hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From li...@apache.org
Subject [1/4] hive git commit: HIVE-15357: Fix and re-enable the spark-only tests (Rui reviewed by Chao)
Date Fri, 23 Dec 2016 03:28:01 GMT
Repository: hive
Updated Branches:
  refs/heads/master ee35ccb19 -> 858ce8c22


http://git-wip-us.apache.org/repos/asf/hive/blob/858ce8c2/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out
index c8f6cd7..699fcc6 100644
--- a/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out
+++ b/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out
@@ -127,6 +127,8 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
 POSTHOOK: Output: database:default
 POSTHOOK: Output: default@srcpart_date
+POSTHOOK: Lineage: srcpart_date.date SIMPLE [(srcpart)srcpart.FieldSchema(name:ds, type:string, comment:null), ]
+POSTHOOK: Lineage: srcpart_date.ds SIMPLE [(srcpart)srcpart.FieldSchema(name:ds, type:string, comment:null), ]
 PREHOOK: query: create table srcpart_hour stored as orc as select hr as hr, hr as hour from srcpart group by hr
 PREHOOK: type: CREATETABLE_AS_SELECT
 PREHOOK: Input: default@srcpart
@@ -145,6 +147,8 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
 POSTHOOK: Output: database:default
 POSTHOOK: Output: default@srcpart_hour
+POSTHOOK: Lineage: srcpart_hour.hour SIMPLE [(srcpart)srcpart.FieldSchema(name:hr, type:string, comment:null), ]
+POSTHOOK: Lineage: srcpart_hour.hr SIMPLE [(srcpart)srcpart.FieldSchema(name:hr, type:string, comment:null), ]
 PREHOOK: query: create table srcpart_date_hour stored as orc as select ds as ds, ds as `date`, hr as hr, hr as hour from srcpart group by ds, hr
 PREHOOK: type: CREATETABLE_AS_SELECT
 PREHOOK: Input: default@srcpart
@@ -163,6 +167,10 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
 POSTHOOK: Output: database:default
 POSTHOOK: Output: default@srcpart_date_hour
+POSTHOOK: Lineage: srcpart_date_hour.date SIMPLE [(srcpart)srcpart.FieldSchema(name:ds, type:string, comment:null), ]
+POSTHOOK: Lineage: srcpart_date_hour.ds SIMPLE [(srcpart)srcpart.FieldSchema(name:ds, type:string, comment:null), ]
+POSTHOOK: Lineage: srcpart_date_hour.hour SIMPLE [(srcpart)srcpart.FieldSchema(name:hr, type:string, comment:null), ]
+POSTHOOK: Lineage: srcpart_date_hour.hr SIMPLE [(srcpart)srcpart.FieldSchema(name:hr, type:string, comment:null), ]
 PREHOOK: query: create table srcpart_double_hour stored as orc as select (hr*2) as hr, hr as hour from srcpart group by hr
 PREHOOK: type: CREATETABLE_AS_SELECT
 PREHOOK: Input: default@srcpart
@@ -181,6 +189,8 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
 POSTHOOK: Output: database:default
 POSTHOOK: Output: default@srcpart_double_hour
+POSTHOOK: Lineage: srcpart_double_hour.hour SIMPLE [(srcpart)srcpart.FieldSchema(name:hr, type:string, comment:null), ]
+POSTHOOK: Lineage: srcpart_double_hour.hr EXPRESSION [(srcpart)srcpart.FieldSchema(name:hr, type:string, comment:null), ]
 PREHOOK: query: -- single column, single key
 EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
 PREHOOK: type: QUERY
@@ -201,10 +211,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                    predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -252,10 +262,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                    predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -297,8 +307,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -361,10 +371,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                    predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -406,8 +416,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -438,14 +448,10 @@ POSTHOOK: Input: default@srcpart_date
 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08'
 PREHOOK: type: QUERY
 PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
 #### A masked pattern was here ####
 POSTHOOK: query: select count(*) from srcpart where ds = '2008-04-08'
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
 #### A masked pattern was here ####
 1000
 PREHOOK: query: -- multiple sources, single key
@@ -470,10 +476,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                    predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -498,10 +504,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: string)
@@ -550,10 +556,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                    predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -569,10 +575,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: string)
@@ -629,8 +635,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -701,10 +707,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                    predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -720,10 +726,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: string)
@@ -780,8 +786,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -816,12 +822,10 @@ POSTHOOK: Input: default@srcpart_hour
 PREHOOK: query: select count(*) from srcpart where hr = 11 and ds = '2008-04-08'
 PREHOOK: type: QUERY
 PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
 #### A masked pattern was here ####
 POSTHOOK: query: select count(*) from srcpart where hr = 11 and ds = '2008-04-08'
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
 #### A masked pattern was here ####
 500
 PREHOOK: query: -- multiple columns single source
@@ -844,10 +848,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date_hour
-                  filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean)
                   Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string), hr (type: string)
@@ -872,10 +876,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date_hour
-                  filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean)
                   Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string), hr (type: string)
@@ -922,10 +926,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date_hour
-                  filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean)
                   Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string), hr (type: string)
@@ -967,8 +971,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -1031,10 +1035,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date_hour
