You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2018/07/19 20:59:45 UTC
[07/18] 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/query60.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query60.q.out b/ql/src/test/results/clientpositive/perf/tez/query60.q.out
index f10a728..277dd5d 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query60.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query60.q.out
@@ -189,290 +189,296 @@ Stage-0
limit:100
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_370]
- Limit [LIM_369] (rows=100 width=108)
+ File Output Operator [FS_375]
+ Limit [LIM_374] (rows=100 width=108)
Number of rows:100
- Select Operator [SEL_368] (rows=335408073 width=108)
+ Select Operator [SEL_373] (rows=335408073 width=108)
Output:["_col0","_col1"]
<-Reducer 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_367]
- Group By Operator [GBY_366] (rows=335408073 width=108)
+ SHUFFLE [RS_372]
+ Group By Operator [GBY_371] (rows=335408073 width=108)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
<-Union 5 [SIMPLE_EDGE]
<-Reducer 10 [CONTAINS] vectorized
- Reduce Output Operator [RS_382]
+ Reduce Output Operator [RS_388]
PartitionCols:_col0
- Group By Operator [GBY_381] (rows=670816147 width=108)
+ Group By Operator [GBY_387] (rows=670816147 width=108)
Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
- Group By Operator [GBY_380] (rows=191657247 width=135)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 9 [SIMPLE_EDGE]
- SHUFFLE [RS_71]
- PartitionCols:_col0
- Group By Operator [GBY_70] (rows=383314495 width=135)
- Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1
- Merge Join Operator [MERGEJOIN_303] (rows=383314495 width=135)
- Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_66]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_293] (rows=508200 width=1436)
- Conds:RS_319._col1=RS_325._col0(Inner),Output:["_col0","_col1"]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_319]
- PartitionCols:_col1
- Select Operator [SEL_318] (rows=462000 width=1436)
- Output:["_col0","_col1"]
- Filter Operator [FIL_317] (rows=462000 width=1436)
- predicate:(i_item_id is not null and i_item_sk is not null)
- TableScan [TS_0] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
- <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_325]
- PartitionCols:_col0
- Group By Operator [GBY_324] (rows=115500 width=1436)
- Output:["_col0"],keys:KEY._col0
- <-Map 15 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_323]
- PartitionCols:_col0
- Group By Operator [GBY_322] (rows=231000 width=1436)
- Output:["_col0"],keys:i_item_id
- Select Operator [SEL_321] (rows=231000 width=1436)
- Output:["i_item_id"]
- Filter Operator [FIL_320] (rows=231000 width=1436)
- predicate:((i_category = 'Children') and i_item_id is not null)
- TableScan [TS_3] (rows=462000 width=1436)
- default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_id","i_category"]
- <-Reducer 23 [SIMPLE_EDGE]
- SHUFFLE [RS_67]
- PartitionCols:_col4
- Select Operator [SEL_62] (rows=348467716 width=135)
- Output:["_col4","_col5"]
- Merge Join Operator [MERGEJOIN_298] (rows=348467716 width=135)
- Conds:RS_59._col1=RS_346._col0(Inner),Output:["_col2","_col3"]
- <-Map 28 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_346]
- PartitionCols:_col0
- Select Operator [SEL_343] (rows=20000000 width=1014)
- Output:["_col0"]
- Filter Operator [FIL_342] (rows=20000000 width=1014)
- predicate:((ca_gmt_offset = -6) and ca_address_sk is not null)
- TableScan [TS_16] (rows=40000000 width=1014)
- default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_gmt_offset"]
- <-Reducer 22 [SIMPLE_EDGE]
- SHUFFLE [RS_59]
+ Top N Key Operator [TNK_386] (rows=670816147 width=108)
+ keys:_col0,sort order:+,top n:100
+ Group By Operator [GBY_385] (rows=191657247 width=135)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_71]
+ PartitionCols:_col0
+ Group By Operator [GBY_70] (rows=383314495 width=135)
+ Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1
+ Merge Join Operator [MERGEJOIN_304] (rows=383314495 width=135)
+ Conds:RS_66._col0=RS_67._col4(Inner),Output:["_col1","_col8"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_66]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_294] (rows=508200 width=1436)
+ Conds:RS_323._col1=RS_329._col0(Inner),Output:["_col0","_col1"]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_323]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_297] (rows=316788826 width=135)
- Conds:RS_379._col0=RS_330._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 20 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_330]
- PartitionCols:_col0
- Select Operator [SEL_327] (rows=18262 width=1119)
- Output:["_col0"]
- Filter Operator [FIL_326] (rows=18262 width=1119)
- predicate:((d_moy = 9) and (d_year = 1999) and d_date_sk is not null)
- TableScan [TS_13] (rows=73049 width=1119)
- default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
- <-Map 32 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_379]
