You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by se...@apache.org on 2016/08/30 22:21:19 UTC
[12/17] hive git commit: HIVE-14362: Support explain analyze in Hive
(Pengcheng Xiong, reviewed by Ashutosh Chauhan, Gopal V and Gabor Szadovszky)
http://git-wip-us.apache.org/repos/asf/hive/blob/20824f27/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out b/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out
index 8d280c1..d56ec6f 100644
--- a/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out
+++ b/ql/src/test/results/clientpositive/columnstats_tbllvl.q.out
@@ -54,23 +54,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: uservisits_web_text_none
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: sourceip (type: string), avgtimeonsite (type: int), adrevenue (type: float)
outputColumnNames: sourceip, avgtimeonsite, adrevenue
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -99,17 +105,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: uservisits_web_text_none
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Select Operator
expressions: sourceip (type: string), avgtimeonsite (type: int), adrevenue (type: float)
outputColumnNames: sourceip, avgtimeonsite, adrevenue
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
auto parallelism: false
@@ -168,11 +178,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -222,23 +234,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: uservisits_web_text_none
+ Statistics: Num rows: 9 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: sourceip (type: string), desturl (type: string), visitdate (type: string), adrevenue (type: float), useragent (type: string), ccode (type: string), lcode (type: string), skeyword (type: string), avgtimeonsite (type: int)
outputColumnNames: sourceip, desturl, visitdate, adrevenue, useragent, ccode, lcode, skeyword, avgtimeonsite
+ Statistics: Num rows: 9 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(sourceip, 16), compute_stats(desturl, 16), compute_stats(visitdate, 16), compute_stats(adrevenue, 16), compute_stats(useragent, 16), compute_stats(ccode, 16), compute_stats(lcode, 16), compute_stats(skeyword, 16), compute_stats(avgtimeonsite, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 1 Data size: 4396 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 4396 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col5 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col6 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
, _col7 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col8 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 1 Data size: 4404 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 4404 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -322,23 +340,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: empty_tab
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: a (type: int), b (type: double), c (type: string), d (type: boolean), e (type: binary)
outputColumnNames: a, b, c, d, e
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: compute_stats(a, 16), compute_stats(b, 16), compute_stats(c, 16), compute_stats(d, 16), compute_stats(e, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 2004 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 2004 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,counttrues:bigint,countfalses:bigint,countnulls:bigint>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -446,23 +470,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: uservisits_in_dummy_db
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: sourceip (type: string), avgtimeonsite (type: int), adrevenue (type: float)
outputColumnNames: sourceip, avgtimeonsite, adrevenue
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -491,17 +521,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: uservisits_in_dummy_db
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Select Operator
expressions: sourceip (type: string), avgtimeonsite (type: int), adrevenue (type: float)
outputColumnNames: sourceip, avgtimeonsite, adrevenue
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
auto parallelism: false
@@ -560,11 +594,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -614,23 +650,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: uservisits_in_dummy_db
+ Statistics: Num rows: 9 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: sourceip (type: string), desturl (type: string), visitdate (type: string), adrevenue (type: float), useragent (type: string), ccode (type: string), lcode (type: string), skeyword (type: string), avgtimeonsite (type: int)
outputColumnNames: sourceip, desturl, visitdate, adrevenue, useragent, ccode, lcode, skeyword, avgtimeonsite
+ Statistics: Num rows: 9 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(sourceip, 16), compute_stats(desturl, 16), compute_stats(visitdate, 16), compute_stats(adrevenue, 16), compute_stats(useragent, 16), compute_stats(ccode, 16), compute_stats(lcode, 16), compute_stats(skeyword, 16), compute_stats(avgtimeonsite, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 1 Data size: 4396 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 4396 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col5 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col6 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
, _col7 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col8 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 1 Data size: 4404 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 4404 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/20824f27/ql/src/test/results/clientpositive/compute_stats_date.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/compute_stats_date.q.out b/ql/src/test/results/clientpositive/compute_stats_date.q.out