-                  filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean)
                   Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0) and ds is not null and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string), hr (type: string)
@@ -1076,8 +1080,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -1108,12 +1112,10 @@ POSTHOOK: Input: default@srcpart_date_hour
 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' and hr = 11
 PREHOOK: type: QUERY
 PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
 #### A masked pattern was here ####
 POSTHOOK: query: select count(*) from srcpart where ds = '2008-04-08' and hr = 11
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
 #### A masked pattern was here ####
 500
 PREHOOK: query: -- empty set
@@ -1136,10 +1138,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = 'I DONT EXIST')) (type: boolean)
+                  filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean)
+                    predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -1187,10 +1189,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = 'I DONT EXIST')) (type: boolean)
+                  filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean)
+                    predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -1232,8 +1234,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -1296,10 +1298,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = 'I DONT EXIST')) (type: boolean)
+                  filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean)
+                    predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -1341,8 +1343,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -1399,10 +1401,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_double_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: double)
@@ -1450,10 +1452,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_double_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: double)
@@ -1495,8 +1497,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -1542,10 +1544,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_double_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: double)
@@ -1585,18 +1587,18 @@ STAGE PLANS:
                     outputColumnNames: _col0
                     Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
+                      key expressions: (UDFToDouble(_col0) * 2.0) (type: double)
                       sort order: +
-                      Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
+                      Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double)
                       Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: srcpart_double_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: double)
@@ -1614,7 +1616,7 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 keys:
-                  0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
+                  0 (UDFToDouble(_col0) * 2.0) (type: double)
                   1 _col0 (type: double)
                 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
@@ -1638,8 +1640,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -1702,10 +1704,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_double_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: double)
@@ -1747,8 +1749,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -1803,18 +1805,18 @@ STAGE PLANS:
                     outputColumnNames: _col0
                     Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
+                      key expressions: (UDFToDouble(_col0) * 2.0) (type: double)
                       sort order: +
-                      Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
+                      Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double)
                       Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: srcpart_double_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: double)
@@ -1832,7 +1834,7 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 keys:
-                  0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
+                  0 (UDFToDouble(_col0) * 2.0) (type: double)
                   1 _col0 (type: double)
                 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
@@ -1856,8 +1858,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -1888,14 +1890,10 @@ POSTHOOK: Input: default@srcpart_double_hour
 PREHOOK: query: select count(*) from srcpart where hr = 11
 PREHOOK: type: QUERY
 PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
 #### A masked pattern was here ####
 POSTHOOK: query: select count(*) from srcpart where hr = 11
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
 #### A masked pattern was here ####
 1000
 PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11
@@ -1916,10 +1914,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_double_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: double)
@@ -1959,18 +1957,18 @@ STAGE PLANS:
                     outputColumnNames: _col0
                     Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string)
+                      key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string)
                       sort order: +
-                      Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string)
+                      Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string)
                       Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: srcpart_double_hour
-                  filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: hr (type: double)
@@ -1988,7 +1986,7 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 keys:
-                  0 UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string)
+                  0 UDFToString((UDFToDouble(_col0) * 2.0)) (type: string)
                   1 UDFToString(_col0) (type: string)
                 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
@@ -2012,8 +2010,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -2044,16 +2042,13 @@ POSTHOOK: Input: default@srcpart_double_hour
 PREHOOK: query: select count(*) from srcpart where cast(hr as string) = 11
 PREHOOK: type: QUERY
 PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
 #### A masked pattern was here ####
 POSTHOOK: query: select count(*) from srcpart where cast(hr as string) = 11
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
 #### A masked pattern was here ####
 1000
+Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
 PREHOOK: query: -- parent is reduce tasks
 EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
 PREHOOK: type: QUERY
@@ -2061,83 +2056,29 @@ POSTHOOK: query: -- parent is reduce tasks
 EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
-    Spark
-      Edges:
-        Reducer 7 <- Map 6 (GROUP, 2)
-#### A masked pattern was here ####
-      Vertices:
-        Map 6 
-            Map Operator Tree:
-                TableScan
-                  alias: srcpart
-                  filterExpr: (ds = '2008-04-08') (type: boolean)
-                  Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                  Select Operator
-                    expressions: '2008-04-08' (type: string)
-                    outputColumnNames: ds
-                    Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Group By Operator
-                      keys: ds (type: string)
-                      mode: hash
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-        Reducer 7 
-            Execution mode: vectorized
-            Reduce Operator Tree:
-              Group By Operator
-                keys: KEY._col0 (type: string)
-                mode: mergepartial
-                outputColumnNames: _col0
-                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string)
-                  outputColumnNames: _col0
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    keys: _col0 (type: string)
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                    Spark Partition Pruning Sink Operator
-                      partition key expr: ds
-                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                      target column name: ds
-                      target work: Map 1
-
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 5 <- Map 4 (GROUP, 2)
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2)
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1)
         Reducer 3 <- Reducer 2 (GROUP, 1)
+        Reducer 5 <- Map 4 (GROUP, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: srcpart
-                  filterExpr: ds is not null (type: boolean)
-                  Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+                  filterExpr: (ds = '2008-04-08') (type: boolean)
+                  Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
-                    expressions: ds (type: string)
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1000 Data size: 10624 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+                      sort order: 
+                      Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
@@ -2145,18 +2086,16 @@ STAGE PLANS:
                   filterExpr: (ds = '2008-04-08') (type: boolean)
                   Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
-                    expressions: '2008-04-08' (type: string)
-                    outputColumnNames: ds
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
-                      keys: ds (type: string)
+                      keys: '2008-04-08' (type: string)
                       mode: hash
                       outputColumnNames: _col0
                       Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
-                        key expressions: _col0 (type: string)
+                        key expressions: '2008-04-08' (type: string)
                         sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
+                        Map-reduce partition columns: '2008-04-08' (type: string)
                         Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
@@ -2164,9 +2103,9 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 keys:
-                  0 _col0 (type: string)
-                  1 _col0 (type: string)
-                Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+                  0 
+                  1 
+                Statistics: Num rows: 500000 Data size: 11124000 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
                   aggregations: count()
                   mode: hash
@@ -2188,22 +2127,22 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
         Reducer 5 
             Execution mode: vectorized
             Reduce Operator Tree:
               Group By Operator
-                keys: KEY._col0 (type: string)
+                keys: '2008-04-08' (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0
                 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
+                Select Operator
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    sort order: 
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-0
     Fetch Operator
@@ -2211,37 +2150,30 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
+Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
 PREHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
 PREHOOK: type: QUERY
 PREHOOK: Input: default@srcpart
 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
 #### A masked pattern was here ####
 POSTHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@srcpart
 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
 #### A masked pattern was here ####
 1000
 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08'
 PREHOOK: type: QUERY
 PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
 #### A masked pattern was here ####
 POSTHOOK: query: select count(*) from srcpart where ds = '2008-04-08'
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
 #### A masked pattern was here ####
 1000
-Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
+Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
 PREHOOK: query: -- non-equi join
 EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr)
 PREHOOK: type: QUERY
@@ -2300,12 +2232,12 @@ STAGE PLANS:
                   0 
                   1 
                 outputColumnNames: _col0, _col1, _col2, _col4
