hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From gunt...@apache.org
Subject svn commit: r1552041 [5/7] - in /hive/branches/tez: ./ ant/src/org/apache/hadoop/hive/ant/ conf/ hbase-handler/src/java/org/apache/hadoop/hive/hbase/ hcatalog/src/test/e2e/templeton/tests/ hcatalog/webhcat/svr/src/main/java/org/apache/hive/hcatalog/tem...
Date Wed, 18 Dec 2013 17:22:05 GMT
Modified: hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out Wed Dec 18 17:22:02 2013
@@ -72,6 +72,7 @@ Table:              	fact_daily         
 Protect Mode:       	None                	 
 #### A masked pattern was here ####
 Partition Parameters:	 	 
+	COLUMN_STATS_ACCURATE	true                
 	numFiles            	3                   
 	numRows             	500                 
 	rawDataSize         	5312                
@@ -130,12 +131,16 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 500 dataSize: 5312 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (value = 'val_484')
                   type: boolean
+              Statistics:
+                  numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: key
@@ -143,6 +148,8 @@ STAGE PLANS:
                       expr: value
                       type: string
                 outputColumnNames: _col0, _col1
+                Statistics:
+                    numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
                 Reduce Output Operator
                   key expressions:
                         expr: _col0
@@ -150,6 +157,8 @@ STAGE PLANS:
                         expr: _col1
                         type: string
                   sort order: ++
+                  Statistics:
+                      numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
                   tag: -1
                   value expressions:
                         expr: _col0
@@ -168,6 +177,7 @@ STAGE PLANS:
               ds 1
               hr 4
             properties:
+              COLUMN_STATS_ACCURATE true
               bucket_count -1
               columns key,value
               columns.types string:string
@@ -192,15 +202,10 @@ STAGE PLANS:
                 columns.types string:string
 #### A masked pattern was here ####
                 name default.fact_daily
-                numFiles 3
-                numPartitions 1
-                numRows 500
                 partition_columns ds/hr
-                rawDataSize 5312
                 serialization.ddl struct fact_daily { string key, string value}
                 serialization.format 1
                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                totalSize 5812
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.fact_daily
@@ -214,6 +219,7 @@ STAGE PLANS:
               ds 1
               hr 4
             properties:
+              COLUMN_STATS_ACCURATE true
               bucket_count -1
               columns key,value
               columns.types string:string
@@ -238,15 +244,10 @@ STAGE PLANS:
                 columns.types string:string
 #### A masked pattern was here ####
                 name default.fact_daily
-                numFiles 3
-                numPartitions 1
-                numRows 500
                 partition_columns ds/hr
-                rawDataSize 5312
                 serialization.ddl struct fact_daily { string key, string value}
                 serialization.format 1
                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                totalSize 5812
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.fact_daily
@@ -257,11 +258,15 @@ STAGE PLANS:
       Needs Tagging: false
       Reduce Operator Tree:
         Extract
+          Statistics:
+              numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
           File Output Operator
             compressed: false
             GlobalTableId: 0
 #### A masked pattern was here ####
             NumFilesPerFileSink: 1
+            Statistics:
+                numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
             table:
                 input format: org.apache.hadoop.mapred.TextInputFormat
@@ -282,7 +287,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: -- List Bucketing Query
 SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484' ORDER BY key, value
 PREHOOK: type: QUERY
@@ -322,22 +326,30 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 500 dataSize: 5312 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (key = '406')
                   type: boolean
+              Statistics:
+                  numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: key
                       type: string
                 outputColumnNames: _col0
+                Statistics:
+                    numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
                 Reduce Output Operator
                   key expressions:
                         expr: _col0
                         type: string
                   sort order: +
+                  Statistics:
+                      numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
                   tag: -1
                   value expressions:
                         expr: _col0
@@ -354,6 +366,7 @@ STAGE PLANS:
               ds 1
               hr 4
             properties:
+              COLUMN_STATS_ACCURATE true
               bucket_count -1
               columns key,value
               columns.types string:string
@@ -378,15 +391,10 @@ STAGE PLANS:
                 columns.types string:string
 #### A masked pattern was here ####
                 name default.fact_daily
-                numFiles 3
-                numPartitions 1
-                numRows 500
                 partition_columns ds/hr
-                rawDataSize 5312
                 serialization.ddl struct fact_daily { string key, string value}
                 serialization.format 1
                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                totalSize 5812
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.fact_daily
@@ -396,11 +404,15 @@ STAGE PLANS:
       Needs Tagging: false
       Reduce Operator Tree:
         Extract
+          Statistics:
+              numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
           File Output Operator
             compressed: false
             GlobalTableId: 0
 #### A masked pattern was here ####
             NumFilesPerFileSink: 1
+            Statistics:
+                numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
             table:
                 input format: org.apache.hadoop.mapred.TextInputFormat
@@ -421,7 +433,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: -- List Bucketing Query
 SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and key= '406' ORDER BY key
 PREHOOK: type: QUERY
@@ -464,12 +475,16 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 500 dataSize: 5312 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (((key = '484') and (value = 'val_484')) or ((key = '238') and (value = 'val_238')))
                   type: boolean
+              Statistics:
+                  numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: key
@@ -477,6 +492,8 @@ STAGE PLANS:
                       expr: value
                       type: string
                 outputColumnNames: _col0, _col1
+                Statistics:
+                    numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
                 Reduce Output Operator
                   key expressions:
                         expr: _col0
@@ -484,6 +501,8 @@ STAGE PLANS:
                         expr: _col1
                         type: string
                   sort order: ++
+                  Statistics:
+                      numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
                   tag: -1
                   value expressions:
                         expr: _col0
@@ -502,6 +521,7 @@ STAGE PLANS:
               ds 1
               hr 4
             properties:
+              COLUMN_STATS_ACCURATE true
               bucket_count -1
               columns key,value
               columns.types string:string
@@ -526,15 +546,10 @@ STAGE PLANS:
                 columns.types string:string
 #### A masked pattern was here ####
                 name default.fact_daily
-                numFiles 3
-                numPartitions 1
-                numRows 500
                 partition_columns ds/hr
-                rawDataSize 5312
                 serialization.ddl struct fact_daily { string key, string value}
                 serialization.format 1
                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                totalSize 5812
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.fact_daily
@@ -548,6 +563,7 @@ STAGE PLANS:
               ds 1
               hr 4
             properties:
+              COLUMN_STATS_ACCURATE true
               bucket_count -1
               columns key,value
               columns.types string:string
@@ -572,15 +588,10 @@ STAGE PLANS:
                 columns.types string:string
 #### A masked pattern was here ####
                 name default.fact_daily
-                numFiles 3
-                numPartitions 1
-                numRows 500
                 partition_columns ds/hr
-                rawDataSize 5312
                 serialization.ddl struct fact_daily { string key, string value}
                 serialization.format 1
                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                totalSize 5812
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.fact_daily
@@ -591,11 +602,15 @@ STAGE PLANS:
       Needs Tagging: false
       Reduce Operator Tree:
         Extract
+          Statistics:
+              numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
           File Output Operator
             compressed: false
             GlobalTableId: 0
 #### A masked pattern was here ####
             NumFilesPerFileSink: 1
+            Statistics:
+                numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
             table:
                 input format: org.apache.hadoop.mapred.TextInputFormat
@@ -616,7 +631,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: -- List Bucketing Query
 SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484')  or (key='238' and value= 'val_238')) ORDER BY key, value
 PREHOOK: type: QUERY

