You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by pr...@apache.org on 2014/09/28 07:58:00 UTC
svn commit: r1628044 - in /hive/trunk/ql/src:
java/org/apache/hadoop/hive/ql/optimizer/ test/queries/clientpositive/
test/results/clientpositive/ test/results/clientpositive/tez/
Author: prasanthj
Date: Sun Sep 28 05:58:00 2014
New Revision: 1628044
URL: http://svn.apache.org/r1628044
Log:
HIVE-8162: Dynamic sort optimization propagates additional columns even in the absence of order by (Prasanth J reviewed by Vikram Dixit)
Modified:
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java
hive/trunk/ql/src/test/queries/clientpositive/dynpart_sort_opt_vectorization.q
hive/trunk/ql/src/test/queries/clientpositive/dynpart_sort_optimization.q
hive/trunk/ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out
hive/trunk/ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out
hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out
hive/trunk/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out
hive/trunk/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out
Modified: hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java?rev=1628044&r1=1628043&r2=1628044&view=diff
==============================================================================
--- hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java (original)
+++ hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java Sun Sep 28 05:58:00 2014
@@ -395,7 +395,8 @@ public class SortedDynPartitionOptimizer
// should honor the ordering of records provided by ORDER BY in SELECT statement
ReduceSinkOperator parentRSOp = OperatorUtils.findSingleOperatorUpstream(parent,
ReduceSinkOperator.class);
- if (parentRSOp != null) {
+ boolean isOrderBy = parseCtx.getQB().getParseInfo().getDestToOrderBy().size() > 0;
+ if (parentRSOp != null && isOrderBy) {
String parentRSOpOrder = parentRSOp.getConf().getOrder();
if (parentRSOpOrder != null && !parentRSOpOrder.isEmpty() && sortPositions.isEmpty()) {
newKeyCols.addAll(parentRSOp.getConf().getKeyCols());
Modified: hive/trunk/ql/src/test/queries/clientpositive/dynpart_sort_opt_vectorization.q
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/queries/clientpositive/dynpart_sort_opt_vectorization.q?rev=1628044&r1=1628043&r2=1628044&view=diff
==============================================================================
--- hive/trunk/ql/src/test/queries/clientpositive/dynpart_sort_opt_vectorization.q (original)
+++ hive/trunk/ql/src/test/queries/clientpositive/dynpart_sort_opt_vectorization.q Sun Sep 28 05:58:00 2014
@@ -108,6 +108,13 @@ set hive.optimize.sort.dynamic.partition
explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by i;
set hive.optimize.sort.dynamic.partition=true;
explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by i;
+explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from (select * from over1k_orc order by i limit 10) tmp where t is null or t=27;
+
+set hive.optimize.sort.dynamic.partition=false;
+explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t;
+set hive.optimize.sort.dynamic.partition=true;
+-- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t;
set hive.optimize.sort.dynamic.partition=false;
insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by i;
Modified: hive/trunk/ql/src/test/queries/clientpositive/dynpart_sort_optimization.q
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/queries/clientpositive/dynpart_sort_optimization.q?rev=1628044&r1=1628043&r2=1628044&view=diff
==============================================================================
--- hive/trunk/ql/src/test/queries/clientpositive/dynpart_sort_optimization.q (original)
+++ hive/trunk/ql/src/test/queries/clientpositive/dynpart_sort_optimization.q Sun Sep 28 05:58:00 2014
@@ -102,6 +102,13 @@ set hive.optimize.sort.dynamic.partition
explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i;
set hive.optimize.sort.dynamic.partition=true;
explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i;
+explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from (select * from over1k order by i limit 10) tmp where t is null or t=27;
+
+set hive.optimize.sort.dynamic.partition=false;
+explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t;
+set hive.optimize.sort.dynamic.partition=true;
+-- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t;
set hive.optimize.sort.dynamic.partition=false;
insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i;
Modified: hive/trunk/ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out?rev=1628044&r1=1628043&r2=1628044&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/dynpart_sort_opt_vectorization.q.out Sun Sep 28 05:58:00 2014
@@ -1408,6 +1408,254 @@ STAGE PLANS:
Stage: Stage-3
Stats-Aggr Operator
+PREHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from (select * from over1k_orc order by i limit 10) tmp where t is null or t=27
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from (select * from over1k_orc order by i limit 10) tmp where t is null or t=27
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: over1k_orc
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: int)
+ sort order: +
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 is null or (_col0 = 27)) (type: boolean)
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col4 (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: _col4 (type: tinyint)
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: over1k_orc
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (t is null or (t = 27)) (type: boolean)
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ outputColumnNames: si, i, b, f, t
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ sort order: +++++
+ Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+PREHOOK: type: QUERY
+POSTHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: over1k_orc
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (t is null or (t = 27)) (type: boolean)
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ outputColumnNames: si, i, b, f, t
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ sort order: +++++
+ Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col4 (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: _col4 (type: tinyint)
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
PREHOOK: query: insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by i
PREHOOK: type: QUERY
PREHOOK: Input: default@over1k_orc
Modified: hive/trunk/ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out?rev=1628044&r1=1628043&r2=1628044&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/dynpart_sort_optimization.q.out Sun Sep 28 05:58:00 2014
@@ -1311,6 +1311,251 @@ STAGE PLANS:
Stage: Stage-3
Stats-Aggr Operator
+PREHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from (select * from over1k order by i limit 10) tmp where t is null or t=27
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from (select * from over1k order by i limit 10) tmp where t is null or t=27
