You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2017/01/21 03:51:47 UTC
[05/10] hive git commit: HIVE-15544 : Support scalar subqueries
(Vineet Garg via Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/d9343f6d/ql/src/test/results/clientpositive/perf/query23.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query23.q.out b/ql/src/test/results/clientpositive/perf/query23.q.out
index 6d4cfca..1df94d1 100644
--- a/ql/src/test/results/clientpositive/perf/query23.q.out
+++ b/ql/src/test/results/clientpositive/perf/query23.q.out
@@ -1,3 +1,7 @@
+Warning: Shuffle Join MERGEJOIN[379][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 19' is a cross product
+Warning: Shuffle Join MERGEJOIN[380][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 20' is a cross product
+Warning: Shuffle Join MERGEJOIN[382][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 51' is a cross product
+Warning: Shuffle Join MERGEJOIN[383][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 52' is a cross product
PREHOOK: query: explain with frequent_ss_items as
(select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date solddate,count(*) cnt
from store_sales
@@ -24,25 +28,28 @@ PREHOOK: query: explain with frequent_ss_items as
,customer
where ss_customer_sk = c_customer_sk
group by c_customer_sk
- having sum(ss_quantity*ss_sales_price) > (95/100.0))
+ having sum(ss_quantity*ss_sales_price) > (95/100.0) * (select
+ *
+from
+ max_store_sales))
select sum(sales)
- from (select cs_quantity*cs_list_price sales
+ from ((select cs_quantity*cs_list_price sales
from catalog_sales
,date_dim
where d_year = 1999
and d_moy = 1
and cs_sold_date_sk = d_date_sk
and cs_item_sk in (select item_sk from frequent_ss_items)
- and cs_bill_customer_sk in (select c_customer_sk from best_ss_customer)
+ and cs_bill_customer_sk in (select c_customer_sk from best_ss_customer))
union all
- select ws_quantity*ws_list_price sales
+ (select ws_quantity*ws_list_price sales
from web_sales
,date_dim
where d_year = 1999
and d_moy = 1
and ws_sold_date_sk = d_date_sk
and ws_item_sk in (select item_sk from frequent_ss_items)
- and ws_bill_customer_sk in (select c_customer_sk from best_ss_customer)) y
+ and ws_bill_customer_sk in (select c_customer_sk from best_ss_customer))) y
limit 100
PREHOOK: type: QUERY
POSTHOOK: query: explain with frequent_ss_items as
@@ -71,25 +78,28 @@ POSTHOOK: query: explain with frequent_ss_items as
,customer
where ss_customer_sk = c_customer_sk
group by c_customer_sk
- having sum(ss_quantity*ss_sales_price) > (95/100.0))
+ having sum(ss_quantity*ss_sales_price) > (95/100.0) * (select
+ *
+from
+ max_store_sales))
select sum(sales)
- from (select cs_quantity*cs_list_price sales
+ from ((select cs_quantity*cs_list_price sales
from catalog_sales
,date_dim
where d_year = 1999
and d_moy = 1
and cs_sold_date_sk = d_date_sk
and cs_item_sk in (select item_sk from frequent_ss_items)
- and cs_bill_customer_sk in (select c_customer_sk from best_ss_customer)
+ and cs_bill_customer_sk in (select c_customer_sk from best_ss_customer))
union all
- select ws_quantity*ws_list_price sales
+ (select ws_quantity*ws_list_price sales
from web_sales
,date_dim
where d_year = 1999
and d_moy = 1
and ws_sold_date_sk = d_date_sk
and ws_item_sk in (select item_sk from frequent_ss_items)
- and ws_bill_customer_sk in (select c_customer_sk from best_ss_customer)) y
+ and ws_bill_customer_sk in (select c_customer_sk from best_ss_customer))) y
limit 100
POSTHOOK: type: QUERY
Plan optimized by CBO.
@@ -97,20 +107,42 @@ Plan optimized by CBO.
Vertex dependency in root stage
Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
-Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE)
-Reducer 16 <- Reducer 15 (SIMPLE_EDGE)
-Reducer 19 <- Map 18 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE)
+Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 22 (SIMPLE_EDGE)
+Reducer 16 <- Map 23 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE)
+Reducer 17 <- Reducer 16 (SIMPLE_EDGE)
+Reducer 18 <- Reducer 17 (SIMPLE_EDGE)
+Reducer 19 <- Reducer 18 (SIMPLE_EDGE), Reducer 28 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
-Reducer 20 <- Reducer 19 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE)
-Reducer 21 <- Reducer 20 (SIMPLE_EDGE), Reducer 31 (SIMPLE_EDGE), Union 5 (CONTAINS)
-Reducer 24 <- Map 23 (SIMPLE_EDGE), Map 27 (SIMPLE_EDGE)
-Reducer 25 <- Map 28 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE)
-Reducer 26 <- Reducer 25 (SIMPLE_EDGE)
+Reducer 20 <- Reducer 19 (SIMPLE_EDGE), Reducer 33 (SIMPLE_EDGE)
+Reducer 21 <- Reducer 20 (SIMPLE_EDGE)
+Reducer 25 <- Map 24 (SIMPLE_EDGE), Map 29 (SIMPLE_EDGE)
+Reducer 26 <- Map 30 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE)
+Reducer 27 <- Reducer 26 (SIMPLE_EDGE)
+Reducer 28 <- Reducer 27 (SIMPLE_EDGE)
Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 30 <- Map 29 (SIMPLE_EDGE), Map 32 (SIMPLE_EDGE)
-Reducer 31 <- Reducer 30 (SIMPLE_EDGE)
-Reducer 4 <- Reducer 16 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS)
+Reducer 32 <- Map 31 (SIMPLE_EDGE), Map 34 (SIMPLE_EDGE)
+Reducer 33 <- Reducer 32 (SIMPLE_EDGE)
+Reducer 36 <- Map 35 (SIMPLE_EDGE), Map 39 (SIMPLE_EDGE)
+Reducer 37 <- Reducer 36 (SIMPLE_EDGE), Reducer 43 (SIMPLE_EDGE)
+Reducer 38 <- Reducer 37 (SIMPLE_EDGE), Reducer 53 (SIMPLE_EDGE), Union 5 (CONTAINS)
+Reducer 4 <- Reducer 21 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS)
+Reducer 41 <- Map 40 (SIMPLE_EDGE), Map 44 (SIMPLE_EDGE)
+Reducer 42 <- Map 45 (SIMPLE_EDGE), Reducer 41 (SIMPLE_EDGE)
+Reducer 43 <- Reducer 42 (SIMPLE_EDGE)
+Reducer 47 <- Map 46 (SIMPLE_EDGE), Map 54 (SIMPLE_EDGE)
