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 2018/10/26 21:12:13 UTC
[63/75] [abbrv] hive git commit: HIVE-20788: Extended SJ reduction
may backtrack columns incorrectly when creating filters (Jesus Camacho
Rodriguez, reviewed by Deepak Jaiswal)
http://git-wip-us.apache.org/repos/asf/hive/blob/3cbc13e9/ql/src/test/results/clientpositive/perf/tez/query24.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query24.q.out b/ql/src/test/results/clientpositive/perf/tez/query24.q.out
index 902358a..43ece85 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query24.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query24.q.out
@@ -1,4 +1,4 @@
-Warning: Shuffle Join MERGEJOIN[290][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 8' is a cross product
+Warning: Shuffle Join MERGEJOIN[301][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 6' is a cross product
PREHOOK: query: explain
with ssales as
(select c_last_name
@@ -23,7 +23,8 @@ where ss_ticket_number = sr_ticket_number
and ss_customer_sk = c_customer_sk
and ss_item_sk = i_item_sk
and ss_store_sk = s_store_sk
- and c_birth_country = upper(ca_country)
+ and c_current_addr_sk = ca_address_sk
+ and c_birth_country <> upper(ca_country)
and s_zip = ca_zip
and s_market_id=7
group by c_last_name
@@ -79,7 +80,8 @@ where ss_ticket_number = sr_ticket_number
and ss_customer_sk = c_customer_sk
and ss_item_sk = i_item_sk
and ss_store_sk = s_store_sk
- and c_birth_country = upper(ca_country)
+ and c_current_addr_sk = ca_address_sk
+ and c_birth_country <> upper(ca_country)
and s_zip = ca_zip
and s_market_id=7
group by c_last_name
@@ -114,234 +116,242 @@ POSTHOOK: Output: hdfs://### HDFS PATH ###
Plan optimized by CBO.
Vertex dependency in root stage
-Map 1 <- Reducer 10 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE)
-Map 24 <- Reducer 20 (BROADCAST_EDGE)
-Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
-Reducer 11 <- Map 9 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE)
-Reducer 12 <- Map 22 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE)
-Reducer 13 <- Map 23 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE)
-Reducer 14 <- Reducer 13 (SIMPLE_EDGE)
-Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE)
-Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE)
-Reducer 18 <- Map 16 (SIMPLE_EDGE), Map 24 (SIMPLE_EDGE)
-Reducer 19 <- Map 21 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE)
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
-Reducer 20 <- Map 16 (CUSTOM_SIMPLE_EDGE)
-Reducer 3 <- Map 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 4 <- Map 21 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
-Reducer 5 <- Map 22 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
-Reducer 6 <- Map 23 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
-Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
-Reducer 8 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
+Map 1 <- Reducer 16 (BROADCAST_EDGE), Reducer 17 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE)
+Map 24 <- Reducer 19 (BROADCAST_EDGE), Reducer 20 (BROADCAST_EDGE)
+Reducer 10 <- Map 23 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
+Reducer 12 <- Reducer 11 (CUSTOM_SIMPLE_EDGE)
+Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE)
+Reducer 15 <- Map 22 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE)
+Reducer 16 <- Reducer 15 (CUSTOM_SIMPLE_EDGE)
+Reducer 17 <- Reducer 15 (CUSTOM_SIMPLE_EDGE)
+Reducer 18 <- Map 24 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE)
+Reducer 19 <- Reducer 15 (CUSTOM_SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
+Reducer 20 <- Reducer 15 (CUSTOM_SIMPLE_EDGE)
+Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Map 23 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
+Reducer 6 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
+Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
+Reducer 9 <- Map 7 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
- Reducer 8
- File Output Operator [FS_91]
- Select Operator [SEL_90] (rows=78393744 width=380)
+ Reducer 6
+ File Output Operator [FS_94]
+ Select Operator [SEL_93] (rows=1313165 width=380)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_89] (rows=78393744 width=492)
+ Filter Operator [FIL_92] (rows=1313165 width=492)
predicate:(_col3 > _col4)
- Merge Join Operator [MERGEJOIN_290] (rows=235181232 width=492)
+ Merge Join Operator [MERGEJOIN_301] (rows=3939496 width=492)
Conds:(Inner),Output:["_col0","_col1","_col2","_col3","_col4"]
- <-Reducer 15 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_345]
- Select Operator [SEL_344] (rows=1 width=112)
+ <-Reducer 12 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_351]
+ Select Operator [SEL_350] (rows=1 width=112)
Output:["_col0"]
- Group By Operator [GBY_343] (rows=1 width=120)
+ Group By Operator [GBY_349] (rows=1 width=120)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","count(VALUE._col1)"]
- <-Reducer 14 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_342]
- Group By Operator [GBY_341] (rows=1 width=120)
+ <-Reducer 11 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_348]
+ Group By Operator [GBY_347] (rows=1 width=120)
Output:["_col0","_col1"],aggregations:["sum(_col10)","count(_col10)"]
- Select Operator [SEL_340] (rows=2121289008973 width=932)
+ Select Operator [SEL_346] (rows=576061174 width=932)
Output:["_col10"]
- Group By Operator [GBY_339] (rows=2121289008973 width=932)
+ Group By Operator [GBY_345] (rows=576061174 width=932)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8, KEY._col9
- <-Reducer 13 [SIMPLE_EDGE]
- SHUFFLE [RS_78]
+ <-Reducer 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_81]
