hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From br...@apache.org
Subject svn commit: r1629544 [24/33] - in /hive/branches/spark-new: ./ accumulo-handler/ beeline/ beeline/src/java/org/apache/hive/beeline/ bin/ bin/ext/ common/ common/src/java/org/apache/hadoop/hive/conf/ common/src/test/org/apache/hadoop/hive/common/type/ c...
Date Sun, 05 Oct 2014 22:26:58 GMT
Modified: hive/branches/spark-new/ql/src/test/results/clientpositive/tez/dynamic_partition_pruning_2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark-new/ql/src/test/results/clientpositive/tez/dynamic_partition_pruning_2.q.out?rev=1629544&r1=1629543&r2=1629544&view=diff
==============================================================================
--- hive/branches/spark-new/ql/src/test/results/clientpositive/tez/dynamic_partition_pruning_2.q.out (original)
+++ hive/branches/spark-new/ql/src/test/results/clientpositive/tez/dynamic_partition_pruning_2.q.out Sun Oct  5 22:26:43 2014
@@ -67,6 +67,34 @@ POSTHOOK: query: load data local inpath 
 POSTHOOK: type: LOAD
 #### A masked pattern was here ####
 POSTHOOK: Output: default@agg_01@dim_shops_id=3
+PREHOOK: query: analyze table dim_shops compute statistics
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dim_shops
+PREHOOK: Output: default@dim_shops
+POSTHOOK: query: analyze table dim_shops compute statistics
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dim_shops
+POSTHOOK: Output: default@dim_shops
+PREHOOK: query: analyze table agg_01 partition (dim_shops_id) compute statistics
+PREHOOK: type: QUERY
+PREHOOK: Input: default@agg_01
+PREHOOK: Input: default@agg_01@dim_shops_id=1
+PREHOOK: Input: default@agg_01@dim_shops_id=2
+PREHOOK: Input: default@agg_01@dim_shops_id=3
+PREHOOK: Output: default@agg_01
+PREHOOK: Output: default@agg_01@dim_shops_id=1
+PREHOOK: Output: default@agg_01@dim_shops_id=2
+PREHOOK: Output: default@agg_01@dim_shops_id=3
+POSTHOOK: query: analyze table agg_01 partition (dim_shops_id) compute statistics
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@agg_01
+POSTHOOK: Input: default@agg_01@dim_shops_id=1
+POSTHOOK: Input: default@agg_01@dim_shops_id=2
+POSTHOOK: Input: default@agg_01@dim_shops_id=3
+POSTHOOK: Output: default@agg_01
+POSTHOOK: Output: default@agg_01@dim_shops_id=1
+POSTHOOK: Output: default@agg_01@dim_shops_id=2
+POSTHOOK: Output: default@agg_01@dim_shops_id=3
 PREHOOK: query: select * from dim_shops
 PREHOOK: type: QUERY
 PREHOOK: Input: default@dim_shops
@@ -137,29 +165,29 @@ STAGE PLANS:
                 TableScan
                   alias: d1
                   filterExpr: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
-                  Statistics: Num rows: 0 Data size: 18 Basic stats: PARTIAL Column stats: NONE
+                  Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
                       key expressions: id (type: int)
                       sort order: +
                       Map-reduce partition columns: id (type: int)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                       value expressions: label (type: string)
                     Select Operator
                       expressions: id (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: int)
                         mode: hash
                         outputColumnNames: _col0
-                        Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                         Dynamic Partitioning Event Operator
                           Target Input: agg
                           Partition key expr: dim_shops_id
-                          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                          Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                           Target column: dim_shops_id
                           Target Vertex: Map 2
         Map 2 
@@ -167,7 +195,7 @@ STAGE PLANS:
                 TableScan
                   alias: agg
                   filterExpr: dim_shops_id is not null (type: boolean)
-                  Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
+                  Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
                   Map Join Operator
                     condition map:
                          Inner Join 0 to 1
@@ -178,25 +206,554 @@ STAGE PLANS:
                       0 dim_shops_id (type: int)
                       1 id (type: int)
                     outputColumnNames: _col0, _col1, _col5, _col6
-                    Statistics: Num rows: 0 Data size: 39 Basic stats: PARTIAL Column stats: NONE
+                    input vertices:
+                      1 Map 1
+                    Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
                     Filter Operator
                       predicate: ((_col1 = _col5) and (_col6) IN ('foo', 'bar')) (type: boolean)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: _col6 (type: string), _col0 (type: decimal(10,0))
                         outputColumnNames: _col6, _col0
-                        Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                        Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
                         Group By Operator
                           aggregations: count(), sum(_col0)
                           keys: _col6 (type: string)
                           mode: hash
                           outputColumnNames: _col0, _col1, _col2
+                          Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+                          Reduce Output Operator
+                            key expressions: _col0 (type: string)
+                            sort order: +
+                            Map-reduce partition columns: _col0 (type: string)
+                            Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+                            value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
+        Reducer 3 
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0), sum(VALUE._col1)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1, _col2
+                Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: decimal(20,0))
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col0 (type: string)
+                    sort order: +
