You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2018/07/14 05:16:26 UTC
[03/12] hive git commit: HIVE-20090 : Extend creation of semijoin
reduction filters to be able to discover new opportunities (Jesus Camacho
Rodriguez via Deepak Jaiswal)
http://git-wip-us.apache.org/repos/asf/hive/blob/ab9e954d/ql/src/test/results/clientpositive/perf/tez/query77.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query77.q.out b/ql/src/test/results/clientpositive/perf/tez/query77.q.out
index 163805b..915d4fd 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query77.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query77.q.out
@@ -1,4 +1,4 @@
-Warning: Shuffle Join MERGEJOIN[307][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 16' is a cross product
+Warning: Shuffle Join MERGEJOIN[315][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 16' is a cross product
PREHOOK: query: explain
with ss as
(select s_store_sk,
@@ -249,296 +249,296 @@ Stage-0
limit:100
Stage-1
Reducer 8 vectorized
- File Output Operator [FS_360]
- Limit [LIM_359] (rows=100 width=163)
+ File Output Operator [FS_368]
+ Limit [LIM_367] (rows=100 width=163)
Number of rows:100
- Select Operator [SEL_358] (rows=956329968 width=163)
+ Select Operator [SEL_366] (rows=956329968 width=163)
Output:["_col0","_col1","_col2","_col3","_col4"]
<-Reducer 7 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_357]
- Select Operator [SEL_356] (rows=956329968 width=163)
+ SHUFFLE [RS_365]
+ Select Operator [SEL_364] (rows=956329968 width=163)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Group By Operator [GBY_355] (rows=956329968 width=163)
+ Group By Operator [GBY_363] (rows=956329968 width=163)
Output:["_col0","_col1","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2
<-Union 6 [SIMPLE_EDGE]
<-Reducer 16 [CONTAINS]
- Reduce Output Operator [RS_311]
+ Reduce Output Operator [RS_319]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_310] (rows=1912659936 width=163)
+ Group By Operator [GBY_318] (rows=1912659936 width=163)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L
- Select Operator [SEL_308] (rows=158394413 width=360)
+ Select Operator [SEL_316] (rows=158394413 width=360)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Merge Join Operator [MERGEJOIN_307] (rows=158394413 width=360)
+ Merge Join Operator [MERGEJOIN_315] (rows=158394413 width=360)
Conds:(Inner),Output:["_col0","_col1","_col2","_col3","_col4"]
<-Reducer 15 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_367]
- Group By Operator [GBY_366] (rows=158394413 width=135)
+ PARTITION_ONLY_SHUFFLE [RS_375]
+ Group By Operator [GBY_374] (rows=158394413 width=135)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0
<-Reducer 14 [SIMPLE_EDGE]
SHUFFLE [RS_55]
PartitionCols:_col0
Group By Operator [GBY_54] (rows=316788826 width=135)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col1
- Merge Join Operator [MERGEJOIN_293] (rows=316788826 width=135)
- Conds:RS_365._col0=RS_322._col0(Inner),Output:["_col1","_col2","_col3"]
+ Merge Join Operator [MERGEJOIN_301] (rows=316788826 width=135)
+ Conds:RS_373._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_322]
+ SHUFFLE [RS_330]
PartitionCols:_col0
- Select Operator [SEL_318] (rows=8116 width=1119)
+ Select Operator [SEL_326] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_317] (rows=8116 width=1119)
+ Filter Operator [FIL_325] (rows=8116 width=1119)
predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-08-04 00:00:00' AND TIMESTAMP'1998-09-03 00:00:00' and d_date_sk is not null)
TableScan [TS_3] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
<-Map 31 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_365]
+ SHUFFLE [RS_373]
PartitionCols:_col0
- Select Operator [SEL_364] (rows=287989836 width=135)
+ Select Operator [SEL_372] (rows=287989836 width=135)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_363] (rows=287989836 width=135)
+ Filter Operator [FIL_371] (rows=287989836 width=135)
predicate:((cs_sold_date_sk BETWEEN DynamicValue(RS_51_date_dim_d_date_sk_min) AND DynamicValue(RS_51_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_51_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null)
TableScan [TS_44] (rows=287989836 width=135)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_call_center_sk","cs_ext_sales_price","cs_net_profit"]
<-Reducer 17 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_362]