index eaf4bbe..fba8cad 100644
--- a/ql/src/test/results/clientpositive/compute_stats_date.q.out
+++ b/ql/src/test/results/clientpositive/compute_stats_date.q.out
@@ -64,23 +64,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: tab_date
+ Statistics: Num rows: 13 Data size: 778 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: fl_date (type: date)
outputColumnNames: fl_date
+ Statistics: Num rows: 13 Data size: 778 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(fl_date, 16)
mode: hash
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 572 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 572 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,min:date,max:date,countnulls:bigint,bitvector:string,numbitvectors:int>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 576 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 576 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/20824f27/ql/src/test/results/clientpositive/constant_prop_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/constant_prop_2.q.out b/ql/src/test/results/clientpositive/constant_prop_2.q.out
index c1de559..24be518 100644
--- a/ql/src/test/results/clientpositive/constant_prop_2.q.out
+++ b/ql/src/test/results/clientpositive/constant_prop_2.q.out
@@ -37,18 +37,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(key, 16), compute_stats(value, 16)
keys: '2008-04-08' (type: string), '11' (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: '2008-04-08' (type: string), '11' (type: string)
sort order: ++
Map-reduce partition columns: '2008-04-08' (type: string), '11' (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
Reduce Operator Tree:
Group By Operator
@@ -56,11 +60,14 @@ STAGE PLANS:
keys: '2008-04-08' (type: string), '11' (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:string>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:string>), '2008-04-08' (type: string), '11' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/20824f27/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out b/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out
index 42aeb6f..d974dbc 100644
--- a/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out
+++ b/ql/src/test/results/clientpositive/display_colstats_tbllvl.q.out
@@ -70,23 +70,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: uservisits_web_text_none
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: sourceip (type: string), avgtimeonsite (type: int), adrevenue (type: float)
outputColumnNames: sourceip, avgtimeonsite, adrevenue
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -115,17 +121,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: uservisits_web_text_none
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Select Operator
expressions: sourceip (type: string), avgtimeonsite (type: int), adrevenue (type: float)
outputColumnNames: sourceip, avgtimeonsite, adrevenue
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
auto parallelism: false
@@ -184,11 +194,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -294,23 +306,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: empty_tab
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: a (type: int), b (type: double), c (type: string), d (type: boolean), e (type: binary)
outputColumnNames: a, b, c, d, e
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: compute_stats(a, 16), compute_stats(b, 16), compute_stats(c, 16), compute_stats(d, 16), compute_stats(e, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 2004 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 2004 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,counttrues:bigint,countfalses:bigint,countnulls:bigint>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/20824f27/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid.q.out b/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid.q.out
index de08dc5..9b7b4d2 100644
--- a/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid.q.out
+++ b/ql/src/test/results/clientpositive/dynpart_sort_optimization_acid.q.out
@@ -80,21 +80,27 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid
+ Statistics: Num rows: 1725 Data size: 5177 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
+ Statistics: Num rows: 862 Data size: 2586 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
+ Statistics: Num rows: 862 Data size: 2586 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
+ Statistics: Num rows: 862 Data size: 2586 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 862 Data size: 2586 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 862 Data size: 2586 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -152,22 +158,28 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid
+ Statistics: Num rows: 1945 Data size: 5835 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
+ Statistics: Num rows: 972 Data size: 2916 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), ds (type: string)
outputColumnNames: _col0, _col3
+ Statistics: Num rows: 972 Data size: 2916 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
+ Statistics: Num rows: 972 Data size: 2916 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: string)
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 972 Data size: 2916 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 972 Data size: 2916 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -317,21 +329,27 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid
+ Statistics: Num rows: 1566 Data size: 4698 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
+ Statistics: Num rows: 783 Data size: 2349 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
+ Statistics: Num rows: 783 Data size: 2349 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
