SHUFFLE [RS_304] - Select Operator [SEL_302] (rows=36524 width=1119) + <-Map 27 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_450] + Select Operator [SEL_448] (rows=36524 width=1119) Output:["_col0"] - Filter Operator [FIL_300] (rows=36524 width=1119) + Filter Operator [FIL_446] (rows=36524 width=1119) predicate:((d_date = '1998-02-19') and d_week_seq is not null) Please refer to the previous TableScan [TS_21] - <-Reducer 17 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_298] - Select Operator [SEL_297] (rows=1 width=8) - Filter Operator [FIL_296] (rows=1 width=8) + <-Reducer 23 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_444] + Select Operator [SEL_443] (rows=1 width=8) + Filter Operator [FIL_442] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_295] (rows=1 width=8) + Group By Operator [GBY_441] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_294] - Group By Operator [GBY_293] (rows=1 width=8) + <-Map 22 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_440] + Group By Operator [GBY_439] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_292] (rows=36524 width=1119) - Filter Operator [FIL_291] (rows=36524 width=1119) + Select Operator [SEL_438] (rows=36524 width=1119) + Filter Operator [FIL_437] (rows=36524 width=1119) predicate:(d_date = '1998-02-19') TableScan [TS_9] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date"] - <-Reducer 8 [SIMPLE_EDGE] + <-Reducer 9 [SIMPLE_EDGE] SHUFFLE [RS_92] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_268] (rows=633595212 width=88) - Conds:RS_311._col1=RS_286._col0(Inner),Output:["_col0","_col2","_col4"] + Merge Join Operator [MERGEJOIN_406] (rows=633595212 width=88) + Conds:RS_466._col1=RS_422._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_286] + SHUFFLE [RS_422] PartitionCols:_col0 - Select Operator [SEL_284] (rows=462000 width=1436) + Select Operator [SEL_419] (rows=462000 width=1436) Output:["_col0","_col1"] - Filter Operator [FIL_283] (rows=462000 width=1436) + Filter Operator [FIL_418] (rows=462000 width=1436) predicate:(i_item_id is not null and i_item_sk is not null) TableScan [TS_3] (rows=462000 width=1436) default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"] - <-Map 22 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_311] + <-Map 28 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_466] PartitionCols:_col1 - Select Operator [SEL_310] (rows=575995635 width=88) + Select Operator [SEL_465] (rows=575995635 width=88) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_309] (rows=575995635 width=88) - predicate:(ss_item_sk is not null and ss_sold_date_sk is not null) + Filter Operator [FIL_464] (rows=575995635 width=88) + predicate:((ss_item_sk BETWEEN DynamicValue(RS_90_item_i_item_sk_min) AND DynamicValue(RS_90_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_90_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_93_date_dim_d_date_sk_min) AND DynamicValue(RS_93_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_93_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not null and ss_sold_date_sk is not null) TableScan [TS_50] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_ext_sales_price"] - <-Reducer 13 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_318] + <-Reducer 12 [BROADCAST_EDGE] vectorized + BROADCAST [RS_461] + Group By Operator [GBY_460] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_430] + Group By Operator [GBY_427] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_423] (rows=462000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_419] + <-Reducer 20 [BROADCAST_EDGE] vectorized + BROADCAST [RS_463] + Group By Operator [GBY_462] (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] + SHUFFLE [RS_321] + Group By Operator [GBY_320] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_319] (rows=80353 width=1119) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_405] + <-Reducer 15 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_477] PartitionCols:_col0 - Group By Operator [GBY_317] (rows=87121617 width=135) + Group By Operator [GBY_476] (rows=87121617 width=135) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 - <-Reducer 12 [SIMPLE_EDGE] + <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_147] PartitionCols:_col0 Group By Operator [GBY_146] (rows=174243235 width=135) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_278] (rows=174243235 width=135) + Merge Join Operator [MERGEJOIN_416] (rows=174243235 width=135) Conds:RS_142._col0=RS_143._col0(Inner),Output:["_col2","_col4"] - <-Reducer 15 [SIMPLE_EDGE] + <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_143] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_267] - <-Reducer 11 [SIMPLE_EDGE] + Please refer to the previous Merge Join Operator [MERGEJOIN_405] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_142] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_272] (rows=158402938 