+ Select Operator [SEL_322] (rows=462000 width=1436)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_321] (rows=462000 width=1436)
+ predicate:(i_item_id is not null and i_item_sk is not null)
+ TableScan [TS_0] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_id"]
+ <-Reducer 16 [ONE_TO_ONE_EDGE] vectorized
+ FORWARD [RS_329]
+ PartitionCols:_col0
+ Group By Operator [GBY_328] (rows=115500 width=1436)
+ Output:["_col0"],keys:KEY._col0
+ <-Map 15 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_327]
PartitionCols:_col0
- Select Operator [SEL_378] (rows=287989836 width=135)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_377] (rows=287989836 width=135)
- predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_60_customer_address_ca_address_sk_min) AND DynamicValue(RS_60_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_60_customer_address_ca_address_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_66_item_i_item_sk_min) AND DynamicValue(RS_66_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_66_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_57_date_dim_d_date_sk_min) AND DynamicValue(RS_57_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_57_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null)
- TableScan [TS_47] (rows=287989836 width=135)
- default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"]
- <-Reducer 11 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_376]
- Group By Operator [GBY_375] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Reducer 2 [CUSTOM_SIMPLE_EDGE]
- SHUFFLE [RS_240]
- Group By Operator [GBY_239] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_238] (rows=508200 width=1436)
- Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_293]
- <-Reducer 24 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_372]
- Group By Operator [GBY_371] (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
- PARTITION_ONLY_SHUFFLE [RS_338]
- Group By Operator [GBY_335] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_331] (rows=18262 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_327]
- <-Reducer 30 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_374]
- Group By Operator [GBY_373] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"]
- <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_354]
- Group By Operator [GBY_351] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"]
- Select Operator [SEL_347] (rows=20000000 width=1014)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_343]
+ Group By Operator [GBY_326] (rows=231000 width=1436)
+ Output:["_col0"],keys:i_item_id
+ Select Operator [SEL_325] (rows=231000 width=1436)
+ Output:["i_item_id"]
+ Filter Operator [FIL_324] (rows=231000 width=1436)
+ predicate:((i_category = 'Children') and i_item_id is not null)
+ TableScan [TS_3] (rows=462000 width=1436)
+ default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_id","i_category"]
+ <-Reducer 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_67]
+ PartitionCols:_col4
+ Select Operator [SEL_62] (rows=348467716 width=135)
+ Output:["_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_299] (rows=348467716 width=135)
+ Conds:RS_59._col1=RS_350._col0(Inner),Output:["_col2","_col3"]
+ <-Map 28 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_350]
+ PartitionCols:_col0
+ Select Operator [SEL_347] (rows=20000000 width=1014)
+ Output:["_col0"]
+ Filter Operator [FIL_346] (rows=20000000 width=1014)
+ predicate:((ca_gmt_offset = -6) and ca_address_sk is not null)
+ TableScan [TS_16] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_gmt_offset"]
+ <-Reducer 22 [SIMPLE_EDGE]
+ SHUFFLE [RS_59]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_298] (rows=316788826 width=135)
+ Conds:RS_384._col0=RS_334._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 20 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_334]
+ PartitionCols:_col0
+ Select Operator [SEL_331] (rows=18262 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_330] (rows=18262 width=1119)
+ predicate:((d_moy = 9) and (d_year = 1999) and d_date_sk is not null)
+ TableScan [TS_13] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
+ <-Map 32 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_384]
+ PartitionCols:_col0
+ Select Operator [SEL_383] (rows=287989836 width=135)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_382] (rows=287989836 width=135)
+ predicate:((cs_bill_addr_sk BETWEEN DynamicValue(RS_60_customer_address_ca_address_sk_min) AND DynamicValue(RS_60_customer_address_ca_address_sk_max) and in_bloom_filter(cs_bill_addr_sk, DynamicValue(RS_60_customer_address_ca_address_sk_bloom_filter))) and (cs_item_sk BETWEEN DynamicValue(RS_66_item_i_item_sk_min) AND DynamicValue(RS_66_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_66_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_57_date_dim_d_date_sk_min) AND DynamicValue(RS_57_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_57_date_dim_d_date_sk_bloom_filter))) and cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null)
+ TableScan [TS_47] (rows=287989836 width=135)