PartitionCols:_col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Group By Operator [GBY_77] (rows=2121289008973 width=932)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col4)"],keys:_col11, _col12, _col6, _col8, _col15, _col16, _col17, _col18, _col19, _col22
- Merge Join Operator [MERGEJOIN_289] (rows=2121289008973 width=932)
- Conds:RS_73._col9, _col13=RS_328._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col8","_col11","_col12","_col15","_col16","_col17","_col18","_col19","_col22"]
+ Group By Operator [GBY_80] (rows=576061174 width=932)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"],aggregations:["sum(_col18)"],keys:_col11, _col12, _col1, _col5, _col7, _col20, _col21, _col22, _col23, _col24
+ Merge Join Operator [MERGEJOIN_300] (rows=589731269 width=928)
+ Conds:RS_76._col14, _col17=RS_332._col0, _col1(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col18","_col20","_col21","_col22","_col23","_col24"]
<-Map 23 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_328]
- PartitionCols:_col1, upper(_col2)
- Select Operator [SEL_326] (rows=40000000 width=272)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_325] (rows=40000000 width=272)
- predicate:(ca_zip is not null and upper(ca_country) is not null)
- TableScan [TS_15] (rows=40000000 width=272)
- default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_state","ca_zip","ca_country"]
- <-Reducer 12 [SIMPLE_EDGE]
- SHUFFLE [RS_73]
- PartitionCols:_col9, _col13
- Merge Join Operator [MERGEJOIN_288] (rows=537799796 width=1023)
- Conds:RS_70._col0, _col3=RS_324._col0, _col1(Inner),Output:["_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"]
- <-Map 22 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_324]
- PartitionCols:_col0, _col1
- Select Operator [SEL_322] (rows=57591150 width=8)
- Output:["_col0","_col1"]
- Filter Operator [FIL_321] (rows=57591150 width=8)
- predicate:(sr_item_sk is not null and sr_ticket_number is not null)
- TableScan [TS_12] (rows=57591150 width=8)
- default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"]
- <-Reducer 11 [SIMPLE_EDGE]
- SHUFFLE [RS_70]
- PartitionCols:_col0, _col3
- Merge Join Operator [MERGEJOIN_287] (rows=385681992 width=1029)
- Conds:RS_67._col0=RS_297._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13","_col15","_col16","_col17","_col18","_col19"]
- <-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_297]
- PartitionCols:_col0
- Select Operator [SEL_294] (rows=462000 width=384)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Filter Operator [FIL_292] (rows=462000 width=384)
- predicate:i_item_sk is not null
- TableScan [TS_3] (rows=462000 width=384)
- default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"]
- <-Reducer 19 [SIMPLE_EDGE]
- SHUFFLE [RS_67]
- PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_286] (rows=385681992 width=648)
- Conds:RS_64._col1=RS_320._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col8","_col9","_col11","_col12","_col13"]
- <-Map 21 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_320]
- PartitionCols:_col0
- Select Operator [SEL_318] (rows=80000000 width=276)
- Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_317] (rows=80000000 width=276)
- predicate:(c_birth_country is not null and c_customer_sk is not null)
- TableScan [TS_9] (rows=80000000 width=276)
- default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_first_name","c_last_name","c_birth_country"]
- <-Reducer 18 [SIMPLE_EDGE]
- SHUFFLE [RS_64]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_285] (rows=385681992 width=379)
- Conds:RS_338._col2=RS_306._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col8","_col9"]
- <-Map 16 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_306]
- PartitionCols:_col0
- Select Operator [SEL_303] (rows=155 width=271)
- Output:["_col0","_col1","_col3","_col4"]
- Filter Operator [FIL_302] (rows=155 width=271)
- predicate:((s_market_id = 7) and s_store_sk is not null and s_zip is not null)
- TableScan [TS_6] (rows=1704 width=270)
- default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"]
- <-Map 24 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_338]
- PartitionCols:_col2
- Select Operator [SEL_337] (rows=525333486 width=122)
- Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_336] (rows=525333486 width=122)
- predicate:((ss_store_sk BETWEEN DynamicValue(RS_62_store_s_store_sk_min) AND DynamicValue(RS_62_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_62_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null)
- TableScan [TS_43] (rows=575995635 width=122)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"]
- <-Reducer 20 [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 16 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_311]
- 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_307] (rows=155 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_303]
- <-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_333]
- Select Operator [SEL_332] (rows=235181232 width=380)
+ SHUFFLE [RS_332]
+ PartitionCols:_col0, _col1
+ Select Operator [SEL_330] (rows=57591150 width=8)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_329] (rows=57591150 width=8)
+ predicate:(sr_item_sk is not null and sr_ticket_number is not null)
+ TableScan [TS_23] (rows=57591150 width=8)
+ default@store_returns,store_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["sr_item_sk","sr_ticket_number"]
+ <-Reducer 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_76]
+ PartitionCols:_col14, _col17
+ Merge Join Operator [MERGEJOIN_299] (rows=576061174 width=936)
+ Conds:RS_73._col14=RS_308._col0(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col14","_col17","_col18","_col20","_col21","_col22","_col23","_col24"]
+ <-Map 7 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_308]