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: over1k
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: int)
+ sort order: +
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float)
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 is null or (_col0 = 27)) (type: boolean)
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col4 (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: _col4 (type: tinyint)
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: over1k
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (t is null or (t = 27)) (type: boolean)
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ outputColumnNames: si, i, b, f, t
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ sort order: +++++
+ Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t
+PREHOOK: type: QUERY
+POSTHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: over1k
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (t is null or (t = 27)) (type: boolean)
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ outputColumnNames: si, i, b, f, t
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ sort order: +++++
+ Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col4 (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: _col4 (type: tinyint)
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
PREHOOK: query: insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i
PREHOOK: type: QUERY
PREHOOK: Input: default@over1k
Modified: hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out?rev=1628044&r1=1628043&r2=1628044&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out Sun Sep 28 05:58:00 2014
@@ -231,7 +231,7 @@ Partition Parameters:
numFiles 1
numRows 0
rawDataSize 0
- totalSize 1342
+ totalSize 1381
#### A masked pattern was here ####
# Storage Information
@@ -302,7 +302,7 @@ Partition Parameters:
numFiles 1
numRows 0
rawDataSize 0
- totalSize 719
+ totalSize 722
#### A masked pattern was here ####
# Storage Information
@@ -344,7 +344,7 @@ Partition Parameters:
numFiles 1
numRows 0
rawDataSize 0
- totalSize 722
+ totalSize 741
#### A masked pattern was here ####
# Storage Information
@@ -523,8 +523,8 @@ STAGE PLANS:
Map Operator Tree:
TableScan
Reduce Output Operator
- key expressions: _col2 (type: string), _col0 (type: string)
- sort order: ++
+ key expressions: _col2 (type: string)
+ sort order: +
Map-reduce partition columns: _col2 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
@@ -681,7 +681,7 @@ Partition Parameters:
numFiles 1
numRows 0
rawDataSize 0
- totalSize 1341
+ totalSize 1346
#### A masked pattern was here ####
# Storage Information
Modified: hive/trunk/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out?rev=1628044&r1=1628043&r2=1628044&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out Sun Sep 28 05:58:00 2014
@@ -1463,6 +1463,266 @@ STAGE PLANS:
Stage: Stage-3
Stats-Aggr Operator
+PREHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from (select * from over1k_orc order by i limit 10) tmp where t is null or t=27
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from (select * from over1k_orc order by i limit 10) tmp where t is null or t=27
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: over1k_orc
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: int)
+ sort order: +
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float)
+ Execution mode: vectorized
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 is null or (_col0 = 27)) (type: boolean)
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col4 (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: _col4 (type: tinyint)
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Execution mode: vectorized
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: over1k_orc
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (t is null or (t = 27)) (type: boolean)
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ outputColumnNames: si, i, b, f, t
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ sort order: +++++
+ Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+PREHOOK: type: QUERY
+POSTHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: over1k_orc
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (t is null or (t = 27)) (type: boolean)
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ outputColumnNames: si, i, b, f, t
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ sort order: +++++
+ Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col4 (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: _col4 (type: tinyint)
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Execution mode: vectorized
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2_orc
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
PREHOOK: query: insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 order by i
PREHOOK: type: QUERY
PREHOOK: Input: default@over1k_orc
Modified: hive/trunk/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out?rev=1628044&r1=1628043&r2=1628044&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out Sun Sep 28 05:58:00 2014
@@ -1381,6 +1381,261 @@ STAGE PLANS:
Stage: Stage-3
Stats-Aggr Operator
+PREHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from (select * from over1k order by i limit 10) tmp where t is null or t=27
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from (select * from over1k order by i limit 10) tmp where t is null or t=27
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: over1k
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: int)
+ sort order: +
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float)
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 is null or (_col0 = 27)) (type: boolean)
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col4 (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: _col4 (type: tinyint)
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: over1k
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (t is null or (t = 27)) (type: boolean)
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ outputColumnNames: si, i, b, f, t
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ sort order: +++++
+ Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t
+PREHOOK: type: QUERY
+POSTHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: over1k
+ Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (t is null or (t = 27)) (type: boolean)
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ outputColumnNames: si, i, b, f, t
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ sort order: +++++
+ Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col4 (type: tinyint)
+ sort order: +
+ Map-reduce partition columns: _col4 (type: tinyint)
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds foo
+ t
+ replace: true
+ 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
+ name: default.over1k_part2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
PREHOOK: query: insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i
PREHOOK: type: QUERY
PREHOOK: Input: default@over1k