+Reducer 48 <- Map 55 (SIMPLE_EDGE), Reducer 47 (SIMPLE_EDGE)
+Reducer 49 <- Reducer 48 (SIMPLE_EDGE)
+Reducer 50 <- Reducer 49 (SIMPLE_EDGE)
+Reducer 51 <- Reducer 50 (SIMPLE_EDGE), Reducer 60 (SIMPLE_EDGE)
+Reducer 52 <- Reducer 51 (SIMPLE_EDGE), Reducer 65 (SIMPLE_EDGE)
+Reducer 53 <- Reducer 52 (SIMPLE_EDGE)
+Reducer 57 <- Map 56 (SIMPLE_EDGE), Map 61 (SIMPLE_EDGE)
+Reducer 58 <- Map 62 (SIMPLE_EDGE), Reducer 57 (SIMPLE_EDGE)
+Reducer 59 <- Reducer 58 (SIMPLE_EDGE)
Reducer 6 <- Union 5 (SIMPLE_EDGE)
+Reducer 60 <- Reducer 59 (SIMPLE_EDGE)
+Reducer 64 <- Map 63 (SIMPLE_EDGE), Map 66 (SIMPLE_EDGE)
+Reducer 65 <- Reducer 64 (SIMPLE_EDGE)
Reducer 9 <- Map 12 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE)
Stage-0
@@ -118,193 +150,435 @@ Stage-0
limit:100
Stage-1
Reducer 6
- File Output Operator [FS_136]
- Limit [LIM_135] (rows=1 width=112)
+ File Output Operator [FS_258]
+ Limit [LIM_257] (rows=1 width=112)
Number of rows:100
- Group By Operator [GBY_133] (rows=1 width=112)
+ Group By Operator [GBY_255] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(VALUE._col0)"]
<-Union 5 [SIMPLE_EDGE]
- <-Reducer 21 [CONTAINS]
- Reduce Output Operator [RS_132]
- Group By Operator [GBY_131] (rows=1 width=112)
+ <-Reducer 38 [CONTAINS]
+ Reduce Output Operator [RS_254]
+ Group By Operator [GBY_253] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(_col0)"]
- Select Operator [SEL_127] (rows=191667562 width=135)
+ Select Operator [SEL_249] (rows=191667562 width=135)
Output:["_col0"]
- Merge Join Operator [MERGEJOIN_206] (rows=191667562 width=135)
- Conds:RS_124._col2=RS_125._col0(Inner),Output:["_col3","_col4"]
- <-Reducer 20 [SIMPLE_EDGE]
- SHUFFLE [RS_124]
+ Merge Join Operator [MERGEJOIN_384] (rows=191667562 width=135)
+ Conds:RS_246._col2=RS_247._col0(Inner),Output:["_col3","_col4"]
+ <-Reducer 37 [SIMPLE_EDGE]
+ SHUFFLE [RS_246]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_204] (rows=174243235 width=135)
- Conds:RS_121._col1=RS_122._col0(Inner),Output:["_col2","_col3","_col4"]
- <-Reducer 19 [SIMPLE_EDGE]
- SHUFFLE [RS_121]
+ Merge Join Operator [MERGEJOIN_378] (rows=174243235 width=135)
+ Conds:RS_243._col1=RS_244._col0(Inner),Output:["_col2","_col3","_col4"]
+ <-Reducer 36 [SIMPLE_EDGE]
+ SHUFFLE [RS_243]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_199] (rows=158402938 width=135)
- Conds:RS_118._col0=RS_119._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
- <-Map 18 [SIMPLE_EDGE]
- SHUFFLE [RS_118]
+ Merge Join Operator [MERGEJOIN_369] (rows=158402938 width=135)
+ Conds:RS_240._col0=RS_241._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ <-Map 35 [SIMPLE_EDGE]
+ SHUFFLE [RS_240]
PartitionCols:_col0
- Select Operator [SEL_66] (rows=144002668 width=135)
+ Select Operator [SEL_127] (rows=144002668 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_186] (rows=144002668 width=135)
+ Filter Operator [FIL_346] (rows=144002668 width=135)
predicate:ws_sold_date_sk is not null
- TableScan [TS_64] (rows=144002668 width=135)
+ TableScan [TS_125] (rows=144002668 width=135)
default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_quantity","ws_list_price"]
- <-Map 22 [SIMPLE_EDGE]
- SHUFFLE [RS_119]
+ <-Map 39 [SIMPLE_EDGE]
+ SHUFFLE [RS_241]
PartitionCols:_col0
- Select Operator [SEL_69] (rows=18262 width=1119)
+ Select Operator [SEL_130] (rows=18262 width=1119)
Output:["_col0"]
- Filter Operator [FIL_187] (rows=18262 width=1119)
+ Filter Operator [FIL_347] (rows=18262 width=1119)
predicate:((d_year = 1999) and (d_moy = 1) and d_date_sk is not null)
- TableScan [TS_67] (rows=73049 width=1119)
+ TableScan [TS_128] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
- <-Reducer 26 [SIMPLE_EDGE]
- SHUFFLE [RS_122]
+ <-Reducer 43 [SIMPLE_EDGE]
+ SHUFFLE [RS_244]
PartitionCols:_col0
- Group By Operator [GBY_95] (rows=58079562 width=88)
+ Group By Operator [GBY_156] (rows=58079562 width=88)
Output:["_col0"],keys:_col1
- Select Operator [SEL_91] (rows=116159124 width=88)
+ Select Operator [SEL_152] (rows=116159124 width=88)
Output:["_col1"]
- Filter Operator [FIL_90] (rows=116159124 width=88)
+ Filter Operator [FIL_151] (rows=116159124 width=88)
predicate:(_col3 > 4)
- Select Operator [SEL_193] (rows=348477374 width=88)
+ Select Operator [SEL_360] (rows=348477374 width=88)
Output:["_col0","_col3"]
- Group By Operator [GBY_89] (rows=348477374 width=88)
+ Group By Operator [GBY_150] (rows=348477374 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
- <-Reducer 25 [SIMPLE_EDGE]
- SHUFFLE [RS_88]
+ <-Reducer 42 [SIMPLE_EDGE]
+ SHUFFLE [RS_149]
PartitionCols:_col0
- Group By Operator [GBY_87] (rows=696954748 width=88)
+ Group By Operator [GBY_148] (rows=696954748 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2
- Select Operator [SEL_85] (rows=696954748 width=88)
+ Select Operator [SEL_146] (rows=696954748 width=88)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_201] (rows=696954748 width=88)
- Conds:RS_82._col1=RS_83._col0(Inner),Output:["_col3","_col5","_col6"]
- <-Map 28 [SIMPLE_EDGE]
- SHUFFLE [RS_83]
+ Merge Join Operator [MERGEJOIN_371] (rows=696954748 width=88)
+ Conds:RS_143._col1=RS_144._col0(Inner),Output:["_col3","_col5","_col6"]
+ <-Map 45 [SIMPLE_EDGE]
+ SHUFFLE [RS_144]
PartitionCols:_col0
- Select Operator [SEL_78] (rows=462000 width=1436)
+ Select Operator [SEL_139] (rows=462000 width=1436)
Output:["_col0","_col1"]
- Filter Operator [FIL_190] (rows=462000 width=1436)
+ Filter Operator [FIL_350] (rows=462000 width=1436)
predicate:i_item_sk is not null
- TableScan [TS_76] (rows=462000 width=1436)
+ TableScan [TS_137] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_item_desc"]