- Group By Operator [GBY_361] (rows=1 width=12)
+ BROADCAST [RS_370]
+ Group By Operator [GBY_369] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_332]
- Group By Operator [GBY_329] (rows=1 width=12)
+ SHUFFLE [RS_340]
+ Group By Operator [GBY_337] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_323] (rows=8116 width=1119)
+ Select Operator [SEL_331] (rows=8116 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_318]
+ Please refer to the previous Select Operator [SEL_326]
<-Reducer 19 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_372]
- Group By Operator [GBY_371] (rows=1 width=224)
+ PARTITION_ONLY_SHUFFLE [RS_380]
+ Group By Operator [GBY_379] (rows=1 width=224)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"]
<-Reducer 18 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_69]
Group By Operator [GBY_68] (rows=1 width=224)
Output:["_col0","_col1"],aggregations:["sum(_col1)","sum(_col2)"]
- Merge Join Operator [MERGEJOIN_294] (rows=31678769 width=106)
- Conds:RS_370._col0=RS_324._col0(Inner),Output:["_col1","_col2"]
+ Merge Join Operator [MERGEJOIN_302] (rows=31678769 width=106)
+ Conds:RS_378._col0=RS_332._col0(Inner),Output:["_col1","_col2"]
<-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_324]
+ SHUFFLE [RS_332]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_318]
+ Please refer to the previous Select Operator [SEL_326]
<-Map 32 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_370]
+ SHUFFLE [RS_378]
PartitionCols:_col0
- Select Operator [SEL_369] (rows=28798881 width=106)
+ Select Operator [SEL_377] (rows=28798881 width=106)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_368] (rows=28798881 width=106)
+ Filter Operator [FIL_376] (rows=28798881 width=106)
predicate:cr_returned_date_sk is not null
TableScan [TS_58] (rows=28798881 width=106)
default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_return_amount","cr_net_loss"]
<-Reducer 23 [CONTAINS]
- Reduce Output Operator [RS_316]
+ Reduce Output Operator [RS_324]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_315] (rows=1912659936 width=163)
+ Group By Operator [GBY_323] (rows=1912659936 width=163)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L
- Select Operator [SEL_313] (rows=95833780 width=135)
+ Select Operator [SEL_321] (rows=95833780 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Merge Join Operator [MERGEJOIN_312] (rows=95833780 width=135)
- Conds:RS_388._col0=RS_393._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_320] (rows=95833780 width=135)
+ Conds:RS_396._col0=RS_401._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"]
<-Reducer 22 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_388]
+ FORWARD [RS_396]
PartitionCols:_col0
- Group By Operator [GBY_387] (rows=87121617 width=135)
+ Group By Operator [GBY_395] (rows=87121617 width=135)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0
<-Reducer 21 [SIMPLE_EDGE]
SHUFFLE [RS_94]
PartitionCols:_col0
Group By Operator [GBY_93] (rows=174243235 width=135)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6
- Merge Join Operator [MERGEJOIN_296] (rows=174243235 width=135)
- Conds:RS_89._col1=RS_377._col0(Inner),Output:["_col2","_col3","_col6"]
+ Merge Join Operator [MERGEJOIN_304] (rows=174243235 width=135)
+ Conds:RS_89._col1=RS_385._col0(Inner),Output:["_col2","_col3","_col6"]
<-Map 34 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_377]
+ PARTITION_ONLY_SHUFFLE [RS_385]
PartitionCols:_col0
- Select Operator [SEL_376] (rows=4602 width=585)
+ Select Operator [SEL_384] (rows=4602 width=585)
Output:["_col0"]
- Filter Operator [FIL_375] (rows=4602 width=585)
+ Filter Operator [FIL_383] (rows=4602 width=585)
predicate:wp_web_page_sk is not null
TableScan [TS_83] (rows=4602 width=585)
default@web_page,web_page,Tbl:COMPLETE,Col:NONE,Output:["wp_web_page_sk"]
<-Reducer 20 [SIMPLE_EDGE]
SHUFFLE [RS_89]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_295] (rows=158402938 width=135)
- Conds:RS_386._col0=RS_325._col0(Inner),Output:["_col1","_col2","_col3"]
+ Merge Join Operator [MERGEJOIN_303] (rows=158402938 width=135)
+ Conds:RS_394._col0=RS_333._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_325]
+ SHUFFLE [RS_333]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_318]
+ Please refer to the previous Select Operator [SEL_326]
<-Map 33 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_386]
+ SHUFFLE [RS_394]