Modified: hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out Wed Dec 18 17:22:02 2013
@@ -74,6 +74,7 @@ Table:              	fact_daily         
 Protect Mode:       	None                	 
 #### A masked pattern was here ####
 Partition Parameters:	 	 
+	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
 	numRows             	500                 
 	rawDataSize         	5312                
@@ -143,6 +144,7 @@ Table:              	fact_daily         
 Protect Mode:       	None                	 
 #### A masked pattern was here ####
 Partition Parameters:	 	 
+	COLUMN_STATS_ACCURATE	true                
 	numFiles            	3                   
 	numRows             	500                 
 	rawDataSize         	5312                
@@ -223,6 +225,7 @@ Table:              	fact_daily         
 Protect Mode:       	None                	 
 #### A masked pattern was here ####
 Partition Parameters:	 	 
+	COLUMN_STATS_ACCURATE	true                
 	numFiles            	2                   
 	numRows             	500                 
 	rawDataSize         	5312                
@@ -272,12 +275,16 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 500 dataSize: 5312 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (key = '145')
                   type: boolean
+              Statistics:
+                  numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: key
@@ -289,11 +296,15 @@ STAGE PLANS:
                       expr: hr
                       type: string
                 outputColumnNames: _col0, _col1, _col2, _col3
+                Statistics:
+                    numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
+                  Statistics:
+                      numRows: 250 dataSize: 2656 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.TextInputFormat
@@ -321,6 +332,7 @@ STAGE PLANS:
               ds 1
               hr 1
             properties:
+              COLUMN_STATS_ACCURATE true
               bucket_count -1
               columns key,value
               columns.types string:string
@@ -345,15 +357,10 @@ STAGE PLANS:
                 columns.types string:string
 #### A masked pattern was here ####
                 name default.fact_daily
-                numFiles 6
-                numPartitions 3
-                numRows 1500
                 partition_columns ds/hr
-                rawDataSize 15936
                 serialization.ddl struct fact_daily { string key, string value}
                 serialization.format 1
                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                totalSize 17436
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.fact_daily
@@ -365,7 +372,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: select * from fact_daily where ds = '1' and  hr='1' and key='145'
 PREHOOK: type: QUERY
 PREHOOK: Input: default@fact_daily
@@ -409,16 +415,24 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 500 dataSize: 5312 basicStatsState: COMPLETE colStatsState: COMPLETE
             GatherStats: false
             Select Operator
+              Statistics:
+                  numRows: 500 dataSize: 5312 basicStatsState: COMPLETE colStatsState: COMPLETE
               Group By Operator
                 aggregations:
                       expr: count()
                 bucketGroup: false
                 mode: hash
                 outputColumnNames: _col0
+                Statistics:
+                    numRows: 1 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
                 Reduce Output Operator
                   sort order: 
+                  Statistics:
+                      numRows: 1 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
                   tag: -1
                   value expressions:
                         expr: _col0
@@ -435,6 +449,7 @@ STAGE PLANS:
               ds 1
               hr 1
             properties:
+              COLUMN_STATS_ACCURATE true
               bucket_count -1
               columns key,value
               columns.types string:string
@@ -459,15 +474,10 @@ STAGE PLANS:
                 columns.types string:string
 #### A masked pattern was here ####
                 name default.fact_daily
-                numFiles 6
-                numPartitions 3
-                numRows 1500
                 partition_columns ds/hr
-                rawDataSize 15936
                 serialization.ddl struct fact_daily { string key, string value}
                 serialization.format 1
                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                totalSize 17436
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.fact_daily
@@ -482,16 +492,22 @@ STAGE PLANS:
           bucketGroup: false
           mode: mergepartial
           outputColumnNames: _col0
+          Statistics:
+              numRows: 1 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
           Select Operator
             expressions:
                   expr: _col0
                   type: bigint
             outputColumnNames: _col0
+            Statistics:
+                numRows: 1 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
             File Output Operator
               compressed: false
               GlobalTableId: 0
 #### A masked pattern was here ####
               NumFilesPerFileSink: 1
+              Statistics:
+                  numRows: 1 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
 #### A masked pattern was here ####
               table:
                   input format: org.apache.hadoop.mapred.TextInputFormat
@@ -512,7 +528,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: select count(*) from fact_daily where ds = '1' and  hr='1'
 PREHOOK: type: QUERY
 PREHOOK: Input: default@fact_daily
@@ -558,12 +573,16 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 500 dataSize: 5312 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: ((key = '484') and (value = 'val_484'))
                   type: boolean
+              Statistics:
+                  numRows: 125 dataSize: 1328 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: key
@@ -575,11 +594,15 @@ STAGE PLANS:
                       expr: hr
                       type: string
                 outputColumnNames: _col0, _col1, _col2, _col3
+                Statistics:
+                    numRows: 125 dataSize: 1328 basicStatsState: COMPLETE colStatsState: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
+                  Statistics:
+                      numRows: 125 dataSize: 1328 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.TextInputFormat
@@ -607,6 +630,7 @@ STAGE PLANS:
               ds 1
               hr 2
             properties:
+              COLUMN_STATS_ACCURATE true
               bucket_count -1
               columns key,value
               columns.types string:string
@@ -631,15 +655,10 @@ STAGE PLANS:
                 columns.types string:string
 #### A masked pattern was here ####
                 name default.fact_daily
-                numFiles 6
-                numPartitions 3
-                numRows 1500
                 partition_columns ds/hr
-                rawDataSize 15936
                 serialization.ddl struct fact_daily { string key, string value}
                 serialization.format 1
                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                totalSize 17436
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.fact_daily
@@ -651,7 +670,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: SELECT * FROM fact_daily WHERE ds='1' and hr='2' and (key='484' and value='val_484')
 PREHOOK: type: QUERY
 PREHOOK: Input: default@fact_daily
@@ -697,12 +715,16 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 500 dataSize: 5312 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: ((key = '327') and (value = 'val_327'))
                   type: boolean
+              Statistics:
+                  numRows: 125 dataSize: 1328 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: key
@@ -714,11 +736,15 @@ STAGE PLANS:
                       expr: hr
                       type: string
                 outputColumnNames: _col0, _col1, _col2, _col3
+                Statistics:
+                    numRows: 125 dataSize: 1328 basicStatsState: COMPLETE colStatsState: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
+                  Statistics:
+                      numRows: 125 dataSize: 1328 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.TextInputFormat
@@ -746,6 +772,7 @@ STAGE PLANS:
               ds 1
               hr 3
             properties:
+              COLUMN_STATS_ACCURATE true
               bucket_count -1
               columns key,value
               columns.types string:string
@@ -770,15 +797,10 @@ STAGE PLANS:
                 columns.types string:string
 #### A masked pattern was here ####
                 name default.fact_daily
-                numFiles 6
-                numPartitions 3
-                numRows 1500
                 partition_columns ds/hr
-                rawDataSize 15936
                 serialization.ddl struct fact_daily { string key, string value}
                 serialization.format 1
                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                totalSize 17436
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.fact_daily
@@ -790,7 +812,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: SELECT * FROM fact_daily WHERE ds='1' and hr='3' and (key='327' and value='val_327')
 PREHOOK: type: QUERY
 PREHOOK: Input: default@fact_daily

Modified: hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out Wed Dec 18 17:22:02 2013
@@ -135,6 +135,12 @@ Table:              	fact_daily         
 Protect Mode:       	None                	 
 #### A masked pattern was here ####
 Partition Parameters:	 	 
+	COLUMN_STATS_ACCURATE	false               
+#### A masked pattern was here ####
+	numFiles            	2                   
+	numRows             	-1                  
+	rawDataSize         	-1                  
+	totalSize           	8                   
 #### A masked pattern was here ####
 	 	 