+ PartitionCols:_col0
+ Select Operator [SEL_305] (rows=462000 width=384)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
+ Filter Operator [FIL_303] (rows=462000 width=384)
+ predicate:i_item_sk is not null
+ TableScan [TS_3] (rows=462000 width=384)
+ default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_current_price","i_size","i_color","i_units","i_manager_id"]
+ <-Reducer 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_73]
+ PartitionCols:_col14
+ Merge Join Operator [MERGEJOIN_298] (rows=576061174 width=555)
+ Conds:RS_70._col9, _col4=RS_344._col1, _col2(Inner),Output:["_col1","_col5","_col7","_col11","_col12","_col14","_col17","_col18"]
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_70]
+ PartitionCols:_col9, _col4
+ Filter Operator [FIL_21] (rows=7276996 width=637)
+ predicate:(_col13 <> upper(_col3))
+ Merge Join Operator [MERGEJOIN_293] (rows=7276996 width=637)
+ Conds:RS_18._col0=RS_321._col1(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col9","_col11","_col12","_col13"]
+ <-Map 22 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_321]
+ PartitionCols:_col1
+ Select Operator [SEL_320] (rows=80000000 width=280)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_319] (rows=80000000 width=280)
+ predicate:(c_current_addr_sk is not null and c_customer_sk is not null)
+ TableScan [TS_12] (rows=80000000 width=280)
+ default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk","c_current_addr_sk","c_first_name","c_last_name","c_birth_country"]
+ <-Reducer 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_292] (rows=611379 width=365)
+ Conds:RS_315._col2=RS_318._col4(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col7"]
+ <-Map 13 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_315]
+ PartitionCols:_col2
+ Select Operator [SEL_314] (rows=40000000 width=276)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_313] (rows=40000000 width=276)
+ predicate:(ca_address_sk is not null and ca_zip is not null)
+ TableScan [TS_6] (rows=40000000 width=276)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state","ca_zip","ca_country"]
+ <-Map 21 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_318]
+ PartitionCols:_col4
+ Select Operator [SEL_317] (rows=155 width=271)
+ Output:["_col0","_col1","_col3","_col4"]
+ Filter Operator [FIL_316] (rows=155 width=271)
+ predicate:((s_market_id = 7) and s_store_sk is not null and s_zip is not null)
+ TableScan [TS_9] (rows=1704 width=270)
+ default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_name","s_market_id","s_state","s_zip"]
+ <-Map 24 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_344]
+ PartitionCols:_col1, _col2
+ Select Operator [SEL_343] (rows=525333486 width=122)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_342] (rows=525333486 width=122)
+ predicate:((ss_customer_sk BETWEEN DynamicValue(RS_70_customer_c_customer_sk_min) AND DynamicValue(RS_70_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_70_customer_c_customer_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_70_store_s_store_sk_min) AND DynamicValue(RS_70_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_70_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null)
+ TableScan [TS_54] (rows=575995635 width=122)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"]
+ <-Reducer 19 [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=6636187)"]
+ <-Reducer 15 [CUSTOM_SIMPLE_EDGE]
+ SHUFFLE [RS_250]
+ Group By Operator [GBY_249] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=6636187)"]
+ Select Operator [SEL_248] (rows=7276996 width=8)
+ Output:["_col0"]
+ Please refer to the previous Filter Operator [FIL_21]
+ <-Reducer 20 [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)"]
+ <-Reducer 15 [CUSTOM_SIMPLE_EDGE]
+ 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=7276996 width=8)
+ Output:["_col0"]
+ Please refer to the previous Filter Operator [FIL_21]
+ <-Reducer 5 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_337]
+ Select Operator [SEL_336] (rows=3939496 width=380)
Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_331] (rows=235181232 width=380)
- Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col9)"],keys:_col1, _col2, _col7
- Select Operator [SEL_330] (rows=365777643230 width=843)
- Output:["_col1","_col2","_col7","_col9"]
- Group By Operator [GBY_329] (rows=365777643230 width=843)
+ Group By Operator [GBY_335] (rows=3939496 width=380)
+ Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col9)"],keys:_col4, _col5, _col7
+ Select Operator [SEL_334] (rows=84010488 width=843)
+ Output:["_col4","_col5","_col7","_col9"]
+ Group By Operator [GBY_333] (rows=84010488 width=843)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2, KEY._col3, KEY._col4, KEY._col5, KEY._col6, KEY._col7, KEY._col8
- <-Reducer 6 [SIMPLE_EDGE]
- SHUFFLE [RS_35]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_37]
PartitionCols:_col0, _col1, _col2
- Group By Operator [GBY_34] (rows=365777643230 width=843)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col17, _col18, _col12, _col22, _col6, _col7, _col9, _col10, _col14
- Merge Join Operator [MERGEJOIN_284] (rows=365777643230 width=843)
- Conds:RS_30._col15, _col19=RS_327._col1, upper(_col2)(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col17","_col18","_col22"]
+ Group By Operator [GBY_36] (rows=84010488 width=843)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"],aggregations:["sum(_col4)"],keys:_col13, _col14, _col21, _col6, _col7, _col9, _col10, _col17, _col23
+ Merge Join Operator [MERGEJOIN_295] (rows=138508741 width=824)
+ Conds:RS_32._col0, _col3=RS_331._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col13","_col14","_col17","_col21","_col23"]
