hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From vg...@apache.org
Subject [2/2] hive git commit: HIVE-17400 : Estimate stats in absence of stats for complex types (Vineet Garg, reviewed by Ashutosh Chauhan)
Date Fri, 29 Sep 2017 19:56:36 GMT
HIVE-17400 : Estimate stats in absence of stats for complex types (Vineet Garg, reviewed by Ashutosh Chauhan)


Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/281965e5
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/281965e5
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/281965e5

Branch: refs/heads/master
Commit: 281965e5b3f6d7f001c1188f653f1e30b44dbeee
Parents: 0f7ce71
Author: Vineet Garg <vgarg@apache.com>
Authored: Fri Sep 29 12:55:52 2017 -0700
Committer: Vineet Garg <vgarg@apache.com>
Committed: Fri Sep 29 12:55:52 2017 -0700

----------------------------------------------------------------------
 .../apache/hadoop/hive/ql/stats/StatsUtils.java |   3 +-
 .../clientpositive/annotate_stats_select.q.out  |  16 +-
 .../clientpositive/llap/lateral_view.q.out      |  32 +--
 .../clientpositive/llap/lvj_mapjoin.q.out       |  60 +++---
 ...chema_evol_orc_nonvec_part_all_complex.q.out |  18 +-
 .../schema_evol_orc_vec_part_all_complex.q.out  |  18 +-
 ...hema_evol_text_nonvec_part_all_complex.q.out |  18 +-
 .../schema_evol_text_vec_part_all_complex.q.out |  18 +-
 ...hema_evol_text_vecrow_part_all_complex.q.out |  18 +-
 .../llap/tez_join_result_complex.q.out          | 212 +++++++++----------
 .../clientpositive/llap/unionDistinct_1.q.out   |   4 +-
 .../llap/vector_complex_all.q.out               |  86 ++++----
 .../llap/vector_complex_join.q.out              |  14 +-
 13 files changed, 258 insertions(+), 259 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/hive/blob/281965e5/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java b/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java
index fde8c53..9ffd12a 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java
@@ -1065,8 +1065,7 @@ public class StatsUtils {
       // epoch, days since epoch
       cs.setRange(0, 25201);
     } else {
-      // Columns statistics for complex datatypes are not supported yet
-      return null;
+      cs.setAvgColLen(getSizeOfComplexTypes(conf, cinfo.getObjectInspector()));
     }
     return cs;
   }

http://git-wip-us.apache.org/repos/asf/hive/blob/281965e5/ql/src/test/results/clientpositive/annotate_stats_select.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/annotate_stats_select.q.out b/ql/src/test/results/clientpositive/annotate_stats_select.q.out
index 7f5b832..c756945 100644
--- a/ql/src/test/results/clientpositive/annotate_stats_select.q.out
+++ b/ql/src/test/results/clientpositive/annotate_stats_select.q.out
@@ -103,11 +103,11 @@ STAGE PLANS:
       Processor Tree:
         TableScan
           alias: alltypes_orc
-          Statistics: Num rows: 2 Data size: 1002 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 2 Data size: 3554 Basic stats: COMPLETE Column stats: NONE
           Select Operator
             expressions: bo1 (type: boolean), ti1 (type: tinyint), si1 (type: smallint), i1 (type: int), bi1 (type: bigint), f1 (type: float), d1 (type: double), de1 (type: decimal(10,0)), ts1 (type: timestamp), da1 (type: timestamp), s1 (type: string), vc1 (type: varchar(5)), m1 (type: map<string,string>), l1 (type: array<int>), st1 (type: struct<c1:int,c2:string>)
             outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
-            Statistics: Num rows: 2 Data size: 1002 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 2 Data size: 3554 Basic stats: COMPLETE Column stats: NONE
             ListSink
 
 PREHOOK: query: analyze table alltypes_orc compute statistics for columns bo1, ti1, si1, i1, bi1, f1, d1, s1, vc1
@@ -132,11 +132,11 @@ STAGE PLANS:
       Processor Tree:
         TableScan
           alias: alltypes_orc
-          Statistics: Num rows: 2 Data size: 804 Basic stats: COMPLETE Column stats: PARTIAL
+          Statistics: Num rows: 2 Data size: 3356 Basic stats: COMPLETE Column stats: PARTIAL
           Select Operator
             expressions: bo1 (type: boolean), ti1 (type: tinyint), si1 (type: smallint), i1 (type: int), bi1 (type: bigint), f1 (type: float), d1 (type: double), de1 (type: decimal(10,0)), ts1 (type: timestamp), da1 (type: timestamp), s1 (type: string), vc1 (type: varchar(5)), m1 (type: map<string,string>), l1 (type: array<int>), st1 (type: struct<c1:int,c2:string>)
             outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
-            Statistics: Num rows: 2 Data size: 804 Basic stats: COMPLETE Column stats: PARTIAL
+            Statistics: Num rows: 2 Data size: 3356 Basic stats: COMPLETE Column stats: PARTIAL
             ListSink
 
 PREHOOK: query: explain select bo1 from alltypes_orc
@@ -216,11 +216,11 @@ STAGE PLANS:
       Processor Tree:
         TableScan
           alias: alltypes_orc
-          Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 2 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
           Select Operator
             expressions: m1 (type: map<string,string>)
             outputColumnNames: _col0
-            Statistics: Num rows: 2 Data size: 1686 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 2 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
             ListSink
 
 PREHOOK: query: explain select bo1, ti1, si1, i1, bi1, f1, d1,s1 from alltypes_orc
@@ -670,11 +670,11 @@ STAGE PLANS:
       Processor Tree:
         TableScan
           alias: alltypes_orc
-          Statistics: Num rows: 2 Data size: 804 Basic stats: COMPLETE Column stats: PARTIAL
+          Statistics: Num rows: 2 Data size: 3356 Basic stats: COMPLETE Column stats: PARTIAL
           Select Operator
             expressions: bo1 (type: boolean), ti1 (type: tinyint), si1 (type: smallint), i1 (type: int), bi1 (type: bigint), f1 (type: float), d1 (type: double), de1 (type: decimal(10,0)), ts1 (type: timestamp), da1 (type: timestamp), s1 (type: string), vc1 (type: varchar(5)), m1 (type: map<string,string>), l1 (type: array<int>), st1 (type: struct<c1:int,c2:string>), 11 (type: int)
             outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
-            Statistics: Num rows: 2 Data size: 812 Basic stats: COMPLETE Column stats: PARTIAL
+            Statistics: Num rows: 2 Data size: 3364 Basic stats: COMPLETE Column stats: PARTIAL
             ListSink
 
 PREHOOK: query: explain select i1 from (select i1 from alltypes_orc limit 10) temp