width=135) - Conds:RS_316._col1=RS_287._col0(Inner),Output:["_col0","_col2","_col4"] + Merge Join Operator [MERGEJOIN_410] (rows=158402938 width=135) + Conds:RS_475._col1=RS_424._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_287] + SHUFFLE [RS_424] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_284] - <-Map 23 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_316] + Please refer to the previous Select Operator [SEL_419] + <-Map 29 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_475] PartitionCols:_col1 - Select Operator [SEL_315] (rows=144002668 width=135) + Select Operator [SEL_474] (rows=144002668 width=135) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_314] (rows=144002668 width=135) - predicate:(ws_item_sk is not null and ws_sold_date_sk is not null) + Filter Operator [FIL_473] (rows=144002668 width=135) + predicate:((ws_item_sk BETWEEN DynamicValue(RS_140_item_i_item_sk_min) AND DynamicValue(RS_140_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_140_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_143_date_dim_d_date_sk_min) AND DynamicValue(RS_143_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_143_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null) TableScan [TS_100] (rows=144002668 width=135) default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_sales_price"] + <-Reducer 16 [BROADCAST_EDGE] vectorized + BROADCAST [RS_470] + Group By Operator [GBY_469] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_431] + Group By Operator [GBY_428] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_425] (rows=462000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_419] + <-Reducer 21 [BROADCAST_EDGE] vectorized + BROADCAST [RS_472] + Group By Operator [GBY_471] (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] + SHUFFLE [RS_367] + Group By Operator [GBY_366] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_365] (rows=80353 width=1119) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_405] <-Reducer 4 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_308] + FORWARD [RS_459] PartitionCols:_col0 - Group By Operator [GBY_307] (rows=174233858 width=135) + Group By Operator [GBY_458] (rows=174233858 width=135) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0 <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_47] PartitionCols:_col0 Group By Operator [GBY_46] (rows=348467716 width=135) Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col4 - Merge Join Operator [MERGEJOIN_276] (rows=348467716 width=135) + Merge Join Operator [MERGEJOIN_414] (rows=348467716 width=135) Conds:RS_42._col0=RS_43._col0(Inner),Output:["_col2","_col4"] - <-Reducer 15 [SIMPLE_EDGE] + <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_43] PartitionCols:_col0 - Please refer to the previous Merge Join Operator [MERGEJOIN_267] + Please refer to the previous Merge Join Operator [MERGEJOIN_405] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_42] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_264] (rows=316788826 width=135) - Conds:RS_282._col1=RS_285._col0(Inner),Output:["_col0","_col2","_col4"] + Merge Join Operator [MERGEJOIN_402] (rows=316788826 width=135) + Conds:RS_457._col1=RS_420._col0(Inner),Output:["_col0","_col2","_col4"] <-Map 7 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_285] + SHUFFLE [RS_420] PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_284] + Please refer to the previous Select Operator [SEL_419] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_282] + SHUFFLE [RS_457] PartitionCols:_col1 - Select Operator [SEL_281] (rows=287989836 width=135) + Select Operator [SEL_456] (rows=287989836 width=135) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_280] (rows=287989836 width=135) - predicate:(cs_item_sk is not null and cs_sold_date_sk is not null) + Filter Operator [FIL_455] (rows=287989836 width=135) + predicate:((cs_item_sk BETWEEN DynamicValue(RS_40_item_i_item_sk_min) AND DynamicValue(RS_40_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_40_item_i_item_sk_bloom_filter))) and (cs_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(cs_sold_date_sk, DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and cs_item_sk is not null and cs_sold_date_sk is not null) TableScan [TS_0] (rows=287989836 width=135) default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_item_sk","cs_ext_sales_price"] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_454] + Group By Operator [GBY_453] (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] + SHUFFLE [RS_271] + Group By Operator [GBY_270] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_269] (rows=80353 width=1119) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_405] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_433] + Group By Operator [GBY_432] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_429] + Group By Operator [GBY_426] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_421] (rows=462000 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_419]