 # Storage Information	 	 
@@ -188,22 +194,30 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 2 dataSize: 8 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (x = 484)
                   type: boolean
+              Statistics:
+                  numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: x
                       type: int
                 outputColumnNames: _col0
+                Statistics:
+                    numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
+                  Statistics:
+                      numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.TextInputFormat
@@ -230,15 +244,20 @@ STAGE PLANS:
             partition values:
               ds 1
             properties:
+              COLUMN_STATS_ACCURATE false
               bucket_count -1
               columns x
               columns.types int
 #### A masked pattern was here ####
               name default.fact_daily
+              numFiles 2
+              numRows -1
               partition_columns ds
+              rawDataSize -1
               serialization.ddl struct fact_daily { i32 x}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 8
 #### A masked pattern was here ####
             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
           
@@ -305,22 +324,30 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 2 dataSize: 8 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (x = 495)
                   type: boolean
+              Statistics:
+                  numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: x
                       type: int
                 outputColumnNames: _col0
+                Statistics:
+                    numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
+                  Statistics:
+                      numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.TextInputFormat
@@ -347,15 +374,20 @@ STAGE PLANS:
             partition values:
               ds 1
             properties:
+              COLUMN_STATS_ACCURATE false
               bucket_count -1
               columns x
               columns.types int
 #### A masked pattern was here ####
               name default.fact_daily
+              numFiles 2
+              numRows -1
               partition_columns ds
+              rawDataSize -1
               serialization.ddl struct fact_daily { i32 x}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 8
 #### A masked pattern was here ####
             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
           
@@ -418,22 +450,30 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 2 dataSize: 8 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (x = 1)
                   type: boolean
+              Statistics:
+                  numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: x
                       type: int
                 outputColumnNames: _col0
+                Statistics:
+                    numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
+                  Statistics:
+                      numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.TextInputFormat
@@ -460,15 +500,20 @@ STAGE PLANS:
             partition values:
               ds 1
             properties:
+              COLUMN_STATS_ACCURATE false
               bucket_count -1
               columns x
               columns.types int
 #### A masked pattern was here ####
               name default.fact_daily
+              numFiles 2
+              numRows -1
               partition_columns ds
+              rawDataSize -1
               serialization.ddl struct fact_daily { i32 x}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 8
 #### A masked pattern was here ####
             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
           

Modified: hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out Wed Dec 18 17:22:02 2013
@@ -151,6 +151,12 @@ Table:              	fact_daily         
 Protect Mode:       	None                	 
 #### A masked pattern was here ####
 Partition Parameters:	 	 
+	COLUMN_STATS_ACCURATE	false               
+#### A masked pattern was here ####
+	numFiles            	2                   
+	numRows             	-1                  
+	rawDataSize         	-1                  
+	totalSize           	24                  
 #### A masked pattern was here ####
 	 	 
 # Storage Information	 	 
@@ -208,22 +214,30 @@ STAGE PLANS:
         subq:fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 6 dataSize: 24 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (x = 484)
                   type: boolean
+              Statistics:
+                  numRows: 3 dataSize: 12 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: x
                       type: int
                 outputColumnNames: _col0
+                Statistics:
+                    numRows: 3 dataSize: 12 basicStatsState: COMPLETE colStatsState: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
+                  Statistics:
+                      numRows: 3 dataSize: 12 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.TextInputFormat
@@ -250,15 +264,20 @@ STAGE PLANS:
             partition values:
               ds 1
             properties:
+              COLUMN_STATS_ACCURATE false
               bucket_count -1
               columns x,y
               columns.types int:string
 #### A masked pattern was here ####
               name default.fact_daily
+              numFiles 2
+              numRows -1
               partition_columns ds
+              rawDataSize -1
               serialization.ddl struct fact_daily { i32 x, string y}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 24
 #### A masked pattern was here ####
             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
           
@@ -329,12 +348,16 @@ STAGE PLANS:
         subq:fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 0 dataSize: 24 basicStatsState: PARTIAL colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (x = 484)
                   type: boolean
+              Statistics:
+                  numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: x
@@ -342,6 +365,8 @@ STAGE PLANS:
                       expr: y
                       type: string
                 outputColumnNames: _col0, _col1
+                Statistics:
+                    numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
                 Reduce Output Operator
                   key expressions:
                         expr: _col0
@@ -349,6 +374,8 @@ STAGE PLANS:
                         expr: _col1
                         type: string
                   sort order: ++
+                  Statistics:
+                      numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
                   tag: -1
                   value expressions:
                         expr: _col0
@@ -366,15 +393,20 @@ STAGE PLANS:
             partition values:
               ds 1
             properties:
+              COLUMN_STATS_ACCURATE false
               bucket_count -1
               columns x,y
               columns.types int:string
 #### A masked pattern was here ####
               name default.fact_daily
+              numFiles 2
+              numRows -1
               partition_columns ds
+              rawDataSize -1
               serialization.ddl struct fact_daily { i32 x, string y}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 24
 #### A masked pattern was here ####
             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
           
@@ -400,11 +432,15 @@ STAGE PLANS:
       Needs Tagging: false
       Reduce Operator Tree:
         Extract
+          Statistics:
+              numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
           File Output Operator
             compressed: false
             GlobalTableId: 0
 #### A masked pattern was here ####
             NumFilesPerFileSink: 1
+            Statistics:
+                numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
 #### A masked pattern was here ####
             table:
                 input format: org.apache.hadoop.mapred.TextInputFormat
@@ -425,7 +461,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: -- List Bucketing Query
 select x1, y1 from(select x as x1, y as y1 from fact_daily where ds ='1') subq where x1 = 484 ORDER BY x1, y1
 PREHOOK: type: QUERY
@@ -469,17 +504,23 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 0 dataSize: 24 basicStatsState: PARTIAL colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (x = 484)
                   type: boolean
+              Statistics:
+                  numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: y
                       type: string
                 outputColumnNames: y
+                Statistics:
+                    numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
                 Group By Operator
                   aggregations:
                         expr: count(1)
@@ -489,6 +530,8 @@ STAGE PLANS:
                         type: string
                   mode: hash
                   outputColumnNames: _col0, _col1
+                  Statistics:
+                      numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
                   Reduce Output Operator
                     key expressions:
                           expr: _col0
@@ -497,6 +540,8 @@ STAGE PLANS:
                     Map-reduce partition columns:
                           expr: _col0
                           type: string
+                    Statistics:
+                        numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
                     tag: -1
                     value expressions:
                           expr: _col1
@@ -512,15 +557,20 @@ STAGE PLANS:
             partition values:
               ds 1
             properties:
+              COLUMN_STATS_ACCURATE false
               bucket_count -1
               columns x,y
               columns.types int:string
 #### A masked pattern was here ####
               name default.fact_daily
+              numFiles 2
+              numRows -1
               partition_columns ds
+              rawDataSize -1
               serialization.ddl struct fact_daily { i32 x, string y}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 24
 #### A masked pattern was here ####
             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
           