+ Statistics: Num rows: 783 Data size: 2349 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 783 Data size: 2349 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 783 Data size: 2349 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -389,21 +407,27 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid
+ Statistics: Num rows: 1785 Data size: 5357 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
+ Statistics: Num rows: 892 Data size: 2676 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), ds (type: string)
outputColumnNames: _col0, _col3
+ Statistics: Num rows: 892 Data size: 2676 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col3 (type: string), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
sort order: +++
Map-reduce partition columns: _col3 (type: string)
+ Statistics: Num rows: 892 Data size: 2676 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Select Operator
expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), KEY._col3 (type: string), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, '_bucket_number'
+ Statistics: Num rows: 892 Data size: 2676 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 892 Data size: 2676 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -559,21 +583,27 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid
+ Statistics: Num rows: 1547 Data size: 4642 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
+ Statistics: Num rows: 773 Data size: 2319 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
+ Statistics: Num rows: 773 Data size: 2319 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
+ Statistics: Num rows: 773 Data size: 2319 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), 11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 773 Data size: 2319 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 773 Data size: 2319 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -632,22 +662,28 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid
+ Statistics: Num rows: 3032 Data size: 9099 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
+ Statistics: Num rows: 1516 Data size: 4549 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), hr (type: int)
outputColumnNames: _col0, _col4
+ Statistics: Num rows: 1516 Data size: 4549 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
+ Statistics: Num rows: 1516 Data size: 4549 Basic stats: COMPLETE Column stats: NONE
value expressions: _col4 (type: int)
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), VALUE._col2 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1516 Data size: 4549 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1516 Data size: 4549 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -810,21 +846,27 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid
+ Statistics: Num rows: 1548 Data size: 4644 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
+ Statistics: Num rows: 774 Data size: 2322 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
outputColumnNames: _col0
+ Statistics: Num rows: 774 Data size: 2322 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
sort order: +
Map-reduce partition columns: UDFToInteger(_col0) (type: int)
+ Statistics: Num rows: 774 Data size: 2322 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), 11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 774 Data size: 2322 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 774 Data size: 2322 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -883,21 +925,27 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid
+ Statistics: Num rows: 3034 Data size: 9103 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
+ Statistics: Num rows: 1517 Data size: 4551 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), hr (type: int)
outputColumnNames: _col0, _col4
+ Statistics: Num rows: 1517 Data size: 4551 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: '2008-04-08' (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
sort order: ++++
Map-reduce partition columns: '2008-04-08' (type: string), _col4 (type: int)
+ Statistics: Num rows: 1517 Data size: 4551 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Select Operator
expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
+ Statistics: Num rows: 1517 Data size: 4551 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1517 Data size: 4551 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -1060,22 +1108,28 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid
+ Statistics: Num rows: 46 Data size: 4644 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
+ Statistics: Num rows: 23 Data size: 2322 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), key (type: string), ds (type: string), hr (type: int)
outputColumnNames: _col0, _col1, _col3, _col4
+ Statistics: Num rows: 23 Data size: 2322 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col3 (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
sort order: ++++
Map-reduce partition columns: _col3 (type: string), _col4 (type: int)
+ Statistics: Num rows: 23 Data size: 2322 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), 'bar' (type: string)
Reduce Operator Tree:
Select Operator
expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
+ Statistics: Num rows: 23 Data size: 2322 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 23 Data size: 2322 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -1134,22 +1188,28 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: acid
+ Statistics: Num rows: 90 Data size: 9101 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 'foo') (type: boolean)
+ Statistics: Num rows: 45 Data size: 4550 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), key (type: string), ds (type: string), hr (type: int)
