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 05:16:25 UTC
[02/12] 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/query80.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query80.q.out b/ql/src/test/results/clientpositive/perf/tez/query80.q.out
index 816b525..ee8cdd8 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query80.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query80.q.out
@@ -232,26 +232,26 @@ Stage-0
limit:100
Stage-1
Reducer 10 vectorized
- File Output Operator [FS_457]
- Limit [LIM_456] (rows=100 width=108)
+ File Output Operator [FS_460]
+ Limit [LIM_459] (rows=100 width=108)
Number of rows:100
- Select Operator [SEL_455] (rows=1217531358 width=108)
+ Select Operator [SEL_458] (rows=1217531358 width=108)
Output:["_col0","_col1","_col2","_col3","_col4"]
<-Reducer 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_454]
- Select Operator [SEL_453] (rows=1217531358 width=108)
+ SHUFFLE [RS_457]
+ Select Operator [SEL_456] (rows=1217531358 width=108)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Group By Operator [GBY_452] (rows=1217531358 width=108)
+ Group By Operator [GBY_455] (rows=1217531358 width=108)
Output:["_col0","_col1","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2
<-Union 8 [SIMPLE_EDGE]
<-Reducer 18 [CONTAINS] vectorized
- Reduce Output Operator [RS_481]
+ Reduce Output Operator [RS_484]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_480] (rows=2435062716 width=108)
+ Group By Operator [GBY_483] (rows=2435062716 width=108)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L
- Select Operator [SEL_479] (rows=231905279 width=135)
+ Select Operator [SEL_482] (rows=231905279 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Group By Operator [GBY_478] (rows=231905279 width=135)
+ Group By Operator [GBY_481] (rows=231905279 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0
<-Reducer 17 [SIMPLE_EDGE]
SHUFFLE [RS_75]
@@ -260,134 +260,134 @@ Stage-0
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)"],keys:_col0
Select Operator [SEL_72] (rows=463810558 width=135)
Output:["_col0","_col1","_col2","_col3"]
- Merge Join Operator [MERGEJOIN_365] (rows=463810558 width=135)
- Conds:RS_69._col1=RS_466._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"]
+ Merge Join Operator [MERGEJOIN_368] (rows=463810558 width=135)
+ Conds:RS_69._col1=RS_469._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"]
<-Map 39 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_466]
+ PARTITION_ONLY_SHUFFLE [RS_469]
PartitionCols:_col0
- Select Operator [SEL_465] (rows=46000 width=460)
+ Select Operator [SEL_468] (rows=46000 width=460)
Output:["_col0","_col1"]
- Filter Operator [FIL_464] (rows=46000 width=460)
+ Filter Operator [FIL_467] (rows=46000 width=460)
predicate:cp_catalog_page_sk is not null
TableScan [TS_54] (rows=46000 width=460)
default@catalog_page,catalog_page,Tbl:COMPLETE,Col:NONE,Output:["cp_catalog_page_sk","cp_catalog_page_id"]
<-Reducer 16 [SIMPLE_EDGE]
SHUFFLE [RS_69]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_364] (rows=421645953 width=135)
- Conds:RS_66._col3=RS_422._col0(Inner),Output:["_col1","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_367] (rows=421645953 width=135)
+ Conds:RS_66._col3=RS_425._col0(Inner),Output:["_col1","_col5","_col6","_col9","_col10"]
<-Map 30 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_422]
+ SHUFFLE [RS_425]
PartitionCols:_col0
- Select Operator [SEL_419] (rows=1150 width=1179)
+ Select Operator [SEL_422] (rows=1150 width=1179)
Output:["_col0"]
- Filter Operator [FIL_418] (rows=1150 width=1179)
+ Filter Operator [FIL_421] (rows=1150 width=1179)
predicate:((p_channel_tv = 'N') and p_promo_sk is not null)
TableScan [TS_12] (rows=2300 width=1179)
default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_tv"]
<-Reducer 15 [SIMPLE_EDGE]
SHUFFLE [RS_66]
PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_363] (rows=383314495 width=135)
- Conds:RS_63._col2=RS_406._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_366] (rows=383314495 width=135)
+ Conds:RS_63._col2=RS_409._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col9","_col10"]
<-Map 26 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_406]
+ SHUFFLE [RS_409]
PartitionCols:_col0
- Select Operator [SEL_403] (rows=154000 width=1436)
+ Select Operator [SEL_406] (rows=154000 width=1436)
Output:["_col0"]
- Filter Operator [FIL_402] (rows=154000 width=1436)
+ Filter Operator [FIL_405] (rows=154000 width=1436)
predicate:((i_current_price > 50) and i_item_sk is not null)
TableScan [TS_9] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_current_price"]
<-Reducer 14 [SIMPLE_EDGE]
SHUFFLE [RS_63]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_362] (rows=348467716 width=135)
- Conds:RS_60._col0=RS_390._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_365] (rows=348467716 width=135)
+ Conds:RS_60._col0=RS_393._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
<-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_390]
+ SHUFFLE [RS_393]
PartitionCols:_col0
- Select Operator [SEL_387] (rows=8116 width=1119)
+ Select Operator [SEL_390] (rows=8116 width=1119)
Output:["_col0"]
- Filter Operator [FIL_386] (rows=8116 width=1119)
+ Filter Operator [FIL_389] (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_6] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