http://git-wip-us.apache.org/repos/asf/hive/blob/281965e5/ql/src/test/results/clientpositive/llap/lateral_view.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/lateral_view.q.out b/ql/src/test/results/clientpositive/llap/lateral_view.q.out
index 45a68e1..20e4437 100644
--- a/ql/src/test/results/clientpositive/llap/lateral_view.q.out
+++ b/ql/src/test/results/clientpositive/llap/lateral_view.q.out
@@ -629,21 +629,21 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: tmp_pyang_src_rcfile
-                  Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 20 Data size: 42080 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: key (type: string), value (type: array<string>)
                     outputColumnNames: key, value
-                    Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 20 Data size: 42080 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       keys: value[0] (type: string), key (type: string)
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 20 Data size: 42080 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-                        Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 20 Data size: 42080 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
         Reducer 2 
@@ -653,27 +653,27 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 10 Data size: 21040 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: array(_col0) (type: array<string>)
                   outputColumnNames: _col1
-                  Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 10 Data size: 21040 Basic stats: COMPLETE Column stats: NONE
                   Lateral View Forward
-                    Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 10 Data size: 21040 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: _col1 (type: array<string>)
                       outputColumnNames: _col1
-                      Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 10 Data size: 21040 Basic stats: COMPLETE Column stats: NONE
                       Lateral View Join Operator
                         outputColumnNames: _col1, _col2
-                        Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 20 Data size: 42080 Basic stats: COMPLETE Column stats: NONE
                         Select Operator
                           expressions: _col1 (type: array<string>), _col2 (type: string)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 20 Data size: 42080 Basic stats: COMPLETE Column stats: NONE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 20 Data size: 42080 Basic stats: COMPLETE Column stats: NONE
                             table:
                                 input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -681,20 +681,20 @@ STAGE PLANS:
                     Select Operator
                       expressions: _col1 (type: array<string>)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 10 Data size: 21040 Basic stats: COMPLETE Column stats: NONE
                       UDTF Operator
-                        Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 10 Data size: 21040 Basic stats: COMPLETE Column stats: NONE
                         function name: explode
                         Lateral View Join Operator
                           outputColumnNames: _col1, _col2
-                          Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 20 Data size: 42080 Basic stats: COMPLETE Column stats: NONE
                           Select Operator
                             expressions: _col1 (type: array<string>), _col2 (type: string)
                             outputColumnNames: _col0, _col1
-                            Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 20 Data size: 42080 Basic stats: COMPLETE Column stats: NONE
                             File Output Operator
                               compressed: false
-                              Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 20 Data size: 42080 Basic stats: COMPLETE Column stats: NONE
                               table:
                                   input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                                   output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/281965e5/ql/src/test/results/clientpositive/llap/lvj_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/lvj_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/lvj_mapjoin.q.out
index 45dfac4..56aff94 100644
--- a/ql/src/test/results/clientpositive/llap/lvj_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/llap/lvj_mapjoin.q.out
@@ -114,23 +114,23 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: expod1
-                  Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: aid is not null (type: boolean)
-                    Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                     Lateral View Forward
-                      Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: aid (type: int)
                         outputColumnNames: aid
-                        Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                         Lateral View Join Operator
                           outputColumnNames: _col0, _col5
-                          Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 6 Data size: 11544 Basic stats: COMPLETE Column stats: NONE
                           Select Operator
                             expressions: _col0 (type: int), _col5 (type: string)
                             outputColumnNames: _col0, _col1
-                            Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 6 Data size: 11544 Basic stats: COMPLETE Column stats: NONE
                             Map Join Operator
                               condition map:
                                    Inner Join 0 to 1
@@ -140,17 +140,17 @@ STAGE PLANS:
                               outputColumnNames: _col0, _col1, _col2, _col3
                               input vertices:
                                 1 Map 2
-                              Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 6 Data size: 12698 Basic stats: COMPLETE Column stats: NONE
                               Filter Operator
                                 predicate: (_col0 = _col2) (type: boolean)
-                                Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+                                Statistics: Num rows: 3 Data size: 6349 Basic stats: COMPLETE Column stats: NONE