<-Map 23 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_327]
- PartitionCols:_col1, upper(_col2)
- Please refer to the previous Select Operator [SEL_326]
- <-Reducer 5 [SIMPLE_EDGE]
- SHUFFLE [RS_30]
- PartitionCols:_col15, _col19
- Merge Join Operator [MERGEJOIN_283] (rows=92733777 width=910)
- Conds:RS_27._col0, _col3=RS_323._col0, _col1(Inner),Output:["_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"]
- <-Map 22 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_323]
- PartitionCols:_col0, _col1
- Please refer to the previous Select Operator [SEL_322]
- <-Reducer 4 [SIMPLE_EDGE]
- SHUFFLE [RS_27]
- PartitionCols:_col0, _col3
- Merge Join Operator [MERGEJOIN_282] (rows=56246341 width=899)
- Conds:RS_24._col1=RS_319._col0(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15","_col17","_col18","_col19"]
- <-Map 21 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_319]
+ SHUFFLE [RS_331]
+ PartitionCols:_col0, _col1
+ Please refer to the previous Select Operator [SEL_330]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_32]
+ PartitionCols:_col0, _col3
+ Merge Join Operator [MERGEJOIN_294] (rows=84010488 width=820)
+ Conds:RS_29._col1, _col2=RS_30._col0, _col9(Inner),Output:["_col0","_col3","_col4","_col6","_col7","_col9","_col10","_col13","_col14","_col17","_col21","_col23"]
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_30]
+ PartitionCols:_col0, _col9
+ Select Operator [SEL_22] (rows=7276996 width=637)
+ Output:["_col0","_col2","_col3","_col6","_col9","_col10","_col12"]
+ Please refer to the previous Filter Operator [FIL_21]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_29]
+ PartitionCols:_col1, _col2
+ Merge Join Operator [MERGEJOIN_291] (rows=76612563 width=382)
+ Conds:RS_328._col0=RS_306._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col10"]
+ <-Map 7 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_306]
+ PartitionCols:_col0
+ Select Operator [SEL_304] (rows=7000 width=385)
+ Output:["_col0","_col1","_col2","_col4","_col5"]
+ Filter Operator [FIL_302] (rows=7000 width=384)
+ predicate:((i_color = 'orchid') and i_item_sk is not null)
+ Please refer to the previous TableScan [TS_3]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_328]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_318]
- <-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_24]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_281] (rows=56246341 width=630)
- Conds:RS_21._col2=RS_304._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col6","_col7","_col9","_col10","_col12","_col14","_col15"]
- <-Map 16 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_304]
- PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_303]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_280] (rows=76612563 width=382)
- Conds:RS_316._col0=RS_295._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col6","_col7","_col9","_col10"]
- <-Map 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_295]
- PartitionCols:_col0
- Select Operator [SEL_293] (rows=7000 width=385)
- Output:["_col0","_col1","_col2","_col4","_col5"]
- Filter Operator [FIL_291] (rows=7000 width=384)
- predicate:((i_color = 'orchid') and i_item_sk is not null)
- Please refer to the previous TableScan [TS_3]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_316]
- PartitionCols:_col0
- Select Operator [SEL_315] (rows=525333486 width=122)
- Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_314] (rows=525333486 width=122)
- predicate:((ss_item_sk BETWEEN DynamicValue(RS_19_item_i_item_sk_min) AND DynamicValue(RS_19_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_19_item_i_item_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_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null)
- TableScan [TS_0] (rows=575995635 width=122)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"]
- <-Reducer 10 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_301]
- Group By Operator [GBY_300] (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_299]
- Group By Operator [GBY_298] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_296] (rows=7000 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_293]
- <-Reducer 17 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_313]
- Group By Operator [GBY_312] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_310]
- 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_305] (rows=155 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_303]
+ Select Operator [SEL_327] (rows=525333486 width=122)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_326] (rows=525333486 width=122)
+ predicate:((ss_customer_sk BETWEEN DynamicValue(RS_30_customer_c_customer_sk_min) AND DynamicValue(RS_30_customer_c_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_30_customer_c_customer_sk_bloom_filter))) and (ss_item_sk BETWEEN DynamicValue(RS_27_item_i_item_sk_min) AND DynamicValue(RS_27_item_i_item_sk_max) and in_bloom_filter(ss_item_sk, DynamicValue(RS_27_item_i_item_sk_bloom_filter))) and (ss_store_sk BETWEEN DynamicValue(RS_30_store_s_store_sk_min) AND DynamicValue(RS_30_store_s_store_sk_max) and in_bloom_filter(ss_store_sk, DynamicValue(RS_30_store_s_store_sk_bloom_filter))) and ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null)
+ TableScan [TS_0] (rows=575995635 width=122)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_item_sk","ss_customer_sk","ss_store_sk","ss_ticket_number","ss_sales_price"]
+ <-Reducer 16 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_323]
+ Group By Operator [GBY_322] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=6636187)"]
+ <-Reducer 15 [CUSTOM_SIMPLE_EDGE]
+ SHUFFLE [RS_152]
+ Group By Operator [GBY_151] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=6636187)"]
