You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2018/10/24 23:12:36 UTC
[2/6] 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/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 61d1dd7..7784792 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query23.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query23.q.out
@@ -1,7 +1,7 @@
-Warning: Shuffle Join MERGEJOIN[589][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product
-Warning: Shuffle Join MERGEJOIN[590][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product
-Warning: Shuffle Join MERGEJOIN[592][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product
-Warning: Shuffle Join MERGEJOIN[593][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' is a cross product
+Warning: Shuffle Join MERGEJOIN[593][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 29' is a cross product
+Warning: Shuffle Join MERGEJOIN[594][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 30' is a cross product
+Warning: Shuffle Join MERGEJOIN[596][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 33' is a cross product
+Warning: Shuffle Join MERGEJOIN[597][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 34' 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
@@ -166,37 +166,37 @@ Stage-0
limit:100
Stage-1
Reducer 6 vectorized
- File Output Operator [FS_695]
- Limit [LIM_694] (rows=1 width=112)
+ File Output Operator [FS_699]
+ Limit [LIM_698] (rows=1 width=112)
Number of rows:100
- Group By Operator [GBY_693] (rows=1 width=112)
+ Group By Operator [GBY_697] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(VALUE._col0)"]
<-Union 5 [CUSTOM_SIMPLE_EDGE]
<-Reducer 12 [CONTAINS]
- Reduce Output Operator [RS_604]
- Group By Operator [GBY_603] (rows=1 width=112)
+ Reduce Output Operator [RS_608]
+ Group By Operator [GBY_607] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(_col0)"]
- Select Operator [SEL_601] (rows=1 width=112)
+ Select Operator [SEL_605] (rows=1 width=112)
Output:["_col0"]
- Merge Join Operator [MERGEJOIN_600] (rows=1 width=116)
+ Merge Join Operator [MERGEJOIN_604] (rows=1 width=116)
Conds:RS_248._col2=RS_249._col0(Inner),Output:["_col3","_col4"]
<-Reducer 11 [SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_248]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_588] (rows=155 width=0)
- Conds:RS_245._col1=RS_638._col0(Inner),Output:["_col2","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_592] (rows=155 width=0)
+ Conds:RS_245._col1=RS_642._col0(Inner),Output:["_col2","_col3","_col4"]
<-Reducer 18 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_638]
+ SHUFFLE [RS_642]
PartitionCols:_col0
- Group By Operator [GBY_635] (rows=2235 width=4)
+ Group By Operator [GBY_639] (rows=2235 width=4)
Output:["_col0"],keys:_col1
- Select Operator [SEL_634] (rows=6548799 width=12)
+ Select Operator [SEL_638] (rows=6548799 width=12)
Output:["_col1"]
- Filter Operator [FIL_633] (rows=6548799 width=12)
+ Filter Operator [FIL_637] (rows=6548799 width=12)
predicate:(_col3 > 4L)
- Select Operator [SEL_632] (rows=19646398 width=12)
+ Select Operator [SEL_636] (rows=19646398 width=12)
Output:["_col0","_col3"]
- Group By Operator [GBY_631] (rows=19646398 width=290)
+ Group By Operator [GBY_635] (rows=19646398 width=290)
Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
<-Reducer 17 [SIMPLE_EDGE]
SHUFFLE [RS_24]
@@ -205,96 +205,96 @@ Stage-0
Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2
Select Operator [SEL_21] (rows=19646398 width=282)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_573] (rows=19646398 width=282)
- Conds:RS_18._col1=RS_630._col0(Inner),Output:["_col3","_col5","_col6"]
+ Merge Join Operator [MERGEJOIN_577] (rows=19646398 width=282)
+ Conds:RS_18._col1=RS_634._col0(Inner),Output:["_col3","_col5","_col6"]
<-Map 23 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_630]
+ SHUFFLE [RS_634]
PartitionCols:_col0
- Select Operator [SEL_629] (rows=462000 width=188)
+ Select Operator [SEL_633] (rows=462000 width=188)
Output:["_col0","_col1"]
- Filter Operator [FIL_628] (rows=462000 width=188)
+ Filter Operator [FIL_632] (rows=462000 width=188)
predicate:i_item_sk is not null
TableScan [TS_12] (rows=462000 width=188)
default@item,item,Tbl:COMPLETE,Col:COMPLETE,Output:["i_item_sk","i_item_desc"]