<-Reducer 37 [SIMPLE_EDGE]
SHUFFLE [RS_60]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_361] (rows=316788826 width=135)
- Conds:RS_474._col2, _col4=RS_477._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_364] (rows=316788826 width=135)
+ Conds:RS_477._col2, _col4=RS_480._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
<-Map 36 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_474]
+ SHUFFLE [RS_477]
PartitionCols:_col2, _col4
- Select Operator [SEL_473] (rows=287989836 width=135)
+ Select Operator [SEL_476] (rows=287989836 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
- Filter Operator [FIL_472] (rows=287989836 width=135)
+ Filter Operator [FIL_475] (rows=287989836 width=135)
predicate:((cs_catalog_page_sk BETWEEN DynamicValue(RS_70_catalog_page_cp_catalog_page_sk_min) AND DynamicValue(RS_70_catalog_page_cp_catalog_page_sk_max) and in_bloom_filter(cs_catalog_page_sk, DynamicValue(RS_70_catalog_page_cp_catalog_page_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_64_item_i_item_sk_min) AND DynamicValue(RS_64_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_64_item_i_item_sk_bloom_filter))) and (cs_promo_sk BETWEEN DynamicValue(RS_67_promotion_p_promo_sk_min) AND DynamicValue(RS_67_promotion_p_promo_sk_max) and in_bloom_filter(cs_promo_sk, DynamicValue(RS_67_promotion_p_promo_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_61_date_dim_d_date_sk_min) AND DynamicValue(RS_61_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_61_date_dim_d_date_sk_bloom_filter))) and cs_catalog_page_sk is not null and cs_item_sk is not null and cs_pr
omo_sk is not null and cs_sold_date_sk is not null)
TableScan [TS_39] (rows=287989836 width=135)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_catalog_page_sk","cs_item_sk","cs_promo_sk","cs_order_number","cs_ext_sales_price","cs_net_profit"]
<-Reducer 19 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_459]
- Group By Operator [GBY_458] (rows=1 width=12)
+ BROADCAST [RS_462]
+ Group By Operator [GBY_461] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_398]
- Group By Operator [GBY_395] (rows=1 width=12)
+ SHUFFLE [RS_401]
+ Group By Operator [GBY_398] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_391] (rows=8116 width=1119)
+ Select Operator [SEL_394] (rows=8116 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_387]
+ Please refer to the previous Select Operator [SEL_390]
<-Reducer 28 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_461]
- Group By Operator [GBY_460] (rows=1 width=12)
+ BROADCAST [RS_464]
+ Group By Operator [GBY_463] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_414]
- Group By Operator [GBY_411] (rows=1 width=12)
+ SHUFFLE [RS_417]
+ Group By Operator [GBY_414] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_407] (rows=154000 width=1436)
+ Select Operator [SEL_410] (rows=154000 width=1436)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_403]
+ Please refer to the previous Select Operator [SEL_406]
<-Reducer 32 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_463]
- Group By Operator [GBY_462] (rows=1 width=12)
+ BROADCAST [RS_466]
+ Group By Operator [GBY_465] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 30 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_430]
- Group By Operator [GBY_427] (rows=1 width=12)
+ SHUFFLE [RS_433]
+ Group By Operator [GBY_430] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_423] (rows=1150 width=1179)
+ Select Operator [SEL_426] (rows=1150 width=1179)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_419]
+ Please refer to the previous Select Operator [SEL_422]
<-Reducer 40 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_471]
- Group By Operator [GBY_470] (rows=1 width=12)
+ BROADCAST [RS_474]
+ Group By Operator [GBY_473] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 39 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_469]
- Group By Operator [GBY_468] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_472]
+ Group By Operator [GBY_471] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_467] (rows=46000 width=460)
+ Select Operator [SEL_470] (rows=46000 width=460)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_465]
+ Please refer to the previous Select Operator [SEL_468]
<-Map 38 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_477]
+ SHUFFLE [RS_480]
PartitionCols:_col0, _col1
- Select Operator [SEL_476] (rows=28798881 width=106)
+ Select Operator [SEL_479] (rows=28798881 width=106)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_475] (rows=28798881 width=106)
+ Filter Operator [FIL_478] (rows=28798881 width=106)
predicate:cr_item_sk is not null
TableScan [TS_42] (rows=28798881 width=106)
default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_item_sk","cr_order_number","cr_return_amount","cr_net_loss"]
<-Reducer 24 [CONTAINS] vectorized
- Reduce Output Operator [RS_505]
+ Reduce Output Operator [RS_508]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_504] (rows=2435062716 width=108)
+ Group By Operator [GBY_507] (rows=2435062716 width=108)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L
- Select Operator [SEL_503] (rows=115958879 width=135)
+ Select Operator [SEL_506] (rows=115958879 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Group By Operator [GBY_502] (rows=115958879 width=135)