+ Select Operator [SEL_150] (rows=7276996 width=4)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_22]
+ <-Reducer 17 [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)"]
+ <-Reducer 15 [CUSTOM_SIMPLE_EDGE]
+ SHUFFLE [RS_157]
+ Group By Operator [GBY_156] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_155] (rows=7276996 width=8)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_22]
+ <-Reducer 8 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_312]
+ Group By Operator [GBY_311] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 7 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_310]
+ 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_307] (rows=7000 width=4)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_304]
http://git-wip-us.apache.org/repos/asf/hive/blob/3cbc13e9/ql/src/test/results/clientpositive/perf/tez/query59.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query59.q.out b/ql/src/test/results/clientpositive/perf/tez/query59.q.out
index 76b4a5e..2ac474a 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query59.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query59.q.out
@@ -110,51 +110,51 @@ Stage-0
limit:100
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_210]
- Limit [LIM_209] (rows=100 width=976)
+ File Output Operator [FS_208]
+ Limit [LIM_207] (rows=100 width=976)
Number of rows:100
- Select Operator [SEL_208] (rows=1012347 width=976)
+ Select Operator [SEL_206] (rows=1012347 width=976)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
<-Reducer 6 [SIMPLE_EDGE]
SHUFFLE [RS_59]
Select Operator [SEL_58] (rows=1012347 width=976)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"]
- Merge Join Operator [MERGEJOIN_185] (rows=1012347 width=1648)
+ Merge Join Operator [MERGEJOIN_183] (rows=1012347 width=1648)
Conds:RS_55._col12, _col0=RS_56._col1, (_col0 - 52)(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13","_col16","_col17","_col18","_col19","_col20","_col21"]
<-Reducer 10 [SIMPLE_EDGE]
SHUFFLE [RS_56]
PartitionCols:_col1, (_col0 - 52)
Select Operator [SEL_48] (rows=28847 width=776)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
- Merge Join Operator [MERGEJOIN_184] (rows=28847 width=776)
- Conds:RS_45._col1=RS_207._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col11"]
+ Merge Join Operator [MERGEJOIN_182] (rows=28847 width=776)
+ Conds:RS_45._col1=RS_205._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col11"]
<-Map 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_207]
+ SHUFFLE [RS_205]
PartitionCols:_col0
- Select Operator [SEL_206] (rows=1704 width=104)
+ Select Operator [SEL_204] (rows=1704 width=104)
Output:["_col0","_col1"]
- Filter Operator [FIL_205] (rows=1704 width=104)
+ Filter Operator [FIL_203] (rows=1704 width=104)
predicate:(s_store_id is not null and s_store_sk is not null)
TableScan [TS_39] (rows=1704 width=104)
default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id"]
<-Reducer 9 [SIMPLE_EDGE]
SHUFFLE [RS_45]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_183] (rows=28847 width=676)
- Conds:RS_204._col0=RS_199._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
+ Merge Join Operator [MERGEJOIN_181] (rows=28847 width=676)
+ Conds:RS_202._col0=RS_197._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
<-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_199]
+ SHUFFLE [RS_197]
PartitionCols:_col1
- Select Operator [SEL_197] (rows=317 width=8)
+ Select Operator [SEL_195] (rows=317 width=8)
Output:["_col1"]
- Filter Operator [FIL_195] (rows=317 width=8)
+ Filter Operator [FIL_193] (rows=317 width=8)
predicate:(d_month_seq BETWEEN 1197 AND 1208 and d_week_seq is not null)
TableScan [TS_15] (rows=73049 width=8)
default@date_dim,d,Tbl:COMPLETE,Col:COMPLETE,Output:["d_month_seq","d_week_seq"]
<-Reducer 8 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_204]
+ SHUFFLE [RS_202]
PartitionCols:_col0
- Group By Operator [GBY_203] (rows=1196832 width=679)
+ Group By Operator [GBY_201] (rows=1196832 width=679)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)"],keys:KEY._col0, KEY._col1
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_33]
@@ -163,57 +163,57 @@ Stage-0
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col2)","sum(_col3)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1
Select Operator [SEL_30] (rows=525329897 width=205)
Output:["_col0","_col1","_col2","_col3","_col5","_col6","_col7","_col8"]
- Merge Join Operator [MERGEJOIN_179] (rows=525329897 width=205)
- Conds:RS_188._col0=RS_191._col0(Inner),Output:["_col1","_col2","_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_177] (rows=525329897 width=205)
+ Conds:RS_186._col0=RS_189._col0(Inner),Output:["_col1","_col2","_col4","_col5"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_188]
+ SHUFFLE [RS_186]
PartitionCols:_col0
- Select Operator [SEL_187] (rows=525329897 width=114)
+ Select Operator [SEL_185] (rows=525329897 width=114)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_186] (rows=525329897 width=114)
+ Filter Operator [FIL_184] (rows=525329897 width=114)
predicate:(ss_sold_date_sk is not null and ss_store_sk is not null)
TableScan [TS_0] (rows=575995635 width=114)
default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_sales_price"]
<-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_191]
+ SHUFFLE [RS_189]
PartitionCols:_col0
- Select Operator [SEL_190] (rows=73049 width=99)
+ Select Operator [SEL_188] (rows=73049 width=99)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_189] (rows=73049 width=99)
+ Filter Operator [FIL_187] (rows=73049 width=99)
predicate:(d_date_sk is not null and d_week_seq is not null)
TableScan [TS_3] (rows=73049 width=99)
