You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by se...@apache.org on 2018/11/13 21:35:09 UTC
[16/59] [abbrv] [partial] hive git commit: HIVE-20850: Push case
conditional from projections to dimension tables if possible (Zoltan
Haindrich via Jesus Camacho Rodriguez)
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query11.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query11.q.out b/ql/src/test/results/clientpositive/perf/tez/query11.q.out
index 2f453f3..da1c349 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query11.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query11.q.out
@@ -189,249 +189,241 @@ Stage-0
limit:100
Stage-1
Reducer 8 vectorized
- File Output Operator [FS_358]
- Limit [LIM_357] (rows=100 width=85)
+ File Output Operator [FS_354]
+ Limit [LIM_353] (rows=100 width=85)
Number of rows:100
- Select Operator [SEL_356] (rows=12248093 width=85)
+ Select Operator [SEL_352] (rows=12248093 width=85)
Output:["_col0"]
<-Reducer 7 [SIMPLE_EDGE]
- SHUFFLE [RS_97]
- Select Operator [SEL_96] (rows=12248093 width=85)
+ SHUFFLE [RS_93]
+ Select Operator [SEL_92] (rows=12248093 width=85)
Output:["_col0"]
- Filter Operator [FIL_95] (rows=12248093 width=533)
- predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > (_col8 / _col3))) ELSE ((null > (_col8 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > null)) ELSE (null) END) END
- Merge Join Operator [MERGEJOIN_291] (rows=24496186 width=533)
- Conds:RS_92._col2=RS_355._col0(Inner),Output:["_col1","_col3","_col5","_col7","_col8"]
+ Filter Operator [FIL_91] (rows=12248093 width=537)
+ predicate:CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col6) THEN (((_col1 / _col5) > (_col9 / _col3))) ELSE ((null > (_col9 / _col3))) END) ELSE (CASE WHEN (_col6) THEN (((_col1 / _col5) > null)) ELSE (null) END) END
+ Merge Join Operator [MERGEJOIN_287] (rows=24496186 width=537)
+ Conds:RS_88._col2=RS_351._col0(Inner),Output:["_col1","_col3","_col5","_col6","_col8","_col9"]
<-Reducer 20 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_355]
+ SHUFFLE [RS_351]
PartitionCols:_col0
- Select Operator [SEL_354] (rows=80000000 width=297)
+ Select Operator [SEL_350] (rows=80000000 width=297)
Output:["_col0","_col1","_col2"]
- Group By Operator [GBY_353] (rows=80000000 width=764)
+ Group By Operator [GBY_349] (rows=80000000 width=764)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6
<-Reducer 19 [SIMPLE_EDGE]
- SHUFFLE [RS_83]
+ SHUFFLE [RS_79]
PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6
- Group By Operator [GBY_82] (rows=80000000 width=764)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6
- Select Operator [SEL_80] (rows=187573258 width=847)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Merge Join Operator [MERGEJOIN_288] (rows=187573258 width=847)
- Conds:RS_77._col1=RS_321._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"]
- <-Map 26 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_321]
- PartitionCols:_col0
- Select Operator [SEL_320] (rows=80000000 width=656)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Filter Operator [FIL_319] (rows=80000000 width=656)
- predicate:(c_customer_id is not null and c_customer_sk is not null)
- TableScan [TS_71] (rows=80000000 width=656)
- default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"]
- <-Reducer 18 [SIMPLE_EDGE]
- SHUFFLE [RS_77]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_287] (rows=187573258 width=199)
- Conds:RS_352._col0=RS_298._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 21 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_298]
- PartitionCols:_col0
- Select Operator [SEL_295] (rows=652 width=8)
- Output:["_col0"]
- Filter Operator [FIL_292] (rows=652 width=8)
- predicate:((d_year = 2002) and d_date_sk is not null)
- TableScan [TS_68] (rows=73049 width=8)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"]
- <-Map 17 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_352]
- PartitionCols:_col0
- Select Operator [SEL_351] (rows=525327388 width=221)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_350] (rows=525327388 width=221)
- predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_75_date_dim_d_date_sk_min) AND DynamicValue(RS_75_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_75_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_65] (rows=575995635 width=221)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"]
- <-Reducer 22 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_349]
- Group By Operator [GBY_348] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_310]
- Group By Operator [GBY_306] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_299] (rows=652 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_295]
+ Group By Operator [GBY_78] (rows=80000000 width=764)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11
+ Merge Join Operator [MERGEJOIN_284] (rows=187573258 width=764)
+ Conds:RS_74._col1=RS_317._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
+ <-Map 26 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_317]
+ PartitionCols:_col0
+ Select Operator [SEL_316] (rows=80000000 width=656)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
+ Filter Operator [FIL_315] (rows=80000000 width=656)
+ predicate:(c_customer_id is not null and c_customer_sk is not null)
+ TableScan [TS_68] (rows=80000000 width=656)
+ default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_customer_id","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_country","c_login","c_email_address"]