PartitionCols:_col0
- Select Operator [SEL_385] (rows=144002668 width=135)
+ Select Operator [SEL_393] (rows=144002668 width=135)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_384] (rows=144002668 width=135)
+ Filter Operator [FIL_392] (rows=144002668 width=135)
predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_87_date_dim_d_date_sk_min) AND DynamicValue(RS_87_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_87_date_dim_d_date_sk_bloom_filter))) and (ws_web_page_sk BETWEEN DynamicValue(RS_90_web_page_wp_web_page_sk_min) AND DynamicValue(RS_90_web_page_wp_web_page_sk_max) and in_bloom_filter(ws_web_page_sk, DynamicValue(RS_90_web_page_wp_web_page_sk_bloom_filter))) and ws_sold_date_sk is not null and ws_web_page_sk is not null)
TableScan [TS_77] (rows=144002668 width=135)
default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_web_page_sk","ws_ext_sales_price","ws_net_profit"]
<-Reducer 24 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_374]
- Group By Operator [GBY_373] (rows=1 width=12)
+ BROADCAST [RS_382]
+ Group By Operator [GBY_381] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_333]
- Group By Operator [GBY_330] (rows=1 width=12)
+ SHUFFLE [RS_341]
+ Group By Operator [GBY_338] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_326] (rows=8116 width=1119)
+ Select Operator [SEL_334] (rows=8116 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_318]
+ Please refer to the previous Select Operator [SEL_326]
<-Reducer 35 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_383]
- Group By Operator [GBY_382] (rows=1 width=12)
+ BROADCAST [RS_391]
+ Group By Operator [GBY_390] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 34 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_381]
- Group By Operator [GBY_380] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_389]
+ Group By Operator [GBY_388] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_378] (rows=4602 width=585)
+ Select Operator [SEL_386] (rows=4602 width=585)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_376]
+ Please refer to the previous Select Operator [SEL_384]
<-Reducer 27 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_393]
+ FORWARD [RS_401]
PartitionCols:_col0
- Group By Operator [GBY_392] (rows=8711072 width=92)
+ Group By Operator [GBY_400] (rows=8711072 width=92)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0
<-Reducer 26 [SIMPLE_EDGE]
SHUFFLE [RS_114]
PartitionCols:_col0
Group By Operator [GBY_113] (rows=17422145 width=92)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6
- Merge Join Operator [MERGEJOIN_298] (rows=17422145 width=92)
- Conds:RS_109._col1=RS_379._col0(Inner),Output:["_col2","_col3","_col6"]
+ Merge Join Operator [MERGEJOIN_306] (rows=17422145 width=92)
+ Conds:RS_109._col1=RS_387._col0(Inner),Output:["_col2","_col3","_col6"]
<-Map 34 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_379]
+ PARTITION_ONLY_SHUFFLE [RS_387]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_376]
+ Please refer to the previous Select Operator [SEL_384]
<-Reducer 25 [SIMPLE_EDGE]
SHUFFLE [RS_109]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_297] (rows=15838314 width=92)
- Conds:RS_391._col0=RS_327._col0(Inner),Output:["_col1","_col2","_col3"]
+ Merge Join Operator [MERGEJOIN_305] (rows=15838314 width=92)
+ Conds:RS_399._col0=RS_335._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_327]
+ SHUFFLE [RS_335]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_318]
+ Please refer to the previous Select Operator [SEL_326]
<-Map 36 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_391]
+ SHUFFLE [RS_399]
PartitionCols:_col0
- Select Operator [SEL_390] (rows=14398467 width=92)
+ Select Operator [SEL_398] (rows=14398467 width=92)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_389] (rows=14398467 width=92)
+ Filter Operator [FIL_397] (rows=14398467 width=92)
predicate:(wr_returned_date_sk is not null and wr_web_page_sk is not null)
TableScan [TS_97] (rows=14398467 width=92)
default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_web_page_sk","wr_return_amt","wr_net_loss"]
<-Reducer 5 [CONTAINS]
- Reduce Output Operator [RS_306]
+ Reduce Output Operator [RS_314]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_305] (rows=1912659936 width=163)
+ Group By Operator [GBY_313] (rows=1912659936 width=163)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L