+                    Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
+        Reducer 4 
+            Reduce Operator Tree:
+              Select Operator
+                expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(20,0))
+                outputColumnNames: _col0, _col1, _col2
+                Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: SELECT d1.label, count(*), sum(agg.amount)
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and
+d1.label in ('foo', 'bar')
+GROUP BY d1.label
+ORDER BY d1.label
+PREHOOK: type: QUERY
+PREHOOK: Input: default@agg_01
+PREHOOK: Input: default@agg_01@dim_shops_id=1
+PREHOOK: Input: default@agg_01@dim_shops_id=2
+PREHOOK: Input: default@agg_01@dim_shops_id=3
+PREHOOK: Input: default@dim_shops
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT d1.label, count(*), sum(agg.amount)
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and
+d1.label in ('foo', 'bar')
+GROUP BY d1.label
+ORDER BY d1.label
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@agg_01
+POSTHOOK: Input: default@agg_01@dim_shops_id=1
+POSTHOOK: Input: default@agg_01@dim_shops_id=2
+POSTHOOK: Input: default@agg_01@dim_shops_id=3
+POSTHOOK: Input: default@dim_shops
+#### A masked pattern was here ####
+bar	3	15
+foo	3	6
+PREHOOK: query: EXPLAIN SELECT d1.label, count(*), sum(agg.amount)
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and
+d1.label in ('foo', 'bar')
+GROUP BY d1.label
+ORDER BY d1.label
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT d1.label, count(*), sum(agg.amount)
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and
+d1.label in ('foo', 'bar')
+GROUP BY d1.label
+ORDER BY d1.label
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Edges:
+        Map 2 <- Map 1 (BROADCAST_EDGE)
+        Reducer 3 <- Map 2 (SIMPLE_EDGE)
+        Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: d1
+                  filterExpr: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
+                  Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
+                    Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: id (type: int)
+                      sort order: +
+                      Map-reduce partition columns: id (type: int)
+                      Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: label (type: string)
+        Map 2 
+            Map Operator Tree:
+                TableScan
+                  alias: agg
+                  filterExpr: dim_shops_id is not null (type: boolean)
+                  Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+                  Map Join Operator
+                    condition map:
+                         Inner Join 0 to 1
+                    condition expressions:
+                      0 {amount} {dim_shops_id}
+                      1 {id} {label}
+                    keys:
+                      0 dim_shops_id (type: int)
+                      1 id (type: int)
+                    outputColumnNames: _col0, _col1, _col5, _col6
+                    input vertices:
+                      1 Map 1
+                    Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+                    Filter Operator
+                      predicate: ((_col1 = _col5) and (_col6) IN ('foo', 'bar')) (type: boolean)
+                      Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: _col6 (type: string), _col0 (type: decimal(10,0))
+                        outputColumnNames: _col6, _col0
+                        Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+                        Group By Operator
+                          aggregations: count(), sum(_col0)
+                          keys: _col6 (type: string)
+                          mode: hash
+                          outputColumnNames: _col0, _col1, _col2
+                          Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+                          Reduce Output Operator
+                            key expressions: _col0 (type: string)
+                            sort order: +
+                            Map-reduce partition columns: _col0 (type: string)
+                            Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+                            value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
+        Reducer 3 
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0), sum(VALUE._col1)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1, _col2
+                Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: decimal(20,0))
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col0 (type: string)
+                    sort order: +
+                    Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
+        Reducer 4 
+            Reduce Operator Tree:
+              Select Operator
+                expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(20,0))
+                outputColumnNames: _col0, _col1, _col2
+                Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: SELECT d1.label, count(*), sum(agg.amount)
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and
+d1.label in ('foo', 'bar')
+GROUP BY d1.label
+ORDER BY d1.label
+PREHOOK: type: QUERY
+PREHOOK: Input: default@agg_01
+PREHOOK: Input: default@agg_01@dim_shops_id=1
+PREHOOK: Input: default@agg_01@dim_shops_id=2
+PREHOOK: Input: default@agg_01@dim_shops_id=3
+PREHOOK: Input: default@dim_shops
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT d1.label, count(*), sum(agg.amount)
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and
+d1.label in ('foo', 'bar')
+GROUP BY d1.label
+ORDER BY d1.label
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@agg_01
+POSTHOOK: Input: default@agg_01@dim_shops_id=1
+POSTHOOK: Input: default@agg_01@dim_shops_id=2
+POSTHOOK: Input: default@agg_01@dim_shops_id=3
+POSTHOOK: Input: default@dim_shops
+#### A masked pattern was here ####
+bar	3	15
+foo	3	6
+PREHOOK: query: EXPLAIN SELECT d1.label
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT d1.label
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Edges:
+        Map 2 <- Map 1 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: d1
+                  filterExpr: id is not null (type: boolean)