+ <-Reducer 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_74]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_283] (rows=187573258 width=115)
+ Conds:RS_348._col0=RS_294._col0(Inner),Output:["_col1","_col2"]
+ <-Map 21 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_294]
+ PartitionCols:_col0
+ Select Operator [SEL_291] (rows=652 width=4)
+ Output:["_col0"]
+ Filter Operator [FIL_288] (rows=652 width=8)
+ predicate:((d_year = 2002) and d_date_sk is not null)
+ TableScan [TS_65] (rows=73049 width=8)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"]
+ <-Map 17 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_348]
+ PartitionCols:_col0
+ Select Operator [SEL_347] (rows=525327388 width=119)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_346] (rows=525327388 width=221)
+ predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_72_date_dim_d_date_sk_min) AND DynamicValue(RS_72_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_72_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_62] (rows=575995635 width=221)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"]
+ <-Reducer 22 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_345]
+ Group By Operator [GBY_344] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_306]
+ Group By Operator [GBY_302] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_295] (rows=652 width=4)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_291]
<-Reducer 6 [ONE_TO_ONE_EDGE]
- FORWARD [RS_92]
+ FORWARD [RS_88]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_290] (rows=20485011 width=436)
- Conds:RS_89._col2=RS_347._col0(Inner),Output:["_col1","_col2","_col3","_col5"]
+ Merge Join Operator [MERGEJOIN_286] (rows=20485011 width=440)
+ Conds:RS_85._col2=RS_343._col0(Inner),Output:["_col1","_col2","_col3","_col5","_col6"]
<-Reducer 16 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_347]
+ SHUFFLE [RS_343]
PartitionCols:_col0
- Select Operator [SEL_346] (rows=17130654 width=212)
- Output:["_col0","_col1"]
- Filter Operator [FIL_345] (rows=17130654 width=212)
+ Select Operator [SEL_342] (rows=17130654 width=216)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_341] (rows=17130654 width=212)
predicate:(_col7 > 0)
- Select Operator [SEL_344] (rows=51391963 width=212)
+ Select Operator [SEL_340] (rows=51391963 width=212)
Output:["_col0","_col7"]
- Group By Operator [GBY_343] (rows=51391963 width=764)
+ Group By Operator [GBY_339] (rows=51391963 width=764)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6
<-Reducer 15 [SIMPLE_EDGE]
- SHUFFLE [RS_61]
+ SHUFFLE [RS_58]
PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6
- Group By Operator [GBY_60] (rows=51391963 width=764)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6
- Select Operator [SEL_58] (rows=51391963 width=875)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Merge Join Operator [MERGEJOIN_286] (rows=51391963 width=875)
- Conds:RS_55._col1=RS_324._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"]
- <-Map 26 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_324]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_320]
- <-Reducer 14 [SIMPLE_EDGE]
- SHUFFLE [RS_55]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_285] (rows=51391963 width=227)
- Conds:RS_342._col0=RS_304._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 21 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_304]
- PartitionCols:_col0
- Select Operator [SEL_297] (rows=652 width=8)
- Output:["_col0"]
- Filter Operator [FIL_294] (rows=652 width=8)
- predicate:((d_year = 2001) and d_date_sk is not null)
- Please refer to the previous TableScan [TS_68]
- <-Map 13 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_342]
- PartitionCols:_col0
- Select Operator [SEL_341] (rows=143930993 width=231)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_340] (rows=143930993 width=231)
- predicate:((ws_sold_date_sk BETWEEN DynamicValue(RS_53_date_dim_d_date_sk_min) AND DynamicValue(RS_53_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_53_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null)
- TableScan [TS_43] (rows=144002668 width=231)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"]
- <-Reducer 25 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_339]
- Group By Operator [GBY_338] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_313]
- Group By Operator [GBY_309] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_305] (rows=652 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_297]
+ Group By Operator [GBY_57] (rows=51391963 width=764)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11
+ Merge Join Operator [MERGEJOIN_282] (rows=51391963 width=764)
+ Conds:RS_53._col1=RS_320._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
+ <-Map 26 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_320]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_316]
+ <-Reducer 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_53]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_281] (rows=51391963 width=115)
+ Conds:RS_338._col0=RS_300._col0(Inner),Output:["_col1","_col2"]
+ <-Map 21 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_300]
+ PartitionCols:_col0
+ Select Operator [SEL_293] (rows=652 width=4)
+ Output:["_col0"]
+ Filter Operator [FIL_290] (rows=652 width=8)
+ predicate:((d_year = 2001) and d_date_sk is not null)
+ Please refer to the previous TableScan [TS_65]
+ <-Map 13 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_338]
+ PartitionCols:_col0
