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 2015/08/02 04:49:23 UTC
hive git commit: HIVE-10855: Make HIVE-10568 work with Spark [Spark
Branch] (Rui reviewed by Xuefu)
Repository: hive
Updated Branches:
refs/heads/branch-1 399168ccf -> b72766d5f
HIVE-10855: Make HIVE-10568 work with Spark [Spark Branch] (Rui reviewed by Xuefu)
Conflicts:
ql/src/test/results/clientpositive/spark/auto_join18.q.out
ql/src/test/results/clientpositive/spark/groupby_position.q.out
ql/src/test/results/clientpositive/spark/join18.q.out
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/b72766d5
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/b72766d5
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/b72766d5
Branch: refs/heads/branch-1
Commit: b72766d5f0a0bc34870a6bee9267e49c7a757c87
Parents: 399168c
Author: Rui Li <ru...@intel.com>
Authored: Fri Jun 12 09:31:18 2015 +0800
Committer: xzhang <xz...@xzdt>
Committed: Sat Aug 1 19:47:09 2015 -0700
----------------------------------------------------------------------
.../hadoop/hive/ql/parse/CalcitePlanner.java | 2 +-
.../clientpositive/spark/auto_join32.q.out | 24 ++++++++-------
.../clientpositive/spark/limit_pushdown.q.out | 31 +++++++++++---------
.../spark/vector_count_distinct.q.out | 30 +++++++++++++++----
4 files changed, 56 insertions(+), 31 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/b72766d5/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
index c5b0afe..130d525 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
@@ -920,7 +920,7 @@ public class CalcitePlanner extends SemanticAnalyzer {
//0. Distinct aggregate rewrite
// Run this optimization early, since it is expanding the operator pipeline.
- if (conf.getVar(HiveConf.ConfVars.HIVE_EXECUTION_ENGINE).equals("tez") &&
+ if (!conf.getVar(HiveConf.ConfVars.HIVE_EXECUTION_ENGINE).equals("mr") &&
conf.getBoolVar(HiveConf.ConfVars.HIVEOPTIMIZEDISTINCTREWRITE)) {
// Its not clear, if this rewrite is always performant on MR, since extra map phase
// introduced for 2nd MR job may offset gains of this multi-stage aggregation.
http://git-wip-us.apache.org/repos/asf/hive/blob/b72766d5/ql/src/test/results/clientpositive/spark/auto_join32.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join32.q.out b/ql/src/test/results/clientpositive/spark/auto_join32.q.out
index e26e4a2..316792b 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join32.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join32.q.out
@@ -450,10 +450,9 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Group By Operator
- aggregations: count(DISTINCT _col1)
keys: _col0 (type: string), _col1 (type: string)
mode: hash
- outputColumnNames: _col0, _col1, _col2
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
@@ -463,18 +462,23 @@ STAGE PLANS:
Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(DISTINCT KEY._col1:0._col0)
- keys: KEY._col0 (type: string)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
+ Group By Operator
+ aggregations: count(_col1)
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/b72766d5/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out b/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out
index 1efa9e7..4a0306d 100644
--- a/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out
+++ b/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out
@@ -476,35 +476,38 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: count(DISTINCT _col1)
keys: _col0 (type: tinyint), _col1 (type: double)
mode: hash
- outputColumnNames: _col0, _col1, _col2
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: double)
sort order: ++
Map-reduce partition columns: _col0 (type: tinyint)
Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.3
Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(DISTINCT KEY._col1:0._col0)
- keys: KEY._col0 (type: tinyint)
+ keys: KEY._col0 (type: tinyint), KEY._col1 (type: double)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 20
- Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Group By Operator
+ aggregations: count(_col1)
+ keys: _col0 (type: tinyint)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3072 Data size: 94309 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
Statistics: Num rows: 20 Data size: 600 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
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 600 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
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/b72766d5/ql/src/test/results/clientpositive/spark/vector_count_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vector_count_distinct.q.out b/ql/src/test/results/clientpositive/spark/vector_count_distinct.q.out
index fecfe0a..aaea86d 100644
--- a/ql/src/test/results/clientpositive/spark/vector_count_distinct.q.out
+++ b/ql/src/test/results/clientpositive/spark/vector_count_distinct.q.out
@@ -1247,7 +1247,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (GROUP, 2)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1260,30 +1261,47 @@ STAGE PLANS:
outputColumnNames: _col0
Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: count(DISTINCT _col0)
keys: _col0 (type: int)
mode: hash
- outputColumnNames: _col0, _col1
+ outputColumnNames: _col0
Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
+ Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(DISTINCT KEY._col0:0._col0)
+ keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 1752000 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(_col0)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 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
+ Execution mode: vectorized
Stage: Stage-0
Fetch Operator