<-Reducer 16 [SIMPLE_EDGE]
SHUFFLE [RS_18]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_572] (rows=19646398 width=98)
- Conds:RS_627._col0=RS_619._col0(Inner),Output:["_col1","_col3"]
+ Merge Join Operator [MERGEJOIN_576] (rows=19646398 width=98)
+ Conds:RS_631._col0=RS_623._col0(Inner),Output:["_col1","_col3"]
<-Map 21 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_619]
+ PARTITION_ONLY_SHUFFLE [RS_623]
PartitionCols:_col0
- Select Operator [SEL_618] (rows=2609 width=102)
+ Select Operator [SEL_622] (rows=2609 width=102)
Output:["_col0","_col1"]
- Filter Operator [FIL_617] (rows=2609 width=102)
+ Filter Operator [FIL_621] (rows=2609 width=102)
predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
TableScan [TS_9] (rows=73049 width=102)
default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_date","d_year"]
<-Map 15 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_627]
+ SHUFFLE [RS_631]
PartitionCols:_col0
- Select Operator [SEL_626] (rows=550076554 width=7)
+ Select Operator [SEL_630] (rows=550076554 width=7)
Output:["_col0","_col1"]
- Filter Operator [FIL_625] (rows=550076554 width=7)
+ Filter Operator [FIL_629] (rows=550076554 width=7)
predicate:((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=7)
default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_item_sk"]
<-Reducer 22 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_624]
- Group By Operator [GBY_623] (rows=1 width=12)
+ BROADCAST [RS_628]
+ Group By Operator [GBY_627] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 21 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_622]
- Group By Operator [GBY_621] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_626]
+ Group By Operator [GBY_625] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_620] (rows=2609 width=4)
+ Select Operator [SEL_624] (rows=2609 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_618]
+ Please refer to the previous Select Operator [SEL_622]
<-Reducer 10 [SIMPLE_EDGE]
SHUFFLE [RS_245]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_579] (rows=3941102 width=122)
- Conds:RS_702._col0=RS_609._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_583] (rows=3941102 width=122)
+ Conds:RS_706._col0=RS_613._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
<-Map 8 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_609]
+ PARTITION_ONLY_SHUFFLE [RS_613]
PartitionCols:_col0
- Select Operator [SEL_606] (rows=50 width=12)
+ Select Operator [SEL_610] (rows=50 width=12)
Output:["_col0"]
- Filter Operator [FIL_605] (rows=50 width=12)
+ Filter Operator [FIL_609] (rows=50 width=12)
predicate:((d_moy = 1) and (d_year = 1999) and d_date_sk is not null)
TableScan [TS_3] (rows=73049 width=12)
default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year","d_moy"]
<-Map 44 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_702]
+ SHUFFLE [RS_706]
PartitionCols:_col0
- Select Operator [SEL_701] (rows=143930993 width=127)
+ Select Operator [SEL_705] (rows=143930993 width=127)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_700] (rows=143930993 width=127)
+ Filter Operator [FIL_704] (rows=143930993 width=127)
predicate:((ws_item_sk BETWEEN DynamicValue(RS_246_item_i_item_sk_min) AND DynamicValue(RS_246_item_i_item_sk_max) and in_bloom_filter(ws_item_sk, DynamicValue(RS_246_item_i_item_sk_bloom_filter))) and (ws_sold_date_sk BETWEEN DynamicValue(RS_243_date_dim_d_date_sk_min) AND DynamicValue(RS_243_date_dim_d_date_sk_max) and in_bloom_filter(ws_sold_date_sk, DynamicValue(RS_243_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_126] (rows=144002668 width=127)
default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_item_sk","ws_bill_customer_sk","ws_quantity","ws_list_price"]
<-Reducer 14 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_697]
- Group By Operator [GBY_696] (rows=1 width=12)
+ BROADCAST [RS_701]
+ Group By Operator [GBY_700] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_614]
- Group By Operator [GBY_612] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_618]
+ Group By Operator [GBY_616] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_610] (rows=50 width=4)
+ Select Operator [SEL_614] (rows=50 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_606]
+ Please refer to the previous Select Operator [SEL_610]