+ Group By Operator [GBY_505] (rows=115958879 width=135)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0
<-Reducer 23 [SIMPLE_EDGE]
SHUFFLE [RS_115]
@@ -396,119 +396,119 @@ Stage-0
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)"],keys:_col0
Select Operator [SEL_112] (rows=231917759 width=135)
Output:["_col0","_col1","_col2","_col3"]
- Merge Join Operator [MERGEJOIN_370] (rows=231917759 width=135)
- Conds:RS_109._col2=RS_490._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"]
+ Merge Join Operator [MERGEJOIN_373] (rows=231917759 width=135)
+ Conds:RS_109._col2=RS_493._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"]
<-Map 44 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_490]
+ PARTITION_ONLY_SHUFFLE [RS_493]
PartitionCols:_col0
- Select Operator [SEL_489] (rows=84 width=1850)
+ Select Operator [SEL_492] (rows=84 width=1850)
Output:["_col0","_col1"]
- Filter Operator [FIL_488] (rows=84 width=1850)
+ Filter Operator [FIL_491] (rows=84 width=1850)
predicate:web_site_sk is not null
TableScan [TS_94] (rows=84 width=1850)
default@web_site,web_site,Tbl:COMPLETE,Col:NONE,Output:["web_site_sk","web_site_id"]
<-Reducer 22 [SIMPLE_EDGE]
SHUFFLE [RS_109]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_369] (rows=210834322 width=135)
- Conds:RS_106._col3=RS_424._col0(Inner),Output:["_col2","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_372] (rows=210834322 width=135)
+ Conds:RS_106._col3=RS_427._col0(Inner),Output:["_col2","_col5","_col6","_col9","_col10"]
<-Map 30 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_424]
+ SHUFFLE [RS_427]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_419]
+ Please refer to the previous Select Operator [SEL_422]
<-Reducer 21 [SIMPLE_EDGE]
SHUFFLE [RS_106]
PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_368] (rows=191667562 width=135)
- Conds:RS_103._col1=RS_408._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_371] (rows=191667562 width=135)
+ Conds:RS_103._col1=RS_411._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col9","_col10"]
<-Map 26 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_408]
+ SHUFFLE [RS_411]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_403]
+ Please refer to the previous Select Operator [SEL_406]
<-Reducer 20 [SIMPLE_EDGE]
SHUFFLE [RS_103]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_367] (rows=174243235 width=135)
- Conds:RS_100._col0=RS_392._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_370] (rows=174243235 width=135)
+ Conds:RS_100._col0=RS_395._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
<-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_392]
+ SHUFFLE [RS_395]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_387]
+ Please refer to the previous Select Operator [SEL_390]
<-Reducer 42 [SIMPLE_EDGE]
SHUFFLE [RS_100]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_366] (rows=158402938 width=135)
- Conds:RS_498._col1, _col4=RS_501._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_369] (rows=158402938 width=135)
+ Conds:RS_501._col1, _col4=RS_504._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
<-Map 41 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_498]
+ SHUFFLE [RS_501]
PartitionCols:_col1, _col4
- Select Operator [SEL_497] (rows=144002668 width=135)
+ Select Operator [SEL_500] (rows=144002668 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
- Filter Operator [FIL_496] (rows=144002668 width=135)
+ Filter Operator [FIL_499] (rows=144002668 width=135)
predicate:((ws_item_sk BETWEEN DynamicValue(RS_104_item_i_item_sk_min) AND DynamicValue(RS_104_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_104_item_i_item_sk_bloom_filter))) and (ws_promo_sk BETWEEN DynamicValue(RS_107_promotion_p_promo_sk_min) AND DynamicValue(RS_107_promotion_p_promo_sk_max) and in_bloom_filter(ws_promo_sk, DynamicValue(RS_107_promotion_p_promo_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_101_date_dim_d_date_sk_min) AND DynamicValue(RS_101_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_101_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_110_web_site_web_site_sk_min) AND DynamicValue(RS_110_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_110_web_site_web_site_sk_bloom_filter))) and ws_item_sk is not null and ws_promo_sk is not null and ws_sold_date_sk is not null and ws_web_si
te_sk is not null)
TableScan [TS_79] (rows=144002668 width=135)
default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_web_site_sk","ws_promo_sk","ws_order_number","ws_ext_sales_price","ws_net_profit"]
<-Reducer 25 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_483]
- Group By Operator [GBY_482] (rows=1 width=12)
+ BROADCAST [RS_486]
+ Group By Operator [GBY_485] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_399]
- Group By Operator [GBY_396] (rows=1 width=12)
+ SHUFFLE [RS_402]
+ Group By Operator [GBY_399] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_393] (rows=8116 width=1119)
+ Select Operator [SEL_396] (rows=8116 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_387]
+ Please refer to the previous Select Operator [SEL_390]
<-Reducer 29 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_485]
- Group By Operator [GBY_484] (rows=1 width=12)
+ BROADCAST [RS_488]