                                 Select Operator
                                   expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
                                   outputColumnNames: _col0, _col1, _col2
-                                  Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+                                  Statistics: Num rows: 3 Data size: 6349 Basic stats: COMPLETE Column stats: NONE
                                   File Output Operator
                                     compressed: false
-                                    Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+                                    Statistics: Num rows: 3 Data size: 6349 Basic stats: COMPLETE Column stats: NONE
                                     table:
                                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -158,17 +158,17 @@ STAGE PLANS:
                       Select Operator
                         expressions: av (type: array<string>)
                         outputColumnNames: _col0
-                        Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                         UDTF Operator
-                          Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                           function name: explode
                           Lateral View Join Operator
                             outputColumnNames: _col0, _col5
-                            Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 6 Data size: 11544 Basic stats: COMPLETE Column stats: NONE
                             Select Operator
                               expressions: _col0 (type: int), _col5 (type: string)
                               outputColumnNames: _col0, _col1
-                              Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 6 Data size: 11544 Basic stats: COMPLETE Column stats: NONE
                               Map Join Operator
                                 condition map:
                                      Inner Join 0 to 1
@@ -178,17 +178,17 @@ STAGE PLANS:
                                 outputColumnNames: _col0, _col1, _col2, _col3
                                 input vertices:
                                   1 Map 2
-                                Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+                                Statistics: Num rows: 6 Data size: 12698 Basic stats: COMPLETE Column stats: NONE
                                 Filter Operator
                                   predicate: (_col0 = _col2) (type: boolean)
-                                  Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+                                  Statistics: Num rows: 3 Data size: 6349 Basic stats: COMPLETE Column stats: NONE
                                   Select Operator
                                     expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
                                     outputColumnNames: _col0, _col1, _col2
-                                    Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+                                    Statistics: Num rows: 3 Data size: 6349 Basic stats: COMPLETE Column stats: NONE
                                     File Output Operator
                                       compressed: false
-                                      Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+                                      Statistics: Num rows: 3 Data size: 6349 Basic stats: COMPLETE Column stats: NONE
                                       table:
                                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -199,48 +199,48 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: expod2
-                  Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: bid is not null (type: boolean)
-                    Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                     Lateral View Forward
-                      Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: bid (type: int)
                         outputColumnNames: bid
-                        Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                         Lateral View Join Operator
                           outputColumnNames: _col0, _col5
-                          Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 6 Data size: 11544 Basic stats: COMPLETE Column stats: NONE
                           Select Operator
                             expressions: _col0 (type: int), _col5 (type: string)
                             outputColumnNames: _col0, _col1
-                            Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 6 Data size: 11544 Basic stats: COMPLETE Column stats: NONE
                             Reduce Output Operator
                               key expressions: _col0 (type: int)
                               sort order: +
                               Map-reduce partition columns: _col0 (type: int)
-                              Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 6 Data size: 11544 Basic stats: COMPLETE Column stats: NONE
                               value expressions: _col1 (type: string)
                       Select Operator
                         expressions: bv (type: array<string>)
                         outputColumnNames: _col0
-                        Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                         UDTF Operator
-                          Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 3 Data size: 5772 Basic stats: COMPLETE Column stats: NONE
                           function name: explode
                           Lateral View Join Operator
                             outputColumnNames: _col0, _col5
-                            Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 6 Data size: 11544 Basic stats: COMPLETE Column stats: NONE
                             Select Operator
                               expressions: _col0 (type: int), _col5 (type: string)
                               outputColumnNames: _col0, _col1
-                              Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 6 Data size: 11544 Basic stats: COMPLETE Column stats: NONE
                               Reduce Output Operator
                                 key expressions: _col0 (type: int)
                                 sort order: +