-                Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 2000 Data size: 743248 Basic stats: COMPLETE Column stats: NONE
                 Filter Operator
                   predicate: ((_col0 = _col2) or (_col1 = _col4)) (type: boolean)
-                  Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 2000 Data size: 743248 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
-                    Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2000 Data size: 743248 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       aggregations: count()
                       mode: hash
@@ -2327,8 +2259,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -2337,7 +2269,7 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
-Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
+Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
 PREHOOK: query: select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr)
 PREHOOK: type: QUERY
 PREHOOK: Input: default@srcpart
@@ -2500,8 +2432,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -2645,8 +2577,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -2768,8 +2700,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -2893,8 +2825,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -2925,10 +2857,10 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                    predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -2964,22 +2896,23 @@ STAGE PLANS:
                   alias: srcpart
                   Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
-                    expressions: ds (type: string)
-                    outputColumnNames: _col0
+                    expressions: ds (type: string), hr (type: string)
+                    outputColumnNames: _col0, _col1
                     Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
         Map 5 
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                    predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -3001,11 +2934,13 @@ STAGE PLANS:
                     predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean)
                     Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
+                      expressions: hr (type: string)
+                      outputColumnNames: _col0
                       Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
-                        key expressions: '11' (type: string)
+                        key expressions: _col0 (type: string)
                         sort order: +
-                        Map-reduce partition columns: '11' (type: string)
+                        Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
             Execution mode: vectorized
         Reducer 2 
@@ -3016,11 +2951,12 @@ STAGE PLANS:
                 keys:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
+                outputColumnNames: _col1
                 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
                 Reduce Output Operator
-                  key expressions: '11' (type: string)
+                  key expressions: _col1 (type: string)
                   sort order: +
-                  Map-reduce partition columns: '11' (type: string)
+                  Map-reduce partition columns: _col1 (type: string)
                   Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
         Reducer 3 
             Reduce Operator Tree:
@@ -3052,8 +2988,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -3104,29 +3040,30 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcpart
-                  filterExpr: (ds is not null and (UDFToDouble(hr) = 13.0)) (type: boolean)
+                  filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean)
                   Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (UDFToDouble(hr) = 13.0)) (type: boolean)
+                    predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
                     Select Operator
-                      expressions: ds (type: string)
-                      outputColumnNames: _col0
+                      expressions: ds (type: string), hr (type: string)
+                      outputColumnNames: _col0, _col1
                       Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+                        value expressions: _col1 (type: string)
             Execution mode: vectorized
         Map 5 
             Map Operator Tree:
                 TableScan
                   alias: srcpart_date
-                  filterExpr: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                  filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
                   Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
+                    predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: ds (type: string)
@@ -3148,11 +3085,13 @@ STAGE PLANS:
                     predicate: (UDFToDouble(hr) = 13.0) (type: boolean)
                     Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
+                      expressions: hr (type: string)
+                      outputColumnNames: _col0
                       Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
-                        key expressions: '13' (type: string)
+                        key expressions: _col0 (type: string)
                         sort order: +
-                        Map-reduce partition columns: '13' (type: string)
+                        Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
             Execution mode: vectorized
         Reducer 2 
@@ -3163,11 +3102,12 @@ STAGE PLANS:
                 keys:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
+                outputColumnNames: _col1
                 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
                 Reduce Output Operator
-                  key expressions: '13' (type: string)
+                  key expressions: _col1 (type: string)
                   sort order: +
-                  Map-reduce partition columns: '13' (type: string)
+                  Map-reduce partition columns: _col1 (type: string)
                   Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
         Reducer 3 
             Reduce Operator Tree:
@@ -3199,8 +3139,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
