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 2018/07/19 21:44:50 UTC
[12/54] [abbrv] hive git commit: HIVE-17896: TopNKey: Create a
standalone vectorizable TopNKey operator (Teddy Choi,
reviewed by Jesus Camacho Rodriguez)
http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/perf/tez/query25.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query25.q.out b/ql/src/test/results/clientpositive/perf/tez/query25.q.out
index 77a9a07..b68c54a 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query25.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query25.q.out
@@ -118,195 +118,197 @@ Stage-0
limit:100
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_269]
- Limit [LIM_268] (rows=100 width=88)
+ File Output Operator [FS_270]
+ Limit [LIM_269] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_267] (rows=421657640 width=88)
+ Select Operator [SEL_268] (rows=421657640 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
<-Reducer 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_266]
- Group By Operator [GBY_265] (rows=421657640 width=88)
+ SHUFFLE [RS_267]
+ Group By Operator [GBY_266] (rows=421657640 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_49]
PartitionCols:_col0, _col1, _col2, _col3
Group By Operator [GBY_48] (rows=843315281 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"],aggregations:["sum(_col5)","sum(_col20)","sum(_col12)"],keys:_col25, _col26, _col28, _col29
- Merge Join Operator [MERGEJOIN_213] (rows=843315281 width=88)
- Conds:RS_44._col3=RS_251._col0(Inner),Output:["_col5","_col12","_col20","_col25","_col26","_col28","_col29"]
- <-Map 20 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_251]
- PartitionCols:_col0
- Select Operator [SEL_250] (rows=1704 width=1910)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_249] (rows=1704 width=1910)
- predicate:s_store_sk is not null
- TableScan [TS_32] (rows=1704 width=1910)
- default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_44]
- PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_212] (rows=766650239 width=88)
- Conds:RS_41._col1=RS_242._col0(Inner),Output:["_col3","_col5","_col12","_col20","_col25","_col26"]
- <-Map 18 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_242]
- PartitionCols:_col0
- Select Operator [SEL_241] (rows=462000 width=1436)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_240] (rows=462000 width=1436)
- predicate:i_item_sk is not null
- TableScan [TS_29] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_41]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_211] (rows=696954748 width=88)
- Conds:RS_38._col1, _col2, _col4=RS_39._col8, _col9, _col10(Inner),Output:["_col1","_col3","_col5","_col12","_col20"]
- <-Reducer 11 [SIMPLE_EDGE]
- SHUFFLE [RS_39]
- PartitionCols:_col8, _col9, _col10
- Merge Join Operator [MERGEJOIN_210] (rows=348467716 width=135)
- Conds:RS_25._col2, _col1=RS_26._col1, _col2(Inner),Output:["_col3","_col8","_col9","_col10","_col11"]
- <-Reducer 13 [SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_26]
- PartitionCols:_col1, _col2
- Merge Join Operator [MERGEJOIN_209] (rows=63350266 width=77)
- Conds:RS_233._col0=RS_224._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
- <-Map 8 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_224]
- PartitionCols:_col0
- Select Operator [SEL_219] (rows=4058 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_216] (rows=4058 width=1119)
- predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10)
- TableScan [TS_3] (rows=73049 width=1119)
- default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
- <-Map 17 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_233]
- PartitionCols:_col0
- Select Operator [SEL_232] (rows=57591150 width=77)
- Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_231] (rows=57591150 width=77)
- predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null)
- TableScan [TS_12] (rows=57591150 width=77)
- default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_net_loss"]
- <-Reducer 10 [SIMPLE_EDGE]
- SHUFFLE [RS_25]
- PartitionCols:_col2, _col1
- Merge Join Operator [MERGEJOIN_208] (rows=316788826 width=135)
- Conds:RS_264._col0=RS_222._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 8 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_222]
- PartitionCols:_col0
- Select Operator [SEL_218] (rows=4058 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_215] (rows=4058 width=1119)
- predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10)
- Please refer to the previous TableScan [TS_3]
- <-Map 16 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_264]
- PartitionCols:_col0
- Select Operator [SEL_263] (rows=287989836 width=135)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_262] (rows=287989836 width=135)
- predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_42_item_i_item_sk_min) AND DynamicValue(RS_42_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_42_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_23_d3_d_date_sk_min) AND DynamicValue(RS_23_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_23_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null)
- TableScan [TS_6] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_net_profit"]
- <-Reducer 14 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_236]
- Group By Operator [GBY_234] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"]
- <-Reducer 13 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_107]