                                 Map-reduce partition columns: _col0 (type: int)
-                                Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                                Statistics: Num rows: 6 Data size: 11544 Basic stats: COMPLETE Column stats: NONE
                                 value expressions: _col1 (type: string)
             Execution mode: llap
             LLAP IO: no inputs

http://git-wip-us.apache.org/repos/asf/hive/blob/281965e5/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out
index 3613da5..76ea043 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_complex.q.out
@@ -155,14 +155,14 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_change_various_various_struct1
-                  Statistics: Num rows: 6 Data size: 5862 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 6 Data size: 21030 Basic stats: COMPLETE Column stats: PARTIAL
                   Select Operator
                     expressions: insert_num (type: int), part (type: int), s1 (type: struct<c1:string,c2:string,c3:string,c4:string,c5:string,c6:string,c7:string,c8:string,c9:string,c10:string,c11:string,c12:string,c13:string>), b (type: string)
                     outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 6 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
-                      Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 6 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL
                       table:
                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -431,14 +431,14 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_add_various_various_struct2
-                  Statistics: Num rows: 8 Data size: 6416 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 8 Data size: 26640 Basic stats: COMPLETE Column stats: PARTIAL
                   Select Operator
                     expressions: insert_num (type: int), part (type: int), b (type: string), s2 (type: struct<c1:string,c2:string,c3:string,c4:string,c5:string,c6:string,c7:string,c8:string,c9:string,c10:string,c11:string,c12:string,c13:string>)
                     outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 8 Data size: 1536 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 8 Data size: 21760 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
-                      Statistics: Num rows: 8 Data size: 1536 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 8 Data size: 21760 Basic stats: COMPLETE Column stats: PARTIAL
                       table:
                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -635,14 +635,14 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_add_to_various_various_struct4
-                  Statistics: Num rows: 4 Data size: 1924 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 4 Data size: 4892 Basic stats: COMPLETE Column stats: PARTIAL
                   Select Operator
                     expressions: insert_num (type: int), part (type: int), b (type: string), s3 (type: struct<c1:boolean,c2:tinyint,c3:smallint,c4:int,c5:bigint,c6:float,c7:double,c8:decimal(38,18),c9:char(25),c10:varchar(25),c11:timestamp,c12:date,c13:binary>)
                     outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 4 Data size: 3736 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
-                      Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 4 Data size: 3736 Basic stats: COMPLETE Column stats: PARTIAL
                       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/281965e5/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out
index 3b25d0b..69f8262 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out
@@ -155,7 +155,7 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_change_various_various_struct1
-                  Statistics: Num rows: 6 Data size: 5862 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 6 Data size: 21030 Basic stats: COMPLETE Column stats: PARTIAL
                   TableScan Vectorization:
                       native: true
                       projectedOutputColumns: [0, 1, 2, 3]
@@ -166,13 +166,13 @@ STAGE PLANS:
                         className: VectorSelectOperator
                         native: true
                         projectedOutputColumns: [0, 3, 1, 2]
-                    Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 6 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
                       File Sink Vectorization:
                           className: VectorFileSinkOperator
                           native: false
-                      Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 6 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL
                       table:
                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -455,7 +455,7 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_add_various_various_struct2
-                  Statistics: Num rows: 8 Data size: 6416 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 8 Data size: 26640 Basic stats: COMPLETE Column stats: PARTIAL
                   TableScan Vectorization:
                       native: true
                       projectedOutputColumns: [0, 1, 2, 3]
@@ -466,13 +466,13 @@ STAGE PLANS:
                         className: VectorSelectOperator
                         native: true
                         projectedOutputColumns: [0, 3, 1, 2]
-                    Statistics: Num rows: 8 Data size: 1536 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 8 Data size: 21760 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
                       File Sink Vectorization:
                           className: VectorFileSinkOperator
                           native: false
-                      Statistics: Num rows: 8 Data size: 1536 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 8 Data size: 21760 Basic stats: COMPLETE Column stats: PARTIAL
                       table:
                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -683,7 +683,7 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_add_to_various_various_struct4
-                  Statistics: Num rows: 4 Data size: 1924 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 4 Data size: 4892 Basic stats: COMPLETE Column stats: PARTIAL
                   TableScan Vectorization:
                       native: true
                       projectedOutputColumns: [0, 1, 2, 3]
@@ -694,13 +694,13 @@ STAGE PLANS:
                         className: VectorSelectOperator