- Select Operator [SEL_303] (rows=383325119 width=88)
+ Select Operator [SEL_311] (rows=383325119 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Merge Join Operator [MERGEJOIN_302] (rows=383325119 width=88)
- Conds:RS_349._col0=RS_354._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_310] (rows=383325119 width=88)
+ Conds:RS_357._col0=RS_362._col0(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5"]
<-Reducer 13 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_354]
+ FORWARD [RS_362]
PartitionCols:_col0
- Group By Operator [GBY_353] (rows=34842647 width=77)
+ Group By Operator [GBY_361] (rows=34842647 width=77)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0
<-Reducer 12 [SIMPLE_EDGE]
SHUFFLE [RS_37]
PartitionCols:_col0
Group By Operator [GBY_36] (rows=69685294 width=77)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6
- Merge Join Operator [MERGEJOIN_292] (rows=69685294 width=77)
- Conds:RS_32._col1=RS_340._col0(Inner),Output:["_col2","_col3","_col6"]
+ Merge Join Operator [MERGEJOIN_300] (rows=69685294 width=77)
+ Conds:RS_32._col1=RS_348._col0(Inner),Output:["_col2","_col3","_col6"]
<-Map 28 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_340]
+ SHUFFLE [RS_348]
PartitionCols:_col0
- Select Operator [SEL_337] (rows=1704 width=1910)
+ Select Operator [SEL_345] (rows=1704 width=1910)
Output:["_col0"]
- Filter Operator [FIL_336] (rows=1704 width=1910)
+ Filter Operator [FIL_344] (rows=1704 width=1910)
predicate:s_store_sk is not null
TableScan [TS_6] (rows=1704 width=1910)
default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk"]
<-Reducer 11 [SIMPLE_EDGE]
SHUFFLE [RS_32]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_291] (rows=63350266 width=77)
- Conds:RS_352._col0=RS_321._col0(Inner),Output:["_col1","_col2","_col3"]
+ Merge Join Operator [MERGEJOIN_299] (rows=63350266 width=77)
+ Conds:RS_360._col0=RS_329._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_321]
+ SHUFFLE [RS_329]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_318]
+ Please refer to the previous Select Operator [SEL_326]
<-Map 30 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_352]
+ SHUFFLE [RS_360]
PartitionCols:_col0
- Select Operator [SEL_351] (rows=57591150 width=77)
+ Select Operator [SEL_359] (rows=57591150 width=77)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_350] (rows=57591150 width=77)
+ Filter Operator [FIL_358] (rows=57591150 width=77)
predicate:(sr_returned_date_sk is not null and sr_store_sk is not null)
TableScan [TS_20] (rows=57591150 width=77)
default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_store_sk","sr_return_amt","sr_net_loss"]
<-Reducer 4 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_349]
+ FORWARD [RS_357]
PartitionCols:_col0
- Group By Operator [GBY_348] (rows=348477374 width=88)
+ Group By Operator [GBY_356] (rows=348477374 width=88)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_17]
PartitionCols:_col0
Group By Operator [GBY_16] (rows=696954748 width=88)
Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","sum(_col3)"],keys:_col6
- Merge Join Operator [MERGEJOIN_290] (rows=696954748 width=88)
- Conds:RS_12._col1=RS_338._col0(Inner),Output:["_col2","_col3","_col6"]
+ Merge Join Operator [MERGEJOIN_298] (rows=696954748 width=88)
+ Conds:RS_12._col1=RS_346._col0(Inner),Output:["_col2","_col3","_col6"]
<-Map 28 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_338]
+ SHUFFLE [RS_346]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_337]
+ Please refer to the previous Select Operator [SEL_345]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_12]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_289] (rows=633595212 width=88)
- Conds:RS_347._col0=RS_319._col0(Inner),Output:["_col1","_col2","_col3"]
+ Merge Join Operator [MERGEJOIN_297] (rows=633595212 width=88)
+ Conds:RS_355._col0=RS_327._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_319]
+ SHUFFLE [RS_327]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_318]
+ Please refer to the previous Select Operator [SEL_326]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_347]
+ SHUFFLE [RS_355]
PartitionCols:_col0
- Select Operator [SEL_346] (rows=575995635 width=88)
+ Select Operator [SEL_354] (rows=575995635 width=88)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_345] (rows=575995635 width=88)
+ Filter Operator [FIL_353] (rows=575995635 width=88)
predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_10_date_dim_d_date_sk_min) AND DynamicValue(RS_10_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_13_store_s_store_sk_min) AND DynamicValue(RS_13_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_13_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_ext_sales_price","ss_net_profit"]
<-Reducer 10 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_335]
- Group By Operator [GBY_334] (rows=1 width=12)
+ BROADCAST [RS_343]
+ Group By Operator [GBY_342] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 9 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_331]
- Group By Operator [GBY_328] (rows=1 width=12)
+ SHUFFLE [RS_339]
+ Group By Operator [GBY_336] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_320] (rows=8116 width=1119)
+ Select Operator [SEL_328] (rows=8116 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_318]
+ Please refer to the previous Select Operator [SEL_326]
<-Reducer 29 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_344]
- Group By Operator [GBY_343] (rows=1 width=12)
+ BROADCAST [RS_352]
+ Group By Operator [GBY_351] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_342]
- Group By Operator [GBY_341] (rows=1 width=12)
+ SHUFFLE [RS_350]
+ Group By Operator [GBY_349] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_339] (rows=1704 width=1910)
+ Select Operator [SEL_347] (rows=1704 width=1910)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_337]
+ Please refer to the previous Select Operator [SEL_345]
http://git-wip-us.apache.org/repos/asf/hive/blob/ab9e954d/ql/src/test/results/clientpositive/perf/tez/query78.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query78.q.out b/ql/src/test/results/clientpositive/perf/tez/query78.q.out
index 90b6f17..b110260 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query78.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query78.q.out
@@ -139,10 +139,10 @@ Stage-0
limit:100
Stage-1
Reducer 6 vectorized
- File Output Operator [FS_235]
- Limit [LIM_234] (rows=100 width=88)
+ File Output Operator [FS_238]
+ Limit [LIM_237] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_233] (rows=23425424 width=88)
+ Select Operator [SEL_236] (rows=23425424 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_73]
@@ -150,28 +150,28 @@ Stage-0
Output:["_col0","_col1","_col6","_col7","_col8","_col9","_col10","_col11","_col12"]
Filter Operator [FIL_71] (rows=23425424 width=88)
predicate:(COALESCE(_col11,0) > 0)
- Merge Join Operator [MERGEJOIN_188] (rows=70276272 width=88)
- Conds:RS_68._col1=RS_232._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col11","_col12","_col13"]
+ Merge Join Operator [MERGEJOIN_191] (rows=70276272 width=88)
+ Conds:RS_68._col1=RS_235._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col7","_col8","_col9","_col11","_col12","_col13"]
<-Reducer 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_232]
+ SHUFFLE [RS_235]
PartitionCols:_col0
- Select Operator [SEL_231] (rows=43558464 width=135)
+ Select Operator [SEL_234] (rows=43558464 width=135)
Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_230] (rows=43558464 width=135)
+ Group By Operator [GBY_233] (rows=43558464 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1
<-Reducer 11 [SIMPLE_EDGE]
SHUFFLE [RS_65]
PartitionCols:_col0, _col1
Group By Operator [GBY_64] (rows=87116928 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col3, _col4
- Merge Join Operator [MERGEJOIN_186] (rows=87116928 width=135)
- Conds:RS_195._col0=RS_61._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"]
+ Merge Join Operator [MERGEJOIN_189] (rows=87116928 width=135)
+ Conds:RS_198._col0=RS_61._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_195]
+ SHUFFLE [RS_198]
PartitionCols:_col0
- Select Operator [SEL_190] (rows=36524 width=1119)
+ Select Operator [SEL_193] (rows=36524 width=1119)
Output:["_col0"]
- Filter Operator [FIL_189] (rows=36524 width=1119)
+ Filter Operator [FIL_192] (rows=36524 width=1119)
predicate:((d_year = 2000) and d_date_sk is not null)
TableScan [TS_0] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
@@ -182,32 +182,32 @@ Stage-0
Output:["_col0","_col1","_col2","_col4","_col5","_col6"]
Filter Operator [FIL_58] (rows=79197206 width=135)
predicate:_col8 is null
- Merge Join Operator [MERGEJOIN_185] (rows=158394413 width=135)
- Conds:RS_227._col2, _col3=RS_229._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"]