<-Reducer 20 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_699]
- Group By Operator [GBY_698] (rows=1 width=12)
+ BROADCAST [RS_703]
+ Group By Operator [GBY_702] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_643]
- Group By Operator [GBY_641] (rows=1 width=12)
+ SHUFFLE [RS_647]
+ Group By Operator [GBY_645] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_639] (rows=2235 width=4)
+ Select Operator [SEL_643] (rows=2235 width=4)
Output:["_col0"]
- Please refer to the previous Group By Operator [GBY_635]
+ Please refer to the previous Group By Operator [GBY_639]
<-Reducer 34 [SIMPLE_EDGE]
SHUFFLE [RS_249]
PartitionCols:_col0
@@ -302,29 +302,29 @@ Stage-0
Output:["_col0"]
Filter Operator [FIL_240] (rows=471875 width=228)
predicate:(_col3 > (0.95 * _col1))
- Merge Join Operator [MERGEJOIN_593] (rows=1415625 width=228)
+ Merge Join Operator [MERGEJOIN_597] (rows=1415625 width=228)
Conds:(Inner),Output:["_col1","_col2","_col3"]
<-Reducer 33 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_237]
- Merge Join Operator [MERGEJOIN_592] (rows=1 width=112)
+ Merge Join Operator [MERGEJOIN_596] (rows=1 width=112)
Conds:(Inner),Output:["_col1"]
<-Reducer 32 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_708]
- Select Operator [SEL_707] (rows=1 width=8)
- Filter Operator [FIL_706] (rows=1 width=8)
+ PARTITION_ONLY_SHUFFLE [RS_712]
+ Select Operator [SEL_711] (rows=1 width=8)
+ Filter Operator [FIL_710] (rows=1 width=8)
predicate:(sq_count_check(_col0) <= 1)
- Group By Operator [GBY_705] (rows=1 width=8)
+ Group By Operator [GBY_709] (rows=1 width=8)
Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_704] (rows=1 width=8)
- Group By Operator [GBY_703] (rows=1 width=8)
+ Select Operator [SEL_708] (rows=1 width=8)
+ Group By Operator [GBY_707] (rows=1 width=8)
Output:["_col0"],aggregations:["count(VALUE._col0)"]
<-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_676]
- Group By Operator [GBY_672] (rows=1 width=8)
+ PARTITION_ONLY_SHUFFLE [RS_680]
+ Group By Operator [GBY_676] (rows=1 width=8)
Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_668] (rows=11859 width=116)
+ Select Operator [SEL_672] (rows=11859 width=116)
Output:["_col0"]
- Group By Operator [GBY_665] (rows=11859 width=116)
+ Group By Operator [GBY_669] (rows=11859 width=116)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
<-Reducer 26 [SIMPLE_EDGE]
SHUFFLE [RS_51]
@@ -333,65 +333,65 @@ Stage-0
Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
Select Operator [SEL_48] (rows=18762463 width=4)
Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_575] (rows=18762463 width=4)
- Conds:RS_45._col1=RS_663._col0(Inner),Output:["_col2","_col3","_col6"]
+ Merge Join Operator [MERGEJOIN_579] (rows=18762463 width=4)
+ Conds:RS_45._col1=RS_667._col0(Inner),Output:["_col2","_col3","_col6"]
<-Map 41 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_663]
+ SHUFFLE [RS_667]
PartitionCols:_col0
- Select Operator [SEL_661] (rows=80000000 width=4)
+ Select Operator [SEL_665] (rows=80000000 width=4)
Output:["_col0"]
- Filter Operator [FIL_660] (rows=80000000 width=4)
+ Filter Operator [FIL_664] (rows=80000000 width=4)
predicate:c_customer_sk is not null
TableScan [TS_96] (rows=80000000 width=4)
default@customer,customer,Tbl:COMPLETE,Col:COMPLETE,Output:["c_customer_sk"]
<-Reducer 25 [SIMPLE_EDGE]
SHUFFLE [RS_45]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_574] (rows=18762463 width=0)
- Conds:RS_659._col0=RS_651._col0(Inner),Output:["_col1","_col2","_col3"]
+ Merge Join Operator [MERGEJOIN_578] (rows=18762463 width=0)
+ Conds:RS_663._col0=RS_655._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 36 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_651]
+ PARTITION_ONLY_SHUFFLE [RS_655]
PartitionCols:_col0
- Select Operator [SEL_650] (rows=2609 width=8)
+ Select Operator [SEL_654] (rows=2609 width=8)
Output:["_col0"]
- Filter Operator [FIL_649] (rows=2609 width=8)
+ Filter Operator [FIL_653] (rows=2609 width=8)
predicate:((d_year) IN (1999, 2000, 2001, 2002) and d_date_sk is not null)
TableScan [TS_36] (rows=73049 width=8)
default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_year"]
<-Map 24 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_659]
+ SHUFFLE [RS_663]
PartitionCols:_col0