http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query59.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query59.q.out b/ql/src/test/results/clientpositive/perf/tez/query59.q.out index 1dd841b..6b2dcc3 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query59.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query59.q.out @@ -87,127 +87,156 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Map 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Map 1 <- Reducer 17 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE) +Map 18 <- Reducer 14 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE) +Reducer 10 <- Map 18 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE) +Reducer 12 <- Map 15 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE) +Reducer 13 <- Map 19 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Reducer 14 <- Map 8 (CUSTOM_SIMPLE_EDGE) +Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE) Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Reducer 10 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 4 <- Map 15 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 16 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 13 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Reducer 2 (SIMPLE_EDGE) -Reducer 9 <- Map 12 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) +Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_129] - Limit [LIM_128] (rows=100 width=88) + File Output Operator [FS_229] + Limit [LIM_228] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_127] (rows=421657640 width=88) + Select Operator [SEL_227] (rows=421657640 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] <-Reducer 6 [SIMPLE_EDGE] SHUFFLE [RS_60] Select Operator [SEL_59] (rows=421657640 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Merge Join Operator [MERGEJOIN_104] (rows=421657640 width=88) + Merge Join Operator [MERGEJOIN_180] (rows=421657640 width=88) Conds:RS_56._col2, _col1=RS_57._col1, (_col0 - 52)(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col12","_col13","_col14","_col15","_col16","_col17"] - <-Reducer 10 [SIMPLE_EDGE] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_57] PartitionCols:_col1, (_col0 - 52) Select Operator [SEL_55] (rows=383325119 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - Merge Join Operator [MERGEJOIN_103] (rows=383325119 width=88) - Conds:RS_52._col1=RS_126._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col11"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_126] + Merge Join Operator [MERGEJOIN_179] (rows=383325119 width=88) + Conds:RS_52._col1=RS_216._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col11"] + <-Map 19 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_216] PartitionCols:_col0 - Select Operator [SEL_125] (rows=1704 width=1910) + Select Operator [SEL_215] (rows=1704 width=1910) Output:["_col0","_col1"] - Filter Operator [FIL_124] (rows=1704 width=1910) + Filter Operator [FIL_214] (rows=1704 width=1910) predicate:(s_store_id is not null and s_store_sk is not null) TableScan [TS_46] (rows=1704 width=1910) default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id"] - <-Reducer 9 [SIMPLE_EDGE] + <-Reducer 12 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_102] (rows=348477374 width=88) - Conds:RS_123._col0=RS_118._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_118] + Merge Join Operator [MERGEJOIN_178] (rows=348477374 width=88) + Conds:RS_226._col0=RS_211._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_211] PartitionCols:_col1 - Select Operator [SEL_116] (rows=8116 width=1119) + Select Operator [SEL_209] (rows=8116 width=1119) Output:["_col1"] - Filter Operator [FIL_114] (rows=8116 width=1119) + Filter Operator [FIL_207] (rows=8116 width=1119) predicate:(d_month_seq BETWEEN 1197 AND 1208 and d_week_seq is not null) TableScan [TS_15] (rows=73049 width=1119) default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_week_seq"] - <-Reducer 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_123] + <-Reducer 11 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_226] PartitionCols:_col0 - Group By Operator [GBY_122] (rows=316797606 width=88) + Group By Operator [GBY_225] (rows=316797606 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)"],keys:KEY._col0, KEY._col1 - <-Reducer 2 [SIMPLE_EDGE] + <-Reducer 10 [SIMPLE_EDGE] SHUFFLE [RS_40] PartitionCols:_col0, _col1 Group By Operator [GBY_39] (rows=633595212 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)","sum(_col3)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 Select Operator [SEL_37] (rows=633595212 width=88) Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8"] - Merge Join Operator [MERGEJOIN_98] (rows=633595212 width=88) - Conds:RS_107._col0=RS_110._col0(Inner),Output:["_col1","_col2","_col4","_col5"] - <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_107] - PartitionCols:_col0 - Select Operator [SEL_106] (rows=575995635 width=88) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_105] (rows=575995635 width=88) - predicate:(ss_sold_date_sk is not null and ss_store_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] - <-Map 11 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_110] + Merge Join Operator [MERGEJOIN_177] (rows=633595212 width=88) + Conds:RS_224._col0=RS_185._col0(Inner),Output:["_col1","_col2","_col4","_col5"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_185] PartitionCols:_col0 - Select Operator [SEL_109] (rows=73049 width=1119) + Select Operator [SEL_182] (rows=73049 width=1119) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_108] (rows=73049 width=1119) + Filter Operator [FIL_181] (rows=73049 width=1119) predicate:(d_date_sk is not null and d_week_seq is not null) TableScan [TS_3] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_week_seq","d_day_name"] + <-Map 18 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_224] + PartitionCols:_col0 + Select Operator [SEL_223] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_222] (rows=575995635 width=88) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_35_date_dim_d_date_sk_min) AND DynamicValue(RS_35_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_35_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_53_store_s_store_sk_min) AND DynamicValue(RS_53_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_53_store_s_store_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_28] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] + <-Reducer 14 [BROADCAST_EDGE] vectorized + BROADCAST [RS_213] + Group By Operator [GBY_212] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_190] + Group By Operator [GBY_188] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_186] (rows=73049 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_182] + <-Reducer 20 [BROADCAST_EDGE] vectorized + BROADCAST [RS_221] + Group By Operator [GBY_220] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 19 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_219] + Group By Operator [GBY_218] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_217] (rows=1704 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_215] <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col2, _col1 Select Operator [SEL_27] (rows=383325119 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] - Merge Join Operator [MERGEJOIN_100] (rows=383325119 width=88) - Conds:RS_24._col1=RS_121._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13"] - <-Map 13 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_121] + Merge Join Operator [MERGEJOIN_176] (rows=383325119 width=88) + Conds:RS_24._col1=RS_195._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13"] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_195] PartitionCols:_col0 - Select Operator [SEL_120] (rows=1704 width=1910) + Select Operator [SEL_194] (rows=1704 width=1910) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_119] (rows=1704 width=1910) + Filter Operator [FIL_193] (rows=1704 width=1910) predicate:(s_store_id is not null and s_store_sk is not null) TableScan [TS_18] (rows=1704 width=1910) default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_99] (rows=348477374 width=88) - Conds:RS_112._col0=RS_117._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - <-Map 12 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_117] + Merge Join Operator [MERGEJOIN_175] (rows=348477374 width=88) + Conds:RS_205._col0=RS_210._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + <-Map 15 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_210] PartitionCols:_col1 - Select Operator [SEL_115] (rows=8116 width=1119) + Select Operator [SEL_208] (rows=8116 width=1119) Output:["_col1"] - Filter Operator [FIL_113] (rows=8116 width=1119) + Filter Operator [FIL_206] (rows=8116 width=1119) predicate:(d_month_seq BETWEEN 1185 AND 1196 and d_week_seq is not null) Please refer to the previous TableScan [TS_15] <-Reducer 3 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_112] + SHUFFLE [RS_205] PartitionCols:_col0 - Group By Operator [GBY_111] (rows=316797606 width=88) + Group By Operator [GBY_204] (rows=316797606 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_12] @@ -216,5 +245,41 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1 Select Operator [SEL_9] (rows=633595212 width=88) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] - Please refer to the previous Merge Join Operator [MERGEJOIN_98] + Merge Join Operator [MERGEJOIN_174] (rows=633595212 width=88) + Conds:RS_203._col0=RS_183._col0(Inner),Output:["_col1","_col2","_col4","_col5"] + <-Map 8 [SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_183] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_182] + <-Map 1 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_203] + PartitionCols:_col0 + Select