- Group By Operator [GBY_106] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"]
- Select Operator [SEL_105] (rows=63350266 width=77)
- Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_209]
- <-Reducer 15 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_239]
- Group By Operator [GBY_237] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"]
- <-Reducer 13 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_122]
- Group By Operator [GBY_121] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"]
- Select Operator [SEL_120] (rows=63350266 width=77)
- Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_209]
- <-Reducer 19 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_248]
- Group By Operator [GBY_246] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_245]
- Group By Operator [GBY_244] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_243] (rows=462000 width=1436)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_241]
- <-Reducer 12 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_261]
- Group By Operator [GBY_260] (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_228]
- Group By Operator [GBY_226] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_223] (rows=4058 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_218]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_38]
- PartitionCols:_col1, _col2, _col4
- Merge Join Operator [MERGEJOIN_207] (rows=633595212 width=88)
- Conds:RS_259._col0=RS_220._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"]
- <-Map 8 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_220]
- PartitionCols:_col0
- Select Operator [SEL_217] (rows=18262 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_214] (rows=18262 width=1119)
- predicate:((d_moy = 4) and (d_year = 2000) and d_date_sk is not null)
- Please refer to the previous TableScan [TS_3]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_259]
- PartitionCols:_col0
- Select Operator [SEL_258] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Filter Operator [FIL_257] (rows=575995635 width=88)
- predicate:((ss_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_42_item_i_item_sk_min) AND DynamicValue(RS_42_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_42_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_36_d1_d_date_sk_min) AND DynamicValue(RS_36_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_36_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_45_store_s_store_sk_min) AND DynamicValue(RS_45_store_s_store_sk_max) and
in_bloom_filter(ss_store_sk, DynamicValue(RS_45_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number 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_customer_sk","ss_store_sk","ss_ticket_number","ss_net_profit"]
- <-Reducer 14 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_235]
- Please refer to the previous Group By Operator [GBY_234]
- <-Reducer 15 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_238]
- Please refer to the previous Group By Operator [GBY_237]
- <-Reducer 19 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_247]
- Please refer to the previous Group By Operator [GBY_246]
- <-Reducer 21 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_256]
- Group By Operator [GBY_255] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_254]
- Group By Operator [GBY_253] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_252] (rows=1704 width=1910)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_250]
- <-Reducer 9 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_230]
- Group By Operator [GBY_229] (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_227]
- Group By Operator [GBY_225] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_221] (rows=18262 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_217]
+ Top N Key Operator [TNK_95] (rows=843315281 width=88)
+ keys:_col25, _col26, _col28, _col29,sort order:++++,top n:100
+ Merge Join Operator [MERGEJOIN_214] (rows=843315281 width=88)
+ Conds:RS_44._col3=RS_252._col0(Inner),Output:["_col5","_col12","_col20","_col25","_col26","_col28","_col29"]
+ <-Map 20 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_252]
+ PartitionCols:_col0
+ Select Operator [SEL_251] (rows=1704 width=1910)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_250] (rows=1704 width=1910)
+ predicate:s_store_sk is not null
+ TableScan [TS_32] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_store_id","s_store_name"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_44]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_213] (rows=766650239 width=88)
+ Conds:RS_41._col1=RS_243._col0(Inner),Output:["_col3","_col5","_col12","_col20","_col25","_col26"]
+ <-Map 18 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_243]
+ PartitionCols:_col0
+ Select Operator [SEL_242] (rows=462000 width=1436)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_241] (rows=462000 width=1436)
+ predicate:i_item_sk is not null
+ TableScan [TS_29] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id","i_item_desc"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_41]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_212] (rows=696954748 width=88)
+ Conds:RS_38._col1, _col2, _col4=RS_39._col8, _col9, _col10(Inner),Output:["_col1","_col3","_col5","_col12","_col20"]
+ <-Reducer 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_39]
+ PartitionCols:_col8, _col9, _col10