@@ -554,6 +604,8 @@ STAGE PLANS:
                 type: string
           mode: mergepartial
           outputColumnNames: _col0, _col1
+          Statistics:
+              numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
           Select Operator
             expressions:
                   expr: _col0
@@ -561,11 +613,15 @@ STAGE PLANS:
                   expr: _col1
                   type: bigint
             outputColumnNames: _col0, _col1
+            Statistics:
+                numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
             File Output Operator
               compressed: false
               GlobalTableId: 0
 #### A masked pattern was here ####
               NumFilesPerFileSink: 1
+              Statistics:
+                  numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE
 #### A masked pattern was here ####
               table:
                   input format: org.apache.hadoop.mapred.TextInputFormat
@@ -586,7 +642,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: -- List Bucketing Query
 select y, count(1) from fact_daily where ds ='1' and x = 484 group by y
 PREHOOK: type: QUERY
@@ -630,17 +685,23 @@ STAGE PLANS:
         subq:fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 6 dataSize: 24 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (x = 484)
                   type: boolean
+              Statistics:
+                  numRows: 3 dataSize: 12 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: x
                       type: int
                 outputColumnNames: x
+                Statistics:
+                    numRows: 3 dataSize: 12 basicStatsState: COMPLETE colStatsState: NONE
                 Group By Operator
                   aggregations:
                         expr: count(1)
@@ -650,6 +711,8 @@ STAGE PLANS:
                         type: int
                   mode: hash
                   outputColumnNames: _col0, _col1
+                  Statistics:
+                      numRows: 3 dataSize: 12 basicStatsState: COMPLETE colStatsState: NONE
                   Reduce Output Operator
                     key expressions:
                           expr: _col0
@@ -658,6 +721,8 @@ STAGE PLANS:
                     Map-reduce partition columns:
                           expr: _col0
                           type: int
+                    Statistics:
+                        numRows: 3 dataSize: 12 basicStatsState: COMPLETE colStatsState: NONE
                     tag: -1
                     value expressions:
                           expr: _col1
@@ -673,15 +738,20 @@ STAGE PLANS:
             partition values:
               ds 1
             properties:
+              COLUMN_STATS_ACCURATE false
               bucket_count -1
               columns x,y
               columns.types int:string
 #### A masked pattern was here ####
               name default.fact_daily
+              numFiles 2
+              numRows -1
               partition_columns ds
+              rawDataSize -1
               serialization.ddl struct fact_daily { i32 x, string y}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 24
 #### A masked pattern was here ####
             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
           
@@ -715,6 +785,8 @@ STAGE PLANS:
                 type: int
           mode: mergepartial
           outputColumnNames: _col0, _col1
+          Statistics:
+              numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
           Select Operator
             expressions:
                   expr: _col0
@@ -722,11 +794,15 @@ STAGE PLANS:
                   expr: _col1
                   type: bigint
             outputColumnNames: _col0, _col1
+            Statistics:
+                numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
             File Output Operator
               compressed: false
               GlobalTableId: 0
 #### A masked pattern was here ####
               NumFilesPerFileSink: 1
+              Statistics:
+                  numRows: 1 dataSize: 4 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
               table:
                   input format: org.apache.hadoop.mapred.TextInputFormat
@@ -747,7 +823,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: -- List Bucketing Query
 select x, c from (select x, count(1) as c from fact_daily where ds = '1' group by x) subq where x = 484
 PREHOOK: type: QUERY

Modified: hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out Wed Dec 18 17:22:02 2013
@@ -201,6 +201,12 @@ Table:              	fact_daily         
 Protect Mode:       	None                	 
 #### A masked pattern was here ####
 Partition Parameters:	 	 
+	COLUMN_STATS_ACCURATE	false               
+#### A masked pattern was here ####
+	numFiles            	3                   
+	numRows             	-1                  
+	rawDataSize         	-1                  
+	totalSize           	117                 
 #### A masked pattern was here ####
 	 	 
 # Storage Information	 	 
@@ -272,22 +278,30 @@ STAGE PLANS:
         fact_daily 
           TableScan
             alias: fact_daily
+            Statistics:
+                numRows: 29 dataSize: 117 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate:
                   expr: (not (x = 86))
                   type: boolean
+              Statistics:
+                  numRows: 15 dataSize: 60 basicStatsState: COMPLETE colStatsState: NONE
               Select Operator
                 expressions:
                       expr: x
                       type: int
                 outputColumnNames: _col0
+                Statistics:
+                    numRows: 15 dataSize: 60 basicStatsState: COMPLETE colStatsState: NONE
                 Reduce Output Operator
                   key expressions:
                         expr: _col0
                         type: int
                   sort order: +
+                  Statistics:
+                      numRows: 15 dataSize: 60 basicStatsState: COMPLETE colStatsState: NONE
                   tag: -1
                   value expressions:
                         expr: _col0
@@ -303,15 +317,20 @@ STAGE PLANS:
             partition values:
               ds 1
             properties:
+              COLUMN_STATS_ACCURATE false
               bucket_count -1
               columns x,y,z
               columns.types int:string:string
 #### A masked pattern was here ####
               name default.fact_daily
+              numFiles 3
+              numRows -1
               partition_columns ds
+              rawDataSize -1
               serialization.ddl struct fact_daily { i32 x, string y, string z}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 117
 #### A masked pattern was here ####
             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
           
@@ -340,15 +359,20 @@ STAGE PLANS:
             partition values:
               ds 1
             properties:
+              COLUMN_STATS_ACCURATE false
               bucket_count -1
               columns x,y,z
               columns.types int:string:string
 #### A masked pattern was here ####
               name default.fact_daily
+              numFiles 3
+              numRows -1
               partition_columns ds
+              rawDataSize -1
               serialization.ddl struct fact_daily { i32 x, string y, string z}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 117
 #### A masked pattern was here ####
             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
           
@@ -377,15 +401,20 @@ STAGE PLANS:
             partition values:
               ds 1
             properties:
+              COLUMN_STATS_ACCURATE false
               bucket_count -1
               columns x,y,z
               columns.types int:string:string
 #### A masked pattern was here ####
               name default.fact_daily
+              numFiles 3
+              numRows -1
               partition_columns ds
+              rawDataSize -1
               serialization.ddl struct fact_daily { i32 x, string y, string z}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 117
 #### A masked pattern was here ####
             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
           
@@ -413,11 +442,15 @@ STAGE PLANS:
       Needs Tagging: false
       Reduce Operator Tree:
         Extract
+          Statistics:
+              numRows: 15 dataSize: 60 basicStatsState: COMPLETE colStatsState: NONE
           File Output Operator
             compressed: false
             GlobalTableId: 0
 #### A masked pattern was here ####
             NumFilesPerFileSink: 1
+            Statistics:
+                numRows: 15 dataSize: 60 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
             table:
                 input format: org.apache.hadoop.mapred.TextInputFormat
@@ -438,7 +471,6 @@ STAGE PLANS:
     Fetch Operator
       limit: -1
 
-
 PREHOOK: query: -- List Bucketing Query
 SELECT x FROM fact_daily WHERE ds='1' and not (x = 86) ORDER BY x
 PREHOOK: type: QUERY

Modified: hive/branches/tez/ql/src/test/results/clientpositive/stats_aggregator_error_1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/stats_aggregator_error_1.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/stats_aggregator_error_1.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/stats_aggregator_error_1.q.out Wed Dec 18 17:22:02 2013
@@ -19,6 +19,7 @@ PREHOOK: query: INSERT OVERWRITE TABLE t
 PREHOOK: type: QUERY
 PREHOOK: Input: default@src
 PREHOOK: Output: default@tmptable
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type custom cannot be connected to
 POSTHOOK: query: INSERT OVERWRITE TABLE tmptable select * from src
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@src
@@ -94,6 +95,7 @@ PREHOOK: query: INSERT OVERWRITE TABLE t
 PREHOOK: type: QUERY
 PREHOOK: Input: default@src
 PREHOOK: Output: default@tmptable
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30000]: StatsPublisher cannot be obtained. There was a error to retrieve the StatsPublisher, and retrying might help. If you dont want the query to fail because accurate statistics could not be collected, set hive.stats.reliable=false
 POSTHOOK: query: INSERT OVERWRITE TABLE tmptable select * from src
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@src