+ Select Operator [SEL_337] (rows=143930993 width=119)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_336] (rows=143930993 width=231)
+ predicate:((ws_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(ws_sold_date_sk, DynamicValue(RS_51_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null)
+ TableScan [TS_41] (rows=144002668 width=231)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"]
+ <-Reducer 25 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_335]
+ Group By Operator [GBY_334] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_309]
+ Group By Operator [GBY_305] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_301] (rows=652 width=4)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_293]
<-Reducer 5 [ONE_TO_ONE_EDGE]
- FORWARD [RS_89]
+ FORWARD [RS_85]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_289] (rows=31888273 width=324)
- Conds:RS_327._col0=RS_337._col0(Inner),Output:["_col1","_col2","_col3"]
+ Merge Join Operator [MERGEJOIN_285] (rows=31888273 width=324)
+ Conds:RS_323._col0=RS_333._col0(Inner),Output:["_col1","_col2","_col3"]
<-Reducer 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_337]
+ SHUFFLE [RS_333]
PartitionCols:_col0
- Select Operator [SEL_336] (rows=26666666 width=212)
+ Select Operator [SEL_332] (rows=26666666 width=212)
Output:["_col0","_col1"]
- Filter Operator [FIL_335] (rows=26666666 width=212)
+ Filter Operator [FIL_331] (rows=26666666 width=212)
predicate:(_col7 > 0)
- Select Operator [SEL_334] (rows=80000000 width=212)
+ Select Operator [SEL_330] (rows=80000000 width=212)
Output:["_col0","_col7"]
- Group By Operator [GBY_333] (rows=80000000 width=764)
+ Group By Operator [GBY_329] (rows=80000000 width=764)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6
<-Reducer 11 [SIMPLE_EDGE]
- SHUFFLE [RS_39]
+ SHUFFLE [RS_37]
PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6
- Group By Operator [GBY_38] (rows=80000000 width=764)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6
- Select Operator [SEL_36] (rows=187573258 width=847)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Merge Join Operator [MERGEJOIN_284] (rows=187573258 width=847)
- Conds:RS_33._col1=RS_323._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"]
- <-Map 26 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_323]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_320]
- <-Reducer 10 [SIMPLE_EDGE]
- SHUFFLE [RS_33]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_283] (rows=187573258 width=199)
- Conds:RS_332._col0=RS_302._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 21 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_302]
- PartitionCols:_col0
- Select Operator [SEL_296] (rows=652 width=8)
- Output:["_col0"]
- Filter Operator [FIL_293] (rows=652 width=8)
- predicate:((d_year = 2001) and d_date_sk is not null)
- Please refer to the previous TableScan [TS_68]
- <-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_332]
- PartitionCols:_col0
- Select Operator [SEL_331] (rows=525327388 width=221)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_330] (rows=525327388 width=221)
- predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_31_date_dim_d_date_sk_min) AND DynamicValue(RS_31_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_31_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_21] (rows=575995635 width=221)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"]
- <-Reducer 24 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_329]
- Group By Operator [GBY_328] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_312]
- Group By Operator [GBY_308] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_303] (rows=652 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_296]
+ Group By Operator [GBY_36] (rows=80000000 width=764)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11
+ Merge Join Operator [MERGEJOIN_280] (rows=187573258 width=764)
+ Conds:RS_32._col1=RS_319._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
+ <-Map 26 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_319]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_316]
+ <-Reducer 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_32]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_279] (rows=187573258 width=115)
+ Conds:RS_328._col0=RS_298._col0(Inner),Output:["_col1","_col2"]
+ <-Map 21 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_298]
+ PartitionCols:_col0
+ Select Operator [SEL_292] (rows=652 width=4)
+ Output:["_col0"]
+ Filter Operator [FIL_289] (rows=652 width=8)
+ predicate:((d_year = 2001) and d_date_sk is not null)
+ Please refer to the previous TableScan [TS_65]
+ <-Map 9 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_328]
+ PartitionCols:_col0
+ Select Operator [SEL_327] (rows=525327388 width=119)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_326] (rows=525327388 width=221)
+ predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_30_date_dim_d_date_sk_min) AND DynamicValue(RS_30_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_30_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_20] (rows=575995635 width=221)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_ext_discount_amt","ss_ext_list_price"]
+ <-Reducer 24 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_325]
+ Group By Operator [GBY_324] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_308]
+ Group By Operator [GBY_304] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_299] (rows=652 width=4)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_292]