+ Merge Join Operator [MERGEJOIN_211] (rows=348467716 width=135)
+ Conds:RS_25._col2, _col1=RS_26._col1, _col2(Inner),Output:["_col3","_col8","_col9","_col10","_col11"]
+ <-Reducer 13 [SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_26]
+ PartitionCols:_col1, _col2
+ Merge Join Operator [MERGEJOIN_210] (rows=63350266 width=77)
+ Conds:RS_234._col0=RS_225._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ <-Map 8 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_225]
+ PartitionCols:_col0
+ Select Operator [SEL_220] (rows=4058 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_217] (rows=4058 width=1119)
+ predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10)
+ TableScan [TS_3] (rows=73049 width=1119)
+ default@date_dim,d1,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
+ <-Map 17 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_234]
+ PartitionCols:_col0
+ Select Operator [SEL_233] (rows=57591150 width=77)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_232] (rows=57591150 width=77)
+ predicate:(sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null)
+ TableScan [TS_12] (rows=57591150 width=77)
+ default@store_returns,store_returns,Tbl:COMPLETE,Col:NONE,Output:["sr_returned_date_sk","sr_item_sk","sr_customer_sk","sr_ticket_number","sr_net_loss"]
+ <-Reducer 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_25]
+ PartitionCols:_col2, _col1
+ Merge Join Operator [MERGEJOIN_209] (rows=316788826 width=135)
+ Conds:RS_265._col0=RS_223._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 8 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_223]
+ PartitionCols:_col0
+ Select Operator [SEL_219] (rows=4058 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_216] (rows=4058 width=1119)
+ predicate:((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10)
+ Please refer to the previous TableScan [TS_3]
+ <-Map 16 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_265]
+ PartitionCols:_col0
+ Select Operator [SEL_264] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_263] (rows=287989836 width=135)
+ predicate:((cs_bill_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(cs_bill_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_42_item_i_item_sk_min) AND DynamicValue(RS_42_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_42_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_23_d3_d_date_sk_min) AND DynamicValue(RS_23_d3_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_23_d3_d_date_sk_bloom_filter))) and cs_bill_customer_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null)
+ TableScan [TS_6] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_net_profit"]
+ <-Reducer 14 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_237]
+ Group By Operator [GBY_235] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"]
+ <-Reducer 13 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_108]
+ Group By Operator [GBY_107] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"]
+ Select Operator [SEL_106] (rows=63350266 width=77)
+ Output:["_col0"]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_210]
+ <-Reducer 15 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_240]
+ Group By Operator [GBY_238] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=63350264)"]
+ <-Reducer 13 [CUSTOM_SIMPLE_EDGE]
+ PARTITION_ONLY_SHUFFLE [RS_123]
+ Group By Operator [GBY_122] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=63350264)"]
+ Select Operator [SEL_121] (rows=63350266 width=77)
+ Output:["_col0"]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_210]
+ <-Reducer 19 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_249]
+ Group By Operator [GBY_247] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 18 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_246]
+ Group By Operator [GBY_245] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_244] (rows=462000 width=1436)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_242]
+ <-Reducer 12 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_262]
+ Group By Operator [GBY_261] (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_229]
+ Group By Operator [GBY_227] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_224] (rows=4058 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_219]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_38]
+ PartitionCols:_col1, _col2, _col4
+ Merge Join Operator [MERGEJOIN_208] (rows=633595212 width=88)
+ Conds:RS_260._col0=RS_221._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"]
+ <-Map 8 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_221]
+ PartitionCols:_col0
+ Select Operator [SEL_218] (rows=18262 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_215] (rows=18262 width=1119)
+ predicate:((d_moy = 4) and (d_year = 2000) and d_date_sk is not null)
+ Please refer to the previous TableScan [TS_3]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_260]
+ PartitionCols:_col0
+ Select Operator [SEL_259] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ Filter Operator [FIL_258] (rows=575995635 width=88)