Modified: hive/branches/tez/ql/src/test/results/clientpositive/stats_counter.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/stats_counter.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/stats_counter.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/stats_counter.q.out Wed Dec 18 17:22:02 2013
@@ -1,13 +1,66 @@
-PREHOOK: query: create table dummy as select * from src
+PREHOOK: query: -- by analyze
+create table dummy1 as select * from src
 PREHOOK: type: CREATETABLE_AS_SELECT
 PREHOOK: Input: default@src
-POSTHOOK: query: create table dummy as select * from src
+POSTHOOK: query: -- by analyze
+create table dummy1 as select * from src
 POSTHOOK: type: CREATETABLE_AS_SELECT
 POSTHOOK: Input: default@src
-POSTHOOK: Output: default@dummy
-PREHOOK: query: desc formatted dummy
+POSTHOOK: Output: default@dummy1
+PREHOOK: query: analyze table dummy1 compute statistics
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dummy1
+PREHOOK: Output: default@dummy1
+POSTHOOK: query: analyze table dummy1 compute statistics
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dummy1
+POSTHOOK: Output: default@dummy1
+PREHOOK: query: desc formatted dummy1
 PREHOOK: type: DESCTABLE
-POSTHOOK: query: desc formatted dummy
+POSTHOOK: query: desc formatted dummy1
+POSTHOOK: type: DESCTABLE
+# col_name            	data_type           	comment             
+	 	 
+key                 	string              	None                
+value               	string              	None                
+	 	 
+# Detailed Table Information	 	 
+Database:           	default             	 
+#### A masked pattern was here ####
+Protect Mode:       	None                	 
+Retention:          	0                   	 
+#### A masked pattern was here ####
+Table Type:         	MANAGED_TABLE       	 
+Table Parameters:	 	 
+	COLUMN_STATS_ACCURATE	true                
+	numFiles            	1                   
+	numRows             	500                 
+	rawDataSize         	5312                
+	totalSize           	5812                
+#### A masked pattern was here ####
+	 	 
+# Storage Information	 	 
+SerDe Library:      	org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe	 
+InputFormat:        	org.apache.hadoop.mapred.TextInputFormat	 
+OutputFormat:       	org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat	 
+Compressed:         	No                  	 
+Num Buckets:        	-1                  	 
+Bucket Columns:     	[]                  	 
+Sort Columns:       	[]                  	 
+Storage Desc Params:	 	 
+	serialization.format	1                   
+PREHOOK: query: -- by autogather
+create table dummy2 as select * from src
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@src
+POSTHOOK: query: -- by autogather
+create table dummy2 as select * from src
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dummy2
+PREHOOK: query: desc formatted dummy2
+PREHOOK: type: DESCTABLE
+POSTHOOK: query: desc formatted dummy2
 POSTHOOK: type: DESCTABLE
 # col_name            	data_type           	comment             
 	 	 

Modified: hive/branches/tez/ql/src/test/results/clientpositive/stats_noscan_1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/stats_noscan_1.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/stats_noscan_1.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/stats_noscan_1.q.out Wed Dec 18 17:22:02 2013
@@ -135,8 +135,8 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
-	numRows             	0                   
-	rawDataSize         	0                   
+	numRows             	-1                  
+	rawDataSize         	-1                  
 	totalSize           	5812                
 #### A masked pattern was here ####
 	 	 
@@ -183,8 +183,8 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
-	numRows             	0                   
-	rawDataSize         	0                   
+	numRows             	-1                  
+	rawDataSize         	-1                  
 	totalSize           	5812                
 #### A masked pattern was here ####
 	 	 
@@ -510,8 +510,8 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
-	numRows             	0                   
-	rawDataSize         	0                   
+	numRows             	-1                  
+	rawDataSize         	-1                  
 	totalSize           	5812                
 #### A masked pattern was here ####
 	 	 
@@ -566,8 +566,8 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
-	numRows             	0                   
-	rawDataSize         	0                   
+	numRows             	-1                  
+	rawDataSize         	-1                  
 	totalSize           	5812                
 #### A masked pattern was here ####
 	 	 

Modified: hive/branches/tez/ql/src/test/results/clientpositive/stats_noscan_2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/stats_noscan_2.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/stats_noscan_2.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/stats_noscan_2.q.out Wed Dec 18 17:22:02 2013
@@ -21,11 +21,11 @@ POSTHOOK: Input: default@anaylyze_extern
 4
 5
 6
-PREHOOK: query: analyze table anaylyze_external compute statistics
+PREHOOK: query: analyze table anaylyze_external compute statistics noscan
 PREHOOK: type: QUERY
 PREHOOK: Input: default@anaylyze_external
 PREHOOK: Output: default@anaylyze_external
-POSTHOOK: query: analyze table anaylyze_external compute statistics
+POSTHOOK: query: analyze table anaylyze_external compute statistics noscan
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@anaylyze_external
 POSTHOOK: Output: default@anaylyze_external
@@ -48,8 +48,8 @@ Table Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	EXTERNAL            	TRUE                
 	numFiles            	0                   
-	numRows             	6                   
-	rawDataSize         	6                   
+	numRows             	-1                  
+	rawDataSize         	-1                  
 	totalSize           	0                   
 #### A masked pattern was here ####
 	 	 
@@ -63,11 +63,11 @@ Bucket Columns:     	[]                 
 Sort Columns:       	[]                  	 
 Storage Desc Params:	 	 
 	serialization.format	1                   
-PREHOOK: query: analyze table anaylyze_external compute statistics noscan
+PREHOOK: query: analyze table anaylyze_external compute statistics
 PREHOOK: type: QUERY
 PREHOOK: Input: default@anaylyze_external
 PREHOOK: Output: default@anaylyze_external
-POSTHOOK: query: analyze table anaylyze_external compute statistics noscan
+POSTHOOK: query: analyze table anaylyze_external compute statistics
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@anaylyze_external
 POSTHOOK: Output: default@anaylyze_external
@@ -90,8 +90,8 @@ Table Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	EXTERNAL            	TRUE                
 	numFiles            	0                   
-	numRows             	0                   
-	rawDataSize         	0                   
+	numRows             	6                   
+	rawDataSize         	6                   
 	totalSize           	0                   
 #### A masked pattern was here ####
 	 	 
@@ -184,14 +184,14 @@ POSTHOOK: Lineage: texternal PARTITION(i
 POSTHOOK: Lineage: texternal PARTITION(insertdate=2008-01-01).val SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
 500
 PREHOOK: query: -- analyze
-analyze table anaylyze_external PARTITION (insertdate='2008-01-01') compute statistics
+analyze table anaylyze_external PARTITION (insertdate='2008-01-01') compute statistics noscan
 PREHOOK: type: QUERY
 PREHOOK: Input: default@anaylyze_external
 PREHOOK: Input: default@anaylyze_external@insertdate=2008-01-01
 PREHOOK: Output: default@anaylyze_external
 PREHOOK: Output: default@anaylyze_external@insertdate=2008-01-01
 POSTHOOK: query: -- analyze
-analyze table anaylyze_external PARTITION (insertdate='2008-01-01') compute statistics
+analyze table anaylyze_external PARTITION (insertdate='2008-01-01') compute statistics noscan
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@anaylyze_external
 POSTHOOK: Input: default@anaylyze_external@insertdate=2008-01-01
@@ -225,8 +225,8 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
-	numRows             	500                 
-	rawDataSize         	5312                
+	numRows             	-1                  
+	rawDataSize         	-1                  
 	totalSize           	5812                
 #### A masked pattern was here ####
 	 	 