<-Reducer 4 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_327]
+ SHUFFLE [RS_323]
PartitionCols:_col0
- Select Operator [SEL_326] (rows=51391963 width=212)
+ Select Operator [SEL_322] (rows=51391963 width=212)
Output:["_col0","_col1"]
- Group By Operator [GBY_325] (rows=51391963 width=764)
+ Group By Operator [GBY_321] (rows=51391963 width=764)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6
<-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_18]
+ SHUFFLE [RS_17]
PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6
- Group By Operator [GBY_17] (rows=51391963 width=764)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col7)"],keys:_col0, _col1, _col2, _col3, _col4, _col5, _col6
- Select Operator [SEL_15] (rows=51391963 width=875)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Merge Join Operator [MERGEJOIN_282] (rows=51391963 width=875)
- Conds:RS_12._col1=RS_322._col0(Inner),Output:["_col2","_col3","_col7","_col8","_col9","_col10","_col11","_col12","_col13"]
- <-Map 26 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_322]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_320]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_12]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_281] (rows=51391963 width=227)
- Conds:RS_318._col0=RS_300._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 21 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_300]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_295]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_318]
- PartitionCols:_col0
- Select Operator [SEL_317] (rows=143930993 width=231)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_316] (rows=143930993 width=231)
- predicate:((ws_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(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null)
- TableScan [TS_0] (rows=144002668 width=231)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"]
- <-Reducer 23 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_315]
- Group By Operator [GBY_314] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_311]
- Group By Operator [GBY_307] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_301] (rows=652 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_295]
+ Group By Operator [GBY_16] (rows=51391963 width=764)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)"],keys:_col5, _col6, _col7, _col8, _col9, _col10, _col11
+ Merge Join Operator [MERGEJOIN_278] (rows=51391963 width=764)
+ Conds:RS_12._col1=RS_318._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9","_col10","_col11"]
+ <-Map 26 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_318]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_316]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_12]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_277] (rows=51391963 width=115)
+ Conds:RS_314._col0=RS_296._col0(Inner),Output:["_col1","_col2"]
+ <-Map 21 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_296]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_291]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_314]
+ PartitionCols:_col0
+ Select Operator [SEL_313] (rows=143930993 width=119)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_312] (rows=143930993 width=231)
+ predicate:((ws_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(ws_sold_date_sk, DynamicValue(RS_10_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk is not null and ws_sold_date_sk is not null)
+ TableScan [TS_0] (rows=144002668 width=231)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_bill_customer_sk","ws_ext_discount_amt","ws_ext_list_price"]
+ <-Reducer 23 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_311]
+ Group By Operator [GBY_310] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_307]
+ Group By Operator [GBY_303] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_297] (rows=652 width=4)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_291]
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query12.q.out b/ql/src/test/results/clientpositive/perf/tez/query12.q.out
index 75156be..b6e4999 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query12.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query12.q.out
@@ -109,9 +109,9 @@ Stage-0
SHUFFLE [RS_17]
PartitionCols:_col0, _col1, _col2, _col3, _col4
Group By Operator [GBY_16] (rows=138600 width=689)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col10, _col9, _col6, _col7, _col8
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col2)"],keys:_col9, _col8, _col5, _col6, _col7
Merge Join Operator [MERGEJOIN_58] (rows=4798568 width=689)
- Conds:RS_12._col1=RS_69._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10"]
+ Conds:RS_12._col1=RS_69._col0(Inner),Output:["_col2","_col5","_col6","_col7","_col8","_col9"]
<-Map 9 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_69]
PartitionCols:_col0
@@ -129,7 +129,7 @@ Stage-0
<-Map 7 [SIMPLE_EDGE] vectorized
PARTITION_ONLY_SHUFFLE [RS_61]
PartitionCols:_col0
- Select Operator [SEL_60] (rows=8116 width=98)
+ Select Operator [SEL_60] (rows=8116 width=4)
Output:["_col0"]
Filter Operator [FIL_59] (rows=8116 width=98)
predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'2001-01-12 00:00:00' AND TIMESTAMP'2001-02-11 00:00:00' and d_date_sk is not null)
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query13.q.out b/ql/src/test/results/clientpositive/perf/tez/query13.q.out
index 0e02e9a..d6e86c4 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query13.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query13.q.out
