kgyrtkirk commented on a change in pull request #1553:
URL: https://github.com/apache/hive/pull/1553#discussion_r503843227
##########
File path: ql/src/test/results/clientpositive/perf/tez/constraints/query2.q.out
##########
@@ -128,46 +128,104 @@ Plan optimized by CBO.
Vertex dependency in root stage
Map 1 <- Union 2 (CONTAINS)
-Map 9 <- Union 2 (CONTAINS)
-Reducer 3 <- Map 10 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE)
+Map 13 <- Union 14 (CONTAINS)
+Map 15 <- Union 14 (CONTAINS)
+Map 8 <- Union 2 (CONTAINS)
+Reducer 10 <- Map 9 (SIMPLE_EDGE), Union 14 (SIMPLE_EDGE)
+Reducer 11 <- Reducer 10 (SIMPLE_EDGE)
+Reducer 12 <- Map 9 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE)
+Reducer 3 <- Map 9 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
-Reducer 5 <- Map 10 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
-Reducer 6 <- Reducer 5 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+Reducer 5 <- Map 9 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+Reducer 6 <- Reducer 12 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
-Reducer 8 <- Map 10 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_173]
- Select Operator [SEL_172] (rows=12881 width=788)
+ File Output Operator [FS_187]
+ Select Operator [SEL_186] (rows=12881 width=788)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
<-Reducer 6 [SIMPLE_EDGE]
SHUFFLE [RS_57]
Select Operator [SEL_56] (rows=12881 width=788)
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
Merge Join Operator [MERGEJOIN_146] (rows=12881 width=1572)
Conds:RS_53.(_col0 -
53)=RS_54._col0(Inner),Output:["_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"]
+ <-Reducer 12 [SIMPLE_EDGE]
+ SHUFFLE [RS_54]
+ PartitionCols:_col0
+ Merge Join Operator [MERGEJOIN_145] (rows=652 width=788)
+
Conds:RS_185._col0=RS_181._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
+ <-Map 9 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_181]
+ PartitionCols:_col0
+ Select Operator [SEL_177] (rows=652 width=4)
+ Output:["_col0"]
+ Filter Operator [FIL_173] (rows=652 width=8)
+ predicate:((d_year = 2001) and d_week_seq is not
null)
+ TableScan [TS_8] (rows=73049 width=99)
+
default@date_dim,date_dim,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_week_seq","d_day_name","d_year"]
+ <-Reducer 11 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_185]
+ PartitionCols:_col0
+ Group By Operator [GBY_184] (rows=13152 width=788)
+
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"],keys:KEY._col0
+ <-Reducer 10 [SIMPLE_EDGE]
+ SHUFFLE [RS_40]
+ PartitionCols:_col0
+ Group By Operator [GBY_39] (rows=3182784 width=788)
+
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"],aggregations:["sum(_col1)","sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)"],keys:_col0
+ Select Operator [SEL_37] (rows=430516591 width=143)
+
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"]
+ Merge Join Operator [MERGEJOIN_144]
(rows=430516591 width=143)
+ Conds:Union
14._col0=RS_180._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10"]
+ <-Map 9 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_180]
+ PartitionCols:_col0
+ Select Operator [SEL_176] (rows=73049
width=36)
+
Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"]
+ Filter Operator [FIL_172] (rows=73049
width=99)
+ predicate:d_week_seq is not null
+ Please refer to the previous TableScan
[TS_8]
+ <-Union 14 [SIMPLE_EDGE]
+ <-Map 13 [CONTAINS] vectorized
+ Reduce Output Operator [RS_193]
+ PartitionCols:_col0
+ Select Operator [SEL_192] (rows=143966864
width=115)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_191]
(rows=143966864 width=115)
+ predicate:ws_sold_date_sk is not null
+ TableScan [TS_157] (rows=144002668
width=115)
+
default@web_sales,web_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ws_sold_date_sk","ws_ext_sales_price"]
+ <-Map 15 [CONTAINS] vectorized
+ Reduce Output Operator [RS_196]
+ PartitionCols:_col0
+ Select Operator [SEL_195] (rows=286549727
width=115)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_194]
(rows=286549727 width=115)
+ predicate:cs_sold_date_sk is not null
+ TableScan [TS_162] (rows=287989836
width=115)
+
default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["cs_sold_date_sk","cs_ext_sales_price"]
Review comment:
> we should understand why we are regressing in these cases
absolutely; it's important to not loose existing stuff!...and in fact the
downstream patch was not fixing all these regressions; so I took the approach
of removing ts merge from this patch - then I'll add downstream merge/etc
changes next - and after that we'll see what when ts-merge is enabled for all
optimizations.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