+ predicate:((ss_customer_sk BETWEEN DynamicValue(RS_26_store_returns_sr_customer_sk_min) AND DynamicValue(RS_26_store_returns_sr_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_26_store_returns_sr_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_26_store_returns_sr_item_sk_min) AND DynamicValue(RS_26_store_returns_sr_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_26_store_returns_sr_item_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_42_item_i_item_sk_min) AND DynamicValue(RS_42_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_42_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_36_d1_d_date_sk_min) AND DynamicValue(RS_36_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_36_d1_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_45_store_s_store_sk_min) AND DynamicValue(RS_45_store_s_store_sk_max) a
nd in_bloom_filter(ss_store_sk, DynamicValue(RS_45_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number 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_customer_sk","ss_store_sk","ss_ticket_number","ss_net_profit"]
+ <-Reducer 14 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_236]
+ Please refer to the previous Group By Operator [GBY_235]
+ <-Reducer 15 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_239]
+ Please refer to the previous Group By Operator [GBY_238]
+ <-Reducer 19 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_248]
+ Please refer to the previous Group By Operator [GBY_247]
+ <-Reducer 21 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_257]
+ Group By Operator [GBY_256] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 20 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_255]
+ Group By Operator [GBY_254] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_253] (rows=1704 width=1910)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_251]
+ <-Reducer 9 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_231]
+ Group By Operator [GBY_230] (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_228]
+ Group By Operator [GBY_226] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_222] (rows=18262 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_218]
http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/perf/tez/query26.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query26.q.out b/ql/src/test/results/clientpositive/perf/tez/query26.q.out
index 0c6c0f8..a90e09f 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query26.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query26.q.out
@@ -58,126 +58,128 @@ Stage-0
limit:100
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_139]
- Limit [LIM_138] (rows=100 width=135)
+ File Output Operator [FS_140]
+ Limit [LIM_139] (rows=100 width=135)
Number of rows:100
- Select Operator [SEL_137] (rows=210822976 width=135)
+ Select Operator [SEL_138] (rows=210822976 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
<-Reducer 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_136]
- Select Operator [SEL_135] (rows=210822976 width=135)
+ SHUFFLE [RS_137]
+ Select Operator [SEL_136] (rows=210822976 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Group By Operator [GBY_134] (rows=210822976 width=135)
+ Group By Operator [GBY_135] (rows=210822976 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)"],keys:KEY._col0
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_29]
PartitionCols:_col0
Group By Operator [GBY_28] (rows=421645953 width=135)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col4)","count(_col4)","sum(_col5)","count(_col5)","sum(_col7)","count(_col7)","sum(_col6)","count(_col6)"],keys:_col18
- Merge Join Operator [MERGEJOIN_98] (rows=421645953 width=135)
- Conds:RS_24._col2=RS_125._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"]
- <-Map 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_125]
- PartitionCols:_col0
- Select Operator [SEL_124] (rows=462000 width=1436)
- Output:["_col0","_col1"]
- Filter Operator [FIL_123] (rows=462000 width=1436)
- predicate:i_item_sk is not null
- TableScan [TS_12] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_24]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_97] (rows=383314495 width=135)
- Conds:RS_21._col3=RS_117._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"]
- <-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_117]
- PartitionCols:_col0
- Select Operator [SEL_116] (rows=2300 width=1179)
- Output:["_col0"]
- Filter Operator [FIL_115] (rows=2300 width=1179)
- predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null)
- TableScan [TS_9] (rows=2300 width=1179)
- default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_email","p_channel_event"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_96] (rows=348467716 width=135)
- Conds:RS_18._col0=RS_109._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7"]
- <-Map 10 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_109]
- PartitionCols:_col0
- Select Operator [SEL_108] (rows=36524 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_107] (rows=36524 width=1119)
- predicate:((d_year = 1998) 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_year"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_18]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_95] (rows=316788826 width=135)
- Conds:RS_133._col1=RS_101._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7"]
- <-Map 8 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_101]
- PartitionCols:_col0
- Select Operator [SEL_100] (rows=232725 width=385)
- Output:["_col0"]
- Filter Operator [FIL_99] (rows=232725 width=385)
- predicate:((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null)
- TableScan [TS_3] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_133]
- PartitionCols:_col1