Operator [SEL_202] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_201] (rows=575995635 width=88) + predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_7_date_dim_d_date_sk_min) AND DynamicValue(RS_7_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_7_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(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_sold_date_sk is not null and ss_store_sk is not null) + TableScan [TS_0] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"] + <-Reducer 17 [BROADCAST_EDGE] vectorized + BROADCAST [RS_200] + Group By Operator [GBY_199] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized + SHUFFLE [RS_198] + Group By Operator [GBY_197] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_196] (rows=1704 width=1910) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_194] + <-Reducer 9 [BROADCAST_EDGE] vectorized + BROADCAST [RS_192] + Group By Operator [GBY_191] (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_189] + Group By Operator [GBY_187] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_184] (rows=73049 width=1119) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_182] http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/query6.q.out b/ql/src/test/results/clientpositive/perf/tez/query6.q.out index bafd175..caa0e0e 100644 --- a/ql/src/test/results/clientpositive/perf/tez/query6.q.out +++ b/ql/src/test/results/clientpositive/perf/tez/query6.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[111][tables = [$hdt$_5, $hdt$_6]] in Stage 'Reducer 12' is a cross product +Warning: Shuffle Join MERGEJOIN[171][tables = [$hdt$_5, $hdt$_6]] in Stage 'Reducer 13' is a cross product PREHOOK: query: explain select a.ca_state state, count(*) cnt from customer_address a @@ -52,175 +52,212 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Map 8 (SIMPLE_EDGE) -Reducer 11 <- Reducer 10 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 19 (CUSTOM_SIMPLE_EDGE) -Reducer 13 <- Map 20 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) -Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) -Reducer 19 <- Map 18 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 9 (ONE_TO_ONE_EDGE) -Reducer 3 <- Map 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Reducer 16 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Reducer 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Map 16 <- Reducer 15 (BROADCAST_EDGE), Reducer 19 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE) +Reducer 10 <- Map 9 (SIMPLE_EDGE) +Reducer 11 <- Map 9 (SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE) +Reducer 13 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 22 (CUSTOM_SIMPLE_EDGE) +Reducer 14 <- Map 23 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE) +Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) +Reducer 19 <- Reducer 18 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 10 (ONE_TO_ONE_EDGE) +Reducer 22 <- Map 21 (SIMPLE_EDGE) +Reducer 3 <- Map 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 18 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 6 <- Reducer 5 (SIMPLE_EDGE) Reducer 7 <- Reducer 6 (SIMPLE_EDGE) -Reducer 9 <- Map 8 (SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 Reducer 7 vectorized - File Output Operator [FS_159] - Limit [LIM_158] (rows=100 width=88) + File Output Operator [FS_225] + Limit [LIM_224] (rows=100 width=88) Number of rows:100 - Select Operator [SEL_157] (rows=127775039 width=88) + Select Operator [SEL_223] (rows=127775039 width=88) Output:["_col0","_col1"] <-Reducer 6 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_156] - Filter Operator [FIL_155] (rows=127775039 width=88) + SHUFFLE [RS_222] + Filter Operator [FIL_221] (rows=127775039 width=88) predicate:(_col1 >= 10L) - Group By Operator [GBY_154] (rows=383325119 width=88) + Group By Operator [GBY_220] (rows=383325119 width=88) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 5 [SIMPLE_EDGE] SHUFFLE [RS_69] PartitionCols:_col0 Group By Operator [GBY_68] (rows=766650239 width=88) Output:["_col0","_col1"],aggregations:["count()"],keys:_col9 - Merge Join Operator [MERGEJOIN_114] (rows=766650239 width=88) + Merge Join Operator [MERGEJOIN_174] (rows=766650239 width=88) Conds:RS_64._col4=RS_65._col0(Inner),Output:["_col9"] - <-Reducer 13 [SIMPLE_EDGE] + <-Reducer 14 [SIMPLE_EDGE] SHUFFLE [RS_65] PartitionCols:_col0 Select Operator [SEL_54] (rows=169400 width=1436) Output:["_col0"] Filter Operator [FIL_53] (rows=169400 width=1436) predicate:(_col4 > (1.2 * CAST( _col0 AS decimal(16,6)))) - Merge Join Operator [MERGEJOIN_112] (rows=508200 width=1436) - Conds:RS_50._col1=RS_153._col2(Inner),Output:["_col0","_col3","_col4"] - <-Map 20 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_153] + Merge Join Operator [MERGEJOIN_172] (rows=508200 width=1436) + Conds:RS_50._col1=RS_214._col2(Inner),Output:["_col0","_col3","_col4"] + <-Map 23 