http://git-wip-us.apache.org/repos/asf/hive/blob/f2c4f319/ql/src/test/results/clientpositive/perf/tez/query23.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query23.q.out
b/ql/src/test/results/clientpositive/perf/tez/query23.q.out
index 3743000..6725bec 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query23.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query23.q.out
@@ -1,5 +1,5 @@
-Warning: Shuffle Join MERGEJOIN[377][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in
Stage 'Reducer 22' is a cross product
-Warning: Shuffle Join MERGEJOIN[379][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in
Stage 'Reducer 25' is a cross product
+Warning: Shuffle Join MERGEJOIN[581][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in
Stage 'Reducer 27' is a cross product
+Warning: Shuffle Join MERGEJOIN[583][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in
Stage 'Reducer 35' 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
@@ -105,307 +105,431 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Reducer 10 <- Reducer 25 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE), Union 5
(CONTAINS)
-Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 15 (SIMPLE_EDGE)
-Reducer 13 <- Map 16 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE)
-Reducer 14 <- Reducer 13 (SIMPLE_EDGE)
-Reducer 18 <- Map 17 (SIMPLE_EDGE), Map 27 (SIMPLE_EDGE)
-Reducer 19 <- Map 31 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE)
+Map 1 <- Reducer 17 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE)
+Map 13 <- Reducer 19 (BROADCAST_EDGE), Reducer 21 (BROADCAST_EDGE)
+Map 22 <- Reducer 30 (BROADCAST_EDGE)
+Map 42 <- Reducer 12 (BROADCAST_EDGE)
+Map 43 <- Reducer 37 (BROADCAST_EDGE)
+Reducer 10 <- Reducer 16 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 35 (SIMPLE_EDGE), Union 5
(CONTAINS)
+Reducer 12 <- Map 7 (CUSTOM_SIMPLE_EDGE)
+Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 18 (SIMPLE_EDGE)
+Reducer 15 <- Map 20 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE)
+Reducer 16 <- Reducer 15 (SIMPLE_EDGE)
+Reducer 17 <- Reducer 16 (CUSTOM_SIMPLE_EDGE)
+Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
-Reducer 20 <- Reducer 19 (SIMPLE_EDGE)
-Reducer 21 <- Reducer 20 (CUSTOM_SIMPLE_EDGE)
-Reducer 22 <- Reducer 21 (CUSTOM_SIMPLE_EDGE), Reducer 23
(CUSTOM_SIMPLE_EDGE), Reducer 30 (CUSTOM_SIMPLE_EDGE)
-Reducer 23 <- Reducer 20 (CUSTOM_SIMPLE_EDGE)
-Reducer 24 <- Reducer 20 (CUSTOM_SIMPLE_EDGE)
-Reducer 25 <- Reducer 24 (CUSTOM_SIMPLE_EDGE), Reducer 26
(CUSTOM_SIMPLE_EDGE), Reducer 30 (CUSTOM_SIMPLE_EDGE)
-Reducer 26 <- Reducer 20 (CUSTOM_SIMPLE_EDGE)
-Reducer 29 <- Map 28 (SIMPLE_EDGE), Map 31 (SIMPLE_EDGE)
-Reducer 3 <- Reducer 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
-Reducer 30 <- Reducer 29 (SIMPLE_EDGE)
-Reducer 4 <- Reducer 22 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5
(CONTAINS)
+Reducer 21 <- Map 20 (CUSTOM_SIMPLE_EDGE)
+Reducer 23 <- Map 22 (SIMPLE_EDGE), Map 29 (SIMPLE_EDGE)
+Reducer 24 <- Map 41 (SIMPLE_EDGE), Reducer 23 (SIMPLE_EDGE)
+Reducer 25 <- Reducer 24 (SIMPLE_EDGE)
+Reducer 26 <- Reducer 25 (CUSTOM_SIMPLE_EDGE)
+Reducer 27 <- Reducer 26 (CUSTOM_SIMPLE_EDGE), Reducer 28
(CUSTOM_SIMPLE_EDGE), Reducer 40 (CUSTOM_SIMPLE_EDGE)
+Reducer 28 <- Reducer 25 (CUSTOM_SIMPLE_EDGE)
+Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+Reducer 30 <- Map 29 (CUSTOM_SIMPLE_EDGE)
+Reducer 31 <- Map 29 (SIMPLE_EDGE), Map 43 (SIMPLE_EDGE)
+Reducer 32 <- Map 41 (SIMPLE_EDGE), Reducer 31 (SIMPLE_EDGE)
+Reducer 33 <- Reducer 32 (SIMPLE_EDGE)
+Reducer 34 <- Reducer 33 (CUSTOM_SIMPLE_EDGE)
+Reducer 35 <- Reducer 34 (CUSTOM_SIMPLE_EDGE), Reducer 36