+                  Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: id is not null (type: boolean)
+                    Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: id (type: int)
+                      sort order: +
+                      Map-reduce partition columns: id (type: int)
+                      Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: label (type: string)
+        Map 2 
+            Map Operator Tree:
+                TableScan
+                  alias: agg
+                  filterExpr: dim_shops_id is not null (type: boolean)
+                  Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+                  Map Join Operator
+                    condition map:
+                         Inner Join 0 to 1
+                    condition expressions:
+                      0 {dim_shops_id}
+                      1 {id} {label}
+                    keys:
+                      0 dim_shops_id (type: int)
+                      1 id (type: int)
+                    outputColumnNames: _col1, _col5, _col6
+                    input vertices:
+                      1 Map 1
+                    Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+                    Filter Operator
+                      predicate: (_col1 = _col5) (type: boolean)
+                      Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: _col6 (type: string)
+                        outputColumnNames: _col0
+                        Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: SELECT d1.label
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@agg_01
+PREHOOK: Input: default@agg_01@dim_shops_id=1
+PREHOOK: Input: default@agg_01@dim_shops_id=2
+PREHOOK: Input: default@agg_01@dim_shops_id=3
+PREHOOK: Input: default@dim_shops
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT d1.label
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@agg_01
+POSTHOOK: Input: default@agg_01@dim_shops_id=1
+POSTHOOK: Input: default@agg_01@dim_shops_id=2
+POSTHOOK: Input: default@agg_01@dim_shops_id=3
+POSTHOOK: Input: default@dim_shops
+#### A masked pattern was here ####
+foo
+foo
+foo
+bar
+bar
+bar
+baz
+baz
+baz
+PREHOOK: query: EXPLAIN SELECT agg.amount
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and agg.dim_shops_id = 1
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT agg.amount
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and agg.dim_shops_id = 1
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Edges:
+        Map 2 <- Map 1 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: d1
+                  filterExpr: (id is not null and (id = 1)) (type: boolean)
+                  Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (id is not null and (id = 1)) (type: boolean)
+                    Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: 1 (type: int)
+                      sort order: +
+                      Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+        Map 2 
+            Map Operator Tree:
+                TableScan
+                  alias: agg
+                  filterExpr: (dim_shops_id is not null and (dim_shops_id = 1)) (type: boolean)
+                  Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+                  Map Join Operator
+                    condition map:
+                         Inner Join 0 to 1
+                    condition expressions:
+                      0 {amount} {dim_shops_id}
+                      1 
+                    keys:
+                      0 dim_shops_id (type: int)
+                      1 1 (type: int)
+                    outputColumnNames: _col0, _col1
+                    input vertices:
+                      1 Map 1
+                    Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+                    Filter Operator
+                      predicate: ((_col1 = 1) and (_col1 = 1)) (type: boolean)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      Select Operator
+                        expressions: _col0 (type: decimal(10,0))
+                        outputColumnNames: _col0
+                        Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                        File Output Operator
+                          compressed: false
                           Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: SELECT agg.amount
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and agg.dim_shops_id = 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@agg_01
+PREHOOK: Input: default@agg_01@dim_shops_id=1
+PREHOOK: Input: default@dim_shops
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT agg.amount
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and agg.dim_shops_id = 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@agg_01
+POSTHOOK: Input: default@agg_01@dim_shops_id=1
+POSTHOOK: Input: default@dim_shops
+#### A masked pattern was here ####
+1
+2
+3
+PREHOOK: query: EXPLAIN SELECT d1.label, count(*), sum(agg.amount)
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and
+d1.label in ('foo', 'bar')
+GROUP BY d1.label
+ORDER BY d1.label
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT d1.label, count(*), sum(agg.amount)
+FROM agg_01 agg,
+dim_shops d1
+WHERE agg.dim_shops_id = d1.id
+and
+d1.label in ('foo', 'bar')
+GROUP BY d1.label
+ORDER BY d1.label
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Edges:
+        Map 2 <- Map 1 (BROADCAST_EDGE)
+        Reducer 3 <- Map 2 (SIMPLE_EDGE)
+        Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: d1
+                  filterExpr: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
+                  Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
+                    Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: id (type: int)
+                      sort order: +
+                      Map-reduce partition columns: id (type: int)
+                      Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: label (type: string)
+                    Select Operator
+                      expressions: id (type: int)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+                      Group By Operator
+                        keys: _col0 (type: int)
+                        mode: hash