@@ -115,17 +115,17 @@ POSTHOOK: Output: hdfs://### HDFS PATH ###
Plan optimized by CBO.
Vertex dependency in root stage
-Map 8 <- Reducer 10 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE)
-Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
+Map 9 <- Reducer 12 (BROADCAST_EDGE), Reducer 14 (BROADCAST_EDGE), Reducer 16 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE)
Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE)
Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE)
Reducer 16 <- Map 15 (CUSTOM_SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
-Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
+Reducer 3 <- Map 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
Reducer 5 <- Map 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
Reducer 6 <- Map 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE)
+Reducer 8 <- Map 1 (CUSTOM_SIMPLE_EDGE)
Stage-0
Fetch Operator
@@ -140,131 +140,131 @@ Stage-0
<-Reducer 6 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_37]
Group By Operator [GBY_36] (rows=1 width=256)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","count(_col6)","sum(_col8)","count(_col8)","sum(_col9)","count(_col9)"]
- Select Operator [SEL_35] (rows=4851 width=183)
- Output:["_col6","_col8","_col9"]
- Filter Operator [FIL_34] (rows=4851 width=183)
- predicate:(((_col19 = 'D') and (_col20 = 'Primary') and _col7 BETWEEN 50 AND 100 and (_col14 = 1)) or ((_col19 = 'M') and (_col20 = '4 yr Degree') and _col7 BETWEEN 100 AND 150 and (_col14 = 3)) or ((_col19 = 'U') and (_col20 = 'Advanced Degree') and _col7 BETWEEN 150 AND 200 and (_col14 = 1)))
- Merge Join Operator [MERGEJOIN_121] (rows=58239 width=183)
- Conds:RS_31._col2=RS_151._col0(Inner),Output:["_col6","_col7","_col8","_col9","_col14","_col19","_col20"]
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["sum(_col6)","count(_col6)","sum(_col7)","count(_col7)","sum(_col8)","count(_col8)"]
+ Select Operator [SEL_35] (rows=40950 width=44)
+ Output:["_col6","_col7","_col8"]
+ Filter Operator [FIL_34] (rows=40950 width=44)
+ predicate:((_col24 and _col25 and _col12 and _col17) or (_col26 and _col27 and _col13 and _col18) or (_col28 and _col29 and _col14 and _col18))
+ Merge Join Operator [MERGEJOIN_121] (rows=218403 width=44)
+ Conds:RS_31._col2=RS_148._col0(Inner),Output:["_col6","_col7","_col8","_col12","_col13","_col14","_col17","_col18","_col24","_col25","_col26","_col27","_col28","_col29"]
<-Map 15 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_151]
+ SHUFFLE [RS_148]
PartitionCols:_col0
- Select Operator [SEL_150] (rows=265971 width=183)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_149] (rows=265971 width=183)
+ Select Operator [SEL_147] (rows=265971 width=28)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
+ Filter Operator [FIL_146] (rows=265971 width=183)
predicate:((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null)
TableScan [TS_15] (rows=1861800 width=183)
default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_31]
PartitionCols:_col2
- Filter Operator [FIL_30] (rows=58239 width=90)
- predicate:(((_col16) IN ('KY', 'GA', 'NM') and _col10 BETWEEN 100 AND 200) or ((_col16) IN ('MT', 'OR', 'IN') and _col10 BETWEEN 150 AND 300) or ((_col16) IN ('WI', 'MO', 'WV') and _col10 BETWEEN 50 AND 250))
- Merge Join Operator [MERGEJOIN_120] (rows=291204 width=90)
- Conds:RS_27._col4=RS_143._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10","_col14","_col16"]
+ Filter Operator [FIL_30] (rows=218403 width=44)
+ predicate:((_col20 and _col9) or (_col21 and _col10) or (_col22 and _col11))
+ Merge Join Operator [MERGEJOIN_120] (rows=291204 width=44)
+ Conds:RS_27._col4=RS_140._col0(Inner),Output:["_col2","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col17","_col18","_col20","_col21","_col22"]
<-Map 13 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_143]
+ SHUFFLE [RS_140]
PartitionCols:_col0
- Select Operator [SEL_142] (rows=3529412 width=187)
- Output:["_col0","_col1"]
- Filter Operator [FIL_141] (rows=3529412 width=187)
+ Select Operator [SEL_139] (rows=3529412 width=16)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_138] (rows=3529412 width=187)
predicate:((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and ca_address_sk is not null)
TableScan [TS_12] (rows=40000000 width=187)
default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_country"]
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_27]
PartitionCols:_col4
- Merge Join Operator [MERGEJOIN_119] (rows=3300311 width=145)
- Conds:RS_24._col3=RS_135._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8","_col9","_col10","_col14"]
+ Merge Join Operator [MERGEJOIN_119] (rows=3300311 width=104)
+ Conds:RS_24._col3=RS_132._col0(Inner),Output:["_col2","_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col17","_col18"]
<-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_135]
+ SHUFFLE [RS_132]
PartitionCols:_col0
- Select Operator [SEL_134] (rows=1309 width=8)
- Output:["_col0","_col1"]
- Filter Operator [FIL_133] (rows=1309 width=8)
+ Select Operator [SEL_131] (rows=1309 width=12)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_130] (rows=1309 width=8)
predicate:((hd_dep_count) IN (3, 1) and hd_demo_sk is not null)
TableScan [TS_9] (rows=7200 width=8)
default@household_demographics,household_demographics,Tbl:COMPLETE,Col:COMPLETE,Output:["hd_demo_sk","hd_dep_count"]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_24]
PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_118] (rows=18152968 width=405)
- Conds:RS_21._col1=RS_127._col0(Inner),Output:["_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"]
- <-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_127]
+ Merge Join Operator [MERGEJOIN_118] (rows=18152968 width=233)
+ Conds:RS_21._col5=RS_159._col0(Inner),Output:["_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"]
+ <-Map 10 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_159]
PartitionCols:_col0
- Select Operator [SEL_126] (rows=652 width=8)
+ Select Operator [SEL_158] (rows=1704 width=4)
Output:["_col0"]
- Filter Operator [FIL_125] (rows=652 width=8)
- predicate:((d_year = 2001) and d_date_sk is not null)
- TableScan [TS_6] (rows=73049 width=8)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"]
+ Filter Operator [FIL_157] (rows=1704 width=4)
+ predicate:s_store_sk is not null
+ TableScan [TS_6] (rows=1704 width=4)
+ default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_21]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_117] (rows=50840141 width=446)
- Conds:RS_124._col0=RS_159._col4(Inner),Output:["_col1","_col2","_col3","_col4","_col6","_col7","_col8","_col9","_col10"]
+ PartitionCols:_col5
+ Merge Join Operator [MERGEJOIN_117] (rows=18152968 width=237)
+ Conds:RS_124._col0=RS_156._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_124]
+ PARTITION_ONLY_SHUFFLE [RS_124]
PartitionCols:_col0
- Select Operator [SEL_123] (rows=1704 width=4)
+ Select Operator [SEL_123] (rows=652 width=4)
Output:["_col0"]
- Filter Operator [FIL_122] (rows=1704 width=4)
- predicate:s_store_sk is not null
- TableScan [TS_0] (rows=1704 width=4)
- default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk"]
- <-Map 8 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_159]
- PartitionCols:_col4
- Select Operator [SEL_158] (rows=50840141 width=450)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
- Filter Operator [FIL_157] (rows=50840141 width=450)
- predicate:((ss_addr_sk BETWEEN DynamicValue(RS_28_customer_address_ca_address_sk_min) AND DynamicValue(RS_28_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_28_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_32_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_32_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_32_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_25_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_25_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_25_household_demographics_hd_demo_sk_bloom_filter))) and (ss_net_profit BETWEEN 100 AND 200 or ss_net_profit BETWEEN 150 AND 300 or ss_net_profit BETWEEN 50 AND 250) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 1
50 AND 200) 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_addr_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null)
+ Filter Operator [FIL_122] (rows=652 width=8)
+ predicate:((d_year = 2001) and d_date_sk is not null)
+ TableScan [TS_0] (rows=73049 width=8)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"]
+ <-Map 9 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_156]
+ PartitionCols:_col0
+ Select Operator [SEL_155] (rows=50840141 width=260)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"]
+ Filter Operator [FIL_154] (rows=50840141 width=450)
+ predicate:((ss_addr_sk BETWEEN DynamicValue(RS_28_customer_address_ca_address_sk_min) AND DynamicValue(RS_28_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_28_customer_address_ca_address_sk_bloom_filter))) and (ss_cdemo_sk BETWEEN DynamicValue(RS_32_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_32_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_32_customer_demographics_cd_demo_sk_bloom_filter))) and (ss_hdemo_sk BETWEEN DynamicValue(RS_25_household_demographics_hd_demo_sk_min) AND DynamicValue(RS_25_household_demographics_hd_demo_sk_max) and in_bloom_filter(ss_hdemo_sk, DynamicValue(RS_25_household_demographics_hd_demo_sk_bloom_filter))) and (ss_net_profit BETWEEN 100 AND 200 or ss_net_profit BETWEEN 150 AND 300 or ss_net_profit BETWEEN 50 AND 250) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 1
50 AND 200) and (ss_sold_date_sk BETWEEN DynamicValue(RS_18_date_dim_d_date_sk_min) AND DynamicValue(RS_18_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_18_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null)
TableScan [TS_3] (rows=575995635 width=450)
default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_cdemo_sk","ss_hdemo_sk","ss_addr_sk","ss_store_sk","ss_quantity","ss_sales_price","ss_ext_sales_price","ss_ext_wholesale_cost","ss_net_profit"]
- <-Reducer 10 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_132]
- Group By Operator [GBY_131] (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_130]
- Group By Operator [GBY_129] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_128] (rows=652 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_126]
<-Reducer 12 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_140]
- Group By Operator [GBY_139] (rows=1 width=12)
+ BROADCAST [RS_137]
+ Group By Operator [GBY_136] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_138]
- Group By Operator [GBY_137] (rows=1 width=12)
+ 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_136] (rows=1309 width=4)
+ Select Operator [SEL_133] (rows=1309 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_134]
+ Please refer to the previous Select Operator [SEL_131]
<-Reducer 14 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_148]