@@ -240,13 +240,13 @@ Bucket Columns:     	[]                 
 Sort Columns:       	[]                  	 
 Storage Desc Params:	 	 
 	serialization.format	1                   
-PREHOOK: query: analyze table anaylyze_external PARTITION (insertdate='2008-01-01') compute statistics noscan
+PREHOOK: query: analyze table anaylyze_external PARTITION (insertdate='2008-01-01') compute statistics
 PREHOOK: type: QUERY
 PREHOOK: Input: default@anaylyze_external
 PREHOOK: Input: default@anaylyze_external@insertdate=2008-01-01
 PREHOOK: Output: default@anaylyze_external
 PREHOOK: Output: default@anaylyze_external@insertdate=2008-01-01
-POSTHOOK: query: analyze table anaylyze_external PARTITION (insertdate='2008-01-01') compute statistics noscan
+POSTHOOK: query: analyze table anaylyze_external PARTITION (insertdate='2008-01-01') compute statistics
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@anaylyze_external
 POSTHOOK: Input: default@anaylyze_external@insertdate=2008-01-01
@@ -280,8 +280,8 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
-	numRows             	0                   
-	rawDataSize         	0                   
+	numRows             	500                 
+	rawDataSize         	5312                
 	totalSize           	5812                
 #### A masked pattern was here ####
 	 	 

Modified: hive/branches/tez/ql/src/test/results/clientpositive/stats_publisher_error_1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/stats_publisher_error_1.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/stats_publisher_error_1.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/stats_publisher_error_1.q.out Wed Dec 18 17:22:02 2013
@@ -94,6 +94,7 @@ PREHOOK: query: INSERT OVERWRITE TABLE t
 PREHOOK: type: QUERY
 PREHOOK: Input: default@src
 PREHOOK: Output: default@tmptable
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30000]: StatsPublisher cannot be obtained. There was a error to retrieve the StatsPublisher, and retrying might help. If you dont want the query to fail because accurate statistics could not be collected, set hive.stats.reliable=false
 POSTHOOK: query: INSERT OVERWRITE TABLE tmptable select * from src
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@src

Modified: hive/branches/tez/ql/src/test/results/clientpositive/tez/ctas.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/tez/ctas.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/tez/ctas.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/tez/ctas.q.out Wed Dec 18 17:22:02 2013
@@ -398,8 +398,8 @@ Table Type:         	MANAGED_TABLE      
 Table Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
-	numRows             	10                  
-	rawDataSize         	96                  
+	numRows             	0                   
+	rawDataSize         	0                   
 	totalSize           	106                 
 #### A masked pattern was here ####
 	 	 
@@ -576,8 +576,8 @@ Table Type:         	MANAGED_TABLE      
 Table Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
-	numRows             	10                  
-	rawDataSize         	120                 
+	numRows             	0                   
+	rawDataSize         	0                   
 	totalSize           	199                 
 #### A masked pattern was here ####
 	 	 
@@ -642,8 +642,8 @@ Table Type:         	MANAGED_TABLE      
 Table Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
-	numRows             	10                  
-	rawDataSize         	120                 
+	numRows             	0                   
+	rawDataSize         	0                   
 	totalSize           	199                 
 #### A masked pattern was here ####
 	 	 
@@ -669,7 +669,7 @@ STAGE DEPENDENCIES:
   Stage-8 depends on stages: Stage-1 , consists of Stage-5, Stage-4, Stage-6
   Stage-5
   Stage-2 depends on stages: Stage-5, Stage-4, Stage-7
-  Stage-9 depends on stages: Stage-2, Stage-0
+  Stage-9 depends on stages: Stage-0, Stage-2
   Stage-3 depends on stages: Stage-9
   Stage-0 depends on stages: Stage-5, Stage-4, Stage-7
   Stage-4
@@ -842,8 +842,8 @@ Table Type:         	MANAGED_TABLE      
 Table Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	1                   
-	numRows             	10                  
-	rawDataSize         	96                  
+	numRows             	0                   
+	rawDataSize         	0                   
 	totalSize           	106                 
 #### A masked pattern was here ####
 	 	 