default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_week_seq","d_day_name"]
<-Reducer 5 [SIMPLE_EDGE]
SHUFFLE [RS_55]
PartitionCols:_col12, _col0
- Merge Join Operator [MERGEJOIN_181] (rows=28847 width=976)
- Conds:RS_52._col1=RS_202._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13"]
+ Merge Join Operator [MERGEJOIN_179] (rows=28847 width=976)
+ Conds:RS_52._col1=RS_200._col0(Inner),Output:["_col0","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col12","_col13"]
<-Map 13 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_202]
+ SHUFFLE [RS_200]
PartitionCols:_col0
- Select Operator [SEL_201] (rows=1704 width=192)
+ Select Operator [SEL_199] (rows=1704 width=192)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_200] (rows=1704 width=192)
+ Filter Operator [FIL_198] (rows=1704 width=192)
predicate:(s_store_id is not null and s_store_sk is not null)
TableScan [TS_18] (rows=1704 width=192)
default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_store_id","s_store_name"]
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_52]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_180] (rows=28847 width=788)
- Conds:RS_193._col0=RS_198._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"]
+ Merge Join Operator [MERGEJOIN_178] (rows=28847 width=788)
+ Conds:RS_191._col0=RS_196._col1(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"]
<-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_198]
+ SHUFFLE [RS_196]
PartitionCols:_col1
- Select Operator [SEL_196] (rows=317 width=8)
+ Select Operator [SEL_194] (rows=317 width=8)
Output:["_col1"]
- Filter Operator [FIL_194] (rows=317 width=8)
+ Filter Operator [FIL_192] (rows=317 width=8)
predicate:(d_month_seq BETWEEN 1185 AND 1196 and d_week_seq is not null)
Please refer to the previous TableScan [TS_15]
<-Reducer 3 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_193]
+ SHUFFLE [RS_191]
PartitionCols:_col0
- Group By Operator [GBY_192] (rows=1196832 width=791)
+ Group By Operator [GBY_190] (rows=1196832 width=791)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0, KEY._col1
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_12]
@@ -222,5 +222,5 @@ Stage-0
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"],aggregations:["sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"],keys:_col0, _col1
Select Operator [SEL_9] (rows=525329897 width=205)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_179]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_177]
http://git-wip-us.apache.org/repos/asf/hive/blob/3cbc13e9/ql/src/test/results/clientpositive/perf/tez/query95.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query95.q.out b/ql/src/test/results/clientpositive/perf/tez/query95.q.out
index a88c534..49e8e86 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query95.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query95.q.out
@@ -104,123 +104,123 @@ Stage-0
limit:-1
Stage-1
Reducer 9 vectorized
- File Output Operator [FS_296]
- Limit [LIM_295] (rows=1 width=240)
+ File Output Operator [FS_302]
+ Limit [LIM_301] (rows=1 width=240)
Number of rows:100
- Select Operator [SEL_294] (rows=1 width=240)
+ Select Operator [SEL_300] (rows=1 width=240)
Output:["_col0","_col1","_col2"]
<-Reducer 8 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_293]
- Select Operator [SEL_292] (rows=1 width=240)
+ SHUFFLE [RS_299]
+ Select Operator [SEL_298] (rows=1 width=240)
Output:["_col1","_col2","_col3"]
- Group By Operator [GBY_291] (rows=1 width=232)
+ Group By Operator [GBY_297] (rows=1 width=232)
Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)"]
<-Reducer 7 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_290]
- Group By Operator [GBY_289] (rows=1 width=232)
+ PARTITION_ONLY_SHUFFLE [RS_296]
+ Group By Operator [GBY_295] (rows=1 width=232)
Output:["_col0","_col1","_col2"],aggregations:["count(_col0)","sum(_col1)","sum(_col2)"]
- Group By Operator [GBY_288] (rows=2511437 width=228)
+ Group By Operator [GBY_294] (rows=2511437 width=228)
Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"],keys:KEY._col0
<-Reducer 6 [SIMPLE_EDGE]
SHUFFLE [RS_115]
PartitionCols:_col0
Group By Operator [GBY_114] (rows=2511437 width=228)
Output:["_col0","_col2","_col3"],aggregations:["sum(_col4)","sum(_col5)"],keys:_col3
- Merge Join Operator [MERGEJOIN_235] (rows=5022875 width=227)
- Conds:RS_61._col3=RS_287._col0(Inner),Output:["_col3","_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_241] (rows=5022875 width=227)
+ Conds:RS_61._col3=RS_293._col0(Inner),Output:["_col3","_col4","_col5"]
<-Reducer 5 [ONE_TO_ONE_EDGE]
FORWARD [RS_61]
PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_234] (rows=5022875 width=227)
- Conds:RS_58._col3=RS_273._col0(Inner),Output:["_col3","_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_240] (rows=5022875 width=227)
+ Conds:RS_58._col3=RS_279._col0(Inner),Output:["_col3","_col4","_col5"]
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_58]
PartitionCols:_col3
- Merge Join Operator [MERGEJOIN_230] (rows=5022875 width=227)
- Conds:RS_55._col2=RS_254._col0(Inner),Output:["_col3","_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_236] (rows=5022875 width=227)
+ Conds:RS_55._col2=RS_260._col0(Inner),Output:["_col3","_col4","_col5"]
<-Map 16 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_254]
+ SHUFFLE [RS_260]
PartitionCols:_col0
- Select Operator [SEL_253] (rows=12 width=91)
+ Select Operator [SEL_259] (rows=12 width=91)
Output:["_col0"]
- Filter Operator [FIL_252] (rows=12 width=92)
+ Filter Operator [FIL_258] (rows=12 width=92)
predicate:((web_company_name = 'pri') and web_site_sk is not null)
TableScan [TS_9] (rows=84 width=92)