- Group By Operator [GBY_147] (rows=1 width=12)
+ BROADCAST [RS_145]
+ Group By Operator [GBY_144] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=3529412)"]
<-Map 13 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_146]
- Group By Operator [GBY_145] (rows=1 width=12)
+ SHUFFLE [RS_143]
+ Group By Operator [GBY_142] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=3529412)"]
- Select Operator [SEL_144] (rows=3529412 width=4)
+ Select Operator [SEL_141] (rows=3529412 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_142]
+ Please refer to the previous Select Operator [SEL_139]
<-Reducer 16 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_156]
- Group By Operator [GBY_155] (rows=1 width=12)
+ BROADCAST [RS_153]
+ Group By Operator [GBY_152] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 15 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_154]
- Group By Operator [GBY_153] (rows=1 width=12)
+ SHUFFLE [RS_151]
+ Group By Operator [GBY_150] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_149] (rows=265971 width=4)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_147]
+ <-Reducer 8 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_129]
+ Group By Operator [GBY_128] (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
+ PARTITION_ONLY_SHUFFLE [RS_127]
+ Group By Operator [GBY_126] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_152] (rows=265971 width=4)
+ Select Operator [SEL_125] (rows=652 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_150]
+ Please refer to the previous Select Operator [SEL_123]
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query14.q.out b/ql/src/test/results/clientpositive/perf/tez/query14.q.out
index 2c28023..2e99363 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query14.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query14.q.out
@@ -376,7 +376,7 @@ Stage-0
<-Map 96 [SIMPLE_EDGE] vectorized
PARTITION_ONLY_SHUFFLE [RS_1623]
PartitionCols:_col0
- Select Operator [SEL_1612] (rows=1957 width=8)
+ Select Operator [SEL_1612] (rows=1957 width=4)
Output:["_col0"]
Filter Operator [FIL_1611] (rows=1957 width=8)
predicate:(d_date_sk is not null and d_year BETWEEN 1999 AND 2001)
@@ -415,7 +415,7 @@ Stage-0
<-Map 24 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_1763]
PartitionCols:_col0
- Select Operator [SEL_1758] (rows=1957 width=8)
+ Select Operator [SEL_1758] (rows=1957 width=4)
Output:["_col0"]
Filter Operator [FIL_1757] (rows=1957 width=8)
predicate:(d_date_sk is not null and d_year BETWEEN 1998 AND 2000)
@@ -454,7 +454,7 @@ Stage-0
<-Map 40 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_1791]
PartitionCols:_col0
- Select Operator [SEL_1786] (rows=1957 width=8)
+ Select Operator [SEL_1786] (rows=1957 width=4)
Output:["_col0"]
Filter Operator [FIL_1785] (rows=1957 width=8)
predicate:(d_date_sk is not null and d_year BETWEEN 1998 AND 2000)
@@ -601,7 +601,7 @@ Stage-0
Select Operator [SEL_368] (rows=1 width=128)
Output:["_col0","_col1","_col2","_col3"]
Merge Join Operator [MERGEJOIN_1438] (rows=1 width=128)
- Conds:RS_365._col1=RS_366._col0(Left Semi),Output:["_col2","_col3","_col8","_col9","_col10"]
+ Conds:RS_365._col1=RS_366._col0(Left Semi),Output:["_col2","_col3","_col6","_col7","_col8"]
<-Reducer 79 [SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_366]
PartitionCols:_col0
@@ -639,9 +639,9 @@ Stage-0
SHUFFLE [RS_302]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_110] (rows=121728 width=19)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6
Merge Join Operator [MERGEJOIN_1401] (rows=14628613 width=11)
- Conds:RS_106._col1=RS_1689._col0(Inner),Output:["_col5","_col6","_col7"]
+ Conds:RS_106._col1=RS_1689._col0(Inner),Output:["_col4","_col5","_col6"]
<-Map 69 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_1689]
PartitionCols:_col0
@@ -690,9 +690,9 @@ Stage-0
SHUFFLE [RS_322]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_130] (rows=121728 width=19)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6
Merge Join Operator [MERGEJOIN_1403] (rows=7620440 width=11)
- Conds:RS_126._col1=RS_1690._col0(Inner),Output:["_col5","_col6","_col7"]
+ Conds:RS_126._col1=RS_1690._col0(Inner),Output:["_col4","_col5","_col6"]
<-Map 69 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_1690]
PartitionCols:_col0
@@ -741,9 +741,9 @@ Stage-0
SHUFFLE [RS_343]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_151] (rows=121728 width=19)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col5, _col6, _col7
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col4, _col5, _col6
Merge Join Operator [MERGEJOIN_1405] (rows=3828623 width=11)
- Conds:RS_147._col1=RS_1691._col0(Inner),Output:["_col5","_col6","_col7"]
+ Conds:RS_147._col1=RS_1691._col0(Inner),Output:["_col4","_col5","_col6"]
<-Map 69 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_1691]
PartitionCols:_col0
@@ -785,7 +785,7 @@ Stage-0
FORWARD [RS_365]
PartitionCols:_col1
Merge Join Operator [MERGEJOIN_1414] (rows=7790806 width=110)
- Conds:RS_360._col1=RS_1692._col0(Inner),Output:["_col1","_col2","_col3","_col8","_col9","_col10"]
+ Conds:RS_360._col1=RS_1692._col0(Inner),Output:["_col1","_col2","_col3","_col6","_col7","_col8"]
<-Map 69 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_1692]
PartitionCols:_col0
@@ -802,7 +802,7 @@ Stage-0
<-Map 57 [SIMPLE_EDGE] vectorized
PARTITION_ONLY_SHUFFLE [RS_1657]
PartitionCols:_col0
- Select Operator [SEL_1654] (rows=50 width=12)
+ Select Operator [SEL_1654] (rows=50 width=4)
Output:["_col0"]