+ Group By Operator [GBY_487] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_415]
- Group By Operator [GBY_412] (rows=1 width=12)
+ SHUFFLE [RS_418]
+ Group By Operator [GBY_415] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_409] (rows=154000 width=1436)
+ Select Operator [SEL_412] (rows=154000 width=1436)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_403]
+ Please refer to the previous Select Operator [SEL_406]
<-Reducer 33 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_487]
- Group By Operator [GBY_486] (rows=1 width=12)
+ BROADCAST [RS_490]
+ Group By Operator [GBY_489] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 30 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_431]
- Group By Operator [GBY_428] (rows=1 width=12)
+ SHUFFLE [RS_434]
+ Group By Operator [GBY_431] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_425] (rows=1150 width=1179)
+ Select Operator [SEL_428] (rows=1150 width=1179)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_419]
+ Please refer to the previous Select Operator [SEL_422]
<-Reducer 45 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_495]
- Group By Operator [GBY_494] (rows=1 width=12)
+ BROADCAST [RS_498]
+ Group By Operator [GBY_497] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 44 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_493]
- Group By Operator [GBY_492] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_496]
+ Group By Operator [GBY_495] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_491] (rows=84 width=1850)
+ Select Operator [SEL_494] (rows=84 width=1850)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_489]
+ Please refer to the previous Select Operator [SEL_492]
<-Map 43 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_501]
+ SHUFFLE [RS_504]
PartitionCols:_col0, _col1
- Select Operator [SEL_500] (rows=14398467 width=92)
+ Select Operator [SEL_503] (rows=14398467 width=92)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_499] (rows=14398467 width=92)
+ Filter Operator [FIL_502] (rows=14398467 width=92)
predicate:wr_item_sk is not null
TableScan [TS_82] (rows=14398467 width=92)
default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_item_sk","wr_order_number","wr_return_amt","wr_net_loss"]
<-Reducer 7 [CONTAINS] vectorized
- Reduce Output Operator [RS_451]
+ Reduce Output Operator [RS_454]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_450] (rows=2435062716 width=108)
+ Group By Operator [GBY_453] (rows=2435062716 width=108)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)"],keys:_col0, _col1, 0L
- Select Operator [SEL_449] (rows=463823414 width=88)
+ Select Operator [SEL_452] (rows=463823414 width=88)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Group By Operator [GBY_448] (rows=463823414 width=88)
+ Group By Operator [GBY_451] (rows=463823414 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0
<-Reducer 6 [SIMPLE_EDGE]
SHUFFLE [RS_36]
@@ -517,108 +517,108 @@ Stage-0
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)"],keys:_col0
Select Operator [SEL_33] (rows=927646829 width=88)
Output:["_col0","_col1","_col2","_col3"]
- Merge Join Operator [MERGEJOIN_360] (rows=927646829 width=88)
- Conds:RS_30._col2=RS_436._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"]
+ Merge Join Operator [MERGEJOIN_363] (rows=927646829 width=88)
+ Conds:RS_30._col2=RS_439._col0(Inner),Output:["_col5","_col6","_col9","_col10","_col18"]
<-Map 34 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_436]
+ SHUFFLE [RS_439]
PartitionCols:_col0
- Select Operator [SEL_435] (rows=1704 width=1910)
+ Select Operator [SEL_438] (rows=1704 width=1910)
Output:["_col0","_col1"]
- Filter Operator [FIL_434] (rows=1704 width=1910)
+ Filter Operator [FIL_437] (rows=1704 width=1910)
predicate:s_store_sk is not null
TableScan [TS_15] (rows=1704 width=1910)
default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id"]
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_30]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_359] (rows=843315281 width=88)
- Conds:RS_27._col3=RS_420._col0(Inner),Output:["_col2","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_362] (rows=843315281 width=88)
+ Conds:RS_27._col3=RS_423._col0(Inner),Output:["_col2","_col5","_col6","_col9","_col10"]
<-Map 30 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_420]
+ SHUFFLE [RS_423]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_419]
+ Please refer to the previous Select Operator [SEL_422]
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_27]
PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_358] (rows=766650239 width=88)
- Conds:RS_24._col1=RS_404._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_361] (rows=766650239 width=88)
+ Conds:RS_24._col1=RS_407._col0(Inner),Output:["_col2","_col3","_col5","_col6","_col9","_col10"]
<-Map 26 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_404]
+ SHUFFLE [RS_407]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_403]
+ Please refer to the previous Select Operator [SEL_406]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_24]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_357] (rows=696954748 width=88)
- Conds:RS_21._col0=RS_388._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_360] (rows=696954748 width=88)