+                        outputColumnNames: _col0
+                        Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+                        Dynamic Partitioning Event Operator
+                          Target Input: agg
+                          Partition key expr: dim_shops_id
+                          Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+                          Target column: dim_shops_id
+                          Target Vertex: Map 2
+        Map 2 
+            Map Operator Tree:
+                TableScan
+                  alias: agg
+                  filterExpr: dim_shops_id is not null (type: boolean)
+                  Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+                  Map Join Operator
+                    condition map:
+                         Inner Join 0 to 1
+                    condition expressions:
+                      0 {amount} {dim_shops_id}
+                      1 {id} {label}
+                    keys:
+                      0 dim_shops_id (type: int)
+                      1 id (type: int)
+                    outputColumnNames: _col0, _col1, _col5, _col6
+                    input vertices:
+                      1 Map 1
+                    Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+                    Filter Operator
+                      predicate: ((_col1 = _col5) and (_col6) IN ('foo', 'bar')) (type: boolean)
+                      Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: _col6 (type: string), _col0 (type: decimal(10,0))
+                        outputColumnNames: _col6, _col0
+                        Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+                        Group By Operator
+                          aggregations: count(), sum(_col0)
+                          keys: _col6 (type: string)
+                          mode: hash
+                          outputColumnNames: _col0, _col1, _col2
+                          Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
                           Reduce Output Operator
                             key expressions: _col0 (type: string)
                             sort order: +
                             Map-reduce partition columns: _col0 (type: string)
-                            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                            Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
                             value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
         Reducer 3 
             Reduce Operator Tree:
@@ -205,25 +762,25 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: decimal(20,0))
                   outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string)
                     sort order: +
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
                     value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
         Reducer 4 
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(20,0))
                 outputColumnNames: _col0, _col1, _col2
-                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
                   table:
                       input format: org.apache.hadoop.mapred.TextInputFormat
                       output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -294,28 +851,28 @@ STAGE PLANS:
                 TableScan
                   alias: dim_shops
                   filterExpr: (id is not null and (label = 'bar')) (type: boolean)
-                  Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (id is not null and (label = 'bar')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
                       key expressions: id (type: int)
                       sort order: +
                       Map-reduce partition columns: id (type: int)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: id (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: int)
                         mode: hash
                         outputColumnNames: _col0
-                        Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                         Dynamic Partitioning Event Operator
                           Target Input: agg_01
                           Partition key expr: dim_shops_id
-                          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                          Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                           Target column: dim_shops_id
                           Target Vertex: Map 3
         Map 2 
@@ -323,28 +880,28 @@ STAGE PLANS:
                 TableScan
                   alias: dim_shops
                   filterExpr: (id is not null and (label = 'foo')) (type: boolean)
-                  Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (id is not null and (label = 'foo')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
                       key expressions: id (type: int)
                       sort order: +
                       Map-reduce partition columns: id (type: int)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: id (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: int)
                         mode: hash
                         outputColumnNames: _col0
-                        Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                         Dynamic Partitioning Event Operator
                           Target Input: agg_01
                           Partition key expr: dim_shops_id
-                          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                          Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
                           Target column: dim_shops_id
                           Target Vertex: Map 5
         Map 3 
@@ -362,6 +919,8 @@ STAGE PLANS:
                       0 dim_shops_id (type: int)
                       1 id (type: int)
                     outputColumnNames: _col0, _col1, _col5
+                    input vertices:
+                      1 Map 1
                     Filter Operator
                       predicate: (_col1 = _col5) (type: boolean)
                       Select Operator
@@ -391,6 +950,8 @@ STAGE PLANS:
                       0 dim_shops_id (type: int)