- <-Reducer 24 [SIMPLE_EDGE]
- SHUFFLE [RS_82]
+ <-Reducer 41 [SIMPLE_EDGE]
+ SHUFFLE [RS_143]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_200] (rows=633595212 width=88)
- Conds:RS_79._col0=RS_80._col0(Inner),Output:["_col1","_col3"]
- <-Map 23 [SIMPLE_EDGE]
- SHUFFLE [RS_79]
+ Merge Join Operator [MERGEJOIN_370] (rows=633595212 width=88)
+ Conds:RS_140._col0=RS_141._col0(Inner),Output:["_col1","_col3"]
+ <-Map 40 [SIMPLE_EDGE]
+ SHUFFLE [RS_140]
PartitionCols:_col0
- Select Operator [SEL_72] (rows=575995635 width=88)
+ Select Operator [SEL_133] (rows=575995635 width=88)
Output:["_col0","_col1"]
- Filter Operator [FIL_188] (rows=575995635 width=88)
+ Filter Operator [FIL_348] (rows=575995635 width=88)
predicate:(ss_sold_date_sk is not null and ss_item_sk is not null)
- TableScan [TS_70] (rows=575995635 width=88)
+ TableScan [TS_131] (rows=575995635 width=88)
default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk"]
- <-Map 27 [SIMPLE_EDGE]
- SHUFFLE [RS_80]
+ <-Map 44 [SIMPLE_EDGE]
+ SHUFFLE [RS_141]
PartitionCols:_col0
- Select Operator [SEL_75] (rows=36525 width=1119)
+ Select Operator [SEL_136] (rows=36525 width=1119)
Output:["_col0","_col1"]
- Filter Operator [FIL_189] (rows=36525 width=1119)
+ Filter Operator [FIL_349] (rows=36525 width=1119)
predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
- TableScan [TS_73] (rows=73049 width=1119)
+ TableScan [TS_134] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_year"]
- <-Reducer 31 [SIMPLE_EDGE]
- SHUFFLE [RS_125]
+ <-Reducer 53 [SIMPLE_EDGE]
+ SHUFFLE [RS_247]
PartitionCols:_col0
- Group By Operator [GBY_116] (rows=52799601 width=88)
- Output:["_col0"],keys:_col0
- Select Operator [SEL_112] (rows=105599202 width=88)
- Output:["_col0"]
- Filter Operator [FIL_111] (rows=105599202 width=88)
- predicate:(_col1 > 0.95)
- Group By Operator [GBY_110] (rows=316797606 width=88)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 30 [SIMPLE_EDGE]
- SHUFFLE [RS_109]
- PartitionCols:_col0
- Group By Operator [GBY_108] (rows=633595212 width=88)
- Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
- Select Operator [SEL_106] (rows=633595212 width=88)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_202] (rows=633595212 width=88)
- Conds:RS_103._col0=RS_104._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 29 [SIMPLE_EDGE]
- SHUFFLE [RS_103]
- PartitionCols:_col0
- Select Operator [SEL_99] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_191] (rows=575995635 width=88)
- predicate:ss_customer_sk is not null
- TableScan [TS_97] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
- <-Map 32 [SIMPLE_EDGE]
- SHUFFLE [RS_104]
+ Group By Operator [GBY_238] (rows=52799601 width=322)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 52 [SIMPLE_EDGE]
+ SHUFFLE [RS_237]
+ PartitionCols:_col0
+ Group By Operator [GBY_236] (rows=105599202 width=322)
+ Output:["_col0"],keys:_col2
+ Select Operator [SEL_235] (rows=105599202 width=322)
+ Output:["_col2"]
+ Filter Operator [FIL_234] (rows=105599202 width=322)
+ predicate:(_col3 > (0.95 * _col1))
+ Merge Join Operator [MERGEJOIN_383] (rows=316797606 width=322)
+ Conds:(Inner),Output:["_col1","_col2","_col3"]
+ <-Reducer 51 [SIMPLE_EDGE]
+ SHUFFLE [RS_231]
+ Merge Join Operator [MERGEJOIN_382] (rows=1 width=233)
+ Conds:(Left Outer),Output:["_col1"]
+ <-Reducer 50 [SIMPLE_EDGE]
+ SHUFFLE [RS_228]
+ Select Operator [SEL_186] (rows=1 width=8)
+ Filter Operator [FIL_185] (rows=1 width=8)
+ predicate:(sq_count_check(_col0) <= 1)
+ Group By Operator [GBY_183] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(VALUE._col0)"]
+ <-Reducer 49 [SIMPLE_EDGE]
+ SHUFFLE [RS_182]
+ Group By Operator [GBY_181] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count()"]
+ Select Operator [SEL_178] (rows=348477374 width=88)
+ Group By Operator [GBY_177] (rows=348477374 width=88)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 48 [SIMPLE_EDGE]
+ SHUFFLE [RS_176]
+ PartitionCols:_col0
+ Group By Operator [GBY_175] (rows=696954748 width=88)
+ Output:["_col0"],keys:_col0
+ Select Operator [SEL_173] (rows=696954748 width=88)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_373] (rows=696954748 width=88)
+ Conds:RS_170._col1=RS_171._col0(Inner),Output:["_col6"]
+ <-Map 55 [SIMPLE_EDGE]
+ SHUFFLE [RS_171]
+ PartitionCols:_col0
+ Select Operator [SEL_166] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_353] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_164] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ <-Reducer 47 [SIMPLE_EDGE]
+ SHUFFLE [RS_170]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_372] (rows=633595212 width=88)
+ Conds:RS_167._col0=RS_168._col0(Inner),Output:["_col1"]
+ <-Map 46 [SIMPLE_EDGE]
+ SHUFFLE [RS_167]
+ PartitionCols:_col0
+ Select Operator [SEL_160] (rows=575995635 width=88)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_351] (rows=575995635 width=88)
+ predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_158] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"]
+ <-Map 54 [SIMPLE_EDGE]
+ SHUFFLE [RS_168]
+ PartitionCols:_col0
+ Select Operator [SEL_163] (rows=36525 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_352] (rows=36525 width=1119)
+ predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
+ TableScan [TS_161] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 60 [SIMPLE_EDGE]
+ SHUFFLE [RS_229]
+ Group By Operator [GBY_211] (rows=1 width=224)
+ Output:["_col0"],aggregations:["max(VALUE._col0)"]
+ <-Reducer 59 [SIMPLE_EDGE]
+ SHUFFLE [RS_210]
+ Group By Operator [GBY_209] (rows=1 width=224)
+ Output:["_col0"],aggregations:["max(_col1)"]