- Select Operator [SEL_658] (rows=525327388 width=118)
+ Select Operator [SEL_662] (rows=525327388 width=118)
Output:["_col0","_col1","_col2","_col3"]
- Filter Operator [FIL_657] (rows=525327388 width=118)
+ Filter Operator [FIL_661] (rows=525327388 width=118)
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=118)
default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_customer_sk","ss_quantity","ss_sales_price"]
<-Reducer 37 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_656]
- Group By Operator [GBY_655] (rows=1 width=12)
+ BROADCAST [RS_660]
+ Group By Operator [GBY_659] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 36 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_654]
- Group By Operator [GBY_653] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_658]
+ Group By Operator [GBY_657] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_652] (rows=2609 width=4)
+ Select Operator [SEL_656] (rows=2609 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_650]
+ Please refer to the previous Select Operator [SEL_654]
<-Reducer 35 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_710]
- Group By Operator [GBY_709] (rows=1 width=112)
+ PARTITION_ONLY_SHUFFLE [RS_714]
+ Group By Operator [GBY_713] (rows=1 width=112)
Output:["_col0"],aggregations:["max(VALUE._col0)"]
<-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_677]
- Group By Operator [GBY_673] (rows=1 width=112)
+ PARTITION_ONLY_SHUFFLE [RS_681]
+ Group By Operator [GBY_677] (rows=1 width=112)
Output:["_col0"],aggregations:["max(_col1)"]
- Select Operator [SEL_669] (rows=11859 width=116)
+ Select Operator [SEL_673] (rows=11859 width=116)
Output:["_col1"]
- Please refer to the previous Group By Operator [GBY_665]
+ Please refer to the previous Group By Operator [GBY_669]
<-Reducer 43 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_717]
- Group By Operator [GBY_716] (rows=1415625 width=116)
+ PARTITION_ONLY_SHUFFLE [RS_721]
+ Group By Operator [GBY_720] (rows=1415625 width=116)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
<-Reducer 42 [SIMPLE_EDGE]
SHUFFLE [RS_231]
@@ -400,89 +400,89 @@ Stage-0
Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
Select Operator [SEL_228] (rows=550080312 width=114)
Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_586] (rows=550080312 width=114)
- Conds:RS_715._col0=RS_664._col0(Inner),Output:["_col1","_col2","_col3"]
+ Merge Join Operator [MERGEJOIN_590] (rows=550080312 width=114)
+ Conds:RS_719._col0=RS_668._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 41 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_664]
+ SHUFFLE [RS_668]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_661]
+ Please refer to the previous Select Operator [SEL_665]
<-Map 45 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_715]
+ SHUFFLE [RS_719]
PartitionCols:_col0
- Select Operator [SEL_714] (rows=550080312 width=114)
+ Select Operator [SEL_718] (rows=550080312 width=114)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_713] (rows=550080312 width=114)
+ Filter Operator [FIL_717] (rows=550080312 width=114)
predicate:((ss_customer_sk BETWEEN DynamicValue(RS_248_web_sales_ws_bill_customer_sk_min) AND DynamicValue(RS_248_web_sales_ws_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_248_web_sales_ws_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null)
TableScan [TS_219] (rows=575995635 width=114)
default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
<-Reducer 13 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_712]
- Group By Operator [GBY_711] (rows=1 width=12)
+ BROADCAST [RS_716]
+ Group By Operator [GBY_715] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Reducer 11 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_562]
- Group By Operator [GBY_561] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_570]
+ Group By Operator [GBY_569] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_560] (rows=155 width=0)
+ Select Operator [SEL_568] (rows=155 width=0)
Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_588]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_592]
<-Reducer 4 [CONTAINS]
- Reduce Output Operator [RS_599]
- Group By Operator [GBY_598] (rows=1 width=112)
+ Reduce Output Operator [RS_603]
+ Group By Operator [GBY_602] (rows=1 width=112)