Modified: hive/branches/tez/ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/tez/filter_join_breaktask.q.out Wed Dec 18 17:22:02 2013
@@ -42,7 +42,7 @@ STAGE PLANS:
           TableScan
             alias: f
             Statistics:
-                numRows: 25 dataSize: 211 basicStatsState: COMPLETE colStatsState: NONE
+                numRows: 59 dataSize: 236 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
@@ -50,7 +50,7 @@ STAGE PLANS:
                   expr: key is not null
                   type: boolean
               Statistics:
-                  numRows: 13 dataSize: 109 basicStatsState: COMPLETE colStatsState: NONE
+                  numRows: 30 dataSize: 120 basicStatsState: COMPLETE colStatsState: NONE
               Reduce Output Operator
                 key expressions:
                       expr: key
@@ -60,7 +60,7 @@ STAGE PLANS:
                       expr: key
                       type: int
                 Statistics:
-                    numRows: 13 dataSize: 109 basicStatsState: COMPLETE colStatsState: NONE
+                    numRows: 30 dataSize: 120 basicStatsState: COMPLETE colStatsState: NONE
                 tag: 0
                 value expressions:
                       expr: key
@@ -82,9 +82,9 @@ STAGE PLANS:
 #### A masked pattern was here ####
               name default.filter_join_breaktask
               numFiles 1
-              numRows 25
+              numRows 0
               partition_columns ds
-              rawDataSize 211
+              rawDataSize 0
               serialization.ddl struct filter_join_breaktask { i32 key, string value}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -115,7 +115,7 @@ STAGE PLANS:
           TableScan
             alias: m
             Statistics:
-                numRows: 25 dataSize: 211 basicStatsState: COMPLETE colStatsState: NONE
+                numRows: 2 dataSize: 236 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
@@ -123,7 +123,7 @@ STAGE PLANS:
                   expr: ((key is not null and value is not null) and (value <> ''))
                   type: boolean
               Statistics:
-                  numRows: 7 dataSize: 59 basicStatsState: COMPLETE colStatsState: NONE
+                  numRows: 1 dataSize: 118 basicStatsState: COMPLETE colStatsState: NONE
               Reduce Output Operator
                 key expressions:
                       expr: key
@@ -133,7 +133,7 @@ STAGE PLANS:
                       expr: key
                       type: int
                 Statistics:
-                    numRows: 7 dataSize: 59 basicStatsState: COMPLETE colStatsState: NONE
+                    numRows: 1 dataSize: 118 basicStatsState: COMPLETE colStatsState: NONE
                 tag: 1
                 value expressions:
                       expr: value
@@ -155,9 +155,9 @@ STAGE PLANS:
 #### A masked pattern was here ####
               name default.filter_join_breaktask
               numFiles 1
-              numRows 25
+              numRows 0
               partition_columns ds
-              rawDataSize 211
+              rawDataSize 0
               serialization.ddl struct filter_join_breaktask { i32 key, string value}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -194,7 +194,7 @@ STAGE PLANS:
           handleSkewJoin: false
           outputColumnNames: _col0, _col6
           Statistics:
-              numRows: 14 dataSize: 119 basicStatsState: COMPLETE colStatsState: NONE
+              numRows: 33 dataSize: 132 basicStatsState: COMPLETE colStatsState: NONE
           Reduce Output Operator
             key expressions:
                   expr: _col6
@@ -204,7 +204,7 @@ STAGE PLANS:
                   expr: _col6
                   type: string
             Statistics:
-                numRows: 14 dataSize: 119 basicStatsState: COMPLETE colStatsState: NONE
+                numRows: 33 dataSize: 132 basicStatsState: COMPLETE colStatsState: NONE
             tag: 0
             value expressions:
                   expr: _col0
@@ -214,7 +214,7 @@ STAGE PLANS:
           TableScan
             alias: g
             Statistics:
-                numRows: 25 dataSize: 211 basicStatsState: COMPLETE colStatsState: NONE
+                numRows: 2 dataSize: 236 basicStatsState: COMPLETE colStatsState: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
@@ -222,7 +222,7 @@ STAGE PLANS:
                   expr: (value <> '')
                   type: boolean
               Statistics:
-                  numRows: 25 dataSize: 211 basicStatsState: COMPLETE colStatsState: NONE
+                  numRows: 2 dataSize: 236 basicStatsState: COMPLETE colStatsState: NONE
               Reduce Output Operator
                 key expressions:
                       expr: value
@@ -232,7 +232,7 @@ STAGE PLANS:
                       expr: value
                       type: string
                 Statistics:
-                    numRows: 25 dataSize: 211 basicStatsState: COMPLETE colStatsState: NONE
+                    numRows: 2 dataSize: 236 basicStatsState: COMPLETE colStatsState: NONE
                 tag: 1
                 value expressions:
                       expr: value
@@ -254,9 +254,9 @@ STAGE PLANS:
 #### A masked pattern was here ####
               name default.filter_join_breaktask
               numFiles 1
-              numRows 25
+              numRows 0
               partition_columns ds
-              rawDataSize 211
+              rawDataSize 0
               serialization.ddl struct filter_join_breaktask { i32 key, string value}
               serialization.format 1
               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -293,7 +293,7 @@ STAGE PLANS:
           handleSkewJoin: false
           outputColumnNames: _col0, _col11
           Statistics:
-              numRows: 27 dataSize: 232 basicStatsState: COMPLETE colStatsState: NONE
+              numRows: 36 dataSize: 145 basicStatsState: COMPLETE colStatsState: NONE
           Select Operator
             expressions:
                   expr: _col0
@@ -302,14 +302,14 @@ STAGE PLANS:
                   type: string
             outputColumnNames: _col0, _col1
             Statistics:
-                numRows: 27 dataSize: 232 basicStatsState: COMPLETE colStatsState: NONE
+                numRows: 36 dataSize: 145 basicStatsState: COMPLETE colStatsState: NONE
             File Output Operator
               compressed: false
               GlobalTableId: 0
 #### A masked pattern was here ####
               NumFilesPerFileSink: 1
               Statistics:
-                  numRows: 27 dataSize: 232 basicStatsState: COMPLETE colStatsState: NONE
+                  numRows: 36 dataSize: 145 basicStatsState: COMPLETE colStatsState: NONE
 #### A masked pattern was here ####
               table:
                   input format: org.apache.hadoop.mapred.TextInputFormat

Modified: hive/branches/tez/ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out
URL: http://svn.apache.org/viewvc/hive/branches/tez/ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out?rev=1552041&r1=1552040&r2=1552041&view=diff
==============================================================================
--- hive/branches/tez/ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out (original)
+++ hive/branches/tez/ql/src/test/results/clientpositive/tez/metadata_only_queries.q.out Wed Dec 18 17:22:02 2013
@@ -813,18 +813,132 @@ ABSTRACT SYNTAX TREE:
   (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME stats_tbl))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTIONSTAR count)) (TOK_SELEXPR (TOK_FUNCTION count 1)) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL s))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL bo))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL bin))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL si))) (TOK_SELEXPR (TOK_FUNCTION max (TOK_TABLE_OR_COL i))) (TOK_SELEXPR (TOK_FUNCTION min (TOK_TABLE_OR_COL b))) (TOK_SELEXPR (TOK_FUNCTION max (TOK_TABLE_OR_COL f))) (TOK_SELEXPR (TOK_FUNCTION min (TOK_TABLE_OR_COL d))))))
 
 STAGE DEPENDENCIES:
+  Stage-1 is a root stage
   Stage-0 is a root stage
 
 STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Alias -> Map Operator Tree:
+        stats_tbl 
+          TableScan
+            alias: stats_tbl
+            Select Operator
+              expressions:
+                    expr: s
+                    type: string
+                    expr: bo
+                    type: boolean
+                    expr: bin
+                    type: binary
+                    expr: si
+                    type: smallint
+                    expr: i
+                    type: int
+                    expr: b
+                    type: bigint
+                    expr: f
+                    type: float
+                    expr: d
+                    type: double
+              outputColumnNames: s, bo, bin, si, i, b, f, d
+              Group By Operator
+                aggregations:
+                      expr: count()
+                      expr: count(1)
+                      expr: count(s)
+                      expr: count(bo)
+                      expr: count(bin)
+                      expr: count(si)
+                      expr: max(i)
+                      expr: min(b)
+                      expr: max(f)
+                      expr: min(d)
+                bucketGroup: false
+                mode: hash
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+                Reduce Output Operator
+                  sort order: 
+                  tag: -1
+                  value expressions:
+                        expr: _col0
+                        type: bigint
+                        expr: _col1
+                        type: bigint
+                        expr: _col2
+                        type: bigint
+                        expr: _col3
+                        type: bigint
+                        expr: _col4
+                        type: bigint
+                        expr: _col5
+                        type: bigint
+                        expr: _col6
+                        type: int
+                        expr: _col7
+                        type: bigint
+                        expr: _col8
+                        type: float
+                        expr: _col9
+                        type: double
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: count(VALUE._col0)
+                expr: count(VALUE._col1)
+                expr: count(VALUE._col2)
+                expr: count(VALUE._col3)
+                expr: count(VALUE._col4)
+                expr: count(VALUE._col5)
+                expr: max(VALUE._col6)
+                expr: min(VALUE._col7)
+                expr: max(VALUE._col8)
+                expr: min(VALUE._col9)
+          bucketGroup: false
+          mode: mergepartial
+          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: bigint
+                  expr: _col1
+                  type: bigint
+                  expr: _col2
+                  type: bigint
+                  expr: _col3
+                  type: bigint
+                  expr: _col4
+                  type: bigint
+                  expr: _col5
+                  type: bigint
+                  expr: _col6
+                  type: int
+                  expr: _col7
+                  type: bigint
+                  expr: _col8
+                  type: float
+                  expr: _col9
+                  type: double
+            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
   Stage: Stage-0
     Fetch Operator
-      limit: 1
+      limit: -1
 