+ Select Operator [SEL_207] (rows=348477374 width=88)
+ Output:["_col1"]
+ Group By Operator [GBY_206] (rows=348477374 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 58 [SIMPLE_EDGE]
+ SHUFFLE [RS_205]
+ PartitionCols:_col0
+ Group By Operator [GBY_204] (rows=696954748 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
+ Select Operator [SEL_202] (rows=696954748 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_375] (rows=696954748 width=88)
+ Conds:RS_199._col1=RS_200._col0(Inner),Output:["_col2","_col3","_col6"]
+ <-Map 62 [SIMPLE_EDGE]
+ SHUFFLE [RS_200]
+ PartitionCols:_col0
+ Select Operator [SEL_195] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_356] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_193] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ <-Reducer 57 [SIMPLE_EDGE]
+ SHUFFLE [RS_199]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_374] (rows=633595212 width=88)
+ Conds:RS_196._col0=RS_197._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 56 [SIMPLE_EDGE]
+ SHUFFLE [RS_196]
+ PartitionCols:_col0
+ Select Operator [SEL_189] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_354] (rows=575995635 width=88)
+ predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_187] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"]
+ <-Map 61 [SIMPLE_EDGE]
+ SHUFFLE [RS_197]
+ PartitionCols:_col0
+ Select Operator [SEL_192] (rows=36525 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_355] (rows=36525 width=1119)
+ predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
+ TableScan [TS_190] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 65 [SIMPLE_EDGE]
+ SHUFFLE [RS_232]
+ Group By Operator [GBY_226] (rows=316797606 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 64 [SIMPLE_EDGE]
+ SHUFFLE [RS_225]
PartitionCols:_col0
- Select Operator [SEL_102] (rows=80000000 width=860)
- Output:["_col0"]
- Filter Operator [FIL_192] (rows=80000000 width=860)
- predicate:c_customer_sk is not null
- TableScan [TS_100] (rows=80000000 width=860)
- default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ Group By Operator [GBY_224] (rows=633595212 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
+ Select Operator [SEL_222] (rows=633595212 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_376] (rows=633595212 width=88)
+ Conds:RS_219._col0=RS_220._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 63 [SIMPLE_EDGE]
+ SHUFFLE [RS_219]
+ PartitionCols:_col0
+ Select Operator [SEL_215] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_357] (rows=575995635 width=88)
+ predicate:ss_customer_sk is not null
+ TableScan [TS_213] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
+ <-Map 66 [SIMPLE_EDGE]
+ SHUFFLE [RS_220]
+ PartitionCols:_col0
+ Select Operator [SEL_218] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_358] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_216] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
<-Reducer 4 [CONTAINS]
- Reduce Output Operator [RS_132]
- Group By Operator [GBY_131] (rows=1 width=112)
+ Reduce Output Operator [RS_254]
+ Group By Operator [GBY_253] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(_col0)"]
- Select Operator [SEL_63] (rows=383314495 width=135)
+ Select Operator [SEL_124] (rows=383314495 width=135)
Output:["_col0"]
- Merge Join Operator [MERGEJOIN_205] (rows=383314495 width=135)
- Conds:RS_60._col1=RS_61._col0(Inner),Output:["_col3","_col4"]
- <-Reducer 16 [SIMPLE_EDGE]
- SHUFFLE [RS_61]
+ Merge Join Operator [MERGEJOIN_381] (rows=383314495 width=135)
+ Conds:RS_121._col1=RS_122._col0(Inner),Output:["_col3","_col4"]
+ <-Reducer 21 [SIMPLE_EDGE]
+ SHUFFLE [RS_122]
PartitionCols:_col0
- Group By Operator [GBY_52] (rows=52799601 width=88)
- Output:["_col0"],keys:_col0
- Select Operator [SEL_48] (rows=105599202 width=88)
- Output:["_col0"]
- Filter Operator [FIL_47] (rows=105599202 width=88)
- predicate:(_col1 > 0.95)
- Group By Operator [GBY_46] (rows=316797606 width=88)
- Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 15 [SIMPLE_EDGE]
- SHUFFLE [RS_45]
- PartitionCols:_col0
- Group By Operator [GBY_44] (rows=633595212 width=88)
- Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
- Select Operator [SEL_42] (rows=633595212 width=88)
- Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_198] (rows=633595212 width=88)
- Conds:RS_39._col0=RS_40._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 14 [SIMPLE_EDGE]
- SHUFFLE [RS_39]
- PartitionCols:_col0
- Select Operator [SEL_35] (rows=575995635 width=88)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_184] (rows=575995635 width=88)
- predicate:ss_customer_sk is not null
- TableScan [TS_33] (rows=575995635 width=88)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
- <-Map 17 [SIMPLE_EDGE]
- SHUFFLE [RS_40]
+ Group By Operator [GBY_113] (rows=52799601 width=322)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 20 [SIMPLE_EDGE]
+ SHUFFLE [RS_112]
+ PartitionCols:_col0
+ Group By Operator [GBY_111] (rows=105599202 width=322)
+ Output:["_col0"],keys:_col2
+ Select Operator [SEL_110] (rows=105599202 width=322)
+ Output:["_col2"]
+ Filter Operator [FIL_109] (rows=105599202 width=322)
+ predicate:(_col3 > (0.95 * _col1))
+ Merge Join Operator [MERGEJOIN_380] (rows=316797606 width=322)
+ Conds:(Inner),Output:["_col1","_col2","_col3"]
+ <-Reducer 19 [SIMPLE_EDGE]
+ SHUFFLE [RS_106]
+ Merge Join Operator [MERGEJOIN_379] (rows=1 width=233)
+ Conds:(Left Outer),Output:["_col1"]
+ <-Reducer 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_103]
+ Select Operator [SEL_61] (rows=1 width=8)
+ Filter Operator [FIL_60] (rows=1 width=8)