(CUSTOM_SIMPLE_EDGE), Reducer 40 (CUSTOM_SIMPLE_EDGE)
+Reducer 36 <- Reducer 33 (CUSTOM_SIMPLE_EDGE)
+Reducer 37 <- Map 29 (CUSTOM_SIMPLE_EDGE)
+Reducer 39 <- Map 38 (SIMPLE_EDGE), Map 41 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 27 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5
(CONTAINS)
+Reducer 40 <- Reducer 39 (SIMPLE_EDGE)
Reducer 6 <- Union 5 (CUSTOM_SIMPLE_EDGE)
-Reducer 8 <- Map 32 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
-Reducer 9 <- Reducer 14 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
+Reducer 9 <- Map 42 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:100
Stage-1
Reducer 6 vectorized
- File Output Operator [FS_453]
- Limit [LIM_452] (rows=1 width=112)
+ File Output Operator [FS_684]
+ Limit [LIM_683] (rows=1 width=112)
Number of rows:100
- Group By Operator [GBY_451] (rows=1 width=112)
+ Group By Operator [GBY_682] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(VALUE._col0)"]
<-Union 5 [CUSTOM_SIMPLE_EDGE]
- <-Reducer 10 [CONTAINS]
- Reduce Output Operator [RS_390]
- Group By Operator [GBY_389] (rows=1 width=112)
+ <-Reducer 11 [CONTAINS]
+ Reduce Output Operator [RS_594]
+ Group By Operator [GBY_593] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(_col0)"]
- Select Operator [SEL_387] (rows=191667562 width=135)
+ Select Operator [SEL_591] (rows=191667562 width=135)
Output:["_col0"]
- Merge Join Operator [MERGEJOIN_386] (rows=191667562
width=135)
+ Merge Join Operator [MERGEJOIN_590] (rows=191667562
width=135)
Conds:RS_244._col2=RS_245._col0(Inner),Output:["_col3","_col4"]
- <-Reducer 25 [SIMPLE_EDGE]
+ <-Reducer 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_244]
+ PartitionCols:_col2
+ Merge Join Operator [MERGEJOIN_580] (rows=174243235
width=135)
+
Conds:RS_241._col1=RS_633._col0(Inner),Output:["_col2","_col3","_col4"]
+ <-Reducer 16 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_633]
+ PartitionCols:_col0
+ Group By Operator [GBY_630] (rows=58079562
width=88)
+ Output:["_col0"],keys:_col1
+ Select Operator [SEL_629] (rows=116159124
width=88)
+ Output:["_col1"]
+ Filter Operator [FIL_628] (rows=116159124
width=88)
+ predicate:(_col3 > 4L)
+ Select Operator [SEL_627] (rows=348477374
width=88)
+ Output:["_col0","_col3"]
+ Group By Operator [GBY_626]
(rows=348477374 width=88)
+
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0,
KEY._col1, KEY._col2
+ <-Reducer 15 [SIMPLE_EDGE]
+ SHUFFLE [RS_24]
+ PartitionCols:_col0
+ Group By Operator [GBY_23]
(rows=696954748 width=88)
+
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_565] (rows=696954748 width=88)
+
Conds:RS_18._col1=RS_617._col0(Inner),Output:["_col3","_col5","_col6"]
+ <-Map 20 [SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_617]
+ PartitionCols:_col0
+ Select Operator [SEL_616]
(rows=462000 width=1436)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_615]
(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 14 [SIMPLE_EDGE]
+ SHUFFLE [RS_18]
+ PartitionCols:_col1
+ Merge Join Operator
[MERGEJOIN_564] (rows=633595212 width=88)
+
Conds:RS_625._col0=RS_609._col0(Inner),Output:["_col1","_col3"]
+ <-Map 18 [SIMPLE_EDGE]
vectorized
+ PARTITION_ONLY_SHUFFLE
[RS_609]
+ PartitionCols:_col0
+ Select Operator [SEL_608]
(rows=36525 width=1119)
+ Output:["_col0","_col1"]
+ Filter Operator
[FIL_607] (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"]
+ <-Map 13 [SIMPLE_EDGE]
vectorized
+ SHUFFLE [RS_625]
+ PartitionCols:_col0
+ Select Operator [SEL_624]
(rows=575995635 width=88)
+ Output:["_col0","_col1"]
+ Filter Operator
[FIL_623] (rows=575995635 width=88)
+ 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_sold_date_sk BETWEEN
DynamicValue(RS_16_date_dim_d_date_sk_min) AND