 PREHOOK: query: select count(*), count(1), count(s), count(bo), count(bin), count(si), max(i), min(b), max(f), min(d) from stats_tbl
 PREHOOK: type: QUERY
+PREHOOK: Input: default@stats_tbl
 #### A masked pattern was here ####
 POSTHOOK: query: select count(*), count(1), count(s), count(bo), count(bin), count(si), max(i), min(b), max(f), min(d) from stats_tbl
 POSTHOOK: type: QUERY
+POSTHOOK: Input: default@stats_tbl
 #### A masked pattern was here ####
 POSTHOOK: Lineage: stats_tbl.b SIMPLE [(over10k)over10k.FieldSchema(name:b, type:bigint, comment:null), ]
 POSTHOOK: Lineage: stats_tbl.bin SIMPLE [(over10k)over10k.FieldSchema(name:bin, type:binary, comment:null), ]
@@ -870,7 +984,7 @@ POSTHOOK: Lineage: stats_tbl_part PARTIT
 POSTHOOK: Lineage: stats_tbl_part PARTITION(dt=2012).si SIMPLE [(over10k)over10k.FieldSchema(name:si, type:smallint, comment:null), ]
 POSTHOOK: Lineage: stats_tbl_part PARTITION(dt=2012).t SIMPLE [(over10k)over10k.FieldSchema(name:t, type:tinyint, comment:null), ]
 POSTHOOK: Lineage: stats_tbl_part PARTITION(dt=2012).ts SIMPLE [(over10k)over10k.FieldSchema(name:ts, type:timestamp, comment:null), ]
-9999	9999	9999	9999	9999	9999	65791	0	99.9800033569336	0.0
+9999	9999	9999	9999	9999	9999	65791	4294967296	99.98	0.01
 PREHOOK: query: explain 
 select count(*), count(1), count(s), count(bo), count(bin), count(si), max(i), min(b), max(f), min(d) from stats_tbl_part
 PREHOOK: type: QUERY
@@ -925,18 +1039,138 @@ ABSTRACT SYNTAX TREE:
   (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME stats_tbl_part))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTIONSTAR count)) (TOK_SELEXPR (TOK_FUNCTION count 1)) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL s))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL bo))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL bin))) (TOK_SELEXPR (TOK_FUNCTION count (TOK_TABLE_OR_COL si))) (TOK_SELEXPR (TOK_FUNCTION max (TOK_TABLE_OR_COL i))) (TOK_SELEXPR (TOK_FUNCTION min (TOK_TABLE_OR_COL b))) (TOK_SELEXPR (TOK_FUNCTION max (TOK_TABLE_OR_COL f))) (TOK_SELEXPR (TOK_FUNCTION min (TOK_TABLE_OR_COL d))))))
 
 STAGE DEPENDENCIES:
+  Stage-1 is a root stage
   Stage-0 is a root stage
 
 STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Alias -> Map Operator Tree:
+        stats_tbl_part 
+          TableScan
+            alias: stats_tbl_part
+            Select Operator
+              expressions:
+                    expr: s
+                    type: string
+                    expr: bo
+                    type: boolean
+                    expr: bin
+                    type: binary
+                    expr: si
+                    type: smallint
+                    expr: i
+                    type: int
+                    expr: b
+                    type: bigint
+                    expr: f
+                    type: float
+                    expr: d
+                    type: double
+              outputColumnNames: s, bo, bin, si, i, b, f, d
+              Group By Operator
+                aggregations:
+                      expr: count()
+                      expr: count(1)
+                      expr: count(s)
+                      expr: count(bo)
+                      expr: count(bin)
+                      expr: count(si)
+                      expr: max(i)
+                      expr: min(b)
+                      expr: max(f)
+                      expr: min(d)
+                bucketGroup: false
+                mode: hash
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+                Reduce Output Operator
+                  sort order: 
+                  tag: -1
+                  value expressions:
+                        expr: _col0
+                        type: bigint
+                        expr: _col1
+                        type: bigint
+                        expr: _col2
+                        type: bigint
+                        expr: _col3
+                        type: bigint
+                        expr: _col4
+                        type: bigint
+                        expr: _col5
+                        type: bigint
+                        expr: _col6
+                        type: int
+                        expr: _col7
+                        type: bigint
+                        expr: _col8
+                        type: float
+                        expr: _col9
+                        type: double
+      Reduce Operator Tree:
+        Group By Operator
+          aggregations:
+                expr: count(VALUE._col0)
+                expr: count(VALUE._col1)
+                expr: count(VALUE._col2)
+                expr: count(VALUE._col3)
+                expr: count(VALUE._col4)
+                expr: count(VALUE._col5)
+                expr: max(VALUE._col6)
+                expr: min(VALUE._col7)
+                expr: max(VALUE._col8)
+                expr: min(VALUE._col9)
+          bucketGroup: false
+          mode: mergepartial
+          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+          Select Operator
+            expressions:
+                  expr: _col0
+                  type: bigint
+                  expr: _col1
+                  type: bigint
+                  expr: _col2
+                  type: bigint
+                  expr: _col3
+                  type: bigint
+                  expr: _col4
+                  type: bigint
+                  expr: _col5
+                  type: bigint
+                  expr: _col6
+                  type: int
+                  expr: _col7
+                  type: bigint
+                  expr: _col8
+                  type: float
+                  expr: _col9
+                  type: double
+            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
   Stage: Stage-0
     Fetch Operator
-      limit: 1
+      limit: -1
 
 PREHOOK: query: select count(*), count(1), count(s), count(bo), count(bin), count(si), max(i), min(b), max(f), min(d) from stats_tbl_part
 PREHOOK: type: QUERY
+PREHOOK: Input: default@stats_tbl_part
+PREHOOK: Input: default@stats_tbl_part@dt=2010
+PREHOOK: Input: default@stats_tbl_part@dt=2011
+PREHOOK: Input: default@stats_tbl_part@dt=2012
 #### A masked pattern was here ####
 POSTHOOK: query: select count(*), count(1), count(s), count(bo), count(bin), count(si), max(i), min(b), max(f), min(d) from stats_tbl_part
 POSTHOOK: type: QUERY
+POSTHOOK: Input: default@stats_tbl_part
+POSTHOOK: Input: default@stats_tbl_part@dt=2010
+POSTHOOK: Input: default@stats_tbl_part@dt=2011
+POSTHOOK: Input: default@stats_tbl_part@dt=2012
 #### A masked pattern was here ####
 POSTHOOK: Lineage: stats_tbl.b SIMPLE [(over10k)over10k.FieldSchema(name:b, type:bigint, comment:null), ]
 POSTHOOK: Lineage: stats_tbl.bin SIMPLE [(over10k)over10k.FieldSchema(name:bin, type:binary, comment:null), ]
@@ -982,7 +1216,7 @@ POSTHOOK: Lineage: stats_tbl_part PARTIT
 POSTHOOK: Lineage: stats_tbl_part PARTITION(dt=2012).si SIMPLE [(over10k)over10k.FieldSchema(name:si, type:smallint, comment:null), ]
 POSTHOOK: Lineage: stats_tbl_part PARTITION(dt=2012).t SIMPLE [(over10k)over10k.FieldSchema(name:t, type:tinyint, comment:null), ]
 POSTHOOK: Lineage: stats_tbl_part PARTITION(dt=2012).ts SIMPLE [(over10k)over10k.FieldSchema(name:ts, type:timestamp, comment:null), ]
-9489	9489	9489	9489	9489	9489	65791	0	99.9800033569336	0.0
+9489	9489	9489	9489	9489	9489	65791	4294967296	99.98	0.01
 PREHOOK: query: explain select count(ts) from stats_tbl_part
 PREHOOK: type: QUERY
 POSTHOOK: query: explain select count(ts) from stats_tbl_part



Mime
View raw message