                         native: true
                         projectedOutputColumns: [0, 3, 1, 2]
-                    Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 4 Data size: 3736 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
                       File Sink Vectorization:
                           className: VectorFileSinkOperator
                           native: false
-                      Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 4 Data size: 3736 Basic stats: COMPLETE Column stats: PARTIAL
                       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/281965e5/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out
index 7f058bb..94a6995 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_complex.q.out
@@ -155,14 +155,14 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_change_various_various_struct1
-                  Statistics: Num rows: 6 Data size: 2059 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 6 Data size: 17227 Basic stats: COMPLETE Column stats: PARTIAL
                   Select Operator
                     expressions: insert_num (type: int), part (type: int), s1 (type: struct<c1:string,c2:string,c3:string,c4:string,c5:string,c6:string,c7:string,c8:string,c9:string,c10:string,c11:string,c12:string,c13:string>), b (type: string)
                     outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 6 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
-                      Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 6 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL
                       table:
                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -431,14 +431,14 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_add_various_various_struct2
-                  Statistics: Num rows: 8 Data size: 2443 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 8 Data size: 22667 Basic stats: COMPLETE Column stats: PARTIAL
                   Select Operator
                     expressions: insert_num (type: int), part (type: int), b (type: string), s2 (type: struct<c1:string,c2:string,c3:string,c4:string,c5:string,c6:string,c7:string,c8:string,c9:string,c10:string,c11:string,c12:string,c13:string>)
                     outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 8 Data size: 1536 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 8 Data size: 21760 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
-                      Statistics: Num rows: 8 Data size: 1536 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 8 Data size: 21760 Basic stats: COMPLETE Column stats: PARTIAL
                       table:
                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -635,14 +635,14 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_add_to_various_various_struct4
-                  Statistics: Num rows: 4 Data size: 1105 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 4 Data size: 4073 Basic stats: COMPLETE Column stats: PARTIAL
                   Select Operator
                     expressions: insert_num (type: int), part (type: int), b (type: string), s3 (type: struct<c1:boolean,c2:tinyint,c3:smallint,c4:int,c5:bigint,c6:float,c7:double,c8:decimal(38,18),c9:char(25),c10:varchar(25),c11:timestamp,c12:date,c13:binary>)
                     outputColumnNames: _col0, _col1, _col2, _col3
-                    Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 4 Data size: 3736 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
-                      Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 4 Data size: 3736 Basic stats: COMPLETE Column stats: PARTIAL
                       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/281965e5/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_complex.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_complex.q.out
index 2cbd94b..d6d7d0a 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_complex.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_complex.q.out
@@ -155,7 +155,7 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_change_various_various_struct1
-                  Statistics: Num rows: 6 Data size: 2059 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 6 Data size: 17227 Basic stats: COMPLETE Column stats: PARTIAL
                   TableScan Vectorization:
                       native: true
                       projectedOutputColumns: [0, 1, 2, 3]
@@ -166,13 +166,13 @@ STAGE PLANS:
                         className: VectorSelectOperator
                         native: true
                         projectedOutputColumns: [0, 3, 1, 2]
-                    Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 6 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
                       File Sink Vectorization:
                           className: VectorFileSinkOperator
                           native: false
-                      Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 6 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL
                       table:
                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -455,7 +455,7 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_add_various_various_struct2
-                  Statistics: Num rows: 8 Data size: 2443 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 8 Data size: 22667 Basic stats: COMPLETE Column stats: PARTIAL
                   TableScan Vectorization:
                       native: true
                       projectedOutputColumns: [0, 1, 2, 3]
@@ -466,13 +466,13 @@ STAGE PLANS:
                         className: VectorSelectOperator
                         native: true
                         projectedOutputColumns: [0, 3, 1, 2]
-                    Statistics: Num rows: 8 Data size: 1536 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 8 Data size: 21760 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
                       File Sink Vectorization:
                           className: VectorFileSinkOperator
                           native: false
-                      Statistics: Num rows: 8 Data size: 1536 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 8 Data size: 21760 Basic stats: COMPLETE Column stats: PARTIAL
                       table:
                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -683,7 +683,7 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_add_to_various_various_struct4