DynamicValue(RS_16_date_dim_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk,
DynamicValue(RS_16_date_dim_d_date_sk_bloom_filter))) and ss_item_sk is not
null and ss_sold_date_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 19
[BROADCAST_EDGE] vectorized
+ BROADCAST [RS_614]
+ Group By Operator
[GBY_613] (rows=1 width=12)
+
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2,
expectedEntries=1000000)"]
+ <-Map 18
[CUSTOM_SIMPLE_EDGE] vectorized
+
PARTITION_ONLY_SHUFFLE [RS_612]
+ Group By
Operator [GBY_611] (rows=1 width=12)
+
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0,
expectedEntries=1000000)"]
+ Select
Operator [SEL_610] (rows=36525 width=1119)
+
Output:["_col0"]
+ Please
refer to the previous Select Operator [SEL_608]
+ <-Reducer 21
[BROADCAST_EDGE] vectorized
+ BROADCAST [RS_622]
+ Group By Operator
[GBY_621] (rows=1 width=12)
+
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2,
expectedEntries=1000000)"]
+ <-Map 20
[CUSTOM_SIMPLE_EDGE] vectorized
+
PARTITION_ONLY_SHUFFLE [RS_620]
+ Group By
Operator [GBY_619] (rows=1 width=12)
+
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0,
expectedEntries=1000000)"]
+ Select
Operator [SEL_618] (rows=462000 width=1436)
+
Output:["_col0"]
+ Please
refer to the previous Select Operator [SEL_616]
+ <-Reducer 9 [SIMPLE_EDGE]
+ SHUFFLE [RS_241]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_571]
(rows=158402938 width=135)
+
Conds:RS_689._col0=RS_599._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ <-Map 7 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_599]
+ PartitionCols:_col0
+ Select Operator [SEL_596] (rows=18262
width=1119)
+ Output:["_col0"]
+ Filter Operator [FIL_595] (rows=18262
width=1119)
+ predicate:((d_moy = 1) and (d_year = 1999)
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"]
+ <-Map 42 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_689]
+ PartitionCols:_col0
+ Select Operator [SEL_688] (rows=144002668
width=135)
+
Output:["_col0","_col1","_col2","_col3","_col4"]
+ Filter Operator [FIL_687] (rows=144002668
width=135)
+ predicate:((ws_sold_date_sk BETWEEN
DynamicValue(RS_239_date_dim_d_date_sk_min) AND
DynamicValue(RS_239_date_dim_d_date_sk_max) and
in_bloom_filter(ws_sold_date_sk,
DynamicValue(RS_239_date_dim_d_date_sk_bloom_filter))) and ws_bill_customer_sk
is not null and ws_item_sk is not null and ws_sold_date_sk is not null)
+ TableScan [TS_124] (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"]
+ <-Reducer 12 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_686]
+ Group By Operator [GBY_685] (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_604]
+ Group By Operator [GBY_602]
(rows=1 width=12)
+
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0,
expectedEntries=1000000)"]
+ Select Operator [SEL_600]
(rows=18262 width=1119)
+ Output:["_col0"]
+ Please refer to the previous
Select Operator [SEL_596]
+ <-Reducer 35 [SIMPLE_EDGE]
SHUFFLE [RS_245]
PartitionCols:_col0
Select Operator [SEL_237] (rows=105599202 width=433)
Output:["_col0"]
Filter Operator [FIL_236] (rows=105599202 width=433)
predicate:(_col3 > (0.95 * _col1))
- Merge Join Operator [MERGEJOIN_379]
(rows=316797606 width=433)
+ Merge Join Operator [MERGEJOIN_583]
(rows=316797606 width=433)
Conds:(Inner),(Inner),Output:["_col1","_col2","_col3"]
- <-Reducer 30 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_450]
- Group By Operator [GBY_448] (rows=316797606
width=88)
+ <-Reducer 40 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_681]
+ Group By Operator [GBY_679] (rows=316797606
width=88)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 29 [SIMPLE_EDGE]
+ <-Reducer 39 [SIMPLE_EDGE]
SHUFFLE [RS_105]
PartitionCols:_col0