+ default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_addr_sk","cs_item_sk","cs_ext_sales_price"]
+ <-Reducer 11 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_381]
+ Group By Operator [GBY_380] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Reducer 2 [CUSTOM_SIMPLE_EDGE]
+ SHUFFLE [RS_241]
+ Group By Operator [GBY_240] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_239] (rows=508200 width=1436)
+ Output:["_col0"]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_294]
+ <-Reducer 24 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_377]
+ Group By Operator [GBY_376] (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
+ PARTITION_ONLY_SHUFFLE [RS_342]
+ Group By Operator [GBY_339] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_335] (rows=18262 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_331]
+ <-Reducer 30 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_379]
+ Group By Operator [GBY_378] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"]
+ <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_358]
+ Group By Operator [GBY_355] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"]
+ Select Operator [SEL_351] (rows=20000000 width=1014)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_347]
<-Reducer 13 [CONTAINS] vectorized
- Reduce Output Operator [RS_394]
+ Reduce Output Operator [RS_401]
PartitionCols:_col0
- Group By Operator [GBY_393] (rows=670816147 width=108)
+ Group By Operator [GBY_400] (rows=670816147 width=108)
Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
- Group By Operator [GBY_392] (rows=95833781 width=135)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 12 [SIMPLE_EDGE]
- SHUFFLE [RS_109]
- PartitionCols:_col0
- Group By Operator [GBY_108] (rows=191667562 width=135)
- Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1
- Merge Join Operator [MERGEJOIN_304] (rows=191667562 width=135)
- Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_104]
- PartitionCols:_col0
- Please refer to the previous Merge Join Operator [MERGEJOIN_293]
- <-Reducer 26 [SIMPLE_EDGE]
- SHUFFLE [RS_105]
- PartitionCols:_col3
- Select Operator [SEL_100] (rows=174243235 width=135)
- Output:["_col3","_col5"]
- Merge Join Operator [MERGEJOIN_301] (rows=174243235 width=135)
- Conds:RS_97._col2=RS_348._col0(Inner),Output:["_col1","_col3"]
- <-Map 28 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_348]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_343]
- <-Reducer 25 [SIMPLE_EDGE]
- SHUFFLE [RS_97]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_300] (rows=158402938 width=135)
- Conds:RS_391._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 20 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_332]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_327]
- <-Map 33 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_391]
- PartitionCols:_col0
- Select Operator [SEL_390] (rows=144002668 width=135)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_389] (rows=144002668 width=135)
- predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_98_customer_address_ca_address_sk_min) AND DynamicValue(RS_98_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_98_customer_address_ca_address_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_104_item_i_item_sk_min) AND DynamicValue(RS_104_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_104_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_95_date_dim_d_date_sk_min) AND DynamicValue(RS_95_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_95_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null)
- TableScan [TS_85] (rows=144002668 width=135)
- default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"]
- <-Reducer 14 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_388]
- Group By Operator [GBY_387] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Reducer 2 [CUSTOM_SIMPLE_EDGE]
- SHUFFLE [RS_280]
- Group By Operator [GBY_279] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_278] (rows=508200 width=1436)
- Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_293]
- <-Reducer 27 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_384]
- Group By Operator [GBY_383] (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
- PARTITION_ONLY_SHUFFLE [RS_339]
- Group By Operator [GBY_336] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_333] (rows=18262 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_327]
- <-Reducer 31 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_386]
- Group By Operator [GBY_385] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"]
- <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_355]
- Group By Operator [GBY_352] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"]
- Select Operator [SEL_349] (rows=20000000 width=1014)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_343]
+ Top N Key Operator [TNK_399] (rows=670816147 width=108)
+ keys:_col0,sort order:+,top n:100
+ Group By Operator [GBY_398] (rows=95833781 width=135)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_109]
+ PartitionCols:_col0
+ Group By Operator [GBY_108] (rows=191667562 width=135)
+ Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1
+ Merge Join Operator [MERGEJOIN_305] (rows=191667562 width=135)
+ Conds:RS_104._col0=RS_105._col3(Inner),Output:["_col1","_col8"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_104]
+ PartitionCols:_col0
+ Please refer to the previous Merge Join Operator [MERGEJOIN_294]
+ <-Reducer 26 [SIMPLE_EDGE]
+ SHUFFLE [RS_105]
+ PartitionCols:_col3
+ Select Operator [SEL_100] (rows=174243235 width=135)
+ Output:["_col3","_col5"]
+ Merge Join Operator [MERGEJOIN_302] (rows=174243235 width=135)
+ Conds:RS_97._col2=RS_352._col0(Inner),Output:["_col1","_col3"]
+ <-Map 28 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_352]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_347]
+ <-Reducer 25 [SIMPLE_EDGE]
+ SHUFFLE [RS_97]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_301] (rows=158402938 width=135)
+ Conds:RS_397._col0=RS_336._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 20 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_336]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_331]
+ <-Map 33 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_397]
+ PartitionCols:_col0
+ Select Operator [SEL_396] (rows=144002668 width=135)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_395] (rows=144002668 width=135)
+ predicate:((ws_bill_addr_sk BETWEEN DynamicValue(RS_98_customer_address_ca_address_sk_min) AND DynamicValue(RS_98_customer_address_ca_address_sk_max) and in_bloom_filter(ws_bill_addr_sk, DynamicValue(RS_98_customer_address_ca_address_sk_bloom_filter))) and (ws_item_sk BETWEEN DynamicValue(RS_104_item_i_item_sk_min) AND DynamicValue(RS_104_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_104_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_95_date_dim_d_date_sk_min) AND DynamicValue(RS_95_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_95_date_dim_d_date_sk_bloom_filter))) and ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null)
+ TableScan [TS_85] (rows=144002668 width=135)
+ default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_addr_sk","ws_ext_sales_price"]
+ <-Reducer 14 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_394]
+ Group By Operator [GBY_393] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Reducer 2 [CUSTOM_SIMPLE_EDGE]
+ SHUFFLE [RS_281]
+ Group By Operator [GBY_280] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_279] (rows=508200 width=1436)
+ Output:["_col0"]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_294]
+ <-Reducer 27 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_390]
+ Group By Operator [GBY_389] (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
+ PARTITION_ONLY_SHUFFLE [RS_343]
+ Group By Operator [GBY_340] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_337] (rows=18262 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_331]
+ <-Reducer 31 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_392]
+ Group By Operator [GBY_391] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"]
+ <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_359]
+ Group By Operator [GBY_356] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"]
+ Select Operator [SEL_353] (rows=20000000 width=1014)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_347]
<-Reducer 4 [CONTAINS] vectorized
- Reduce Output Operator [RS_365]
+ Reduce Output Operator [RS_370]
PartitionCols:_col0
- Group By Operator [GBY_364] (rows=670816147 width=108)
+ Group By Operator [GBY_369] (rows=670816147 width=108)
Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
- Group By Operator [GBY_363] (rows=383325119 width=88)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_34]
- PartitionCols:_col0
- Group By Operator [GBY_33] (rows=766650239 width=88)
- Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1
- Merge Join Operator [MERGEJOIN_302] (rows=766650239 width=88)
- Conds:RS_29._col0=RS_30._col3(Inner),Output:["_col1","_col8"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_29]
- PartitionCols:_col0
- Please refer to the previous Merge Join Operator [MERGEJOIN_293]
- <-Reducer 19 [SIMPLE_EDGE]
- SHUFFLE [RS_30]
- PartitionCols:_col3
- Select Operator [SEL_25] (rows=696954748 width=88)
- Output:["_col3","_col5"]
- Merge Join Operator [MERGEJOIN_295] (rows=696954748 width=88)
- Conds:RS_22._col2=RS_344._col0(Inner),Output:["_col1","_col3"]
- <-Map 28 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_344]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_343]
- <-Reducer 18 [SIMPLE_EDGE]
- SHUFFLE [RS_22]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_294] (rows=633595212 width=88)
- Conds:RS_362._col0=RS_328._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 20 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_328]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_327]
- <-Map 17 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_362]
- PartitionCols:_col0
- Select Operator [SEL_361] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_360] (rows=575995635 width=88)
