You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2014/10/11 00:17:25 UTC
svn commit: r1630998 - in /hive/branches/spark:
itests/src/test/resources/testconfiguration.properties
ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out
ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out
Author: xuefu
Date: Fri Oct 10 22:17:25 2014
New Revision: 1630998
URL: http://svn.apache.org/r1630998
Log:
HIVE-8425: enable vectorized_mapjoin.q,vectorized_nested_mapjoin.q [Sparch Branch] (Chinna via Xuefu)
Added:
hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out
hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out
Modified:
hive/branches/spark/itests/src/test/resources/testconfiguration.properties
Modified: hive/branches/spark/itests/src/test/resources/testconfiguration.properties
URL: http://svn.apache.org/viewvc/hive/branches/spark/itests/src/test/resources/testconfiguration.properties?rev=1630998&r1=1630997&r2=1630998&view=diff
==============================================================================
--- hive/branches/spark/itests/src/test/resources/testconfiguration.properties (original)
+++ hive/branches/spark/itests/src/test/resources/testconfiguration.properties Fri Oct 10 22:17:25 2014
@@ -621,6 +621,8 @@ spark.query.files=add_part_multiple.q \
vectorization_part_project.q \
vectorized_timestamp_funcs.q \
vectorized_ptf.q \
+ vectorized_mapjoin.q \
+ vectorized_nested_mapjoin.q \
windowing.q \
subquery_exists.q \
subquery_in.q \
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out?rev=1630998&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_mapjoin.q.out Fri Oct 10 22:17:25 2014
@@ -0,0 +1,96 @@
+PREHOOK: query: EXPLAIN SELECT COUNT(t1.cint), MAX(t2.cint), MIN(t1.cint), AVG(t1.cint+t2.cint)
+ FROM alltypesorc t1
+ JOIN alltypesorc t2 ON t1.cint = t2.cint
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT COUNT(t1.cint), MAX(t2.cint), MIN(t1.cint), AVG(t1.cint+t2.cint)
+ FROM alltypesorc t1
+ JOIN alltypesorc t2 ON t1.cint = t2.cint
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT), Map 4 (GROUP PARTITION-LEVEL SORT)
+ Reducer 3 <- Reducer 2 (GROUP)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: t2
+ Filter Operator
+ predicate: cint is not null (type: boolean)
+ Reduce Output Operator
+ key expressions: cint (type: int)
+ sort order: +
+ Map-reduce partition columns: cint (type: int)
+ Execution mode: vectorized
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Filter Operator
+ predicate: cint is not null (type: boolean)
+ Reduce Output Operator
+ key expressions: cint (type: int)
+ sort order: +
+ Map-reduce partition columns: cint (type: int)
+ Execution mode: vectorized
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {KEY.reducesinkkey0}
+ outputColumnNames: _col2, _col17
+ Select Operator
+ expressions: _col2 (type: int), _col17 (type: int)
+ outputColumnNames: _col2, _col17
+ Group By Operator
+ aggregations: count(_col2), max(_col17), min(_col2), avg((_col2 + _col17))
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Reduce Output Operator
+ sort order:
+ value expressions: _col0 (type: bigint), _col1 (type: int), _col2 (type: int), _col3 (type: struct<count:bigint,sum:double,input:int>)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0), max(VALUE._col1), min(VALUE._col2), avg(VALUE._col3)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions: _col0 (type: bigint), _col1 (type: int), _col2 (type: int), _col3 (type: double)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT COUNT(t1.cint), MAX(t2.cint), MIN(t1.cint), AVG(t1.cint+t2.cint)
+ FROM alltypesorc t1
+ JOIN alltypesorc t2 ON t1.cint = t2.cint
+PREHOOK: type: QUERY
+PREHOOK: Input: default@alltypesorc
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT COUNT(t1.cint), MAX(t2.cint), MIN(t1.cint), AVG(t1.cint+t2.cint)
+ FROM alltypesorc t1
+ JOIN alltypesorc t2 ON t1.cint = t2.cint
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@alltypesorc
+#### A masked pattern was here ####
+3152013 1073680599 -1073279343 9.375396162525452E8
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out?rev=1630998&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_nested_mapjoin.q.out Fri Oct 10 22:17:25 2014
@@ -0,0 +1,121 @@
+PREHOOK: query: explain select sum(t1.td) from (select v1.csmallint as tsi, v1.cdouble as td from alltypesorc v1, alltypesorc v2 where v1.ctinyint=v2.ctinyint) t1 join alltypesorc v3 on t1.tsi=v3.csmallint
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select sum(t1.td) from (select v1.csmallint as tsi, v1.cdouble as td from alltypesorc v1, alltypesorc v2 where v1.ctinyint=v2.ctinyint) t1 join alltypesorc v3 on t1.tsi=v3.csmallint
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT), Reducer 5 (GROUP PARTITION-LEVEL SORT)
+ Reducer 3 <- Reducer 2 (GROUP)
+ Reducer 5 <- Map 4 (GROUP PARTITION-LEVEL SORT), Map 6 (GROUP PARTITION-LEVEL SORT)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: v3
+ Filter Operator
+ predicate: csmallint is not null (type: boolean)
+ Reduce Output Operator
+ key expressions: csmallint (type: smallint)
+ sort order: +
+ Map-reduce partition columns: csmallint (type: smallint)
+ Execution mode: vectorized
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: v1
+ Filter Operator
+ predicate: (ctinyint is not null and csmallint is not null) (type: boolean)
+ Reduce Output Operator
+ key expressions: ctinyint (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: ctinyint (type: tinyint)
+ value expressions: csmallint (type: smallint), cdouble (type: double)
+ Execution mode: vectorized
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: v2
+ Filter Operator
+ predicate: ctinyint is not null (type: boolean)
+ Reduce Output Operator
+ key expressions: ctinyint (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: ctinyint (type: tinyint)
+ Execution mode: vectorized
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ outputColumnNames: _col1
+ Select Operator
+ expressions: _col1 (type: double)
+ outputColumnNames: _col1
+ Group By Operator
+ aggregations: sum(_col1)
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ value expressions: _col0 (type: double)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions: _col0 (type: double)
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized
+ Reducer 5
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col4}
+ 1 {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col1, _col5, _col15
+ Filter Operator
+ predicate: (_col0 = _col15) (type: boolean)
+ Select Operator
+ expressions: _col1 (type: smallint), _col5 (type: double)
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions: _col0 (type: smallint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: smallint)
+ value expressions: _col1 (type: double)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select sum(t1.td) from (select v1.csmallint as tsi, v1.cdouble as td from alltypesorc v1, alltypesorc v2 where v1.ctinyint=v2.ctinyint) t1 join alltypesorc v3 on t1.tsi=v3.csmallint
+PREHOOK: type: QUERY
+PREHOOK: Input: default@alltypesorc
+#### A masked pattern was here ####
+POSTHOOK: query: select sum(t1.td) from (select v1.csmallint as tsi, v1.cdouble as td from alltypesorc v1, alltypesorc v2 where v1.ctinyint=v2.ctinyint) t1 join alltypesorc v3 on t1.tsi=v3.csmallint
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@alltypesorc
+#### A masked pattern was here ####
+6.065190932485957E11