Group By Operator [GBY_104]
(rows=633595212 width=88)
Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
Select Operator [SEL_102]
(rows=633595212 width=88)
Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_366]
(rows=633595212 width=88)
-
Conds:RS_447._col0=RS_422._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 31 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_422]
+ Merge Join Operator [MERGEJOIN_570]
(rows=633595212 width=88)
+
Conds:RS_678._col0=RS_658._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 41 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_658]
PartitionCols:_col0
- Select Operator [SEL_421]
(rows=80000000 width=860)
+ Select Operator [SEL_657]
(rows=80000000 width=860)
Output:["_col0"]
- Filter Operator [FIL_420]
(rows=80000000 width=860)
+ Filter Operator [FIL_656]
(rows=80000000 width=860)
predicate:c_customer_sk is not
null
TableScan [TS_96]
(rows=80000000 width=860)
default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk"]
- <-Map 28 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_447]
+ <-Map 38 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_678]
PartitionCols:_col0
- Select Operator [SEL_446]
(rows=575995635 width=88)
+ Select Operator [SEL_677]
(rows=575995635 width=88)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_445]
(rows=575995635 width=88)
+ Filter Operator [FIL_676]
(rows=575995635 width=88)
predicate:ss_customer_sk is
not null
TableScan [TS_93]
(rows=575995635 width=88)
default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
- <-Reducer 24 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_462]
- Select Operator [SEL_461] (rows=1 width=120)
- Filter Operator [FIL_460] (rows=1 width=120)
+ <-Reducer 34 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_707]
+ Select Operator [SEL_706] (rows=1 width=120)
+ Filter Operator [FIL_705] (rows=1 width=120)
predicate:(sq_count_check(_col0) <= 1)
- Group By Operator [GBY_459] (rows=1
width=120)
+ Group By Operator [GBY_704] (rows=1
width=120)
Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_458] (rows=1
width=120)
- Group By Operator [GBY_457] (rows=1
width=120)
+ Select Operator [SEL_703] (rows=1
width=120)
+ Group By Operator [GBY_702] (rows=1
width=120)
Output:["_col0"],aggregations:["count(VALUE._col0)"]
- <-Reducer 20 [CUSTOM_SIMPLE_EDGE]
vectorized
- PARTITION_ONLY_SHUFFLE [RS_435]
- Group By Operator [GBY_431]
(rows=1 width=120)
+ <-Reducer 33 [CUSTOM_SIMPLE_EDGE]
vectorized
+ PARTITION_ONLY_SHUFFLE [RS_700]
+ Group By Operator [GBY_698]
(rows=1 width=120)
Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_427]
(rows=348477374 width=88)
+ Select Operator [SEL_696]
(rows=348477374 width=88)
Output:["_col0"]
- Group By Operator [GBY_424]
(rows=348477374 width=88)
+ Group By Operator [GBY_695]
(rows=348477374 width=88)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
- <-Reducer 19 [SIMPLE_EDGE]
- SHUFFLE [RS_51]
+ <-Reducer 32 [SIMPLE_EDGE]
+ SHUFFLE [RS_175]
PartitionCols:_col0
- Group By Operator [GBY_50]
(rows=696954748 width=88)
+ Group By Operator
[GBY_174] (rows=696954748 width=88)
Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
- Select Operator [SEL_48]
(rows=696954748 width=88)
+ Select Operator
[SEL_172] (rows=696954748 width=88)
Output:["_col0","_col1"]
- Merge Join Operator
[MERGEJOIN_363] (rows=696954748 width=88)
-
Conds:RS_45._col1=RS_423._col0(Inner),Output:["_col2","_col3","_col6"]
- <-Map 31 [SIMPLE_EDGE]
vectorized
- SHUFFLE [RS_423]
+ Merge Join Operator
[MERGEJOIN_575] (rows=696954748 width=88)
+
Conds:RS_169._col1=RS_660._col0(Inner),Output:["_col2","_col3","_col6"]
+ <-Map 41 [SIMPLE_EDGE]
vectorized
+ SHUFFLE [RS_660]
PartitionCols:_col0
