hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From hashut...@apache.org
Subject [29/51] [partial] hive git commit: HIVE-13567 : Enable auto-gather column stats by default (Zoltan Haindrich, Pengcheng Xiong via Ashutosh Chauhan)
Date Tue, 12 Dec 2017 00:00:27 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_13.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_13.q.out
index a6d7309..b78a517 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_13.q.out
+++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_13.q.out
@@ -79,21 +79,23 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 1 <- Map 2 (BROADCAST_EDGE)
+        Map 1 <- Map 4 (BROADCAST_EDGE)
+        Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+        Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats:
COMPLETE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -102,54 +104,110 @@ STAGE PLANS:
                           1 _col0 (type: int)
                         outputColumnNames: _col0, _col1, _col2, _col3
                         input vertices:
-                          1 Map 2
-                        Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column
stats: NONE
+                          1 Map 4
+                        Statistics: Num rows: 16 Data size: 2976 Basic stats: COMPLETE Column
stats: COMPLETE
                         Select Operator
                           expressions: _col0 (type: int), _col2 (type: int)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                          Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column
stats: COMPLETE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                            Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE
Column stats: COMPLETE
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                                 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                                 name: default.dest1
+                          Select Operator
+                            expressions: _col0 (type: int), _col1 (type: int)
+                            outputColumnNames: k1, k2
+                            Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE
Column stats: COMPLETE
+                            Group By Operator
+                              aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll')
+                              mode: hash
+                              outputColumnNames: _col0, _col1
+                              Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE
Column stats: COMPLETE
+                              Reduce Output Operator
+                                sort order: 
+                                Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE
Column stats: COMPLETE
+                                value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>),
_col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
                         Select Operator
                           expressions: _col1 (type: string), _col3 (type: string)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                          Statistics: Num rows: 16 Data size: 2848 Basic stats: COMPLETE
Column stats: COMPLETE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                            Statistics: Num rows: 16 Data size: 2848 Basic stats: COMPLETE
Column stats: COMPLETE
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                                 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                                 name: default.dest2
+                          Select Operator
+                            expressions: _col0 (type: string), _col1 (type: string)
+                            outputColumnNames: k1, k2
+                            Statistics: Num rows: 16 Data size: 2848 Basic stats: COMPLETE
Column stats: COMPLETE
+                            Group By Operator
+                              aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll')
+                              mode: hash
+                              outputColumnNames: _col0, _col1
+                              Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE
Column stats: COMPLETE
+                              Reduce Output Operator
+                                sort order: 
+                                Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE
Column stats: COMPLETE
+                                value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>),
_col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
             Execution mode: llap
             LLAP IO: no inputs
-        Map 2 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats:
COMPLETE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                       Reduce Output Operator
                         key expressions: _col0 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: int)
-                        Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                         value expressions: _col1 (type: string)
             Execution mode: llap
             LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            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: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+        Reducer 3 
+            Execution mode: llap
+            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: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-3
     Dependency Collection
@@ -167,6 +225,10 @@ STAGE PLANS:
   Stage: Stage-4
     Stats Work
       Basic Stats Work:
+      Column Stats Desc:
+          Columns: k1, k2
+          Column Types: int, int
+          Table: default.dest1
 
   Stage: Stage-1
     Move Operator
@@ -181,6 +243,10 @@ STAGE PLANS:
   Stage: Stage-5
     Stats Work
       Basic Stats Work:
+      Column Stats Desc:
+          Columns: k1, k2
+          Column Types: string, string
+          Table: default.dest2
 
 PREHOOK: query: from (
   SELECT a.key key1, a.value value1, b.key key2, b.value value2 
@@ -296,30 +362,34 @@ STAGE PLANS:
   Stage: Stage-2
     Tez
 #### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+        Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats:
COMPLETE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats:
COMPLETE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                       Merge Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -327,32 +397,88 @@ STAGE PLANS:
                           0 _col0 (type: int)
                           1 _col0 (type: int)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 16 Data size: 2976 Basic stats: COMPLETE Column
stats: COMPLETE
                         Select Operator
                           expressions: _col0 (type: int), _col2 (type: int)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                          Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column
stats: COMPLETE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                            Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE
Column stats: COMPLETE
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                                 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                                 name: default.dest1
+                          Select Operator
+                            expressions: _col0 (type: int), _col1 (type: int)
+                            outputColumnNames: k1, k2
+                            Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE
Column stats: COMPLETE
+                            Group By Operator
+                              aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll')
+                              mode: hash
+                              outputColumnNames: _col0, _col1
+                              Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE
Column stats: COMPLETE
+                              Reduce Output Operator
+                                sort order: 
+                                Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE
Column stats: COMPLETE
+                                value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>),
_col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
                         Select Operator
                           expressions: _col1 (type: string), _col3 (type: string)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                          Statistics: Num rows: 16 Data size: 2848 Basic stats: COMPLETE
Column stats: COMPLETE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                            Statistics: Num rows: 16 Data size: 2848 Basic stats: COMPLETE
Column stats: COMPLETE
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                                 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                                 name: default.dest2
+                          Select Operator
+                            expressions: _col0 (type: string), _col1 (type: string)
+                            outputColumnNames: k1, k2
+                            Statistics: Num rows: 16 Data size: 2848 Basic stats: COMPLETE
Column stats: COMPLETE
+                            Group By Operator
+                              aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll')
+                              mode: hash
+                              outputColumnNames: _col0, _col1
+                              Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE
Column stats: COMPLETE
+                              Reduce Output Operator
+                                sort order: 
+                                Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE
Column stats: COMPLETE
+                                value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>),
_col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+            Execution mode: llap
+        Reducer 2 
             Execution mode: llap
+            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: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+        Reducer 3 
+            Execution mode: llap
+            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: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-3
     Dependency Collection
@@ -370,6 +496,10 @@ STAGE PLANS:
   Stage: Stage-4
     Stats Work
       Basic Stats Work:
+      Column Stats Desc:
+          Columns: k1, k2
+          Column Types: int, int
+          Table: default.dest1
 