-                  Statistics: Num rows: 4 Data size: 1105 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 4 Data size: 4073 Basic stats: COMPLETE Column stats: PARTIAL
                   TableScan Vectorization:
                       native: true
                       projectedOutputColumns: [0, 1, 2, 3]
@@ -694,13 +694,13 @@ STAGE PLANS:
                         className: VectorSelectOperator
                         native: true
                         projectedOutputColumns: [0, 3, 1, 2]
-                    Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 4 Data size: 3736 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
                       File Sink Vectorization:
                           className: VectorFileSinkOperator
                           native: false
-                      Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 4 Data size: 3736 Basic stats: COMPLETE Column stats: PARTIAL
                       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/281965e5/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_complex.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_complex.q.out
index 98e6496..bf34e37 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_complex.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_complex.q.out
@@ -155,7 +155,7 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_change_various_various_struct1
-                  Statistics: Num rows: 6 Data size: 2059 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 6 Data size: 17227 Basic stats: COMPLETE Column stats: PARTIAL
                   TableScan Vectorization:
                       native: true
                       projectedOutputColumns: [0, 1, 2, 3]
@@ -166,13 +166,13 @@ STAGE PLANS:
                         className: VectorSelectOperator
                         native: true
                         projectedOutputColumns: [0, 3, 1, 2]
-                    Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 6 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
                       File Sink Vectorization:
                           className: VectorFileSinkOperator
                           native: false
-                      Statistics: Num rows: 6 Data size: 1152 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 6 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL
                       table:
                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -455,7 +455,7 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_add_various_various_struct2
-                  Statistics: Num rows: 8 Data size: 2443 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 8 Data size: 22667 Basic stats: COMPLETE Column stats: PARTIAL
                   TableScan Vectorization:
                       native: true
                       projectedOutputColumns: [0, 1, 2, 3]
@@ -466,13 +466,13 @@ STAGE PLANS:
                         className: VectorSelectOperator
                         native: true
                         projectedOutputColumns: [0, 3, 1, 2]
-                    Statistics: Num rows: 8 Data size: 1536 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 8 Data size: 21760 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
                       File Sink Vectorization:
                           className: VectorFileSinkOperator
                           native: false
-                      Statistics: Num rows: 8 Data size: 1536 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 8 Data size: 21760 Basic stats: COMPLETE Column stats: PARTIAL
                       table:
                           input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -683,7 +683,7 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: part_add_to_various_various_struct4
-                  Statistics: Num rows: 4 Data size: 1105 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 4 Data size: 4073 Basic stats: COMPLETE Column stats: PARTIAL
                   TableScan Vectorization:
                       native: true
                       projectedOutputColumns: [0, 1, 2, 3]
@@ -694,13 +694,13 @@ STAGE PLANS:
                         className: VectorSelectOperator
                         native: true
                         projectedOutputColumns: [0, 3, 1, 2]
-                    Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 4 Data size: 3736 Basic stats: COMPLETE Column stats: PARTIAL
                     File Output Operator
                       compressed: false
                       File Sink Vectorization:
                           className: VectorFileSinkOperator
                           native: false
-                      Statistics: Num rows: 4 Data size: 768 Basic stats: COMPLETE Column stats: PARTIAL
+                      Statistics: Num rows: 4 Data size: 3736 Basic stats: COMPLETE Column stats: PARTIAL
                       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/281965e5/ql/src/test/results/clientpositive/llap/tez_join_result_complex.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/tez_join_result_complex.q.out b/ql/src/test/results/clientpositive/llap/tez_join_result_complex.q.out
index 5197e44..417d318 100644
--- a/ql/src/test/results/clientpositive/llap/tez_join_result_complex.q.out
+++ b/ql/src/test/results/clientpositive/llap/tez_join_result_complex.q.out
@@ -160,60 +160,32 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 1 <- Map 2 (BROADCAST_EDGE)
+        Map 2 <- Map 1 (BROADCAST_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 1292 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 3212 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: contact_event_id is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 1292 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 3212 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: contact_event_id (type: string), ce_create_dt (type: string), ce_end_dt (type: string), contact_type (type: string), cnctevs_cd (type: string), contact_mode (type: string), cntvnst_stts_cd (type: string), total_transfers (type: int), ce_notes (type: array<string>)
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
-                      Statistics: Num rows: 1 Data size: 1292 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        Estimated key counts: Map 2 => 1
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16
-                        input vertices:
-                          1 Map 2
-                        Position of Big Table: 0