- Please refer to
the previous Select Operator [SEL_421]
- <-Reducer 18
[SIMPLE_EDGE]
- SHUFFLE [RS_45]
+ Please refer to
the previous Select Operator [SEL_657]
+ <-Reducer 31
[SIMPLE_EDGE]
+ SHUFFLE [RS_169]
PartitionCols:_col1
- Merge Join
Operator [MERGEJOIN_362] (rows=633595212 width=88)
-
Conds:RS_416._col0=RS_419._col0(Inner),Output:["_col1","_col2","_col3"]
- <-Map 17
[SIMPLE_EDGE] vectorized
- SHUFFLE [RS_416]
-
PartitionCols:_col0
- Select
Operator [SEL_415] (rows=575995635 width=88)
-
Output:["_col0","_col1","_col2","_col3"]
- Filter
Operator [FIL_414] (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","ss_quantity","ss_sales_price"]
- <-Map 27
[SIMPLE_EDGE] vectorized
- SHUFFLE [RS_419]
+ Merge Join
Operator [MERGEJOIN_574] (rows=633595212 width=88)
+
Conds:RS_694._col0=RS_645._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 29
[SIMPLE_EDGE] vectorized
+
PARTITION_ONLY_SHUFFLE [RS_645]
PartitionCols:_col0
- Select
Operator [SEL_418] (rows=36525 width=1119)
+ Select
Operator [SEL_642] (rows=36525 width=1119)
Output:["_col0"]
- Filter
Operator [FIL_417] (rows=36525 width=1119)
+ Filter
Operator [FIL_641] (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 26 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_464]
- Group By Operator [GBY_463] (rows=1 width=224)
+ <-Map 43
[SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_694]
+
PartitionCols:_col0
+ Select
Operator [SEL_693] (rows=575995635 width=88)
+
Output:["_col0","_col1","_col2","_col3"]
+ Filter
Operator [FIL_692] (rows=575995635 width=88)
+
predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_167_date_dim_d_date_sk_min)
AND DynamicValue(RS_167_date_dim_d_date_sk_max) and
in_bloom_filter(ss_sold_date_sk,
DynamicValue(RS_167_date_dim_d_date_sk_bloom_filter))) and ss_customer_sk is
not null and ss_sold_date_sk is not null)
+ TableScan
[TS_157] (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"]
+ <-Reducer
37 [BROADCAST_EDGE] vectorized
+
BROADCAST [RS_691]
+ Group
By Operator [GBY_690] (rows=1 width=12)
+
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2,
expectedEntries=1000000)"]
+ <-Map
29 [CUSTOM_SIMPLE_EDGE] vectorized
+
PARTITION_ONLY_SHUFFLE [RS_650]
+
Group By Operator [GBY_648] (rows=1 width=12)
+
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0,
expectedEntries=1000000)"]
+
Select Operator [SEL_646] (rows=36525 width=1119)
+
Output:["_col0"]
+
Please refer to the previous Select Operator [SEL_642]
+ <-Reducer 36 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_709]
+ Group By Operator [GBY_708] (rows=1 width=224)
Output:["_col0"],aggregations:["max(VALUE._col0)"]
- <-Reducer 20 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_436]
- Group By Operator [GBY_432] (rows=1
width=224)
+ <-Reducer 33 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_701]
+ Group By Operator [GBY_699] (rows=1
width=224)
Output:["_col0"],aggregations:["max(_col1)"]
- Select Operator [SEL_428]
(rows=348477374 width=88)
+ Select Operator [SEL_697]
(rows=348477374 width=88)
Output:["_col1"]
- Please refer to the previous Group By
Operator [GBY_424]
- <-Reducer 9 [SIMPLE_EDGE]
- SHUFFLE [RS_244]
- PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_376] (rows=174243235
width=135)
-
Conds:RS_241._col1=RS_413._col0(Inner),Output:["_col2","_col3","_col4"]
- <-Reducer 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_413]
- PartitionCols:_col0
- Group By Operator [GBY_411] (rows=58079562
width=88)
- Output:["_col0"],keys:_col1
- Select Operator [SEL_410] (rows=116159124
width=88)
- Output:["_col1"]
- Filter Operator [FIL_409] (rows=116159124
width=88)
- predicate:(_col3 > 4L)
- Select Operator [SEL_408] (rows=348477374