   Stage: Stage-1
     Move Operator
@@ -384,6 +514,10 @@ STAGE PLANS:
   Stage: Stage-5
     Stats Work
       Basic Stats Work:
+      Column Stats Desc:
+          Columns: k1, k2
+          Column Types: string, string
+          Table: default.dest2
 
 PREHOOK: query: from (
   SELECT a.key key1, a.value value1, b.key key2, b.value value2 
@@ -499,30 +633,34 @@ STAGE PLANS:
   Stage: Stage-2
     Tez
 #### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+        Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats:
COMPLETE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats:
COMPLETE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 10 Data size: 1880 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column
stats: COMPLETE
                       Merge Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -530,32 +668,88 @@ STAGE PLANS:
                           0 _col0 (type: int)
                           1 _col0 (type: int)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 16 Data size: 2976 Basic stats: COMPLETE Column
stats: COMPLETE
                         Select Operator
                           expressions: _col0 (type: int), _col2 (type: int)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                          Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column
stats: COMPLETE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                            Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE
Column stats: COMPLETE
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                                 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                                 name: default.dest1
+                          Select Operator
+                            expressions: _col0 (type: int), _col1 (type: int)
+                            outputColumnNames: k1, k2
+                            Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE
Column stats: COMPLETE
+                            Group By Operator
+                              aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll')
+                              mode: hash
+                              outputColumnNames: _col0, _col1
+                              Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE
Column stats: COMPLETE
+                              Reduce Output Operator
+                                sort order: 
+                                Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE
Column stats: COMPLETE
+                                value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>),
_col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
                         Select Operator
                           expressions: _col1 (type: string), _col3 (type: string)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                          Statistics: Num rows: 16 Data size: 2848 Basic stats: COMPLETE
Column stats: COMPLETE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE
Column stats: NONE
+                            Statistics: Num rows: 16 Data size: 2848 Basic stats: COMPLETE
Column stats: COMPLETE
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                                 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                                 name: default.dest2
+                          Select Operator
+                            expressions: _col0 (type: string), _col1 (type: string)
+                            outputColumnNames: k1, k2
+                            Statistics: Num rows: 16 Data size: 2848 Basic stats: COMPLETE
Column stats: COMPLETE
+                            Group By Operator
+                              aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll')
+                              mode: hash
+                              outputColumnNames: _col0, _col1
+                              Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE
Column stats: COMPLETE
+                              Reduce Output Operator
+                                sort order: 
+                                Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE
Column stats: COMPLETE
+                                value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>),
_col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+            Execution mode: llap
+        Reducer 2 
+            Execution mode: llap
+            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: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+        Reducer 3 
             Execution mode: llap
+            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: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats:
COMPLETE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-3
     Dependency Collection
@@ -573,6 +767,10 @@ STAGE PLANS:
   Stage: Stage-4
     Stats Work
       Basic Stats Work:
+      Column Stats Desc:
+          Columns: k1, k2
+          Column Types: int, int
+          Table: default.dest1
 
   Stage: Stage-1
     Move Operator
@@ -587,6 +785,10 @@ STAGE PLANS:
   Stage: Stage-5
     Stats Work
       Basic Stats Work:
+      Column Stats Desc:
+          Columns: k1, k2
+          Column Types: string, string
+          Table: default.dest2
 