@@ -3239,11 +3179,12 @@ STAGE PLANS:
   Stage: Stage-2
     Spark
       Edges:
-        Reducer 11 <- Map 10 (GROUP, 1)
-        Reducer 9 <- Map 8 (GROUP, 1)
+        Reducer 10 <- Map 9 (GROUP, 1)
+        Reducer 11 <- Reducer 10 (GROUP, 2), Reducer 13 (GROUP, 2)
+        Reducer 13 <- Map 12 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 10 
+        Map 12 
             Map Operator Tree:
                 TableScan
                   alias: srcpart
@@ -3256,12 +3197,12 @@ STAGE PLANS:
                       aggregations: min(ds)
                       mode: hash
                       outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         sort order: 
-                        Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string)
-        Map 8 
+        Map 9 
             Map Operator Tree:
                 TableScan
                   alias: srcpart
@@ -3274,86 +3215,84 @@ STAGE PLANS:
                       aggregations: max(ds)
                       mode: hash
                       outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         sort order: 
-                        Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string)
+        Reducer 10 
+            Execution mode: vectorized
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: max(VALUE._col0)
+                mode: mergepartial
+                outputColumnNames: _col0
+                Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  keys: _col0 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 2 Data size: 368 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: 368 Basic stats: COMPLETE Column stats: NONE
         Reducer 11 
             Execution mode: vectorized
             Reduce Operator Tree:
               Group By Operator
-                aggregations: min(VALUE._col0)
+                keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
-                Filter Operator
-                  predicate: _col0 is not null (type: boolean)
-                  Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string)
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     keys: _col0 (type: string)
                     mode: hash
                     outputColumnNames: _col0
-                    Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: string)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                      Group By Operator
-                        keys: _col0 (type: string)
-                        mode: hash
-                        outputColumnNames: _col0
-                        Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                        Spark Partition Pruning Sink Operator
-                          partition key expr: ds
-                          Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                          target column name: ds
-                          target work: Map 1
-        Reducer 9 
+                    Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                    Spark Partition Pruning Sink Operator
+                      partition key expr: ds
+                      Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                      target column name: ds
+                      target work: Map 1
+        Reducer 13 
             Execution mode: vectorized
             Reduce Operator Tree:
               Group By Operator
-                aggregations: max(VALUE._col0)
+                aggregations: min(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
-                Filter Operator
-                  predicate: _col0 is not null (type: boolean)
-                  Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    keys: _col0 (type: string)
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: string)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                      Group By Operator
-                        keys: _col0 (type: string)
-                        mode: hash
-                        outputColumnNames: _col0
-                        Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                        Spark Partition Pruning Sink Operator
-                          partition key expr: ds
-                          Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                          target column name: ds
-                          target work: Map 1
+                Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  keys: _col0 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 2 Data size: 368 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: 368 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 5 <- Map 4 (GROUP, 1)
-        Reducer 7 <- Map 6 (GROUP, 1)
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2)
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2)
         Reducer 3 <- Reducer 2 (GROUP, 1)
+        Reducer 5 <- Map 4 (GROUP, 1)
+        Reducer 6 <- Reducer 5 (GROUP, 2), Reducer 8 (GROUP, 2)
+        Reducer 8 <- Map 7 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: srcpart
-                  filterExpr: ds is not null (type: boolean)
                   Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: ds (type: string)
@@ -3377,12 +3316,12 @@ STAGE PLANS:
                       aggregations: max(ds)
                       mode: hash
                       outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         sort order: 
-                        Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string)
-        Map 6 
+        Map 7 
             Map Operator Tree:
                 TableScan
                   alias: srcpart
@@ -3395,16 +3334,16 @@ STAGE PLANS:
                       aggregations: min(ds)
                       mode: hash
                       outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         sort order: 
-                        Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string)
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
-                     Left Semi Join 0 to 1
+                     Inner Join 0 to 1
                 keys:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
@@ -3430,8 +3369,8 @@ STAGE PLANS:
                   compressed: false