width=88)
- Output:["_col0","_col3"]
- Group By Operator [GBY_407]
(rows=348477374 width=88)
-
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0,
KEY._col1, KEY._col2
- <-Reducer 13 [SIMPLE_EDGE]
- SHUFFLE [RS_24]
- PartitionCols:_col0
- Group By Operator [GBY_23]
(rows=696954748 width=88)
-
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_361] (rows=696954748 width=88)
-
Conds:RS_18._col1=RS_406._col0(Inner),Output:["_col3","_col5","_col6"]
- <-Map 16 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_406]
- PartitionCols:_col0
- Select Operator [SEL_405]
(rows=462000 width=1436)
- Output:["_col0","_col1"]
- Filter Operator [FIL_404]
(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 12 [SIMPLE_EDGE]
- SHUFFLE [RS_18]
- PartitionCols:_col1
- Merge Join Operator
[MERGEJOIN_360] (rows=633595212 width=88)
-
Conds:RS_400._col0=RS_403._col0(Inner),Output:["_col1","_col3"]
- <-Map 11 [SIMPLE_EDGE]
vectorized
- SHUFFLE [RS_400]
- PartitionCols:_col0
- Select Operator [SEL_399]
(rows=575995635 width=88)
- Output:["_col0","_col1"]
- Filter Operator
[FIL_398] (rows=575995635 width=88)
- predicate:(ss_item_sk
is not null and ss_sold_date_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"]
- <-Map 15 [SIMPLE_EDGE]
vectorized
- SHUFFLE [RS_403]
- PartitionCols:_col0
- Select Operator [SEL_402]
(rows=36525 width=1119)
- Output:["_col0","_col1"]
- Filter Operator
[FIL_401] (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"]
- <-Reducer 8 [SIMPLE_EDGE]
- SHUFFLE [RS_241]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_367]
(rows=158402938 width=135)
-
Conds:RS_456._col0=RS_397._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
- <-Map 7 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_397]
- PartitionCols:_col0
- Select Operator [SEL_395] (rows=18262
width=1119)
- Output:["_col0"]
- Filter Operator [FIL_394] (rows=18262
width=1119)
- predicate:((d_moy = 1) and (d_year = 1999)
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"]
- <-Map 32 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_456]
- PartitionCols:_col0
- Select Operator [SEL_455] (rows=144002668
width=135)
-
Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_454] (rows=144002668
width=135)
- predicate:(ws_bill_customer_sk is not null
and ws_item_sk is not null and ws_sold_date_sk is not null)
- TableScan [TS_124] (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"]
+ Please refer to the previous Group By
Operator [GBY_695]
<-Reducer 4 [CONTAINS]
- Reduce Output Operator [RS_385]
- Group By Operator [GBY_384] (rows=1 width=112)
+ Reduce Output Operator [RS_589]
+ Group By Operator [GBY_588] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(_col0)"]
- Select Operator [SEL_382] (rows=383314495 width=135)
+ Select Operator [SEL_586] (rows=383314495 width=135)
Output:["_col0"]
- Merge Join Operator [MERGEJOIN_381] (rows=383314495
width=135)
+ Merge Join Operator [MERGEJOIN_585] (rows=383314495
width=135)
Conds:RS_120._col1=RS_121._col0(Inner),Output:["_col3","_col4"]
- <-Reducer 22 [SIMPLE_EDGE]
+ <-Reducer 27 [SIMPLE_EDGE]
SHUFFLE [RS_121]
PartitionCols:_col0
Select Operator [SEL_113] (rows=105599202 width=433)
Output:["_col0"]
Filter Operator [FIL_112] (rows=105599202 width=433)
predicate:(_col3 > (0.95 * _col1))
- Merge Join Operator [MERGEJOIN_377]
(rows=316797606 width=433)
+ Merge Join Operator [MERGEJOIN_581]
(rows=316797606 width=433)
Conds:(Inner),(Inner),Output:["_col1","_col2","_col3"]
- <-Reducer 30 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_449]
- Please refer to the previous Group By
Operator [GBY_448]
- <-Reducer 21 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_442]