outputColumnNames: _col0, _col1, _col3, _col4
+ Statistics: Num rows: 45 Data size: 4550 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col3 (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>)
sort order: ++++
Map-reduce partition columns: _col3 (type: string), _col4 (type: int)
+ Statistics: Num rows: 45 Data size: 4550 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), 'bar' (type: string)
Reduce Operator Tree:
Select Operator
expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number'
+ Statistics: Num rows: 45 Data size: 4550 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 45 Data size: 4550 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/20824f27/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out b/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out
index 4fcde91..f256ec1 100644
--- a/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out
+++ b/ql/src/test/results/clientpositive/exec_parallel_column_stats.q.out
@@ -12,23 +12,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(key, 16), compute_stats(value, 16)
mode: hash
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 984 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 984 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 984 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 984 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/20824f27/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out b/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out
index e229dba..d60ba82 100644
--- a/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out
+++ b/ql/src/test/results/clientpositive/temp_table_display_colstats_tbllvl.q.out
@@ -78,23 +78,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: uservisits_web_text_none
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: sourceip (type: string), avgtimeonsite (type: int), adrevenue (type: float)
outputColumnNames: sourceip, avgtimeonsite, adrevenue
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -123,17 +129,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: uservisits_web_text_none
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Select Operator
expressions: sourceip (type: string), avgtimeonsite (type: int), adrevenue (type: float)
outputColumnNames: sourceip, avgtimeonsite, adrevenue
+ Statistics: Num rows: 65 Data size: 7060 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(sourceip, 16), compute_stats(avgtimeonsite, 16), compute_stats(adrevenue, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
+ Statistics: Num rows: 1 Data size: 1444 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>)
auto parallelism: false
@@ -188,11 +198,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 1452 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -298,23 +310,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: empty_tab
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: a (type: int), b (type: double), c (type: string), d (type: boolean), e (type: binary)
outputColumnNames: a, b, c, d, e
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: compute_stats(a, 16), compute_stats(b, 16), compute_stats(c, 16), compute_stats(d, 16), compute_stats(e, 16)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 2004 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
+ Statistics: Num rows: 1 Data size: 2004 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:string,numbitvectors:int>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:string,numbitvectors:int>), _col3 (type: struct<columntype:string,counttrues:bigint,countfalses:bigint,countnulls:bigint>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint>)
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 1 Data size: 2012 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/20824f27/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out
new file mode 100644
index 0000000..6fe287a
--- /dev/null
+++ b/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out
@@ -0,0 +1,471 @@
+PREHOOK: query: select * from src a union all select * from src b limit 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select * from src a union all select * from src b limit 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain analyze select * from src a union all select * from src b limit 10
+PREHOOK: type: QUERY
+POSTHOOK: query: explain analyze select * from src a union all select * from src b limit 10
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Vertex dependency in root stage
+Map 1 <- Union 2 (CONTAINS)
+Map 3 <- Union 2 (CONTAINS)
+
+Stage-0
+ Fetch Operator
+ limit:10
+ Stage-1
+ Union 2
+ <-Map 1 [CONTAINS]
+ File Output Operator [FS_7]
+ Limit [LIM_6] (rows=10/20 width=178)
+ Number of rows:10
+ Select Operator [SEL_1] (rows=500/12 width=178)
+ Output:["_col0","_col1"]
+ TableScan [TS_0] (rows=500/13 width=178)
+ Output:["key","value"]
+ <-Map 3 [CONTAINS]
+ File Output Operator [FS_7]
+ Limit [LIM_6] (rows=10/20 width=178)
+ Number of rows:10
+ Select Operator [SEL_3] (rows=500/12 width=178)
+ Output:["_col0","_col1"]
+ TableScan [TS_2] (rows=500/13 width=178)
+ Output:["key","value"]
+
+PREHOOK: query: select key from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain analyze select key from src
+PREHOOK: type: QUERY
+POSTHOOK: query: explain analyze select key from src
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Stage-0
+ Fetch Operator
+ limit:-1
+ Select Operator [SEL_1]
+ Output:["_col0"]
+ TableScan [TS_0]
+ Output:["key"]
+
+PREHOOK: query: create table t as select key from src
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@src
+PREHOOK: Output: database:default
+PREHOOK: Output: default@t
+POSTHOOK: query: create table t as select key from src