Output:["_col0"],aggregations:["sum(_col0)"]
- Select Operator [SEL_596] (rows=1 width=112)
+ Select Operator [SEL_600] (rows=1 width=112)
Output:["_col0"]
- Merge Join Operator [MERGEJOIN_595] (rows=1 width=116)
+ Merge Join Operator [MERGEJOIN_599] (rows=1 width=116)
Conds:RS_122._col1=RS_123._col0(Inner),Output:["_col3","_col4"]
<-Reducer 3 [SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_122]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_587] (rows=304 width=0)
- Conds:RS_119._col2=RS_636._col0(Inner),Output:["_col1","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_591] (rows=304 width=0)
+ Conds:RS_119._col2=RS_640._col0(Inner),Output:["_col1","_col3","_col4"]
<-Reducer 18 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_636]
+ SHUFFLE [RS_640]
PartitionCols:_col0
- Please refer to the previous Group By Operator [GBY_635]
+ Please refer to the previous Group By Operator [GBY_639]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_119]
PartitionCols:_col2
- Merge Join Operator [MERGEJOIN_571] (rows=7751875 width=101)
- Conds:RS_648._col0=RS_607._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
+ Merge Join Operator [MERGEJOIN_575] (rows=7751875 width=101)
+ Conds:RS_652._col0=RS_611._col0(Inner),Output:["_col1","_col2","_col3","_col4"]
<-Map 8 [SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_607]
+ PARTITION_ONLY_SHUFFLE [RS_611]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_606]
+ Please refer to the previous Select Operator [SEL_610]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_648]
+ SHUFFLE [RS_652]
PartitionCols:_col0
- Select Operator [SEL_647] (rows=285117831 width=127)
+ Select Operator [SEL_651] (rows=285117831 width=127)
Output:["_col0","_col1","_col2","_col3","_col4"]
- Filter Operator [FIL_646] (rows=285117831 width=127)
+ Filter Operator [FIL_650] (rows=285117831 width=127)
predicate:((cs_item_sk BETWEEN DynamicValue(RS_120_item_i_item_sk_min) AND DynamicValue(RS_120_item_i_item_sk_max) and in_bloom_filter(cs_item_sk, DynamicValue(RS_120_item_i_item_sk_bloom_filter))) and (cs_sold_date_sk BETWEEN DynamicValue(RS_117_date_dim_d_date_sk_min) AND DynamicValue(RS_117_date_dim_d_date_sk_max) and in_bloom_filter(cs_sold_date_sk, DynamicValue(RS_117_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=127)
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_bill_customer_sk","cs_item_sk","cs_quantity","cs_list_price"]
<-Reducer 19 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_645]
- Group By Operator [GBY_644] (rows=1 width=12)
+ BROADCAST [RS_649]
+ Group By Operator [GBY_648] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Reducer 18 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_642]
- Group By Operator [GBY_640] (rows=1 width=12)
+ SHUFFLE [RS_646]
+ Group By Operator [GBY_644] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_637] (rows=2235 width=4)
+ Select Operator [SEL_641] (rows=2235 width=4)
Output:["_col0"]
- Please refer to the previous Group By Operator [GBY_635]
+ Please refer to the previous Group By Operator [GBY_639]
<-Reducer 9 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_616]
- Group By Operator [GBY_615] (rows=1 width=12)
+ BROADCAST [RS_620]
+ Group By Operator [GBY_619] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 8 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_613]
- Group By Operator [GBY_611] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_617]
+ Group By Operator [GBY_615] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_608] (rows=50 width=4)
+ Select Operator [SEL_612] (rows=50 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_606]
+ Please refer to the previous Select Operator [SEL_610]
<-Reducer 30 [SIMPLE_EDGE]
SHUFFLE [RS_123]
PartitionCols:_col0
@@ -490,43 +490,43 @@ Stage-0
Output:["_col0"]
Filter Operator [FIL_114] (rows=471875 width=228)
predicate:(_col3 > (0.95 * _col1))
- Merge Join Operator [MERGEJOIN_590] (rows=1415625 width=228)
+ Merge Join Operator [MERGEJOIN_594] (rows=1415625 width=228)
Conds:(Inner),Output:["_col1","_col2","_col3"]
<-Reducer 29 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_111]
- Merge Join Operator [MERGEJOIN_589] (rows=1 width=112)
+ Merge Join Operator [MERGEJOIN_593] (rows=1 width=112)
Conds:(Inner),Output:["_col1"]