- Select Operator [SEL_441] (rows=1 width=120)
- Filter Operator [FIL_440] (rows=1 width=120)
+ <-Reducer 40 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_680]
+ Please refer to the previous Group By
Operator [GBY_679]
+ <-Reducer 26 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_673]
+ Select Operator [SEL_672] (rows=1 width=120)
+ Filter Operator [FIL_671] (rows=1 width=120)
predicate:(sq_count_check(_col0) <= 1)
- Group By Operator [GBY_439] (rows=1
width=120)
+ Group By Operator [GBY_670] (rows=1
width=120)
Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_438] (rows=1
width=120)
- Group By Operator [GBY_437] (rows=1
width=120)
+ Select Operator [SEL_669] (rows=1
width=120)
+ Group By Operator [GBY_668] (rows=1
width=120)
Output:["_col0"],aggregations:["count(VALUE._col0)"]
- <-Reducer 20 [CUSTOM_SIMPLE_EDGE]
vectorized
- PARTITION_ONLY_SHUFFLE [RS_433]
- Group By Operator [GBY_429]
(rows=1 width=120)
+ <-Reducer 25 [CUSTOM_SIMPLE_EDGE]
vectorized
+ PARTITION_ONLY_SHUFFLE [RS_666]
+ Group By Operator [GBY_664]
(rows=1 width=120)
Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_425]
(rows=348477374 width=88)
+ Select Operator [SEL_662]
(rows=348477374 width=88)
Output:["_col0"]
- Please refer to the previous
Group By Operator [GBY_424]
- <-Reducer 23 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_444]
- Group By Operator [GBY_443] (rows=1 width=224)
+ Group By Operator [GBY_661]
(rows=348477374 width=88)
+
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
+ <-Reducer 24 [SIMPLE_EDGE]
+ SHUFFLE [RS_51]
+ PartitionCols:_col0
+ Group By Operator [GBY_50]
(rows=696954748 width=88)
+
Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
+ Select Operator [SEL_48]
(rows=696954748 width=88)
+
Output:["_col0","_col1"]
+ Merge Join Operator
[MERGEJOIN_567] (rows=696954748 width=88)
+
Conds:RS_45._col1=RS_659._col0(Inner),Output:["_col2","_col3","_col6"]
+ <-Map 41 [SIMPLE_EDGE]
vectorized
+ SHUFFLE [RS_659]
+ PartitionCols:_col0
+ Please refer to
the previous Select Operator [SEL_657]
+ <-Reducer 23
[SIMPLE_EDGE]
+ SHUFFLE [RS_45]
+ PartitionCols:_col1
+ Merge Join
Operator [MERGEJOIN_566] (rows=633595212 width=88)
+
Conds:RS_655._col0=RS_643._col0(Inner),Output:["_col1","_col2","_col3"]
+ <-Map 29
[SIMPLE_EDGE] vectorized
+
PARTITION_ONLY_SHUFFLE [RS_643]
+
PartitionCols:_col0
+ Please refer
to the previous Select Operator [SEL_642]
+ <-Map 22
[SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_655]
+
PartitionCols:_col0
+ Select
Operator [SEL_654] (rows=575995635 width=88)
+
Output:["_col0","_col1","_col2","_col3"]
+ Filter
Operator [FIL_653] (rows=575995635 width=88)
+
predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_43_date_dim_d_date_sk_min)
AND DynamicValue(RS_43_date_dim_d_date_sk_max) and
in_bloom_filter(ss_sold_date_sk,
DynamicValue(RS_43_date_dim_d_date_sk_bloom_filter))) and 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","ss_quantity","ss_sales_price"]
+ <-Reducer
30 [BROADCAST_EDGE] vectorized
+
BROADCAST [RS_652]
+ Group
By Operator [GBY_651] (rows=1 width=12)
+
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2,
expectedEntries=1000000)"]
+ <-Map
29 [CUSTOM_SIMPLE_EDGE] vectorized
+
PARTITION_ONLY_SHUFFLE [RS_649]
+
Group By Operator [GBY_647] (rows=1 width=12)
+
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0,
expectedEntries=1000000)"]
+
Select Operator [SEL_644] (rows=36525 width=1119)
+
Output:["_col0"]
+
Please refer to the previous Select Operator [SEL_642]
+ <-Reducer 28 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_675]
+ Group By Operator [GBY_674] (rows=1 width=224)
Output:["_col0"],aggregations:["max(VALUE._col0)"]
- <-Reducer 20 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_434]