- Select Operator [SEL_132] (rows=287989836 width=135)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Filter Operator [FIL_131] (rows=287989836 width=135)
- predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (cs_promo_sk BETWEEN DynamicValue(RS_22_promotion_p_promo_sk_min) AND DynamicValue(RS_22_promotion_p_promo_sk_max) and in_bloom_filter(cs_promo_sk, DynamicValue(RS_22_promotion_p_promo_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_item_sk is not null and cs_promo_sk is not null
and cs_sold_date_sk is not null)
- TableScan [TS_0] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_cdemo_sk","cs_item_sk","cs_promo_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt"]
- <-Reducer 11 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_114]
- Group By Operator [GBY_113] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_112]
- Group By Operator [GBY_111] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_110] (rows=36524 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_108]
- <-Reducer 13 [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 12 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_120]
- Group By Operator [GBY_119] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_118] (rows=2300 width=1179)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_116]
- <-Reducer 15 [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 14 [CUSTOM_SIMPLE_EDGE] vectorized
- 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=462000 width=1436)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_124]
- <-Reducer 9 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_106]
- Group By Operator [GBY_105] (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_104]
- Group By Operator [GBY_103] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_102] (rows=232725 width=385)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_100]
+ Top N Key Operator [TNK_55] (rows=421645953 width=135)
+ keys:_col18,sort order:+,top n:100
+ Merge Join Operator [MERGEJOIN_99] (rows=421645953 width=135)
+ Conds:RS_24._col2=RS_126._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col18"]
+ <-Map 14 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_126]
+ PartitionCols:_col0
+ Select Operator [SEL_125] (rows=462000 width=1436)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_124] (rows=462000 width=1436)
+ predicate:i_item_sk is not null
+ TableScan [TS_12] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_98] (rows=383314495 width=135)
+ Conds:RS_21._col3=RS_118._col0(Inner),Output:["_col2","_col4","_col5","_col6","_col7"]
+ <-Map 12 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_118]
+ PartitionCols:_col0
+ Select Operator [SEL_117] (rows=2300 width=1179)
+ Output:["_col0"]
+ Filter Operator [FIL_116] (rows=2300 width=1179)
+ predicate:(((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null)
+ TableScan [TS_9] (rows=2300 width=1179)
+ default@promotion,promotion,Tbl:COMPLETE,Col:NONE,Output:["p_promo_sk","p_channel_email","p_channel_event"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_21]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_97] (rows=348467716 width=135)
+ Conds:RS_18._col0=RS_110._col0(Inner),Output:["_col2","_col3","_col4","_col5","_col6","_col7"]
+ <-Map 10 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_110]
+ PartitionCols:_col0
+ Select Operator [SEL_109] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_108] (rows=36524 width=1119)
+ predicate:((d_year = 1998) 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_year"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_96] (rows=316788826 width=135)
+ Conds:RS_134._col1=RS_102._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7"]
+ <-Map 8 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_102]
+ PartitionCols:_col0
+ Select Operator [SEL_101] (rows=232725 width=385)
+ Output:["_col0"]
+ Filter Operator [FIL_100] (rows=232725 width=385)
+ predicate:((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null)
+ TableScan [TS_3] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_134]
+ PartitionCols:_col1
+ Select Operator [SEL_133] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
+ Filter Operator [FIL_132] (rows=287989836 width=135)
+ predicate:((cs_bill_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(cs_bill_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_25_item_i_item_sk_min) AND DynamicValue(RS_25_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_25_item_i_item_sk_bloom_filter))) and (cs_promo_sk BETWEEN DynamicValue(RS_22_promotion_p_promo_sk_min) AND DynamicValue(RS_22_promotion_p_promo_sk_max) and in_bloom_filter(cs_promo_sk, DynamicValue(RS_22_promotion_p_promo_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and cs_bill_cdemo_sk is not null and cs_item_sk is not null and cs_promo_sk is not nul
l and cs_sold_date_sk is not null)
+ TableScan [TS_0] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_cdemo_sk","cs_item_sk","cs_promo_sk","cs_quantity","cs_list_price","cs_sales_price","cs_coupon_amt"]
+ <-Reducer 11 [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 10 [CUSTOM_SIMPLE_EDGE] vectorized
+ 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_111] (rows=36524 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_109]
+ <-Reducer 13 [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 12 [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=2300 width=1179)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_117]
