You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by vg...@apache.org on 2019/09/23 18:15:49 UTC
[hive] branch master updated: HIVE-22145: Avoid optimizations for
analyze compute statistics (Vineet Garg, reviewed by Ashutosh Chauhan)
This is an automated email from the ASF dual-hosted git repository.
vgarg pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git
The following commit(s) were added to refs/heads/master by this push:
new 75b0b0e HIVE-22145: Avoid optimizations for analyze compute statistics (Vineet Garg, reviewed by Ashutosh Chauhan)
75b0b0e is described below
commit 75b0b0eaa7eba17bb5bb1ee5ba81eb0536ba754e
Author: Vineet Garg <vg...@apache.org>
AuthorDate: Mon Sep 23 11:15:20 2019 -0700
HIVE-22145: Avoid optimizations for analyze compute statistics (Vineet Garg, reviewed by Ashutosh Chauhan)
---
ql/src/java/org/apache/hadoop/hive/ql/parse/TaskCompiler.java | 5 ++++-
ql/src/test/results/clientpositive/spark/stats10.q.out | 1 -
ql/src/test/results/clientpositive/spark/stats12.q.out | 1 -
ql/src/test/results/clientpositive/spark/stats13.q.out | 1 -
ql/src/test/results/clientpositive/spark/stats2.q.out | 1 -
ql/src/test/results/clientpositive/spark/stats5.q.out | 1 -
ql/src/test/results/clientpositive/spark/stats7.q.out | 1 -
ql/src/test/results/clientpositive/spark/stats8.q.out | 5 -----
ql/src/test/results/clientpositive/spark/stats9.q.out | 1 -
ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out | 3 +--
ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out | 3 +--
ql/src/test/results/clientpositive/tez/explainuser_3.q.out | 3 +--
12 files changed, 7 insertions(+), 19 deletions(-)
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/TaskCompiler.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/TaskCompiler.java
index 0b55a39..38bc04e 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/TaskCompiler.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/TaskCompiler.java
@@ -156,7 +156,10 @@ public abstract class TaskCompiler {
return;
}
- optimizeOperatorPlan(pCtx, inputs, outputs);
+ if (!pCtx.getQueryProperties().isAnalyzeCommand()) {
+ LOG.debug("Skipping optimize operator plan for analyze command.");
+ optimizeOperatorPlan(pCtx, inputs, outputs);
+ }
/*
* In case of a select, use a fetch task instead of a move task.
diff --git a/ql/src/test/results/clientpositive/spark/stats10.q.out b/ql/src/test/results/clientpositive/spark/stats10.q.out
index 7a2861e..e29ef07 100644
--- a/ql/src/test/results/clientpositive/spark/stats10.q.out
+++ b/ql/src/test/results/clientpositive/spark/stats10.q.out
@@ -396,7 +396,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: bucket3_1_n0
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-1
Stats Work
diff --git a/ql/src/test/results/clientpositive/spark/stats12.q.out b/ql/src/test/results/clientpositive/spark/stats12.q.out
index 083dee3..fb537b8 100644
--- a/ql/src/test/results/clientpositive/spark/stats12.q.out
+++ b/ql/src/test/results/clientpositive/spark/stats12.q.out
@@ -64,7 +64,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_srcpart_n3
- Statistics: Num rows: 392 Data size: 232480 Basic stats: PARTIAL Column stats: NONE
Statistics Aggregation Key Prefix: default.analyze_srcpart_n3/
GatherStats: true
Path -> Alias:
diff --git a/ql/src/test/results/clientpositive/spark/stats13.q.out b/ql/src/test/results/clientpositive/spark/stats13.q.out
index ca9efc2..14b4d9d 100644
--- a/ql/src/test/results/clientpositive/spark/stats13.q.out
+++ b/ql/src/test/results/clientpositive/spark/stats13.q.out
@@ -60,7 +60,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_srcpart
- Statistics: Num rows: 392 Data size: 232480 Basic stats: PARTIAL Column stats: NONE
Statistics Aggregation Key Prefix: default.analyze_srcpart/
GatherStats: true
Path -> Alias:
diff --git a/ql/src/test/results/clientpositive/spark/stats2.q.out b/ql/src/test/results/clientpositive/spark/stats2.q.out
index f74738b..5816bf6 100644
--- a/ql/src/test/results/clientpositive/spark/stats2.q.out
+++ b/ql/src/test/results/clientpositive/spark/stats2.q.out