 PREHOOK: query: from (
   SELECT a.key key1, a.value value1, b.key key2, b.value value2 

http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_14.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_14.q.out
index 2d03e8c..72d2c62 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_14.q.out
+++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_14.q.out
@@ -57,11 +57,11 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
COMPLETE
                   Select Operator
                     expressions: key (type: int)
                     outputColumnNames: _col0
-                    Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
COMPLETE
                     Map Join Operator
                       condition map:
                            Left Outer Join 0 to 1
@@ -70,15 +70,15 @@ STAGE PLANS:
                         1 _col0 (type: int)
                       input vertices:
                         1 Map 3
-                      Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column
stats: COMPLETE
                       Group By Operator
                         aggregations: count()
                         mode: hash
                         outputColumnNames: _col0
-                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE
                         Reduce Output Operator
                           sort order: 
-                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE
                           value expressions: _col0 (type: bigint)
             Execution mode: llap
             LLAP IO: no inputs
@@ -86,16 +86,16 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
COMPLETE
                   Select Operator
                     expressions: key (type: int)
                     outputColumnNames: _col0
-                    Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
COMPLETE
                     Reduce Output Operator
                       key expressions: _col0 (type: int)
                       sort order: +
                       Map-reduce partition columns: _col0 (type: int)
-                      Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column
stats: COMPLETE
             Execution mode: llap
             LLAP IO: no inputs
         Reducer 2 
@@ -105,10 +105,10 @@ STAGE PLANS:
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
COMPLETE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -164,27 +164,27 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
COMPLETE
                   Select Operator
                     expressions: key (type: int)
                     outputColumnNames: _col0
-                    Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
COMPLETE
                     Reduce Output Operator
                       key expressions: _col0 (type: int)
                       sort order: +
                       Map-reduce partition columns: _col0 (type: int)
-                      Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column
stats: COMPLETE
             Execution mode: llap
             LLAP IO: no inputs
         Map 2 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 189 Data size: 724 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 189 Data size: 756 Basic stats: COMPLETE Column stats:
COMPLETE
                   Select Operator
                     expressions: key (type: int)
                     outputColumnNames: _col0
-                    Statistics: Num rows: 189 Data size: 724 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 189 Data size: 756 Basic stats: COMPLETE Column
stats: COMPLETE
                     Map Join Operator
                       condition map:
                            Right Outer Join 0 to 1
@@ -193,15 +193,15 @@ STAGE PLANS:
                         1 _col0 (type: int)
                       input vertices:
                         0 Map 1
-                      Statistics: Num rows: 207 Data size: 796 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 189 Data size: 1512 Basic stats: COMPLETE Column
stats: COMPLETE
                       Group By Operator
                         aggregations: count()
                         mode: hash
                         outputColumnNames: _col0
-                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE
                         Reduce Output Operator
                           sort order: 
-                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE
                           value expressions: _col0 (type: bigint)
             Execution mode: llap
             LLAP IO: no inputs
@@ -212,10 +212,10 @@ STAGE PLANS:
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
COMPLETE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
COMPLETE
                   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/3bbc24d2/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_15.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_15.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_15.q.out
index ce41569..91b1d8e 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_15.q.out
+++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_15.q.out
@@ -57,11 +57,11 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
COMPLETE
                   Select Operator
                     expressions: key (type: int)
                     outputColumnNames: _col0
-                    Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
COMPLETE
                     Map Join Operator
                       condition map:
                            Left Outer Join 0 to 1
@@ -70,15 +70,15 @@ STAGE PLANS:
                         1 _col0 (type: int)
                       input vertices:
                         1 Map 3
-                      Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column
stats: COMPLETE
                       Group By Operator
                         aggregations: count()
                         mode: hash
                         outputColumnNames: _col0
-                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE
                         Reduce Output Operator
                           sort order: 
-                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE
                           value expressions: _col0 (type: bigint)
             Execution mode: llap
             LLAP IO: no inputs
@@ -86,16 +86,16 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
COMPLETE
                   Select Operator
                     expressions: key (type: int)
                     outputColumnNames: _col0
-                    Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
COMPLETE
                     Reduce Output Operator
                       key expressions: _col0 (type: int)
                       sort order: +
                       Map-reduce partition columns: _col0 (type: int)
-                      Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column
stats: COMPLETE
             Execution mode: llap
             LLAP IO: no inputs
         Reducer 2 
@@ -105,10 +105,10 @@ STAGE PLANS:
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
COMPLETE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -143,27 +143,27 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
COMPLETE
                   Select Operator
                     expressions: key (type: int)
                     outputColumnNames: _col0
-                    Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats:
COMPLETE
                     Reduce Output Operator
                       key expressions: _col0 (type: int)
                       sort order: +
                       Map-reduce partition columns: _col0 (type: int)
-                      Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column
stats: COMPLETE
             Execution mode: llap
             LLAP IO: no inputs
         Map 2 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
COMPLETE
                   Select Operator
                     expressions: key (type: int)
                     outputColumnNames: _col0
-                    Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats:
COMPLETE
                     Map Join Operator
                       condition map:
                            Right Outer Join 0 to 1
@@ -172,15 +172,15 @@ STAGE PLANS:
                         1 _col0 (type: int)
                       input vertices:
                         0 Map 1
-                      Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column
stats: COMPLETE
                       Group By Operator
                         aggregations: count()
                         mode: hash
                         outputColumnNames: _col0
-                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE
                         Reduce Output Operator
                           sort order: 
-                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE
                           value expressions: _col0 (type: bigint)
             Execution mode: llap
             LLAP IO: no inputs
@@ -191,10 +191,10 @@ STAGE PLANS:
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
COMPLETE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
COMPLETE
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat


Mime
View raw message