+ <-Reducer 15 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_131]
+ Group By Operator [GBY_130] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_129]
+ Group By Operator [GBY_128] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_127] (rows=462000 width=1436)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_125]
+ <-Reducer 9 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_107]
+ Group By Operator [GBY_106] (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_105]
+ Group By Operator [GBY_104] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_103] (rows=232725 width=385)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_101]
http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/perf/tez/query27.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query27.q.out b/ql/src/test/results/clientpositive/perf/tez/query27.q.out
index df1e15f..7ea13c8 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query27.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query27.q.out
@@ -62,128 +62,130 @@ Stage-0
limit:100
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_140]
- Limit [LIM_139] (rows=100 width=88)
+ File Output Operator [FS_141]
+ Limit [LIM_140] (rows=100 width=88)
Number of rows:100
- Select Operator [SEL_138] (rows=1264972921 width=88)
+ Select Operator [SEL_139] (rows=1264972921 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
<-Reducer 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_137]
- Select Operator [SEL_136] (rows=1264972921 width=88)
+ SHUFFLE [RS_138]
+ Select Operator [SEL_137] (rows=1264972921 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
- Group By Operator [GBY_135] (rows=1264972921 width=88)
+ Group By Operator [GBY_136] (rows=1264972921 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)","sum(VALUE._col2)","count(VALUE._col3)","sum(VALUE._col4)","count(VALUE._col5)","sum(VALUE._col6)","count(VALUE._col7)"],keys:KEY._col0, KEY._col1, KEY._col2
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_30]
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_29] (rows=2529945843 width=88)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col2)","count(_col2)","sum(_col3)","count(_col3)","sum(_col4)","count(_col4)","sum(_col5)","count(_col5)"],keys:_col0, _col1, 0L
- Select Operator [SEL_27] (rows=843315281 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Merge Join Operator [MERGEJOIN_99] (rows=843315281 width=88)
- Conds:RS_24._col1=RS_126._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col15","_col17"]
- <-Map 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_126]
- PartitionCols:_col0
- Select Operator [SEL_125] (rows=462000 width=1436)
- Output:["_col0","_col1"]
- Filter Operator [FIL_124] (rows=462000 width=1436)
- predicate:i_item_sk is not null
- TableScan [TS_12] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_24]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_98] (rows=766650239 width=88)
- Conds:RS_21._col3=RS_118._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col15"]
- <-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_118]
- PartitionCols:_col0
- Select Operator [SEL_117] (rows=852 width=1910)
- Output:["_col0","_col1"]
- Filter Operator [FIL_116] (rows=852 width=1910)
- predicate:((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') and s_store_sk is not null)
- TableScan [TS_9] (rows=1704 width=1910)
- default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_97] (rows=696954748 width=88)
- Conds:RS_18._col0=RS_110._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"]
- <-Map 10 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_110]
- PartitionCols:_col0
- Select Operator [SEL_109] (rows=36524 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_108] (rows=36524 width=1119)
- predicate:((d_year = 2001) 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_year"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_18]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_96] (rows=633595212 width=88)
- Conds:RS_134._col2=RS_102._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"]
- <-Map 8 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_102]
- PartitionCols:_col0
- Select Operator [SEL_101] (rows=232725 width=385)
- Output:["_col0"]
- Filter Operator [FIL_100] (rows=232725 width=385)
- predicate:((cd_education_status = '2 yr Degree') and (cd_gender = 'M') and (cd_marital_status = 'U') and cd_demo_sk is not null)
- TableScan [TS_3] (rows=1861800 width=385)
- default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_134]
- PartitionCols:_col2
- Select Operator [SEL_133] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Filter Operator [FIL_132] (rows=575995635 width=88)
- predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (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_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_cdemo_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is no
t 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_cdemo_sk","ss_store_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"]
- <-Reducer 11 [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 10 [CUSTOM_SIMPLE_EDGE] vectorized
- 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_111] (rows=36524 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_109]