+ predicate:(sq_count_check(_col0) <= 1)
+ Group By Operator [GBY_58] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count(VALUE._col0)"]
+ <-Reducer 17 [SIMPLE_EDGE]
+ SHUFFLE [RS_57]
+ Group By Operator [GBY_56] (rows=1 width=8)
+ Output:["_col0"],aggregations:["count()"]
+ Select Operator [SEL_53] (rows=348477374 width=88)
+ Group By Operator [GBY_52] (rows=348477374 width=88)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_51]
+ PartitionCols:_col0
+ Group By Operator [GBY_50] (rows=696954748 width=88)
+ Output:["_col0"],keys:_col0
+ Select Operator [SEL_48] (rows=696954748 width=88)
+ Output:["_col0"]
+ Merge Join Operator [MERGEJOIN_365] (rows=696954748 width=88)
+ Conds:RS_45._col1=RS_46._col0(Inner),Output:["_col6"]
+ <-Map 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_46]
+ PartitionCols:_col0
+ Select Operator [SEL_41] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_340] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_39] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_45]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_364] (rows=633595212 width=88)
+ Conds:RS_42._col0=RS_43._col0(Inner),Output:["_col1"]
+ <-Map 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_42]
+ PartitionCols:_col0
+ Select Operator [SEL_35] (rows=575995635 width=88)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_338] (rows=575995635 width=88)
+ predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_33] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"]
+ <-Map 22 [SIMPLE_EDGE]
+ SHUFFLE [RS_43]
+ PartitionCols:_col0
+ Select Operator [SEL_38] (rows=36525 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_339] (rows=36525 width=1119)
+ predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
+ TableScan [TS_36] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 28 [SIMPLE_EDGE]
+ SHUFFLE [RS_104]
+ Group By Operator [GBY_86] (rows=1 width=224)
+ Output:["_col0"],aggregations:["max(VALUE._col0)"]
+ <-Reducer 27 [SIMPLE_EDGE]
+ SHUFFLE [RS_85]
+ Group By Operator [GBY_84] (rows=1 width=224)
+ Output:["_col0"],aggregations:["max(_col1)"]
+ Select Operator [SEL_82] (rows=348477374 width=88)
+ Output:["_col1"]
+ Group By Operator [GBY_81] (rows=348477374 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 26 [SIMPLE_EDGE]
+ SHUFFLE [RS_80]
+ PartitionCols:_col0
+ Group By Operator [GBY_79] (rows=696954748 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
+ Select Operator [SEL_77] (rows=696954748 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_367] (rows=696954748 width=88)
+ Conds:RS_74._col1=RS_75._col0(Inner),Output:["_col2","_col3","_col6"]
+ <-Map 30 [SIMPLE_EDGE]
+ SHUFFLE [RS_75]
+ PartitionCols:_col0
+ Select Operator [SEL_70] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_343] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_68] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ <-Reducer 25 [SIMPLE_EDGE]
+ SHUFFLE [RS_74]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_366] (rows=633595212 width=88)
+ Conds:RS_71._col0=RS_72._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 24 [SIMPLE_EDGE]
+ SHUFFLE [RS_71]
+ PartitionCols:_col0
+ Select Operator [SEL_64] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_341] (rows=575995635 width=88)
+ predicate:(ss_customer_sk is not null and ss_sold_date_sk is not null)
+ TableScan [TS_62] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"]
+ <-Map 29 [SIMPLE_EDGE]
+ SHUFFLE [RS_72]
+ PartitionCols:_col0
+ Select Operator [SEL_67] (rows=36525 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_342] (rows=36525 width=1119)
+ predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
+ TableScan [TS_65] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 33 [SIMPLE_EDGE]
+ SHUFFLE [RS_107]
+ Group By Operator [GBY_101] (rows=316797606 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 32 [SIMPLE_EDGE]
+ SHUFFLE [RS_100]
PartitionCols:_col0
- Select Operator [SEL_38] (rows=80000000 width=860)
- Output:["_col0"]
- Filter Operator [FIL_185] (rows=80000000 width=860)
- predicate:c_customer_sk is not null
- TableScan [TS_36] (rows=80000000 width=860)
- default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
+ Group By Operator [GBY_99] (rows=633595212 width=88)
+ Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
+ Select Operator [SEL_97] (rows=633595212 width=88)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_368] (rows=633595212 width=88)
+ Conds:RS_94._col0=RS_95._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 31 [SIMPLE_EDGE]
+ SHUFFLE [RS_94]
+ PartitionCols:_col0
+ Select Operator [SEL_90] (rows=575995635 width=88)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_344] (rows=575995635 width=88)
+ predicate:ss_customer_sk is not null
+ TableScan [TS_88] (rows=575995635 width=88)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
+ <-Map 34 [SIMPLE_EDGE]
+ SHUFFLE [RS_95]
+ PartitionCols:_col0
+ Select Operator [SEL_93] (rows=80000000 width=860)
+ Output:["_col0"]
+ Filter Operator [FIL_345] (rows=80000000 width=860)
+ predicate:c_customer_sk is not null
+ TableScan [TS_91] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
<-Reducer 3 [SIMPLE_EDGE]
- SHUFFLE [RS_60]
+ SHUFFLE [RS_121]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_203] (rows=348467716 width=135)
- Conds:RS_57._col2=RS_58._col0(Inner),Output:["_col1","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_377] (rows=348467716 width=135)
+ Conds:RS_118._col2=RS_119._col0(Inner),Output:["_col1","_col3","_col4"]
<-Reducer 11 [SIMPLE_EDGE]
- SHUFFLE [RS_58]
+ SHUFFLE [RS_119]
PartitionCols:_col0