default@web_site,web_site,Tbl:COMPLETE,Col:COMPLETE,Output:["web_site_sk","web_company_name"]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_55]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_229] (rows=15673790 width=231)
- Conds:RS_52._col1=RS_246._col0(Inner),Output:["_col2","_col3","_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_235] (rows=15673790 width=231)
+ Conds:RS_52._col1=RS_252._col0(Inner),Output:["_col2","_col3","_col4","_col5"]
<-Map 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_246]
+ SHUFFLE [RS_252]
PartitionCols:_col0
- Select Operator [SEL_245] (rows=784314 width=90)
+ Select Operator [SEL_251] (rows=784314 width=90)
Output:["_col0"]
- Filter Operator [FIL_244] (rows=784314 width=90)
+ Filter Operator [FIL_250] (rows=784314 width=90)
predicate:((ca_state = 'TX') and ca_address_sk is not null)
TableScan [TS_6] (rows=40000000 width=90)
default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE,Output:["ca_address_sk","ca_state"]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_52]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_228] (rows=15987241 width=235)
- Conds:RS_262._col0=RS_238._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"]
+ Merge Join Operator [MERGEJOIN_234] (rows=15987241 width=235)
+ Conds:RS_268._col0=RS_244._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5"]
<-Map 12 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_238]
+ SHUFFLE [RS_244]
PartitionCols:_col0
- Select Operator [SEL_237] (rows=8116 width=98)
+ Select Operator [SEL_243] (rows=8116 width=98)
Output:["_col0"]
- Filter Operator [FIL_236] (rows=8116 width=98)
+ Filter Operator [FIL_242] (rows=8116 width=98)
predicate:(CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1999-05-01 00:00:00' AND TIMESTAMP'1999-06-30 00:00:00' and d_date_sk is not null)
TableScan [TS_3] (rows=73049 width=98)
default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_262]
+ SHUFFLE [RS_268]
PartitionCols:_col0
- Select Operator [SEL_261] (rows=143895019 width=239)
+ Select Operator [SEL_267] (rows=143895019 width=239)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- Filter Operator [FIL_260] (rows=143895019 width=239)
+ Filter Operator [FIL_266] (rows=143895019 width=239)
predicate:((ws_ship_addr_sk BETWEEN DynamicValue(RS_53_customer_address_ca_address_sk_min) AND DynamicValue(RS_53_customer_address_ca_address_sk_max) and in_bloom_filter(ws_ship_addr_sk, DynamicValue(RS_53_customer_address_ca_address_sk_bloom_filter))) and (ws_ship_date_sk BETWEEN DynamicValue(RS_50_date_dim_d_date_sk_min) AND DynamicValue(RS_50_date_dim_d_date_sk_max) and in_bloom_filter(ws_ship_date_sk, DynamicValue(RS_50_date_dim_d_date_sk_bloom_filter))) and (ws_web_site_sk BETWEEN DynamicValue(RS_56_web_site_web_site_sk_min) AND DynamicValue(RS_56_web_site_web_site_sk_max) and in_bloom_filter(ws_web_site_sk, DynamicValue(RS_56_web_site_web_site_sk_bloom_filter))) and ws_order_number is not null and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null)
TableScan [TS_0] (rows=144002668 width=239)
default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_ship_date_sk","ws_ship_addr_sk","ws_web_site_sk","ws_order_number","ws_ext_ship_cost","ws_net_profit"]
<-Reducer 13 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_243]
- Group By Operator [GBY_242] (rows=1 width=12)
+ BROADCAST [RS_249]
+ Group By Operator [GBY_248] (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_241]
- Group By Operator [GBY_240] (rows=1 width=12)
+ SHUFFLE [RS_247]
+ Group By Operator [GBY_246] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_239] (rows=8116 width=4)
+ Select Operator [SEL_245] (rows=8116 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_237]
+ Please refer to the previous Select Operator [SEL_243]
<-Reducer 15 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_251]
- Group By Operator [GBY_250] (rows=1 width=12)
+ 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 14 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_249]
- Group By Operator [GBY_248] (rows=1 width=12)
+ 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_247] (rows=784314 width=4)
+ Select Operator [SEL_253] (rows=784314 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_245]
+ Please refer to the previous Select Operator [SEL_251]
<-Reducer 17 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_259]
- Group By Operator [GBY_258] (rows=1 width=12)
+ BROADCAST [RS_265]
+ Group By Operator [GBY_264] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 16 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_257]
- Group By Operator [GBY_256] (rows=1 width=12)
+ SHUFFLE [RS_263]
+ Group By Operator [GBY_262] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_255] (rows=12 width=4)
+ Select Operator [SEL_261] (rows=12 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_253]
+ Please refer to the previous Select Operator [SEL_259]
<-Reducer 20 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_273]
+ FORWARD [RS_279]
PartitionCols:_col0
- Group By Operator [GBY_272] (rows=14686712 width=4)
+ Group By Operator [GBY_278] (rows=14686712 width=4)
Output:["_col0"],keys:KEY._col0
<-Reducer 19 [SIMPLE_EDGE]
SHUFFLE [RS_24]
@@ -231,58 +231,58 @@ Stage-0
Output:["_col1"]
Filter Operator [FIL_21] (rows=1411940834 width=11)
predicate:(_col0 <> _col2)
- Merge Join Operator [MERGEJOIN_231] (rows=1411940834 width=11)
- Conds:RS_268._col1=RS_271._col1(Inner),Output:["_col0","_col1","_col2"]
+ Merge Join Operator [MERGEJOIN_237] (rows=1411940834 width=11)
+ Conds:RS_274._col1=RS_277._col1(Inner),Output:["_col0","_col1","_col2"]
<-Map 18 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_268]
+ SHUFFLE [RS_274]
PartitionCols:_col1
- Select Operator [SEL_267] (rows=144002668 width=7)
+ Select Operator [SEL_273] (rows=144002668 width=7)
Output:["_col0","_col1"]