+ Conds:RS_21._col0=RS_391._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
<-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_388]
+ SHUFFLE [RS_391]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_387]
+ Please refer to the previous Select Operator [SEL_390]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_21]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_356] (rows=633595212 width=88)
- Conds:RS_444._col1, _col4=RS_447._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_359] (rows=633595212 width=88)
+ Conds:RS_447._col1, _col4=RS_450._col0, _col1(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col9","_col10"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_444]
+ SHUFFLE [RS_447]
PartitionCols:_col1, _col4
- Select Operator [SEL_443] (rows=575995635 width=88)
+ Select Operator [SEL_446] (rows=575995635 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
- Filter Operator [FIL_442] (rows=575995635 width=88)
+ Filter Operator [FIL_445] (rows=575995635 width=88)
predicate:((ss_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (ss_promo_sk BETWEEN DynamicValue(RS_28_promotion_p_promo_sk_min) AND DynamicValue(RS_28_promotion_p_promo_sk_max) and in_bloom_filter(ss_promo_sk, DynamicValue(RS_28_promotion_p_promo_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_22_date_dim_d_date_sk_min) AND DynamicValue(RS_22_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_22_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_31_store_s_store_sk_min) AND DynamicValue(RS_31_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_31_store_s_store_sk_bloom_filter))) and ss_item_sk is not null and ss_promo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null)
TableScan [TS_0] (rows=575995635 width=88)
default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_store_sk","ss_promo_sk","ss_ticket_number","ss_ext_sales_price","ss_net_profit"]
<-Reducer 13 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_401]
- Group By Operator [GBY_400] (rows=1 width=12)
+ BROADCAST [RS_404]
+ Group By Operator [GBY_403] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 12 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_397]
- Group By Operator [GBY_394] (rows=1 width=12)
+ SHUFFLE [RS_400]
+ Group By Operator [GBY_397] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_389] (rows=8116 width=1119)
+ Select Operator [SEL_392] (rows=8116 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_387]
+ Please refer to the previous Select Operator [SEL_390]
<-Reducer 27 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_417]
- Group By Operator [GBY_416] (rows=1 width=12)
+ BROADCAST [RS_420]
+ Group By Operator [GBY_419] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 26 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_413]
- Group By Operator [GBY_410] (rows=1 width=12)
+ SHUFFLE [RS_416]
+ Group By Operator [GBY_413] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_405] (rows=154000 width=1436)
+ Select Operator [SEL_408] (rows=154000 width=1436)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_403]
+ Please refer to the previous Select Operator [SEL_406]
<-Reducer 31 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_433]
- Group By Operator [GBY_432] (rows=1 width=12)
+ BROADCAST [RS_436]
+ Group By Operator [GBY_435] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 30 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_429]
- Group By Operator [GBY_426] (rows=1 width=12)
+ SHUFFLE [RS_432]
+ Group By Operator [GBY_429] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_421] (rows=1150 width=1179)
+ Select Operator [SEL_424] (rows=1150 width=1179)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_419]
+ Please refer to the previous Select Operator [SEL_422]
<-Reducer 35 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_441]
- Group By Operator [GBY_440] (rows=1 width=12)
+ BROADCAST [RS_444]
+ Group By Operator [GBY_443] (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
- SHUFFLE [RS_439]
- Group By Operator [GBY_438] (rows=1 width=12)
+ SHUFFLE [RS_442]
+ Group By Operator [GBY_441] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_437] (rows=1704 width=1910)
+ Select Operator [SEL_440] (rows=1704 width=1910)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_435]
+ Please refer to the previous Select Operator [SEL_438]
<-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_447]
+ SHUFFLE [RS_450]
PartitionCols:_col0, _col1
- Select Operator [SEL_446] (rows=57591150 width=77)
+ Select Operator [SEL_449] (rows=57591150 width=77)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_445] (rows=57591150 width=77)
+ Filter Operator [FIL_448] (rows=57591150 width=77)
predicate:sr_item_sk is not null
TableScan [TS_3] (rows=57591150 width=77)
default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_item_sk","sr_ticket_number","sr_return_amt","sr_net_loss"]
http://git-wip-us.apache.org/repos/asf/hive/blob/ab9e954d/ql/src/test/results/clientpositive/perf/tez/query91.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query91.q.out b/ql/src/test/results/clientpositive/perf/tez/query91.q.out
index 5e0f00a..a53c7d79 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query91.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query91.q.out
@@ -75,109 +75,109 @@ Stage-0