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@src
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@t
+PREHOOK: query: explain analyze create table t as select key from src
+PREHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: query: explain analyze create table t as select key from src
+POSTHOOK: type: CREATETABLE_AS_SELECT
+Plan optimized by CBO.
+
+Stage-3
+ Stats-Aggr Operator
+ Stage-4
+ Create Table Operator:
+ name:default.t
+ Stage-2
+ Dependency Collection{}
+ Stage-1
+ Map 1
+ File Output Operator [FS_2]
+ table:{"name:":"default.t"}
+ Select Operator [SEL_1] (rows=500/500 width=87)
+ Output:["_col0"]
+ TableScan [TS_0] (rows=500/500 width=87)
+ default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
+ Stage-0
+ Move Operator
+ Please refer to the previous Stage-1
+
+PREHOOK: query: create table t as select key from src
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@src
+PREHOOK: Output: database:default
+PREHOOK: Output: default@t
+POSTHOOK: query: create table t as select key from src
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@src
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@t
+POSTHOOK: Lineage: t.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: insert overwrite table t select key from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@t
+POSTHOOK: query: insert overwrite table t select key from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@t
+PREHOOK: query: explain analyze insert overwrite table t select key from src
+PREHOOK: type: QUERY
+POSTHOOK: query: explain analyze insert overwrite table t select key from src
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Stage-3
+ Stats-Aggr Operator
+ Stage-0
+ Move Operator
+ table:{"name:":"default.t"}
+ Stage-2
+ Dependency Collection{}
+ Stage-1
+ Map 1
+ File Output Operator [FS_2]
+ table:{"name:":"default.t"}
+ Select Operator [SEL_1] (rows=500/500 width=87)
+ Output:["_col0"]
+ TableScan [TS_0] (rows=500/500 width=87)
+ default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
+
+PREHOOK: query: select key from src limit 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key from src limit 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain analyze select key from src limit 10
+PREHOOK: type: QUERY
+POSTHOOK: query: explain analyze select key from src limit 10
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Stage-0
+ Fetch Operator
+ limit:10
+ Limit [LIM_2]
+ Number of rows:10
+ Select Operator [SEL_1]
+ Output:["_col0"]
+ TableScan [TS_0]
+ Output:["key"]
+
+PREHOOK: query: select key from src where value < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key from src where value < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain analyze select key from src where value < 10
+PREHOOK: type: QUERY
+POSTHOOK: query: explain analyze select key from src where value < 10
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Stage-0
+ Fetch Operator
+ limit:-1
+ Select Operator [SEL_2]
+ Output:["_col0"]
+ Filter Operator [FIL_4]
+ predicate:(UDFToDouble(value) < 10.0)
+ TableScan [TS_0]
+ Output:["key","value"]
+
+PREHOOK: query: select key from src where key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key from src where key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain analyze select key from src where key < 10
+PREHOOK: type: QUERY
+POSTHOOK: query: explain analyze select key from src where key < 10
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Stage-0
+ Fetch Operator
+ limit:-1
+ Select Operator [SEL_2]
+ Output:["_col0"]
+ Filter Operator [FIL_4]
+ predicate:(UDFToDouble(key) < 10.0)
+ TableScan [TS_0]
+ Output:["key"]
+
+PREHOOK: query: select count(*) from (select key from src where key < 10)subq
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from (select key from src where key < 10)subq
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+10
+PREHOOK: query: select key, count(key) from src group by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key, count(key) from src group by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain analyze select key, count(key) from src group by key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain analyze select key, count(key) from src group by key
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Vertex dependency in root stage
+Reducer 2 <- Map 1 (SIMPLE_EDGE)
+
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Reducer 2
+ File Output Operator [FS_6]
+ Group By Operator [GBY_4] (rows=205/309 width=95)
+ Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_3]
+ PartitionCols:_col0
+ Group By Operator [GBY_2] (rows=205/309 width=95)
+ Output:["_col0","_col1"],aggregations:["count(key)"],keys:key
+ Select Operator [SEL_1] (rows=500/500 width=87)
+ Output:["key"]
+ TableScan [TS_0] (rows=500/500 width=87)
+ default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
+
+PREHOOK: query: select count(*) from (select key, count(key) from src group by key)subq
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from (select key, count(key) from src group by key)subq
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+309
+PREHOOK: query: select count(*) from src a join src b on a.key = b.value where a.key > 0
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from src a join src b on a.key = b.value where a.key > 0
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain analyze select count(*) from src a join src b on a.key = b.value where a.key > 0
+PREHOOK: type: QUERY
+POSTHOOK: query: explain analyze select count(*) from src a join src b on a.key = b.value where a.key > 0
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Vertex dependency in root stage
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Reducer 3
+ File Output Operator [FS_14]