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_214] PartitionCols:_col2 - Select Operator [SEL_152] (rows=462000 width=1436) + Select Operator [SEL_213] (rows=462000 width=1436) Output:["_col0","_col1","_col2"] - Filter Operator [FIL_151] (rows=462000 width=1436) + Filter Operator [FIL_212] (rows=462000 width=1436) predicate:(i_category is not null and i_item_sk is not null) TableScan [TS_44] (rows=462000 width=1436) default@item,i,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price","i_category"] - <-Reducer 12 [SIMPLE_EDGE] + <-Reducer 13 [SIMPLE_EDGE] SHUFFLE [RS_50] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_111] (rows=231000 width=1445) + Merge Join Operator [MERGEJOIN_171] (rows=231000 width=1445) Conds:(Inner),Output:["_col0","_col1"] - <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_144] - Select Operator [SEL_143] (rows=1 width=8) - Filter Operator [FIL_142] (rows=1 width=8) + <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_205] + Select Operator [SEL_204] (rows=1 width=8) + Filter Operator [FIL_203] (rows=1 width=8) predicate:(sq_count_check(_col0) <= 1) - Group By Operator [GBY_141] (rows=1 width=8) + Group By Operator [GBY_202] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] - <-Reducer 10 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_140] - Group By Operator [GBY_139] (rows=1 width=8) + <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_201] + Group By Operator [GBY_200] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_138] (rows=9131 width=1119) - Group By Operator [GBY_137] (rows=9131 width=1119) + Select Operator [SEL_199] (rows=9131 width=1119) + Group By Operator [GBY_198] (rows=9131 width=1119) Output:["_col0"],keys:KEY._col0 - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_125] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_185] PartitionCols:_col0 - Group By Operator [GBY_123] (rows=18262 width=1119) + Group By Operator [GBY_183] (rows=18262 width=1119) Output:["_col0"],keys:d_month_seq - Select Operator [SEL_121] (rows=18262 width=1119) + Select Operator [SEL_181] (rows=18262 width=1119) Output:["d_month_seq"] - Filter Operator [FIL_119] (rows=18262 width=1119) + Filter Operator [FIL_179] (rows=18262 width=1119) predicate:((d_moy = 2) and (d_year = 2000)) TableScan [TS_3] (rows=73049 width=1119) default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_month_seq","d_year","d_moy"] - <-Reducer 19 [CUSTOM_SIMPLE_EDGE] vectorized - PARTITION_ONLY_SHUFFLE [RS_150] - Select Operator [SEL_149] (rows=231000 width=1436) + <-Reducer 22 [CUSTOM_SIMPLE_EDGE] vectorized + PARTITION_ONLY_SHUFFLE [RS_211] + Select Operator [SEL_210] (rows=231000 width=1436) Output:["_col0","_col1"] - Group By Operator [GBY_148] (rows=231000 width=1436) + Group By Operator [GBY_209] (rows=231000 width=1436) Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0 - <-Map 18 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_147] + <-Map 21 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_208] PartitionCols:_col0 - Group By Operator [GBY_146] (rows=462000 width=1436) + Group By Operator [GBY_207] (rows=462000 width=1436) Output:["_col0","_col1","_col2"],aggregations:["sum(i_current_price)","count(i_current_price)"],keys:i_category - Filter Operator [FIL_145] (rows=462000 width=1436) + Filter Operator [FIL_206] (rows=462000 width=1436) predicate:i_category is not null TableScan [TS_23] (rows=462000 width=1436) default@item,j,Tbl:COMPLETE,Col:NONE,Output:["i_current_price","i_category"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_64] PartitionCols:_col4 - Merge Join Operator [MERGEJOIN_113] (rows=696954748 width=88) + Merge Join Operator [MERGEJOIN_173] (rows=696954748 width=88) Conds:RS_61._col5=RS_62._col0(Inner),Output:["_col4","_col9"] - <-Reducer 16 [SIMPLE_EDGE] + <-Reducer 18 [SIMPLE_EDGE] SHUFFLE [RS_62] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_110] (rows=88000001 width=860) - Conds:RS_133._col1=RS_136._col0(Inner),Output:["_col0","_col3"] - <-Map 15 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_133] + Merge Join Operator [MERGEJOIN_170] (rows=88000001 width=860) + Conds:RS_192._col1=RS_195._col0(Inner),Output:["_col0","_col3"] + <-Map 17 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_192] PartitionCols:_col1 - Select Operator [SEL_132] (rows=80000000 width=860) + Select Operator [SEL_191] (rows=80000000 width=860) Output:["_col0","_col1"] - Filter Operator [FIL_131] (rows=80000000 width=860) + Filter Operator [FIL_190] (rows=80000000 width=860) predicate:(c_current_addr_sk is not null and c_customer_sk is not null) TableScan [TS_13] (rows=80000000 width=860) default@customer,c,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_addr_sk"] - <-Map 17 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_136] + <-Map 20 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_195] PartitionCols:_col0 - Select Operator [SEL_135] (rows=40000000 width=1014) + Select Operator [SEL_194] (rows=40000000 width=1014) Output:["_col0","_col1"] - Filter Operator [FIL_134] (rows=40000000 width=1014) + Filter Operator [FIL_193] (rows=40000000 width=1014) predicate:ca_address_sk is not null TableScan [TS_16] (rows=40000000 width=1014) default@customer_address,a,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_61] PartitionCols:_col5 - Merge Join Operator [MERGEJOIN_109] (rows=633595212 width=88) - Conds:RS_58._col0=RS_130._col0(Inner),Output:["_col4","_col5"] - <-Map 14 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_130] - PartitionCols:_col0 - Select Operator [SEL_129] (rows=575995635 width=88) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_128] (rows=575995635 width=88) - predicate:(ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) - TableScan [TS_10] (rows=575995635 width=88) - default@store_sales,s,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] + Merge Join Operator [MERGEJOIN_169] (rows=633595212 width=88) + Conds:RS_58._col0=RS_219._col0(Inner),Output:["_col4","_col5"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_58] + PARTITION_ONLY_SHUFFLE [RS_58] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_108] (rows=80353 width=1119) - Conds:RS_117._col1=RS_127._col0(Inner),Output:["_col0"] + Merge Join Operator [MERGEJOIN_168] (rows=80353 width=1119) + Conds:RS_177._col1=RS_187._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_117] + SHUFFLE [RS_177] PartitionCols:_col1 - Select Operator [SEL_116] (rows=73049 width=1119) + Select Operator [SEL_176] (rows=73049 width=1119) Output:["_col0","_col1"] - Filter Operator [FIL_115] (rows=73049 width=1119) + Filter Operator [FIL_175] (rows=73049 width=1119) predicate:(d_date_sk is not null and d_month_seq is not null) TableScan [TS_0] (rows=73049 width=1119) default@date_dim,d,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_month_seq"] - <-Reducer 9 [ONE_TO_ONE_EDGE] vectorized - FORWARD [RS_127] + <-Reducer 10 [ONE_TO_ONE_EDGE] vectorized + FORWARD [RS_187] PartitionCols:_col0 - Group By Operator [GBY_126] (rows=9131 width=1119) + Group By Operator [GBY_186] (rows=9131 width=1119) Output:["_col0"],keys:KEY._col0 - <-Map 8 [SIMPLE_EDGE] vectorized - SHUFFLE [RS_124] + <-Map 9 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_184] PartitionCols:_col0 - Group By Operator [GBY_122] (rows=18262 width=1119) + Group By Operator [GBY_182] (rows=18262 width=1119) Output:["_col0"],keys:d_month_seq - Select Operator [SEL_120] (rows=18262 width=1119) + Select Operator [SEL_180] (rows=18262 width=1119) Output:["d_month_seq"] - Filter Operator [FIL_118] (rows=18262 width=1119) + Filter Operator [FIL_178] (rows=18262 width=1119) predicate:((d_moy = 2) and (d_year = 2000) and d_month_seq is not null) Please refer to the previous TableScan [TS_3] + <-Map 16 [SIMPLE_EDGE] vectorized + SHUFFLE [RS_219] + PartitionCols:_col0 + Select Operator [SEL_218] (rows=575995635 width=88) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_217] (rows=575995635 width=88) + predicate:((ss_customer_sk BETWEEN DynamicValue(RS_62_c_c_customer_sk_min) AND DynamicValue(RS_62_c_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_62_c_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_65_i_i_item_sk_min) AND DynamicValue(RS_65_i_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_65_i_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_58_d_d_date_sk_min) AND DynamicValue(RS_58_d_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_58_d_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) + TableScan [TS_10] (rows=575995635 width=88) + default@store_sales,s,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk"] + <-Reducer 15 [BROADCAST_EDGE] vectorized + BROADCAST [RS_216] + Group By Operator [GBY_215] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 14 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_135] + Group By Operator [GBY_134] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_133] (rows=169400 width=1436) + Output:["_col0"] + Please refer to the previous Select Operator [SEL_54] + <-Reducer 19 [BROADCAST_EDGE] vectorized + BROADCAST [RS_197] + Group By Operator [GBY_196] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=88000000)"] + <-Reducer 18 [CUSTOM_SIMPLE_EDGE] + SHUFFLE [RS_130] + Group By Operator [GBY_129] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=88000000)"] + Select Operator [SEL_128] (rows=88000001 width=860) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_170] + <-Reducer 8 [BROADCAST_EDGE] vectorized + BROADCAST [RS_189] + Group By Operator [GBY_188] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"] + <-Reducer 2 [CUSTOM_SIMPLE_EDGE] + PARTITION_ONLY_SHUFFLE [RS_125] + Group By Operator [GBY_124] (rows=1 width=12) + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"] + Select Operator [SEL_123] (rows=80353 width=1119) + Output:["_col0"] + Please refer to the previous Merge Join Operator [MERGEJOIN_168]