                       1 id (type: int)
                     outputColumnNames: _col0, _col1, _col5
+                    input vertices:
+                      1 Map 2
                     Filter Operator
                       predicate: (_col1 = _col5) (type: boolean)
                       Select Operator

Modified: hive/branches/spark-new/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark-new/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out?rev=1629544&r1=1629543&r2=1629544&view=diff
==============================================================================
--- hive/branches/spark-new/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out (original)
+++ hive/branches/spark-new/ql/src/test/results/clientpositive/tez/dynpart_sort_opt_vectorization.q.out Sun Oct  5 22:26:43 2014
@@ -214,6 +214,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
                       serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
                       name: default.over1k_part_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -300,6 +301,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
                       serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
                       name: default.over1k_part_limit_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -350,11 +352,11 @@ STAGE PLANS:
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4
                       Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
-                        key expressions: _col4 (type: tinyint), -1 (type: int)
+                        key expressions: _col4 (type: tinyint), '_bucket_number' (type: string)
                         sort order: ++
                         Map-reduce partition columns: _col4 (type: tinyint)
                         Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string)
             Execution mode: vectorized
         Reducer 2 
             Reduce Operator Tree:
@@ -368,6 +370,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
                       serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
                       name: default.over1k_part_buck_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -417,11 +420,11 @@ STAGE PLANS:
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4
                       Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
-                        key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float)
+                        key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float)
                         sort order: +++
                         Map-reduce partition columns: _col4 (type: tinyint)
                         Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string)
             Execution mode: vectorized
         Reducer 2 
             Reduce Operator Tree:
@@ -435,6 +438,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
                       serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
                       name: default.over1k_part_buck_sort_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -585,6 +589,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
                       serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
                       name: default.over1k_part_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -671,6 +676,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
                       serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
                       name: default.over1k_part_limit_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -721,11 +727,11 @@ STAGE PLANS:
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4
                       Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
-                        key expressions: _col4 (type: tinyint), -1 (type: int)
+                        key expressions: _col4 (type: tinyint), '_bucket_number' (type: string)
                         sort order: ++
                         Map-reduce partition columns: _col4 (type: tinyint)
                         Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string)
             Execution mode: vectorized
         Reducer 2 
             Reduce Operator Tree:
@@ -739,6 +745,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
                       serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
                       name: default.over1k_part_buck_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -788,11 +795,11 @@ STAGE PLANS:
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4
                       Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
-                        key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float)
+                        key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float)
                         sort order: +++
                         Map-reduce partition columns: _col4 (type: tinyint)
                         Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string)
             Execution mode: vectorized
         Reducer 2 
             Reduce Operator Tree:
@@ -806,6 +813,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
                       serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
                       name: default.over1k_part_buck_sort_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -922,8 +930,8 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	2                   
-	numRows             	16                  
-	rawDataSize         	320                 
+	numRows             	32                  
+	rawDataSize         	640                 
 	totalSize           	1348                
 #### A masked pattern was here ####
 	 	 
@@ -966,9 +974,9 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	2                   
-	numRows             	3                   
-	rawDataSize         	60                  
-	totalSize           	1034                
+	numRows             	6                   
+	rawDataSize         	120                 
+	totalSize           	1050                
 #### A masked pattern was here ####
 	 	 
 # Storage Information	 	 
@@ -1010,8 +1018,8 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	2                   