limit:-1
Stage-1
Reducer 6 vectorized
- File Output Operator [FS_168]
- Select Operator [SEL_167] (rows=58564004 width=860)
+ File Output Operator [FS_170]
+ Select Operator [SEL_169] (rows=58564004 width=860)
Output:["_col0","_col1","_col2","_col3"]
<-Reducer 5 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_166]
- Select Operator [SEL_165] (rows=58564004 width=860)
+ SHUFFLE [RS_168]
+ Select Operator [SEL_167] (rows=58564004 width=860)
Output:["_col0","_col1","_col2","_col4"]
- Group By Operator [GBY_164] (rows=58564004 width=860)
+ Group By Operator [GBY_166] (rows=58564004 width=860)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_42]
PartitionCols:_col0, _col1, _col2, _col3, _col4
Group By Operator [GBY_41] (rows=117128008 width=860)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col3)"],keys:_col8, _col9, _col10, _col18, _col19
- Merge Join Operator [MERGEJOIN_142] (rows=117128008 width=860)
+ Merge Join Operator [MERGEJOIN_144] (rows=117128008 width=860)
Conds:RS_37._col1=RS_38._col2(Inner),Output:["_col3","_col8","_col9","_col10","_col18","_col19"]
<-Reducer 12 [SIMPLE_EDGE]
SHUFFLE [RS_38]
PartitionCols:_col2
Select Operator [SEL_30] (rows=106480005 width=860)
Output:["_col2","_col7","_col8"]
- Merge Join Operator [MERGEJOIN_141] (rows=106480005 width=860)
- Conds:RS_27._col2=RS_163._col0(Inner),Output:["_col0","_col5","_col6"]
+ Merge Join Operator [MERGEJOIN_143] (rows=106480005 width=860)
+ Conds:RS_27._col2=RS_165._col0(Inner),Output:["_col0","_col5","_col6"]
<-Map 15 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_163]
+ SHUFFLE [RS_165]
PartitionCols:_col0
- Select Operator [SEL_162] (rows=3600 width=107)
+ Select Operator [SEL_164] (rows=3600 width=107)
Output:["_col0"]
- Filter Operator [FIL_161] (rows=3600 width=107)
+ Filter Operator [FIL_163] (rows=3600 width=107)
predicate:((hd_buy_potential like '0-500%') and hd_demo_sk is not null)
TableScan [TS_18] (rows=7200 width=107)
default@household_demographics,household_demographics,Tbl:COMPLETE,Col:NONE,Output:["hd_demo_sk","hd_buy_potential"]
<-Reducer 11 [SIMPLE_EDGE]
SHUFFLE [RS_27]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_140] (rows=96800003 width=860)
- Conds:RS_24._col3=RS_160._col0(Inner),Output:["_col0","_col2","_col5","_col6"]
+ Merge Join Operator [MERGEJOIN_142] (rows=96800003 width=860)
+ Conds:RS_24._col3=RS_162._col0(Inner),Output:["_col0","_col2","_col5","_col6"]
<-Map 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_160]
+ SHUFFLE [RS_162]
PartitionCols:_col0
- Select Operator [SEL_159] (rows=20000000 width=1014)
+ Select Operator [SEL_161] (rows=20000000 width=1014)
Output:["_col0"]
- Filter Operator [FIL_158] (rows=20000000 width=1014)
+ Filter Operator [FIL_160] (rows=20000000 width=1014)
predicate:((ca_gmt_offset = -7) and ca_address_sk is not null)
TableScan [TS_15] (rows=40000000 width=1014)
default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_gmt_offset"]
<-Reducer 10 [SIMPLE_EDGE]
SHUFFLE [RS_24]
PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_139] (rows=88000001 width=860)
- Conds:RS_154._col1=RS_157._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6"]
+ Merge Join Operator [MERGEJOIN_141] (rows=88000001 width=860)
+ Conds:RS_156._col1=RS_159._col0(Inner),Output:["_col0","_col2","_col3","_col5","_col6"]
<-Map 13 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_157]
+ SHUFFLE [RS_159]
PartitionCols:_col0
- Select Operator [SEL_156] (rows=930900 width=385)
+ Select Operator [SEL_158] (rows=930900 width=385)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_155] (rows=930900 width=385)
+ Filter Operator [FIL_157] (rows=930900 width=385)
predicate:((((cd_marital_status = 'M') and (cd_education_status = 'Unknown')) or ((cd_marital_status = 'W') and (cd_education_status = 'Advanced Degree'))) and ((cd_education_status = 'Unknown') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'W')) and cd_demo_sk is not null)
TableScan [TS_12] (rows=1861800 width=385)
default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
<-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_154]
+ SHUFFLE [RS_156]
PartitionCols:_col1
- Select Operator [SEL_153] (rows=80000000 width=860)
+ Select Operator [SEL_155] (rows=80000000 width=860)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_152] (rows=80000000 width=860)
+ Filter Operator [FIL_154] (rows=80000000 width=860)
predicate:(c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null and c_customer_sk is not null)
TableScan [TS_9] (rows=80000000 width=860)
default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_current_cdemo_sk","c_current_hdemo_sk","c_current_addr_sk"]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_37]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_138] (rows=34846646 width=106)
- Conds:RS_34._col2=RS_151._col0(Inner),Output:["_col1","_col3","_col8","_col9","_col10"]
+ Merge Join Operator [MERGEJOIN_140] (rows=34846646 width=106)
+ Conds:RS_34._col2=RS_153._col0(Inner),Output:["_col1","_col3","_col8","_col9","_col10"]
<-Map 8 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_151]
+ SHUFFLE [RS_153]
PartitionCols:_col0
- Select Operator [SEL_150] (rows=60 width=2045)
+ Select Operator [SEL_152] (rows=60 width=2045)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_149] (rows=60 width=2045)