+ Group By Operator [GBY_12] (rows=1/1 width=8)
+ Output:["_col0"],aggregations:["count(VALUE._col0)"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_11]
+ Group By Operator [GBY_10] (rows=1/1 width=8)
+ Output:["_col0"],aggregations:["count()"]
+ Merge Join Operator [MERGEJOIN_19] (rows=382/0 width=8)
+ Conds:RS_6._col0=RS_7._col0(Inner)
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_6]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=166/497 width=87)
+ Output:["_col0"]
+ Filter Operator [FIL_17] (rows=166/497 width=87)
+ predicate:(UDFToDouble(key) > 0.0)
+ TableScan [TS_0] (rows=500/500 width=87)
+ default@src,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
+ <-Map 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_7]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=166/0 width=91)
+ Output:["_col0"]
+ Filter Operator [FIL_18] (rows=166/0 width=91)
+ predicate:(UDFToDouble(value) > 0.0)
+ TableScan [TS_3] (rows=500/500 width=91)
+ default@src,b,Tbl:COMPLETE,Col:COMPLETE,Output:["value"]
+
+PREHOOK: query: select count(*) from src a join src b on a.key = b.key where a.key > 0
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from src a join src b on a.key = b.key where a.key > 0
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain analyze select count(*) from src a join src b on a.key = b.key where a.key > 0
+PREHOOK: type: QUERY
+POSTHOOK: query: explain analyze select count(*) from src a join src b on a.key = b.key where a.key > 0
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Vertex dependency in root stage
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Reducer 3
+ File Output Operator [FS_14]
+ Group By Operator [GBY_12] (rows=1/1 width=8)
+ Output:["_col0"],aggregations:["count(VALUE._col0)"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_11]
+ Group By Operator [GBY_10] (rows=1/1 width=8)
+ Output:["_col0"],aggregations:["count()"]
+ Merge Join Operator [MERGEJOIN_19] (rows=399/1019 width=8)
+ Conds:RS_6._col0=RS_7._col0(Inner)
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_6]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=166/497 width=87)
+ Output:["_col0"]
+ Filter Operator [FIL_17] (rows=166/497 width=87)
+ predicate:(UDFToDouble(key) > 0.0)
+ TableScan [TS_0] (rows=500/500 width=87)
+ default@src,a,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
+ <-Map 4 [SIMPLE_EDGE]
+ SHUFFLE [RS_7]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=166/497 width=87)
+ Output:["_col0"]
+ Filter Operator [FIL_18] (rows=166/497 width=87)
+ predicate:(UDFToDouble(key) > 0.0)
+ TableScan [TS_3] (rows=500/500 width=87)
+ default@src,b,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
+
+PREHOOK: query: select count(*) from src a join src b on a.key = b.key where a.key > 0
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from src a join src b on a.key = b.key where a.key > 0
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+1019
+PREHOOK: query: select * from src a union all select * from src b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select * from src a union all select * from src b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain analyze select * from src a union all select * from src b
+PREHOOK: type: QUERY
+POSTHOOK: query: explain analyze select * from src a union all select * from src b
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Vertex dependency in root stage
+Map 1 <- Union 2 (CONTAINS)
+Map 3 <- Union 2 (CONTAINS)
+
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Union 2
+ <-Map 1 [CONTAINS]
+ File Output Operator [FS_6]
+ Select Operator [SEL_1] (rows=500/500 width=178)
+ Output:["_col0","_col1"]
+ TableScan [TS_0] (rows=500/500 width=178)
+ Output:["key","value"]
+ <-Map 3 [CONTAINS]
+ File Output Operator [FS_6]
+ Select Operator [SEL_3] (rows=500/500 width=178)
+ Output:["_col0","_col1"]
+ TableScan [TS_2] (rows=500/500 width=178)
+ Output:["key","value"]
+
+PREHOOK: query: select count(*) from (select * from src a union all select * from src b)subq
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from (select * from src a union all select * from src b)subq
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+1000
+PREHOOK: query: SELECT x.key, y.value
+FROM src x JOIN src y ON (x.key = y.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT x.key, y.value
+FROM src x JOIN src y ON (x.key = y.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: EXPLAIN analyze
+SELECT x.key, y.value
+FROM src x JOIN src y ON (x.key = y.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN analyze
+SELECT x.key, y.value
+FROM src x JOIN src y ON (x.key = y.key)
+POSTHOOK: type: QUERY
+Plan optimized by CBO.
+
+Vertex dependency in root stage
+Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
+
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Reducer 2
+ File Output Operator [FS_10]
+ Select Operator [SEL_9] (rows=1219/1028 width=178)
+ Output:["_col0","_col1"]
+ Merge Join Operator [MERGEJOIN_15] (rows=1219/1028 width=178)
+ Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col2"]
+ <-Map 1 [SIMPLE_EDGE]
+ SHUFFLE [RS_6]
+ PartitionCols:_col0
+ Select Operator [SEL_2] (rows=500/500 width=87)
+ Output:["_col0"]
+ Filter Operator [FIL_13] (rows=500/500 width=87)
+ predicate:key is not null
+ TableScan [TS_0] (rows=500/500 width=87)
+ default@src,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
+ <-Map 3 [SIMPLE_EDGE]
+ SHUFFLE [RS_7]
+ PartitionCols:_col0
+ Select Operator [SEL_5] (rows=500/500 width=178)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_14] (rows=500/500 width=178)
+ predicate:key is not null
+ TableScan [TS_3] (rows=500/500 width=178)
+ default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
+