Group By Operator [GBY_31] (rows=58079562 width=88)
Output:["_col0"],keys:_col1
@@ -312,7 +586,7 @@ Stage-0
Output:["_col1"]
Filter Operator [FIL_26] (rows=116159124 width=88)
predicate:(_col3 > 4)
- Select Operator [SEL_194] (rows=348477374 width=88)
+ Select Operator [SEL_359] (rows=348477374 width=88)
Output:["_col0","_col3"]
Group By Operator [GBY_25] (rows=348477374 width=88)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
@@ -323,28 +597,28 @@ Stage-0
Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2
Select Operator [SEL_21] (rows=696954748 width=88)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_197] (rows=696954748 width=88)
+ Merge Join Operator [MERGEJOIN_363] (rows=696954748 width=88)
Conds:RS_18._col1=RS_19._col0(Inner),Output:["_col3","_col5","_col6"]
<-Map 13 [SIMPLE_EDGE]
SHUFFLE [RS_19]
PartitionCols:_col0
Select Operator [SEL_14] (rows=462000 width=1436)
Output:["_col0","_col1"]
- Filter Operator [FIL_183] (rows=462000 width=1436)
+ Filter Operator [FIL_337] (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_desc"]
<-Reducer 9 [SIMPLE_EDGE]
SHUFFLE [RS_18]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_196] (rows=633595212 width=88)
+ Merge Join Operator [MERGEJOIN_362] (rows=633595212 width=88)
Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col1","_col3"]
<-Map 12 [SIMPLE_EDGE]
SHUFFLE [RS_16]
PartitionCols:_col0
Select Operator [SEL_11] (rows=36525 width=1119)
Output:["_col0","_col1"]
- Filter Operator [FIL_182] (rows=36525 width=1119)
+ Filter Operator [FIL_336] (rows=36525 width=1119)
predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
TableScan [TS_9] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_year"]
@@ -353,30 +627,30 @@ Stage-0
PartitionCols:_col0
Select Operator [SEL_8] (rows=575995635 width=88)
Output:["_col0","_col1"]
- Filter Operator [FIL_181] (rows=575995635 width=88)
+ Filter Operator [FIL_335] (rows=575995635 width=88)
predicate:(ss_sold_date_sk is not null and ss_item_sk is not null)
TableScan [TS_6] (rows=575995635 width=88)
default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_item_sk"]
<-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_57]
+ SHUFFLE [RS_118]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_195] (rows=316788826 width=135)
- Conds:RS_54._col0=RS_55._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_361] (rows=316788826 width=135)
+ Conds:RS_115._col0=RS_116._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
<-Map 1 [SIMPLE_EDGE]
- SHUFFLE [RS_54]
+ SHUFFLE [RS_115]
PartitionCols:_col0
Select Operator [SEL_2] (rows=287989836 width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_179] (rows=287989836 width=135)
+ Filter Operator [FIL_333] (rows=287989836 width=135)
predicate: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_customer_sk","cs_item_sk","cs_quantity","cs_list_price"]
<-Map 7 [SIMPLE_EDGE]
- SHUFFLE [RS_55]
+ SHUFFLE [RS_116]
PartitionCols:_col0
Select Operator [SEL_5] (rows=18262 width=1119)
Output:["_col0"]
- Filter Operator [FIL_180] (rows=18262 width=1119)
+ Filter Operator [FIL_334] (rows=18262 width=1119)
predicate:((d_year = 1999) and (d_moy = 1) and d_date_sk is not null)
TableScan [TS_3] (rows=73049 width=1119)
default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year","d_moy"]
http://git-wip-us.apache.org/repos/asf/hive/blob/d9343f6d/ql/src/test/results/clientpositive/perf/query30.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query30.q.out b/ql/src/test/results/clientpositive/perf/query30.q.out
new file mode 100644
index 0000000..56cf617
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/query30.q.out
@@ -0,0 +1,308 @@
+Warning: Shuffle Join MERGEJOIN[154][tables = [$hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 22' is a cross product
+PREHOOK: query: explain with customer_total_return as
+ (select wr_returning_customer_sk as ctr_customer_sk
+ ,ca_state as ctr_state,
+ sum(wr_return_amt) as ctr_total_return
+ from web_returns
+ ,date_dim
+ ,customer_address
+ where wr_returned_date_sk = d_date_sk
+ and d_year =2002
+ and wr_returning_addr_sk = ca_address_sk
+ group by wr_returning_customer_sk
+ ,ca_state)
+ select c_customer_id,c_salutation,c_first_name,c_last_name,c_preferred_cust_flag
+ ,c_birth_day,c_birth_month,c_birth_year,c_birth_country,c_login,c_email_address
+ ,c_last_review_date,ctr_total_return
+ from customer_total_return ctr1
+ ,customer_address
+ ,customer
+ where ctr1.ctr_total_return > (select avg(ctr_total_return)*1.2
+ from customer_total_return ctr2
+ where ctr1.ctr_state = ctr2.ctr_state)
+ and ca_address_sk = c_current_addr_sk
+ and ca_state = 'IL'
+ and ctr1.ctr_customer_sk = c_customer_sk
+ order by c_customer_id,c_salutation,c_first_name,c_last_name,c_preferred_cust_flag
+ ,c_birth_day,c_birth_month,c_birth_year,c_birth_country,c_login,c_email_address
+ ,c_last_review_date,ctr_total_return
+limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain with customer_total_return as
+ (select wr_returning_customer_sk as ctr_customer_sk
+ ,ca_state as ctr_state,
+ sum(wr_return_amt) as ctr_total_return
+ from web_returns
+ ,date_dim
+ ,customer_address
+ where wr_returned_date_sk = d_date_sk
+ and d_year =2002
+ and wr_returning_addr_sk = ca_address_sk
+ group by wr_returning_customer_sk
+ ,ca_state)
+ select c_customer_id,c_salutation,c_first_name,c_last_name,c_preferred_cust_flag
+ ,c_birth_day,c_birth_month,c_birth_year,c_birth_country,c_login,c_email_address
+ ,c_last_review_date,ctr_total_return
+ from customer_total_return ctr1
+ ,customer_address
+ ,customer
+ where ctr1.ctr_total_return > (select avg(ctr_total_return)*1.2