Filter Operator [FIL_1653] (rows=50 width=12)
predicate:((d_moy = 11) and (d_year = 2000) and d_date_sk is not null)
@@ -994,7 +994,7 @@ Stage-0
Select Operator [SEL_560] (rows=1 width=128)
Output:["_col0","_col1","_col2","_col3"]
Merge Join Operator [MERGEJOIN_1439] (rows=1 width=128)
- Conds:RS_557._col1=RS_558._col0(Left Semi),Output:["_col2","_col3","_col8","_col9","_col10"]
+ Conds:RS_557._col1=RS_558._col0(Left Semi),Output:["_col2","_col3","_col6","_col7","_col8"]
<-Reducer 84 [SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_558]
PartitionCols:_col0
@@ -1057,7 +1057,7 @@ Stage-0
FORWARD [RS_557]
PartitionCols:_col1
Merge Join Operator [MERGEJOIN_1429] (rows=3942084 width=130)
- Conds:RS_552._col1=RS_1694._col0(Inner),Output:["_col1","_col2","_col3","_col8","_col9","_col10"]
+ Conds:RS_552._col1=RS_1694._col0(Inner),Output:["_col1","_col2","_col3","_col6","_col7","_col8"]
<-Map 69 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_1694]
PartitionCols:_col0
@@ -1261,7 +1261,7 @@ Stage-0
Select Operator [SEL_177] (rows=1 width=128)
Output:["_col0","_col1","_col2","_col3"]
Merge Join Operator [MERGEJOIN_1437] (rows=1 width=128)
- Conds:RS_174._col1=RS_175._col0(Left Semi),Output:["_col2","_col3","_col8","_col9","_col10"]
+ Conds:RS_174._col1=RS_175._col0(Left Semi),Output:["_col2","_col3","_col6","_col7","_col8"]
<-Reducer 70 [SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_175]
PartitionCols:_col0
@@ -1324,7 +1324,7 @@ Stage-0
FORWARD [RS_174]
PartitionCols:_col1
Merge Join Operator [MERGEJOIN_1399] (rows=15062131 width=15)
- Conds:RS_169._col1=RS_1687._col0(Inner),Output:["_col1","_col2","_col3","_col8","_col9","_col10"]
+ Conds:RS_169._col1=RS_1687._col0(Inner),Output:["_col1","_col2","_col3","_col6","_col7","_col8"]
<-Map 69 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_1687]
PartitionCols:_col0
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/tez/query15.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query15.q.out b/ql/src/test/results/clientpositive/perf/tez/query15.q.out
index 565f101..c3c08a1 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query15.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query15.q.out
@@ -74,21 +74,21 @@ Stage-0
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_25]
PartitionCols:_col0
- Group By Operator [GBY_24] (rows=56210 width=201)
- Output:["_col0","_col1"],aggregations:["sum(_col7)"],keys:_col4
- Top N Key Operator [TNK_44] (rows=20154874 width=279)
- keys:_col4,sort order:+,top n:100
- Select Operator [SEL_23] (rows=20154874 width=279)
- Output:["_col4","_col7"]
- Filter Operator [FIL_22] (rows=20154874 width=279)
- predicate:((_col3) IN ('CA', 'WA', 'GA') or (_col7 > 500) or (substr(_col4, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792'))
- Merge Join Operator [MERGEJOIN_77] (rows=20154874 width=279)
- Conds:RS_19._col0=RS_20._col1(Inner),Output:["_col3","_col4","_col7"]
+ Group By Operator [GBY_24] (rows=43435 width=201)
+ Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col3
+ Top N Key Operator [TNK_44] (rows=20154874 width=205)
+ keys:_col3,sort order:+,top n:100
+ Select Operator [SEL_23] (rows=20154874 width=205)
+ Output:["_col3","_col8"]
+ Filter Operator [FIL_22] (rows=20154874 width=205)
+ predicate:(_col4 or _col5 or _col9)
+ Merge Join Operator [MERGEJOIN_77] (rows=20154874 width=205)
+ Conds:RS_19._col0=RS_20._col1(Inner),Output:["_col3","_col4","_col5","_col8","_col9"]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_19]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_75] (rows=80000000 width=179)
- Conds:RS_80._col1=RS_83._col0(Inner),Output:["_col0","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_75] (rows=80000000 width=101)
+ Conds:RS_80._col1=RS_83._col0(Inner),Output:["_col0","_col3","_col4","_col5"]
<-Map 1 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_80]
PartitionCols:_col1
@@ -101,8 +101,8 @@ Stage-0
<-Map 6 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_83]
PartitionCols:_col0
- Select Operator [SEL_82] (rows=40000000 width=179)
- Output:["_col0","_col1","_col2"]
+ Select Operator [SEL_82] (rows=40000000 width=101)
+ Output:["_col0","_col1","_col2","_col3"]
Filter Operator [FIL_81] (rows=40000000 width=179)
predicate:ca_address_sk is not null
TableScan [TS_3] (rows=40000000 width=179)
@@ -110,12 +110,12 @@ Stage-0
<-Reducer 8 [SIMPLE_EDGE]
SHUFFLE [RS_20]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_76] (rows=20154874 width=107)
- Conds:RS_94._col0=RS_86._col0(Inner),Output:["_col1","_col2"]
+ Merge Join Operator [MERGEJOIN_76] (rows=20154874 width=111)
+ Conds:RS_94._col0=RS_86._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 9 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_86]
PartitionCols:_col0
- Select Operator [SEL_85] (rows=130 width=12)
+ Select Operator [SEL_85] (rows=130 width=4)
Output:["_col0"]
Filter Operator [FIL_84] (rows=130 width=12)
predicate:((d_qoy = 2) and (d_year = 2000) and d_date_sk is not null)
@@ -124,8 +124,8 @@ Stage-0
<-Map 7 [SIMPLE_EDGE] vectorized
SHUFFLE [RS_94]
PartitionCols:_col0
- Select Operator [SEL_93] (rows=285117831 width=119)
- Output:["_col0","_col1","_col2"]
+ Select Operator [SEL_93] (rows=285117831 width=123)
+ Output:["_col0","_col1","_col2","_col3"]
Filter Operator [FIL_92] (rows=285117831 width=119)
predicate:((cs_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(cs_sold_date_sk, DynamicValue(RS_13_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_sold_date_sk is not null)
TableScan [TS_6] (rows=287989836 width=119)