-	numRows             	7                   
-	rawDataSize         	140                 
+	numRows             	14                  
+	rawDataSize         	280                 
 	totalSize           	1166                
 #### A masked pattern was here ####
 	 	 
@@ -1054,9 +1062,9 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	2                   
-	numRows             	3                   
-	rawDataSize         	60                  
-	totalSize           	1040                
+	numRows             	6                   
+	rawDataSize         	120                 
+	totalSize           	1050                
 #### A masked pattern was here ####
 	 	 
 # Storage Information	 	 
@@ -1097,9 +1105,9 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	8                   
-	numRows             	16                  
-	rawDataSize         	320                 
-	totalSize           	4332                
+	numRows             	32                  
+	rawDataSize         	640                 
+	totalSize           	4340                
 #### A masked pattern was here ####
 	 	 
 # Storage Information	 	 
@@ -1140,8 +1148,8 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	8                   
-	numRows             	3                   
-	rawDataSize         	60                  
+	numRows             	6                   
+	rawDataSize         	120                 
 	totalSize           	2094                
 #### A masked pattern was here ####
 	 	 
@@ -1183,9 +1191,9 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	8                   
-	numRows             	16                  
-	rawDataSize         	320                 
-	totalSize           	4318                
+	numRows             	32                  
+	rawDataSize         	640                 
+	totalSize           	4326                
 #### A masked pattern was here ####
 	 	 
 # Storage Information	 	 
@@ -1226,8 +1234,8 @@ Protect Mode:       	None               
 Partition Parameters:	 	 
 	COLUMN_STATS_ACCURATE	true                
 	numFiles            	8                   
-	numRows             	3                   
-	rawDataSize         	60                  
+	numRows             	6                   
+	rawDataSize         	120                 
 	totalSize           	2094                
 #### A masked pattern was here ####
 	 	 
@@ -1362,6 +1370,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       name: default.over1k_part2_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -1443,6 +1452,270 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       name: default.over1k_part2_orc
+            Execution mode: vectorized
+
+  Stage: Stage-2
+    Dependency Collection
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          partition:
+            ds foo
+            t 
+          replace: true
+          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.over1k_part2_orc
+
+  Stage: Stage-3
+    Stats-Aggr Operator
+
+PREHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from (select * from over1k_orc order by i limit 10) tmp where t is null or t=27
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from (select * from over1k_orc order by i limit 10) tmp where t is null or t=27
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-2 depends on stages: Stage-1
+  Stage-0 depends on stages: Stage-2
+  Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: over1k_orc
+                  Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float)
+                    outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                    Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: _col2 (type: int)
+                      sort order: +
+                      Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float)
+            Execution mode: vectorized
+        Reducer 2 
+            Reduce Operator Tree:
+              Select Operator
+                expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+                Limit
+                  Number of rows: 10
+                  Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (_col0 is null or (_col0 = 27)) (type: boolean)
+                    Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint)
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                      Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+                      Reduce Output Operator
+                        key expressions: _col4 (type: tinyint)
+                        sort order: +
+                        Map-reduce partition columns: _col4 (type: tinyint)
+                        Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+            Execution mode: vectorized
+        Reducer 3 
+            Reduce Operator Tree:
+              Extract
+                Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+                  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.over1k_part2_orc
+            Execution mode: vectorized
+
+  Stage: Stage-2
+    Dependency Collection
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          partition:
+            ds foo
+            t 
+          replace: true
+          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.over1k_part2_orc
+
+  Stage: Stage-3
+    Stats-Aggr Operator
+
+PREHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-2 depends on stages: Stage-1
+  Stage-0 depends on stages: Stage-2
+  Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: over1k_orc
+                  Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (t is null or (t = 27)) (type: boolean)
+                    Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+                      outputColumnNames: si, i, b, f, t
+                      Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+                      Group By Operator
+                        keys: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+                        mode: hash
+                        outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                        Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+                        Reduce Output Operator