- <-Reducer 13 [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 12 [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=852 width=1910)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_117]
- <-Reducer 15 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_131]
- Group By Operator [GBY_130] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 14 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_129]
- Group By Operator [GBY_128] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_127] (rows=462000 width=1436)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_125]
- <-Reducer 9 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_107]
- Group By Operator [GBY_106] (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_105]
- Group By Operator [GBY_104] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_103] (rows=232725 width=385)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_101]
+ Top N Key Operator [TNK_56] (rows=843315281 width=88)
+ keys:_col0, _col1, 0L,sort order:+++,top n:100
+ Select Operator [SEL_27] (rows=843315281 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_100] (rows=843315281 width=88)
+ Conds:RS_24._col1=RS_127._col0(Inner),Output:["_col4","_col5","_col6","_col7","_col15","_col17"]
+ <-Map 14 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_127]
+ PartitionCols:_col0
+ Select Operator [SEL_126] (rows=462000 width=1436)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_125] (rows=462000 width=1436)
+ predicate:i_item_sk is not null
+ TableScan [TS_12] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_99] (rows=766650239 width=88)
+ Conds:RS_21._col3=RS_119._col0(Inner),Output:["_col1","_col4","_col5","_col6","_col7","_col15"]
+ <-Map 12 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_119]
+ PartitionCols:_col0
+ Select Operator [SEL_118] (rows=852 width=1910)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_117] (rows=852 width=1910)
+ predicate:((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') and s_store_sk is not null)
+ TableScan [TS_9] (rows=1704 width=1910)
+ default@store,store,Tbl:COMPLETE,Col:NONE,Output:["s_store_sk","s_state"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_21]
+ PartitionCols:_col3
+ Merge Join Operator [MERGEJOIN_98] (rows=696954748 width=88)
+ Conds:RS_18._col0=RS_111._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7"]
+ <-Map 10 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_111]
+ PartitionCols:_col0
+ Select Operator [SEL_110] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_109] (rows=36524 width=1119)
+ predicate:((d_year = 2001) 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_year"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_97] (rows=633595212 width=88)
+ Conds:RS_135._col2=RS_103._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7"]
+ <-Map 8 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_103]
+ PartitionCols:_col0
+ Select Operator [SEL_102] (rows=232725 width=385)
+ Output:["_col0"]
+ Filter Operator [FIL_101] (rows=232725 width=385)
+ predicate:((cd_education_status = '2 yr Degree') and (cd_gender = 'M') and (cd_marital_status = 'U') and cd_demo_sk is not null)
+ TableScan [TS_3] (rows=1861800 width=385)
+ default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_135]
+ PartitionCols:_col2
+ Select Operator [SEL_134] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
+ Filter Operator [FIL_133] (rows=575995635 width=88)
+ predicate:((ss_cdemo_sk BETWEEN DynamicValue(RS_16_customer_demographics_cd_demo_sk_min) AND DynamicValue(RS_16_customer_demographics_cd_demo_sk_max) and in_bloom_filter(ss_cdemo_sk, DynamicValue(RS_16_customer_demographics_cd_demo_sk_bloom_filter))) and (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_sold_date_sk BETWEEN DynamicValue(RS_19_date_dim_d_date_sk_min) AND DynamicValue(RS_19_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_19_date_dim_d_date_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_22_store_s_store_sk_min) AND DynamicValue(RS_22_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_22_store_s_store_sk_bloom_filter))) and ss_cdemo_sk is not null and ss_item_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_cdemo_sk","ss_store_sk","ss_quantity","ss_list_price","ss_sales_price","ss_coupon_amt"]
+ <-Reducer 11 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_116]
+ Group By Operator [GBY_115] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 10 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_114]
+ 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_112] (rows=36524 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_110]
+ <-Reducer 13 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_124]
+ Group By Operator [GBY_123] (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_122]
+ Group By Operator [GBY_121] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_120] (rows=852 width=1910)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_118]
+ <-Reducer 15 [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 14 [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=462000 width=1436)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_126]
+ <-Reducer 9 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_108]
+ Group By Operator [GBY_107] (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_106]
+ Group By Operator [GBY_105] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_104] (rows=232725 width=385)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_102]