-                        Statistics: Num rows: 1 Data size: 1421 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: array<string>), _col10 (type: string), _col15 (type: array<string>), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col11 (type: string), _col16 (type: array<string>)
-                          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
-                          Statistics: Num rows: 1 Data size: 1421 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            GlobalTableId: 1
-#### A masked pattern was here ####
-                            NumFilesPerFileSink: 1
-                            Statistics: Num rows: 1 Data size: 1421 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
-                            table:
-                                input format: org.apache.hadoop.mapred.TextInputFormat
-                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                properties:
-                                  columns contact_event_id,ce_create_dt,ce_end_dt,contact_type,cnctevs_cd,contact_mode,cntvnst_stts_cd,total_transfers,ce_notes,svcrqst_id,svcrqct_cds,svcrtyp_cd,cmpltyp_cd,src,cnctmd_cd,notes
-                                  columns.types string:string:string:string:string:string:string:int:array<string>:string:array<string>:string:string:string:string:array<string>
-                                  name default.ct_events1_test
-                                  serialization.format 1
-                                  serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                                name: default.ct_events1_test
-                            TotalFiles: 1
-                            GatherStats: true
-                            MultiFileSpray: false
+                      Statistics: Num rows: 1 Data size: 3212 Basic stats: COMPLETE Column stats: NONE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        null sort order: a
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 1 Data size: 3212 Basic stats: COMPLETE Column stats: NONE
+                        tag: 0
+                        value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: array<string>)
+                        auto parallelism: true
             Execution mode: llap
             LLAP IO: no inputs
             Path -> Alias:
@@ -277,25 +249,53 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 4944 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: cnctevn_id is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 4944 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: cnctevn_id (type: string), svcrqst_id (type: string), cnctmd_cd (type: string), svcrtyp_cd (type: string), cmpltyp_cd (type: string), sum_reason_cd (type: string), svcrqct_cds (type: array<string>), notes (type: array<string>)
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
-                      Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        null sort order: a
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
-                        tag: 1
-                        value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: array<string>), _col7 (type: array<string>)
-                        auto parallelism: true
+                      Statistics: Num rows: 1 Data size: 4944 Basic stats: COMPLETE Column stats: NONE
+                      Map Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        Estimated key counts: Map 1 => 1
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16
+                        input vertices:
+                          0 Map 1
+                        Position of Big Table: 1
+                        Statistics: Num rows: 1 Data size: 3533 Basic stats: COMPLETE Column stats: NONE
+                        Select Operator
+                          expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: array<string>), _col10 (type: string), _col15 (type: array<string>), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col11 (type: string), _col16 (type: array<string>)
+                          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
+                          Statistics: Num rows: 1 Data size: 3533 Basic stats: COMPLETE Column stats: NONE
+                          File Output Operator
+                            compressed: false
+                            GlobalTableId: 1
+#### A masked pattern was here ####
+                            NumFilesPerFileSink: 1
+                            Statistics: Num rows: 1 Data size: 3533 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                properties:
+                                  columns contact_event_id,ce_create_dt,ce_end_dt,contact_type,cnctevs_cd,contact_mode,cntvnst_stts_cd,total_transfers,ce_notes,svcrqst_id,svcrqct_cds,svcrtyp_cd,cmpltyp_cd,src,cnctmd_cd,notes
+                                  columns.types string:string:string:string:string:string:string:int:array<string>:string:array<string>:string:string:string:string:array<string>
+                                  name default.ct_events1_test
+                                  serialization.format 1
+                                  serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                                name: default.ct_events1_test
+                            TotalFiles: 1
+                            GatherStats: true
+                            MultiFileSpray: false
             Execution mode: llap
             LLAP IO: no inputs
             Path -> Alias:
@@ -1144,60 +1144,32 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 1 <- Map 2 (BROADCAST_EDGE)
+        Map 2 <- Map 1 (BROADCAST_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 1292 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 3212 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: contact_event_id is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 1292 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 3212 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: contact_event_id (type: string), ce_create_dt (type: string), ce_end_dt (type: string), contact_type (type: string), cnctevs_cd (type: string), contact_mode (type: string), cntvnst_stts_cd (type: string), total_transfers (type: int), ce_notes (type: array<string>)
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
-                      Statistics: Num rows: 1 Data size: 1292 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        Estimated key counts: Map 2 => 1