+ from customer_total_return ctr2
+ where ctr1.ctr_state = ctr2.ctr_state)
+ and ca_address_sk = c_current_addr_sk
+ and ca_state = 'IL'
+ and ctr1.ctr_customer_sk = c_customer_sk
+ order by c_customer_id,c_salutation,c_first_name,c_last_name,c_preferred_cust_flag
+ ,c_birth_day,c_birth_month,c_birth_year,c_birth_country,c_login,c_email_address
+ ,c_last_review_date,ctr_total_return
+limit 100
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Vertex dependency in root stage
+Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
+Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 19 (SIMPLE_EDGE)
+Reducer 15 <- Map 20 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE)
+Reducer 16 <- Reducer 15 (SIMPLE_EDGE)
+Reducer 17 <- Reducer 16 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE)
+Reducer 18 <- Reducer 17 (SIMPLE_EDGE)
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
+Reducer 22 <- Map 21 (SIMPLE_EDGE), Map 30 (SIMPLE_EDGE), Reducer 27 (SIMPLE_EDGE)
+Reducer 23 <- Reducer 22 (SIMPLE_EDGE)
+Reducer 25 <- Map 24 (SIMPLE_EDGE), Map 28 (SIMPLE_EDGE)
+Reducer 26 <- Map 29 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE)
+Reducer 27 <- Reducer 26 (SIMPLE_EDGE)
+Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 18 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
+Reducer 8 <- Map 11 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
+Reducer 9 <- Map 12 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+
+Stage-0
+ Fetch Operator
+ limit:100
+ Stage-1
+ Reducer 5
+ File Output Operator [FS_102]
+ Limit [LIM_101] (rows=100 width=1)
+ Number of rows:100
+ Select Operator [SEL_100] (rows=930023387364950016 width=1)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"]
+ <-Reducer 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_99]
+ Select Operator [SEL_98] (rows=930023387364950016 width=1)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"]
+ Filter Operator [FIL_97] (rows=930023387364950016 width=1)
+ predicate:(_col2 > CASE WHEN (_col20 is null) THEN (null) ELSE (_col19) END)
+ Select Operator [SEL_96] (rows=2790070162094850048 width=1)
+ Output:["_col2","_col6","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"]
+ Merge Join Operator [MERGEJOIN_162] (rows=2790070162094850048 width=1)
+ Conds:RS_93._col17=RS_94._col2(Left Outer),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col18","_col19","_col20"]
+ <-Reducer 18 [SIMPLE_EDGE]
+ SHUFFLE [RS_94]
+ PartitionCols:_col2
+ Select Operator [SEL_86] (rows=2536427365110644736 width=1)
+ Output:["_col0","_col1","_col2"]
+ Group By Operator [GBY_85] (rows=2536427365110644736 width=1)
+ Output:["_col0","_col1"],aggregations:["avg(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 17 [SIMPLE_EDGE]
+ SHUFFLE [RS_84]
+ PartitionCols:_col0
+ Group By Operator [GBY_83] (rows=5072854730221289472 width=1)
+ Output:["_col0","_col1"],aggregations:["avg(_col2)"],keys:_col3
+ Select Operator [SEL_82] (rows=5072854730221289472 width=1)
+ Output:["_col3","_col2"]
+ Merge Join Operator [MERGEJOIN_161] (rows=5072854730221289472 width=1)
+ Conds:RS_79._col1=RS_80._col0(Inner),Output:["_col2","_col3"]
+ <-Reducer 16 [SIMPLE_EDGE]
+ SHUFFLE [RS_79]
+ PartitionCols:_col1
+ Select Operator [SEL_45] (rows=22000000 width=1014)
+ Output:["_col1","_col2"]
+ Group By Operator [GBY_44] (rows=22000000 width=1014)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_43]
+ PartitionCols:_col0, _col1
+ Group By Operator [GBY_42] (rows=44000000 width=1014)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col7, _col1
+ Select Operator [SEL_41] (rows=44000000 width=1014)
+ Output:["_col7","_col1","_col3"]
+ Merge Join Operator [MERGEJOIN_159] (rows=44000000 width=1014)
+ Conds:RS_38._col2=RS_39._col0(Inner),Output:["_col1","_col3","_col7"]
+ <-Map 20 [SIMPLE_EDGE]
+ SHUFFLE [RS_39]
+ PartitionCols:_col0
+ Select Operator [SEL_34] (rows=40000000 width=1014)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_148] (rows=40000000 width=1014)
+ predicate:ca_address_sk is not null
+ TableScan [TS_32] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]
+ <-Reducer 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_38]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_158] (rows=15838314 width=92)
+ Conds:RS_35._col0=RS_36._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 13 [SIMPLE_EDGE]
+ SHUFFLE [RS_35]
+ PartitionCols:_col0
+ Select Operator [SEL_28] (rows=14398467 width=92)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_146] (rows=14398467 width=92)
+ predicate:(wr_returned_date_sk is not null and wr_returning_addr_sk is not null)
+ TableScan [TS_26] (rows=14398467 width=92)
+ default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_returning_customer_sk","wr_returning_addr_sk","wr_return_amt"]
+ <-Map 19 [SIMPLE_EDGE]
+ SHUFFLE [RS_36]
+ PartitionCols:_col0
+ Select Operator [SEL_31] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_147] (rows=36524 width=1119)
+ predicate:((d_year = 2002) and d_date_sk is not null)
+ TableScan [TS_29] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 23 [SIMPLE_EDGE]
+ SHUFFLE [RS_80]
+ PartitionCols:_col0
+ Group By Operator [GBY_77] (rows=4611686018427387903 width=1)
+ Output:["_col0"],keys:KEY._col0
+ <-Reducer 22 [SIMPLE_EDGE]
+ SHUFFLE [RS_76]
+ PartitionCols:_col0
+ Group By Operator [GBY_75] (rows=9223372036854775807 width=1)
+ Output:["_col0"],keys:_col2
+ Merge Join Operator [MERGEJOIN_154] (rows=9223372036854775807 width=1)
+ Conds:(Inner),(Inner),Output:["_col2"]
+ <-Map 21 [SIMPLE_EDGE]
+ SHUFFLE [RS_70]
+ Select Operator [SEL_47] (rows=80000000 width=4)