<-Reducer 28 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_683]
- Select Operator [SEL_682] (rows=1 width=8)
- Filter Operator [FIL_681] (rows=1 width=8)
+ PARTITION_ONLY_SHUFFLE [RS_687]
+ Select Operator [SEL_686] (rows=1 width=8)
+ Filter Operator [FIL_685] (rows=1 width=8)
predicate:(sq_count_check(_col0) <= 1)
- Group By Operator [GBY_680] (rows=1 width=8)
+ Group By Operator [GBY_684] (rows=1 width=8)
Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_679] (rows=1 width=8)
- Group By Operator [GBY_678] (rows=1 width=8)
+ Select Operator [SEL_683] (rows=1 width=8)
+ Group By Operator [GBY_682] (rows=1 width=8)
Output:["_col0"],aggregations:["count(VALUE._col0)"]
<-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_674]
- Group By Operator [GBY_670] (rows=1 width=8)
+ PARTITION_ONLY_SHUFFLE [RS_678]
+ Group By Operator [GBY_674] (rows=1 width=8)
Output:["_col0"],aggregations:["count(_col0)"]
- Select Operator [SEL_666] (rows=11859 width=116)
+ Select Operator [SEL_670] (rows=11859 width=116)
Output:["_col0"]
- Please refer to the previous Group By Operator [GBY_665]
+ Please refer to the previous Group By Operator [GBY_669]
<-Reducer 31 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_685]
- Group By Operator [GBY_684] (rows=1 width=112)
+ PARTITION_ONLY_SHUFFLE [RS_689]
+ Group By Operator [GBY_688] (rows=1 width=112)
Output:["_col0"],aggregations:["max(VALUE._col0)"]
<-Reducer 27 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_675]
- Group By Operator [GBY_671] (rows=1 width=112)
+ PARTITION_ONLY_SHUFFLE [RS_679]
+ Group By Operator [GBY_675] (rows=1 width=112)
Output:["_col0"],aggregations:["max(_col1)"]
- Select Operator [SEL_667] (rows=11859 width=116)
+ Select Operator [SEL_671] (rows=11859 width=116)
Output:["_col1"]
- Please refer to the previous Group By Operator [GBY_665]
+ Please refer to the previous Group By Operator [GBY_669]
<-Reducer 40 [CUSTOM_SIMPLE_EDGE] vectorized
- PARTITION_ONLY_SHUFFLE [RS_692]
- Group By Operator [GBY_691] (rows=1415625 width=116)
+ PARTITION_ONLY_SHUFFLE [RS_696]
+ Group By Operator [GBY_695] (rows=1415625 width=116)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
<-Reducer 39 [SIMPLE_EDGE]
SHUFFLE [RS_105]
@@ -535,30 +535,30 @@ Stage-0
Output:["_col0","_col1"],aggregations:["sum(_col1)"],keys:_col0
Select Operator [SEL_102] (rows=550080312 width=114)
Output:["_col0","_col1"]
- Merge Join Operator [MERGEJOIN_578] (rows=550080312 width=114)
- Conds:RS_690._col0=RS_662._col0(Inner),Output:["_col1","_col2","_col3"]
+ Merge Join Operator [MERGEJOIN_582] (rows=550080312 width=114)
+ Conds:RS_694._col0=RS_666._col0(Inner),Output:["_col1","_col2","_col3"]
<-Map 41 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_662]
+ SHUFFLE [RS_666]
PartitionCols:_col0
- Please refer to the previous Select Operator [SEL_661]
+ Please refer to the previous Select Operator [SEL_665]
<-Map 38 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_690]
+ SHUFFLE [RS_694]
PartitionCols:_col0
- Select Operator [SEL_689] (rows=550080312 width=114)
+ Select Operator [SEL_693] (rows=550080312 width=114)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_688] (rows=550080312 width=114)
+ Filter Operator [FIL_692] (rows=550080312 width=114)
predicate:((ss_customer_sk BETWEEN DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_min) AND DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_max) and in_bloom_filter(ss_customer_sk, DynamicValue(RS_122_catalog_sales_cs_bill_customer_sk_bloom_filter))) and ss_customer_sk is not null)
TableScan [TS_93] (rows=575995635 width=114)
default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_customer_sk","ss_quantity","ss_sales_price"]
<-Reducer 7 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_687]
- Group By Operator [GBY_686] (rows=1 width=12)
+ 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)"]
<-Reducer 3 [CUSTOM_SIMPLE_EDGE]
- PARTITION_ONLY_SHUFFLE [RS_458]
- Group By Operator [GBY_457] (rows=1 width=12)
+ PARTITION_ONLY_SHUFFLE [RS_464]
+ Group By Operator [GBY_463] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_456] (rows=304 width=0)
+ Select Operator [SEL_462] (rows=304 width=0)
Output:["_col0"]
- Please refer to the previous Merge Join Operator [MERGEJOIN_587]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_591]