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16
-                        input vertices:
-                          1 Map 2
-                        Position of Big Table: 0
-                        Statistics: Num rows: 1 Data size: 1421 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: array<string>), _col10 (type: string), _col15 (type: array<string>), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col11 (type: string), _col16 (type: array<string>)
-                          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
-                          Statistics: Num rows: 1 Data size: 1421 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            GlobalTableId: 1
-#### A masked pattern was here ####
-                            NumFilesPerFileSink: 1
-                            Statistics: Num rows: 1 Data size: 1421 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
-                            table:
-                                input format: org.apache.hadoop.mapred.TextInputFormat
-                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                properties:
-                                  columns contact_event_id,ce_create_dt,ce_end_dt,contact_type,cnctevs_cd,contact_mode,cntvnst_stts_cd,total_transfers,ce_notes,svcrqst_id,svcrqct_cds,svcrtyp_cd,cmpltyp_cd,src,cnctmd_cd,notes
-                                  columns.types string:string:string:string:string:string:string:int:array<string>:string:array<string>:string:string:string:string:array<string>
-                                  name default.ct_events1_test
-                                  serialization.format 1
-                                  serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                                name: default.ct_events1_test
-                            TotalFiles: 1
-                            GatherStats: true
-                            MultiFileSpray: false
+                      Statistics: Num rows: 1 Data size: 3212 Basic stats: COMPLETE Column stats: NONE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        null sort order: a
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 1 Data size: 3212 Basic stats: COMPLETE Column stats: NONE
+                        tag: 0
+                        value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: array<string>)
+                        auto parallelism: true
             Execution mode: llap
             LLAP IO: no inputs
             Path -> Alias:
@@ -1261,25 +1233,53 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 4944 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: cnctevn_id is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 4944 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: cnctevn_id (type: string), svcrqst_id (type: string), cnctmd_cd (type: string), svcrtyp_cd (type: string), cmpltyp_cd (type: string), sum_reason_cd (type: string), svcrqct_cds (type: array<string>), notes (type: array<string>)
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
-                      Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        null sort order: a
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
-                        tag: 1
-                        value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: array<string>), _col7 (type: array<string>)
-                        auto parallelism: true
+                      Statistics: Num rows: 1 Data size: 4944 Basic stats: COMPLETE Column stats: NONE
+                      Map Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        Estimated key counts: Map 1 => 1
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16
+                        input vertices:
+                          0 Map 1
+                        Position of Big Table: 1
+                        Statistics: Num rows: 1 Data size: 3533 Basic stats: COMPLETE Column stats: NONE
+                        Select Operator
+                          expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: array<string>), _col10 (type: string), _col15 (type: array<string>), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col11 (type: string), _col16 (type: array<string>)
+                          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
+                          Statistics: Num rows: 1 Data size: 3533 Basic stats: COMPLETE Column stats: NONE
+                          File Output Operator
+                            compressed: false
+                            GlobalTableId: 1
+#### A masked pattern was here ####
+                            NumFilesPerFileSink: 1
+                            Statistics: Num rows: 1 Data size: 3533 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                properties:
+                                  columns contact_event_id,ce_create_dt,ce_end_dt,contact_type,cnctevs_cd,contact_mode,cntvnst_stts_cd,total_transfers,ce_notes,svcrqst_id,svcrqct_cds,svcrtyp_cd,cmpltyp_cd,src,cnctmd_cd,notes
+                                  columns.types string:string:string:string:string:string:string:int:array<string>:string:array<string>:string:string:string:string:array<string>
+                                  name default.ct_events1_test
+                                  serialization.format 1
+                                  serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                                name: default.ct_events1_test
+                            TotalFiles: 1
+                            GatherStats: true
+                            MultiFileSpray: false
             Execution mode: llap
             LLAP IO: no inputs
             Path -> Alias:

http://git-wip-us.apache.org/repos/asf/hive/blob/281965e5/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
index c353280..9401479 100644
--- a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
@@ -5705,11 +5705,11 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: src_thrift
-                  Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 11 Data size: 21120 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: lstring[0] (type: string)
                     outputColumnNames: _col0
-                    Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 11 Data size: 21120 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       keys: _col0 (type: string)
                       mode: hash


Mime
View raw message