+ TableScan [TS_46] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:COMPLETE
+ <-Map 30 [SIMPLE_EDGE]
+ SHUFFLE [RS_72]
+ Select Operator [SEL_69] (rows=40000000 width=4)
+ TableScan [TS_68] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:COMPLETE
+ <-Reducer 27 [SIMPLE_EDGE]
+ SHUFFLE [RS_71]
+ Select Operator [SEL_67] (rows=22000000 width=1014)
+ Output:["_col1"]
+ Group By Operator [GBY_66] (rows=22000000 width=1014)
+ Output:["_col0","_col1"],keys:KEY._col0, KEY._col1
+ <-Reducer 26 [SIMPLE_EDGE]
+ SHUFFLE [RS_65]
+ PartitionCols:_col0, _col1
+ Group By Operator [GBY_64] (rows=44000000 width=1014)
+ Output:["_col0","_col1"],keys:_col7, _col1
+ Select Operator [SEL_63] (rows=44000000 width=1014)
+ Output:["_col7","_col1"]
+ Merge Join Operator [MERGEJOIN_153] (rows=44000000 width=1014)
+ Conds:RS_60._col2=RS_61._col0(Inner),Output:["_col1","_col7"]
+ <-Map 29 [SIMPLE_EDGE]
+ SHUFFLE [RS_61]
+ PartitionCols:_col0
+ Select Operator [SEL_56] (rows=40000000 width=1014)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_151] (rows=40000000 width=1014)
+ predicate:ca_address_sk is not null
+ TableScan [TS_54] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]
+ <-Reducer 25 [SIMPLE_EDGE]
+ SHUFFLE [RS_60]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_152] (rows=15838314 width=92)
+ Conds:RS_57._col0=RS_58._col0(Inner),Output:["_col1","_col2"]
+ <-Map 24 [SIMPLE_EDGE]
+ SHUFFLE [RS_57]
+ PartitionCols:_col0
+ Select Operator [SEL_50] (rows=14398467 width=92)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_149] (rows=14398467 width=92)
+ predicate:(wr_returned_date_sk is not null and wr_returning_addr_sk is not null)
+ TableScan [TS_48] (rows=14398467 width=92)
+ default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_returning_customer_sk","wr_returning_addr_sk"]
+ <-Map 28 [SIMPLE_EDGE]
+ SHUFFLE [RS_58]
+ PartitionCols:_col0
+ Select Operator [SEL_53] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_150] (rows=36524 width=1119)
+ predicate:((d_year = 2002) and d_date_sk is not null)
+ TableScan [TS_51] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Reducer 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_93]
+ PartitionCols:_col17
+ Merge Join Operator [MERGEJOIN_160] (rows=96800003 width=860)
+ Conds:RS_90._col0=RS_91._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col17","_col18"]
+ <-Reducer 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_91]
+ PartitionCols:_col0
+ Group By Operator [GBY_24] (rows=22000000 width=1014)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1
+ <-Reducer 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_23]
+ PartitionCols:_col0, _col1
+ Group By Operator [GBY_22] (rows=44000000 width=1014)
+ Output:["_col0","_col1","_col2"],aggregations:["sum(_col3)"],keys:_col1, _col7
+ Select Operator [SEL_21] (rows=44000000 width=1014)
+ Output:["_col1","_col7","_col3"]
+ Merge Join Operator [MERGEJOIN_157] (rows=44000000 width=1014)
+ Conds:RS_18._col2=RS_19._col0(Inner),Output:["_col1","_col3","_col7"]
+ <-Map 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_19]
+ PartitionCols:_col0
+ Select Operator [SEL_14] (rows=40000000 width=1014)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_145] (rows=40000000 width=1014)
+ predicate:ca_address_sk is not null
+ TableScan [TS_12] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]
+ <-Reducer 8 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_156] (rows=15838314 width=92)
+ Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 11 [SIMPLE_EDGE]
+ SHUFFLE [RS_16]
+ PartitionCols:_col0
+ Select Operator [SEL_11] (rows=36524 width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_144] (rows=36524 width=1119)
+ predicate:((d_year = 2002) and d_date_sk is not null)
+ TableScan [TS_9] (rows=73049 width=1119)
+ default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_year"]
+ <-Map 7 [SIMPLE_EDGE]
+ SHUFFLE [RS_15]
+ PartitionCols:_col0
+ Select Operator [SEL_8] (rows=14398467 width=92)
+ Output:["_col0","_col1","_col2","_col3"]
+ Filter Operator [FIL_143] (rows=14398467 width=92)
+ predicate:(wr_returned_date_sk is not null and wr_returning_addr_sk is not null and wr_returning_customer_sk is not null)
+ TableScan [TS_6] (rows=14398467 width=92)
+ default@web_returns,web_returns,Tbl:COMPLETE,Col:NONE,Output:["wr_returned_date_sk","wr_returning_customer_sk","wr_returning_addr_sk","wr_return_amt"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_90]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_155] (rows=88000001 width=860)
+ Conds:RS_87._col2=RS_88._col0(Inner),Output:["_col0","_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_87]
+ PartitionCols:_col2
+ Select Operator [SEL_2] (rows=80000000 width=860)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13"]
+ Filter Operator [FIL_141] (rows=80000000 width=860)
+ predicate:(c_customer_sk is not null and c_current_addr_sk is not null)
+ TableScan [TS_0] (rows=80000000 width=860)
+ default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_customer_id","c_current_addr_sk","c_salutation","c_first_name","c_last_name","c_preferred_cust_flag","c_birth_day","c_birth_month","c_birth_year","c_birth_country","c_login","c_email_address","c_last_review_date"]
+ <-Map 6 [SIMPLE_EDGE]
+ SHUFFLE [RS_88]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=20000000 width=1014)
+ Output:["_col0"]
+ Filter Operator [FIL_142] (rows=20000000 width=1014)
+ predicate:((ca_state = 'IL') and ca_address_sk is not null)
+ TableScan [TS_3] (rows=40000000 width=1014)
+ default@customer_address,customer_address,Tbl:COMPLETE,Col:NONE,Output:["ca_address_sk","ca_state"]
+