+ Merge Join Operator [MERGEJOIN_188] (rows=158394413 width=135)
+ Conds:RS_230._col2, _col3=RS_232._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"]
<-Map 20 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_227]
+ SHUFFLE [RS_230]
PartitionCols:_col2, _col3
- Select Operator [SEL_226] (rows=143994918 width=135)
+ Select Operator [SEL_229] (rows=143994918 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
- Filter Operator [FIL_225] (rows=143994918 width=135)
+ Filter Operator [FIL_228] (rows=143994918 width=135)
predicate:((cs_item_sk = cs_item_sk) and (cs_sold_date_sk BETWEEN DynamicValue(RS_60_date_dim_d_date_sk_min) AND DynamicValue(RS_60_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_60_date_dim_d_date_sk_bloom_filter))) and cs_sold_date_sk is not null)
TableScan [TS_50] (rows=287989836 width=135)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_order_number","cs_quantity","cs_wholesale_cost","cs_sales_price"]
<-Reducer 13 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_224]
- Group By Operator [GBY_223] (rows=1 width=12)
+ BROADCAST [RS_227]
+ Group By Operator [GBY_226] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_202]
- Group By Operator [GBY_199] (rows=1 width=12)
+ SHUFFLE [RS_205]
+ Group By Operator [GBY_202] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_196] (rows=36524 width=1119)
+ Select Operator [SEL_199] (rows=36524 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_190]
+ Please refer to the previous Select Operator [SEL_193]
<-Map 22 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_229]
+ SHUFFLE [RS_232]
PartitionCols:_col0, _col1
- Select Operator [SEL_228] (rows=28798881 width=106)
+ Select Operator [SEL_231] (rows=28798881 width=106)
Output:["_col0","_col1"]
TableScan [TS_53] (rows=28798881 width=106)
default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number"]
@@ -216,26 +216,26 @@ Stage-0
PartitionCols:_col1
Filter Operator [FIL_45] (rows=63887519 width=88)
predicate:(COALESCE(_col7,0) > 0)
- Merge Join Operator [MERGEJOIN_187] (rows=191662559 width=88)
- Conds:RS_212._col1, _col0=RS_222._col1, _col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col7","_col8","_col9"]
+ Merge Join Operator [MERGEJOIN_190] (rows=191662559 width=88)
+ Conds:RS_215._col1, _col0=RS_225._col1, _col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col4","_col7","_col8","_col9"]
<-Reducer 3 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_212]
+ FORWARD [RS_215]
PartitionCols:_col1, _col0
- Select Operator [SEL_211] (rows=174238687 width=88)
+ Select Operator [SEL_214] (rows=174238687 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Group By Operator [GBY_210] (rows=174238687 width=88)
+ Group By Operator [GBY_213] (rows=174238687 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_18]
PartitionCols:_col0, _col1
Group By Operator [GBY_17] (rows=348477374 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col4, _col3
- Merge Join Operator [MERGEJOIN_182] (rows=348477374 width=88)
- Conds:RS_191._col0=RS_14._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"]
+ Merge Join Operator [MERGEJOIN_185] (rows=348477374 width=88)
+ Conds:RS_194._col0=RS_14._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_191]
+ SHUFFLE [RS_194]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_190]
+ Please refer to the previous Select Operator [SEL_193]
<-Reducer 15 [SIMPLE_EDGE]
SHUFFLE [RS_14]
PartitionCols:_col0
@@ -243,53 +243,53 @@ Stage-0
Output:["_col0","_col1","_col2","_col4","_col5","_col6"]
Filter Operator [FIL_11] (rows=316797606 width=88)
predicate:_col8 is null
- Merge Join Operator [MERGEJOIN_181] (rows=633595212 width=88)
- Conds:RS_207._col1, _col3=RS_209._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"]
+ Merge Join Operator [MERGEJOIN_184] (rows=633595212 width=88)
+ Conds:RS_210._col1, _col3=RS_212._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"]
<-Map 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_207]
+ SHUFFLE [RS_210]
PartitionCols:_col1, _col3
- Select Operator [SEL_206] (rows=575995635 width=88)
+ Select Operator [SEL_209] (rows=575995635 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
- Filter Operator [FIL_205] (rows=575995635 width=88)
+ Filter Operator [FIL_208] (rows=575995635 width=88)
predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null)
TableScan [TS_3] (rows=575995635 width=88)