- predicate:((ss_addr_sk BETWEEN DynamicValue(RS_23_customer_address_ca_address_sk_min) AND DynamicValue(RS_23_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_23_customer_address_ca_address_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_29_item_i_item_sk_min) AND DynamicValue(RS_29_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_29_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null)
- TableScan [TS_10] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"]
- <-Reducer 21 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_341]
- Group By Operator [GBY_340] (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
- PARTITION_ONLY_SHUFFLE [RS_337]
- Group By Operator [GBY_334] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_329] (rows=18262 width=1119)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_327]
- <-Reducer 29 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_357]
- Group By Operator [GBY_356] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"]
- <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_353]
- Group By Operator [GBY_350] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"]
- Select Operator [SEL_345] (rows=20000000 width=1014)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_343]
- <-Reducer 8 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_359]
- Group By Operator [GBY_358] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Reducer 2 [CUSTOM_SIMPLE_EDGE]
- SHUFFLE [RS_200]
- Group By Operator [GBY_199] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_198] (rows=508200 width=1436)
- Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_293]
+ Top N Key Operator [TNK_368] (rows=670816147 width=108)
+ keys:_col0,sort order:+,top n:100
+ Group By Operator [GBY_367] (rows=383325119 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_34]
+ PartitionCols:_col0
+ Group By Operator [GBY_33] (rows=766650239 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(_col8)"],keys:_col1
+ Merge Join Operator [MERGEJOIN_303] (rows=766650239 width=88)
+ Conds:RS_29._col0=RS_30._col3(Inner),Output:["_col1","_col8"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_29]
+ PartitionCols:_col0
+ Please refer to the previous Merge Join Operator [MERGEJOIN_294]
+ <-Reducer 19 [SIMPLE_EDGE]
+ SHUFFLE [RS_30]
+ PartitionCols:_col3
+ Select Operator [SEL_25] (rows=696954748 width=88)
+ Output:["_col3","_col5"]
+ Merge Join Operator [MERGEJOIN_296] (rows=696954748 width=88)
+ Conds:RS_22._col2=RS_348._col0(Inner),Output:["_col1","_col3"]
+ <-Map 28 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_348]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_347]
+ <-Reducer 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_22]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_295] (rows=633595212 width=88)
+ Conds:RS_366._col0=RS_332._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 20 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_332]
+ PartitionCols:_col0
+ Please refer to the previous Select Operator [SEL_331]
+ <-Map 17 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_366]
+ PartitionCols:_col0
+ Select Operator [SEL_365] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_364] (rows=575995635 width=88)
+ predicate:((ss_addr_sk BETWEEN DynamicValue(RS_23_customer_address_ca_address_sk_min) AND DynamicValue(RS_23_customer_address_ca_address_sk_max) and in_bloom_filter(ss_addr_sk, DynamicValue(RS_23_customer_address_ca_address_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_29_item_i_item_sk_min) AND DynamicValue(RS_29_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_29_item_i_item_sk_bloom_filter))) and (ss_sold_date_sk BETWEEN DynamicValue(RS_20_date_dim_d_date_sk_min) AND DynamicValue(RS_20_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_20_date_dim_d_date_sk_bloom_filter))) and ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_10] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk","ss_addr_sk","ss_ext_sales_price"]
+ <-Reducer 21 [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 20 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_341]
+ Group By Operator [GBY_338] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_333] (rows=18262 width=1119)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_331]
+ <-Reducer 29 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_361]
+ Group By Operator [GBY_360] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=20000000)"]
+ <-Map 28 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_357]
+ Group By Operator [GBY_354] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=20000000)"]
+ Select Operator [SEL_349] (rows=20000000 width=1014)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_347]
+ <-Reducer 8 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_363]
+ Group By Operator [GBY_362] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Reducer 2 [CUSTOM_SIMPLE_EDGE]
+ SHUFFLE [RS_201]
+ Group By Operator [GBY_200] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_199] (rows=508200 width=1436)
+ Output:["_col0"]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_294]