- Filter Operator [FIL_266] (rows=144002668 width=7)
+ Filter Operator [FIL_272] (rows=144002668 width=7)
predicate:((ws_order_number BETWEEN DynamicValue(RS_58_ws1_ws_order_number_min) AND DynamicValue(RS_58_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_58_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null)
TableScan [TS_12] (rows=144002668 width=7)
default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"]
<-Reducer 11 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_264]
- Group By Operator [GBY_263] (rows=1 width=12)
+ BROADCAST [RS_270]
+ Group By Operator [GBY_269] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Reducer 4 [CUSTOM_SIMPLE_EDGE]
- SHUFFLE [RS_183]
- Group By Operator [GBY_182] (rows=1 width=12)
+ SHUFFLE [RS_193]
+ Group By Operator [GBY_192] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_181] (rows=5022875 width=8)
+ Select Operator [SEL_191] (rows=5022875 width=8)
Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_230]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_236]
<-Map 21 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_271]
+ SHUFFLE [RS_277]
PartitionCols:_col1
- Select Operator [SEL_270] (rows=144002668 width=7)
+ Select Operator [SEL_276] (rows=144002668 width=7)
Output:["_col0","_col1"]
- Filter Operator [FIL_269] (rows=144002668 width=7)
+ Filter Operator [FIL_275] (rows=144002668 width=7)
predicate:((ws_order_number BETWEEN DynamicValue(RS_58_ws1_ws_order_number_min) AND DynamicValue(RS_58_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_58_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null)
TableScan [TS_15] (rows=144002668 width=7)
default@web_sales,ws2,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"]
<-Reducer 11 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_265]
- Please refer to the previous Group By Operator [GBY_263]
+ BROADCAST [RS_271]
+ Please refer to the previous Group By Operator [GBY_269]
<-Reducer 25 [ONE_TO_ONE_EDGE] vectorized
- FORWARD [RS_287]
+ FORWARD [RS_293]
PartitionCols:_col0
- Group By Operator [GBY_286] (rows=8007986 width=4)
+ Group By Operator [GBY_292] (rows=8007986 width=4)
Output:["_col0"],keys:KEY._col0
<-Reducer 24 [SIMPLE_EDGE]
SHUFFLE [RS_46]
PartitionCols:_col0
Group By Operator [GBY_45] (rows=14398467 width=4)
Output:["_col0"],keys:_col14
- Merge Join Operator [MERGEJOIN_233] (rows=1384229738 width=4)
- Conds:RS_41._col0=RS_285._col13(Inner),Output:["_col14"]
+ Merge Join Operator [MERGEJOIN_239] (rows=1384229738 width=4)
+ Conds:RS_41._col0=RS_291._col13(Inner),Output:["_col14"]
<-Map 27 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_285]
+ SHUFFLE [RS_291]
PartitionCols:_col13
- Select Operator [SEL_284] (rows=14398467 width=272)
+ Select Operator [SEL_290] (rows=14398467 width=272)
Output:["_col13"]
- Filter Operator [FIL_283] (rows=14398467 width=4)
+ Filter Operator [FIL_289] (rows=14398467 width=4)
predicate:wr_order_number is not null
TableScan [TS_38] (rows=14398467 width=4)
default@web_returns,web_returns,Tbl:COMPLETE,Col:COMPLETE,Output:["wr_order_number"]
@@ -293,38 +293,38 @@ Stage-0
Output:["_col0"]
Filter Operator [FIL_36] (rows=1411940834 width=11)
predicate:(_col0 <> _col2)
- Merge Join Operator [MERGEJOIN_232] (rows=1411940834 width=11)
- Conds:RS_279._col1=RS_282._col1(Inner),Output:["_col0","_col1","_col2"]
+ Merge Join Operator [MERGEJOIN_238] (rows=1411940834 width=11)
+ Conds:RS_285._col1=RS_288._col1(Inner),Output:["_col0","_col1","_col2"]
<-Map 22 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_279]
+ SHUFFLE [RS_285]
PartitionCols:_col1
- Select Operator [SEL_278] (rows=144002668 width=7)
+ Select Operator [SEL_284] (rows=144002668 width=7)
Output:["_col0","_col1"]
- Filter Operator [FIL_277] (rows=144002668 width=7)
+ Filter Operator [FIL_283] (rows=144002668 width=7)
predicate:((ws_order_number BETWEEN DynamicValue(RS_61_ws1_ws_order_number_min) AND DynamicValue(RS_61_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_61_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null)
TableScan [TS_27] (rows=144002668 width=7)
default@web_sales,ws1,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"]
<-Reducer 10 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_275]
- Group By Operator [GBY_274] (rows=1 width=12)
+ BROADCAST [RS_281]
+ Group By Operator [GBY_280] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Reducer 5 [CUSTOM_SIMPLE_EDGE]
- FORWARD [RS_202]
- Group By Operator [GBY_201] (rows=1 width=12)
+ FORWARD [RS_212]
+ Group By Operator [GBY_211] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_200] (rows=5022875 width=8)
+ Select Operator [SEL_210] (rows=5022875 width=8)
Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_234]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_240]
<-Map 26 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_282]
+ SHUFFLE [RS_288]
PartitionCols:_col1
- Select Operator [SEL_281] (rows=144002668 width=7)
+ Select Operator [SEL_287] (rows=144002668 width=7)
Output:["_col0","_col1"]
- Filter Operator [FIL_280] (rows=144002668 width=7)
+ Filter Operator [FIL_286] (rows=144002668 width=7)
predicate:((ws_order_number BETWEEN DynamicValue(RS_61_ws1_ws_order_number_min) AND DynamicValue(RS_61_ws1_ws_order_number_max) and in_bloom_filter(ws_order_number, DynamicValue(RS_61_ws1_ws_order_number_bloom_filter))) and ws_order_number is not null)
TableScan [TS_30] (rows=144002668 width=7)
default@web_sales,ws2,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_warehouse_sk","ws_order_number"]
<-Reducer 10 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_276]
- Please refer to the previous Group By Operator [GBY_274]
+ BROADCAST [RS_282]
+ Please refer to the previous Group By Operator [GBY_280]