default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_customer_sk","ss_ticket_number","ss_quantity","ss_wholesale_cost","ss_sales_price"]
<-Reducer 7 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_204]
- Group By Operator [GBY_203] (rows=1 width=12)
+ BROADCAST [RS_207]
+ Group By Operator [GBY_206] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_200]
- Group By Operator [GBY_197] (rows=1 width=12)
+ SHUFFLE [RS_203]
+ Group By Operator [GBY_200] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_192] (rows=36524 width=1119)
+ Select Operator [SEL_195] (rows=36524 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_190]
+ Please refer to the previous Select Operator [SEL_193]
<-Map 16 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_209]
+ SHUFFLE [RS_212]
PartitionCols:_col0, _col1
- Select Operator [SEL_208] (rows=57591150 width=77)
+ Select Operator [SEL_211] (rows=57591150 width=77)
Output:["_col0","_col1"]
TableScan [TS_6] (rows=57591150 width=77)
default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number"]
<-Reducer 9 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_222]
+ FORWARD [RS_225]
PartitionCols:_col1, _col0
- Select Operator [SEL_221] (rows=43560808 width=135)
+ Select Operator [SEL_224] (rows=43560808 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Group By Operator [GBY_220] (rows=43560808 width=135)
+ Group By Operator [GBY_223] (rows=43560808 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1
<-Reducer 8 [SIMPLE_EDGE]
SHUFFLE [RS_39]
PartitionCols:_col0, _col1
Group By Operator [GBY_38] (rows=87121617 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col4, _col3
- Merge Join Operator [MERGEJOIN_184] (rows=87121617 width=135)
- Conds:RS_193._col0=RS_35._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"]
+ Merge Join Operator [MERGEJOIN_187] (rows=87121617 width=135)
+ Conds:RS_196._col0=RS_35._col0(Inner),Output:["_col3","_col4","_col6","_col7","_col8"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_193]
+ SHUFFLE [RS_196]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_190]
+ Please refer to the previous Select Operator [SEL_193]
<-Reducer 18 [SIMPLE_EDGE]
SHUFFLE [RS_35]
PartitionCols:_col0
@@ -297,32 +297,32 @@ Stage-0
Output:["_col0","_col1","_col2","_col4","_col5","_col6"]
Filter Operator [FIL_32] (rows=79201469 width=135)
predicate:_col8 is null
- Merge Join Operator [MERGEJOIN_183] (rows=158402938 width=135)
- Conds:RS_217._col1, _col3=RS_219._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"]
+ Merge Join Operator [MERGEJOIN_186] (rows=158402938 width=135)
+ Conds:RS_220._col1, _col3=RS_222._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col4","_col5","_col6","_col8"]
<-Map 17 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_217]
+ SHUFFLE [RS_220]
PartitionCols:_col1, _col3
- Select Operator [SEL_216] (rows=144002668 width=135)
+ Select Operator [SEL_219] (rows=144002668 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
- Filter Operator [FIL_215] (rows=144002668 width=135)
+ Filter Operator [FIL_218] (rows=144002668 width=135)
predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_34_date_dim_d_date_sk_min) AND DynamicValue(RS_34_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_34_date_dim_d_date_sk_bloom_filter))) and ws_sold_date_sk is not null)
TableScan [TS_24] (rows=144002668 width=135)
default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_order_number","ws_quantity","ws_wholesale_cost","ws_sales_price"]
<-Reducer 10 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_214]
- Group By Operator [GBY_213] (rows=1 width=12)
+ BROADCAST [RS_217]
+ Group By Operator [GBY_216] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_201]
- Group By Operator [GBY_198] (rows=1 width=12)
+ SHUFFLE [RS_204]
+ Group By Operator [GBY_201] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_194] (rows=36524 width=1119)
+ Select Operator [SEL_197] (rows=36524 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_190]
+ Please refer to the previous Select Operator [SEL_193]
<-Map 19 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_219]
+ SHUFFLE [RS_222]
PartitionCols:_col0, _col1
- Select Operator [SEL_218] (rows=14398467 width=92)
+ Select Operator [SEL_221] (rows=14398467 width=92)
Output:["_col0","_col1"]
TableScan [TS_27] (rows=14398467 width=92)
default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_item_sk","wr_order_number"]