- Group By Operator [GBY_430] (rows=1
width=224)
+ <-Reducer 25 [CUSTOM_SIMPLE_EDGE] vectorized
+ PARTITION_ONLY_SHUFFLE [RS_667]
+ Group By Operator [GBY_665] (rows=1
width=224)
Output:["_col0"],aggregations:["max(_col1)"]
- Select Operator [SEL_426]
(rows=348477374 width=88)
+ Select Operator [SEL_663]
(rows=348477374 width=88)
Output:["_col1"]
- Please refer to the previous Group By
Operator [GBY_424]
+ Please refer to the previous Group By
Operator [GBY_661]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_120]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_375] (rows=348467716
width=135)
-
Conds:RS_117._col2=RS_412._col0(Inner),Output:["_col1","_col3","_col4"]
- <-Reducer 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_412]
+ Merge Join Operator [MERGEJOIN_579] (rows=348467716
width=135)
+
Conds:RS_117._col2=RS_631._col0(Inner),Output:["_col1","_col3","_col4"]
+ <-Reducer 16 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_631]
PartitionCols:_col0
- Please refer to the previous Group By Operator
[GBY_411]
+ Please refer to the previous Group By Operator
[GBY_630]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_117]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_359]
(rows=316788826 width=135)
-
Conds:RS_393._col0=RS_396._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_563]
(rows=316788826 width=135)
+
Conds:RS_640._col0=RS_597._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
<-Map 7 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_396]
+ SHUFFLE [RS_597]
PartitionCols:_col0
- Please refer to the previous Select Operator
[SEL_395]
+ Please refer to the previous Select Operator
[SEL_596]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_393]
+ SHUFFLE [RS_640]
PartitionCols:_col0
- Select Operator [SEL_392] (rows=287989836
width=135)
+ Select Operator [SEL_639] (rows=287989836
width=135)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_391] (rows=287989836
width=135)
- predicate:(cs_bill_customer_sk is not null
and cs_item_sk is not null and cs_sold_date_sk is not null)
+ Filter Operator [FIL_638] (rows=287989836
width=135)
+ predicate:((cs_item_sk BETWEEN
DynamicValue(RS_118_item_i_item_sk_min) AND
DynamicValue(RS_118_item_i_item_sk_max) and in_bloom_filter(cs_item_sk,
DynamicValue(RS_118_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN
DynamicValue(RS_115_date_dim_d_date_sk_min) AND
DynamicValue(RS_115_date_dim_d_date_sk_max) and
in_bloom_filter(cs_sold_date_sk,
DynamicValue(RS_115_date_dim_d_date_sk_bloom_filter))) and cs_bill_customer_sk
is not null and cs_item_sk is not null and cs_sold_date_sk is not null)
TableScan [TS_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"]
+ <-Reducer 17 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_637]
+ Group By Operator [GBY_636] (rows=1
width=20)
+
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2,
expectedEntries=58079560)"]
+ <-Reducer 16 [CUSTOM_SIMPLE_EDGE]
vectorized
+ SHUFFLE [RS_635]
+ Group By Operator [GBY_634]
(rows=1 width=20)
+
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0,
expectedEntries=58079560)"]
+ Select Operator [SEL_632]
(rows=58079562 width=88)
+ Output:["_col0"]
+ Please refer to the previous
Group By Operator [GBY_630]
+ <-Reducer 8 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_606]
+ Group By Operator [GBY_605] (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_603]
+ Group By Operator [GBY_601]
(rows=1 width=12)
+
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0,
expectedEntries=1000000)"]
+ Select Operator [SEL_598]
(rows=18262 width=1119)
+ Output:["_col0"]
+ Please refer to the previous
Select Operator [SEL_596]