+ Filter Operator [FIL_151] (rows=60 width=2045)
predicate:cc_call_center_sk is not null
TableScan [TS_6] (rows=60 width=2045)
default@call_center,call_center,Tbl:COMPLETE,Col:NONE,Output:["cc_call_center_sk","cc_call_center_id","cc_name","cc_manager"]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_34]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_137] (rows=31678769 width=106)
- Conds:RS_145._col0=RS_148._col0(Inner),Output:["_col1","_col2","_col3"]
+ Merge Join Operator [MERGEJOIN_139] (rows=31678769 width=106)
+ Conds:RS_147._col0=RS_150._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_145]
+ SHUFFLE [RS_147]
PartitionCols:_col0
- Select Operator [SEL_144] (rows=28798881 width=106)
+ Select Operator [SEL_146] (rows=28798881 width=106)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_143] (rows=28798881 width=106)
+ Filter Operator [FIL_145] (rows=28798881 width=106)
predicate:(cr_call_center_sk is not null and cr_returned_date_sk is not null and cr_returning_customer_sk is not null)
TableScan [TS_0] (rows=28798881 width=106)
default@catalog_returns,catalog_returns,Tbl:COMPLETE,Col:NONE,Output:["cr_returned_date_sk","cr_returning_customer_sk","cr_call_center_sk","cr_net_loss"]
<-Map 7 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_148]
+ SHUFFLE [RS_150]
PartitionCols:_col0
- Select Operator [SEL_147] (rows=18262 width=1119)
+ Select Operator [SEL_149] (rows=18262 width=1119)
Output:["_col0"]
- Filter Operator [FIL_146] (rows=18262 width=1119)
+ Filter Operator [FIL_148] (rows=18262 width=1119)
predicate:((d_moy = 11) and (d_year = 1999) 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_year","d_moy"]
http://git-wip-us.apache.org/repos/asf/hive/blob/ab9e954d/ql/src/test/results/clientpositive/perf/tez/query92.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query92.q.out b/ql/src/test/results/clientpositive/perf/tez/query92.q.out
index 061fcf7..4b4afa9 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query92.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query92.q.out
@@ -59,34 +59,31 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Map 1 <- Reducer 7 (BROADCAST_EDGE)
-Map 12 <- Reducer 11 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE)
-Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (ONE_TO_ONE_EDGE)
-Reducer 11 <- Map 6 (CUSTOM_SIMPLE_EDGE)
-Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
-Reducer 3 <- Reducer 10 (ONE_TO_ONE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 9 (BROADCAST_EDGE)
+Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
+Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (ONE_TO_ONE_EDGE)
Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
-Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
-Reducer 8 <- Map 12 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
-Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
+Reducer 6 <- Reducer 2 (SIMPLE_EDGE)
+Reducer 7 <- Map 10 (SIMPLE_EDGE), Reducer 6 (ONE_TO_ONE_EDGE)
+Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
Reducer 5 vectorized
- File Output Operator [FS_142]
- Limit [LIM_141] (rows=1 width=112)
+ File Output Operator [FS_135]
+ Limit [LIM_134] (rows=1 width=112)
Number of rows:100
- Select Operator [SEL_140] (rows=1 width=112)
+ Select Operator [SEL_133] (rows=1 width=112)
Output:["_col0"]
<-Reducer 4 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_139]
- Select Operator [SEL_138] (rows=1 width=112)
+ SHUFFLE [RS_132]
+ Select Operator [SEL_131] (rows=1 width=112)
Output:["_col1"]
- Group By Operator [GBY_137] (rows=1 width=112)
+ Group By Operator [GBY_130] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(VALUE._col0)"]
<-Reducer 3 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_36]
@@ -96,103 +93,78 @@ Stage-0
Output:["_col2"]
Filter Operator [FIL_33] (rows=58081078 width=135)
predicate:(_col2 > CAST( (1.3 * _col6) AS decimal(14,7)))
- Merge Join Operator [MERGEJOIN_105] (rows=174243235 width=135)
+ Merge Join Operator [MERGEJOIN_107] (rows=174243235 width=135)
Conds:RS_30._col1=RS_31._col2(Inner),Output:["_col2","_col6"]
- <-Reducer 10 [ONE_TO_ONE_EDGE]
- FORWARD [RS_31]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_104] (rows=87121617 width=135)
- Conds:RS_136._col0=RS_125._col0(Inner),Output:["_col1","_col2"]
- <-Map 13 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_125]
- PartitionCols:_col0
- Select Operator [SEL_124] (rows=231000 width=1436)
- Output:["_col0"]
- Filter Operator [FIL_123] (rows=231000 width=1436)
- predicate:((i_manufact_id = 269) and i_item_sk is not null)
- TableScan [TS_20] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_manufact_id"]
- <-Reducer 9 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_136]
- PartitionCols:_col0
- Select Operator [SEL_135] (rows=79201469 width=135)
- Output:["_col0","_col1"]
- Group By Operator [GBY_134] (rows=79201469 width=135)
- Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0
- <-Reducer 8 [SIMPLE_EDGE]
- SHUFFLE [RS_17]
- PartitionCols:_col0
- Group By Operator [GBY_16] (rows=158402938 width=135)
- Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1
- Merge Join Operator [MERGEJOIN_103] (rows=158402938 width=135)
- Conds:RS_133._col0=RS_110._col0(Inner),Output:["_col1","_col2"]
- <-Map 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_110]