@@ -183,7 +183,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_t1
- Statistics: Num rows: 392 Data size: 232480 Basic stats: PARTIAL Column stats: NONE
Stage: Stage-1
Stats Work
diff --git a/ql/src/test/results/clientpositive/spark/stats5.q.out b/ql/src/test/results/clientpositive/spark/stats5.q.out
index c4eeab0..09969e4 100644
--- a/ql/src/test/results/clientpositive/spark/stats5.q.out
+++ b/ql/src/test/results/clientpositive/spark/stats5.q.out
@@ -31,7 +31,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-1
Stats Work
diff --git a/ql/src/test/results/clientpositive/spark/stats7.q.out b/ql/src/test/results/clientpositive/spark/stats7.q.out
index 8fdd1d2..79bd187 100644
--- a/ql/src/test/results/clientpositive/spark/stats7.q.out
+++ b/ql/src/test/results/clientpositive/spark/stats7.q.out
@@ -62,7 +62,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_srcpart_n4
- Statistics: Num rows: 392 Data size: 232480 Basic stats: PARTIAL Column stats: NONE
Stage: Stage-1
Stats Work
diff --git a/ql/src/test/results/clientpositive/spark/stats8.q.out b/ql/src/test/results/clientpositive/spark/stats8.q.out
index 92c4087..e48c906 100644
--- a/ql/src/test/results/clientpositive/spark/stats8.q.out
+++ b/ql/src/test/results/clientpositive/spark/stats8.q.out
@@ -93,7 +93,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_srcpart_n1
- Statistics: Num rows: 392 Data size: 232480 Basic stats: PARTIAL Column stats: NONE
Stage: Stage-1
Stats Work
@@ -249,7 +248,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_srcpart_n1
- Statistics: Num rows: 794 Data size: 179672 Basic stats: PARTIAL Column stats: NONE
Stage: Stage-1
Stats Work
@@ -330,7 +328,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_srcpart_n1
- Statistics: Num rows: 1196 Data size: 126864 Basic stats: PARTIAL Column stats: NONE
Stage: Stage-1
Stats Work
@@ -411,7 +408,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_srcpart_n1
- Statistics: Num rows: 1598 Data size: 74056 Basic stats: PARTIAL Column stats: NONE
Stage: Stage-1
Stats Work
@@ -504,7 +500,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_srcpart_n1
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-1
Stats Work
diff --git a/ql/src/test/results/clientpositive/spark/stats9.q.out b/ql/src/test/results/clientpositive/spark/stats9.q.out
index bd4d59e..7e1f957 100644
--- a/ql/src/test/results/clientpositive/spark/stats9.q.out
+++ b/ql/src/test/results/clientpositive/spark/stats9.q.out
@@ -37,7 +37,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: analyze_srcbucket
- Statistics: Num rows: 391 Data size: 116030 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-1
Stats Work
diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out
index d6ec53d..2ef7b13 100644
--- a/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out
@@ -268,8 +268,7 @@ Stage-2
Stats Work{}
Stage-0
Map 1
- TableScan [TS_0] (rows=500/500 width=10)
- default@src_stats,src_stats,Tbl:COMPLETE,Col:COMPLETE
+ TableScan [TS_0]
PREHOOK: query: analyze table src_stats compute statistics for columns
PREHOOK: type: ANALYZE_TABLE
diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
index 419f6fd..5088a3d 100644
--- a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
@@ -34,8 +34,7 @@ Stage-2
Stats Work{}
Stage-0
Map 1
- TableScan [TS_0] (rows=500/500 width=10)
- default@src_stats_n0,src_stats_n0,Tbl:COMPLETE,Col:COMPLETE
+ TableScan [TS_0]
PREHOOK: query: analyze table src_stats_n0 compute statistics for columns
PREHOOK: type: ANALYZE_TABLE
diff --git a/ql/src/test/results/clientpositive/tez/explainuser_3.q.out b/ql/src/test/results/clientpositive/tez/explainuser_3.q.out
index f9f01fa..fa85521 100644
--- a/ql/src/test/results/clientpositive/tez/explainuser_3.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainuser_3.q.out
@@ -234,8 +234,7 @@ Stage-2
Stats Work{}
Stage-0
Map 1
- TableScan [TS_0] (rows=500 width=10)
- default@src,src,Tbl:COMPLETE,Col:COMPLETE
+ TableScan [TS_0]
PREHOOK: query: explain analyze table src compute statistics for columns
PREHOOK: type: ANALYZE_TABLE