+                          key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                          sort order: +++++
+                          Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                          Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+            Execution mode: vectorized
+        Reducer 2 
+            Reduce Operator Tree:
+              Group By Operator
+                keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                  Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+                    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.over1k_part2_orc
+            Execution mode: vectorized
+
+  Stage: Stage-2
+    Dependency Collection
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          partition:
+            ds foo
+            t 
+          replace: true
+          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.over1k_part2_orc
+
+  Stage: Stage-3
+    Stats-Aggr Operator
+
+PREHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+PREHOOK: type: QUERY
+POSTHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator
+explain insert overwrite table over1k_part2_orc partition(ds="foo",t) select si,i,b,f,t from over1k_orc where t is null or t=27 group by si,i,b,f,t
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-2 depends on stages: Stage-1
+  Stage-0 depends on stages: Stage-2
+  Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: over1k_orc
+                  Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (t is null or (t = 27)) (type: boolean)
+                    Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+                      outputColumnNames: si, i, b, f, t
+                      Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+                      Group By Operator
+                        keys: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint)
+                        mode: hash
+                        outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                        Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+                        Reduce Output Operator
+                          key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                          sort order: +++++
+                          Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                          Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
+            Execution mode: vectorized
+        Reducer 2 
+            Reduce Operator Tree:
+              Group By Operator
+                keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                  Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col4 (type: tinyint)
+                    sort order: +
+                    Map-reduce partition columns: _col4 (type: tinyint)
+                    Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+            Execution mode: vectorized
+        Reducer 3 
+            Reduce Operator Tree:
+              Extract
+                Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+                  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.over1k_part2_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -1837,6 +2110,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       name: default.over1k_part_buck_sort2_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -1886,11 +2160,11 @@ STAGE PLANS:
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4
                       Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
-                        key expressions: _col4 (type: tinyint), -1 (type: int), _col3 (type: float)
+                        key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float)
                         sort order: +++
                         Map-reduce partition columns: _col4 (type: tinyint)
                         Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
+                        value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint), '_bucket_number' (type: string)
             Execution mode: vectorized
         Reducer 2 
             Reduce Operator Tree:
@@ -1904,6 +2178,7 @@ STAGE PLANS:
                       output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       name: default.over1k_part_buck_sort2_orc
+            Execution mode: vectorized
 
   Stage: Stage-2
     Dependency Collection
@@ -2095,17 +2370,17 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: over1k_part_buck_sort2_orc
-                  Statistics: Num rows: 19 Data size: 493 Basic stats: COMPLETE Column stats: COMPLETE
+                  Statistics: Num rows: 19 Data size: 493 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
-                    Statistics: Num rows: 19 Data size: 493 Basic stats: COMPLETE Column stats: COMPLETE
+                    Statistics: Num rows: 19 Data size: 493 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       aggregations: count()
                       mode: hash
                       outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         sort order: 
-                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: bigint)
         Reducer 2 
             Reduce Operator Tree:
@@ -2113,14 +2388,14 @@ STAGE PLANS:
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -2318,17 +2593,17 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: over1k_part_buck_sort2_orc
-                  Statistics: Num rows: 19 Data size: 493 Basic stats: COMPLETE Column stats: COMPLETE
+                  Statistics: Num rows: 19 Data size: 493 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
-                    Statistics: Num rows: 19 Data size: 493 Basic stats: COMPLETE Column stats: COMPLETE
+                    Statistics: Num rows: 19 Data size: 493 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       aggregations: count()
                       mode: hash
                       outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         sort order: 
-                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: bigint)
         Reducer 2 
             Reduce Operator Tree:
@@ -2336,14 +2611,14 @@ STAGE PLANS:
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat



Mime
View raw message