- PartitionCols:_col0
- Select Operator [SEL_107] (rows=8116 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_106] (rows=8116 width=1119)
- predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null)
- TableScan [TS_3] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
- <-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_133]
- PartitionCols:_col0
- Select Operator [SEL_132] (rows=144002668 width=135)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_131] (rows=144002668 width=135)
- predicate:((ws_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_13_date_dim_d_date_sk_min) AND DynamicValue(RS_13_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null)
- TableScan [TS_6] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_discount_amt"]
- <-Reducer 11 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_122]
- Group By Operator [GBY_121] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_115]
- Group By Operator [GBY_113] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_111] (rows=8116 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_107]
- <-Reducer 14 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_130]
- Group By Operator [GBY_129] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_128]
- Group By Operator [GBY_127] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_126] (rows=231000 width=1436)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_124]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_30]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_102] (rows=158402938 width=135)
- Conds:RS_120._col0=RS_108._col0(Inner),Output:["_col1","_col2"]
- <-Map 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_108]
+ Merge Join Operator [MERGEJOIN_104] (rows=158402938 width=135)
+ Conds:RS_126._col0=RS_110._col0(Inner),Output:["_col1","_col2"]
+ <-Map 8 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_110]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_107]
+ Select Operator [SEL_109] (rows=8116 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_108] (rows=8116 width=1119)
+ predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-18 00:00:00' AND TIMESTAMP'1998-06-16 00:00:00' and d_date_sk is not null)
+ TableScan [TS_3] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_120]
+ SHUFFLE [RS_126]
PartitionCols:_col0
- Select Operator [SEL_119] (rows=144002668 width=135)
+ Select Operator [SEL_125] (rows=144002668 width=135)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_118] (rows=144002668 width=135)
- predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null)
+ Filter Operator [FIL_124] (rows=144002668 width=135)
+ predicate:((ws_item_sk BETWEEN DynamicValue(RS_24_item_i_item_sk_min) AND DynamicValue(RS_24_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_24_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_28_date_dim_d_date_sk_min) AND DynamicValue(RS_28_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_28_date_dim_d_date_sk_bloom_filter))) and ws_item_sk is not null and ws_sold_date_sk is not null)
TableScan [TS_0] (rows=144002668 width=135)
default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_ext_discount_amt"]
- <-Reducer 7 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_117]
- Group By Operator [GBY_116] (rows=1 width=12)
+ <-Reducer 11 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_123]
+ Group By Operator [GBY_122] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 6 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_114]
+ <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_121]
+ Group By Operator [GBY_120] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_119] (rows=231000 width=1436)
+ Output:["_col0"]
+ Select Operator [SEL_117] (rows=231000 width=1436)
+ Output:["_col0"]
+ Filter Operator [FIL_116] (rows=231000 width=1436)
+ predicate:((i_manufact_id = 269) and i_item_sk is not null)
+ TableScan [TS_20] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_manufact_id"]
+ <-Reducer 9 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_115]
+ Group By Operator [GBY_114] (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_113]
Group By Operator [GBY_112] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_109] (rows=8116 width=1119)
+ Select Operator [SEL_111] (rows=8116 width=1119)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_107]
+ Please refer to the previous Select Operator [SEL_109]
+ <-Reducer 7 [ONE_TO_ONE_EDGE]
+ FORWARD [RS_31]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_106] (rows=87121617 width=135)
+ Conds:RS_129._col0=RS_118._col0(Inner),Output:["_col1","_col2"]
+ <-Map 10 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_118]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_117]
+ <-Reducer 6 [ONE_TO_ONE_EDGE] vectorized
+ FORWARD [RS_129]
+ PartitionCols:_col0
+ Select Operator [SEL_128] (rows=79201469 width=135)
+ Output:["_col0","_col1"]
+ Group By Operator [GBY_127] (rows=79201469 width=135)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"],keys:KEY._col0
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_17]
+ PartitionCols:_col0
+ Group By Operator [GBY_16] (rows=158402938 width=135)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(_col2)","count(_col2)"],keys:_col1
+ Please refer to the previous Merge Join Operator [MERGEJOIN_104]