                   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
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                       serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
         Reducer 5 
             Execution mode: vectorized
@@ -3440,41 +3379,48 @@ STAGE PLANS:
                 aggregations: max(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
-                Filter Operator
-                  predicate: _col0 is not null (type: boolean)
-                  Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    keys: _col0 (type: string)
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 2 Data size: 168 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: 168 Basic stats: COMPLETE Column stats: NONE
-        Reducer 7 
+                Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  keys: _col0 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 2 Data size: 368 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: 368 Basic stats: COMPLETE Column stats: NONE
+        Reducer 6 
+            Execution mode: vectorized
+            Reduce Operator Tree:
+              Group By Operator
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0
+                Statistics: Num rows: 1 Data size: 184 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: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+        Reducer 8 
             Execution mode: vectorized
             Reduce Operator Tree:
               Group By Operator
                 aggregations: min(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
-                Filter Operator
-                  predicate: _col0 is not null (type: boolean)
-                  Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    keys: _col0 (type: string)
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 2 Data size: 168 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: 168 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  keys: _col0 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 2 Data size: 368 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: 368 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-0
     Fetch Operator
@@ -3512,11 +3458,12 @@ STAGE PLANS:
   Stage: Stage-2
     Spark
       Edges:
-        Reducer 11 <- Map 10 (GROUP, 1)
-        Reducer 9 <- Map 8 (GROUP, 1)
+        Reducer 10 <- Map 9 (GROUP, 1)
+        Reducer 11 <- Reducer 10 (GROUP, 2), Reducer 13 (GROUP, 2)
+        Reducer 13 <- Map 12 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 10 
+        Map 12 
             Map Operator Tree:
                 TableScan
                   alias: srcpart
@@ -3529,12 +3476,12 @@ STAGE PLANS:
                       aggregations: min(ds)
                       mode: hash
                       outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         sort order: 
-                        Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string)
-        Map 8 
+        Map 9 
             Map Operator Tree:
                 TableScan
                   alias: srcpart
@@ -3547,86 +3494,84 @@ STAGE PLANS:
                       aggregations: max(ds)
                       mode: hash
                       outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         sort order: 
-                        Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string)
+        Reducer 10 
+            Execution mode: vectorized
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: max(VALUE._col0)
+                mode: mergepartial
+                outputColumnNames: _col0
+                Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  keys: _col0 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 2 Data size: 368 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: 368 Basic stats: COMPLETE Column stats: NONE
         Reducer 11 
             Execution mode: vectorized
             Reduce Operator Tree:
               Group By Operator
-                aggregations: min(VALUE._col0)
+                keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
-                Filter Operator
-                  predicate: _col0 is not null (type: boolean)
-                  Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string)
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     keys: _col0 (type: string)
                     mode: hash
                     outputColumnNames: _col0
-                    Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: string)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                      Group By Operator
-                        keys: _col0 (type: string)
-                        mode: hash
-                        outputColumnNames: _col0
-                        Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                        Spark Partition Pruning Sink Operator
-                          partition key expr: ds
-                          Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                          target column name: ds
-                          target work: Map 1
-        Reducer 9 
+                    Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                    Spark Partition Pruning Sink Operator
+                      partition key expr: ds
+                      Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                      target column name: ds
+                      target work: Map 1
+        Reducer 13 
             Execution mode: vectorized
             Reduce Operator Tree:
               Group By Operator
-                aggregations: max(VALUE._col0)
+                aggregations: min(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
-                Filter Operator
-                  predicate: _col0 is not null (type: boolean)
-                  Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    keys: _col0 (type: string)
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: string)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                      Group By Operator
-                        keys: _col0 (type: string)
-                        mode: hash
-                        outputColumnNames: _col0
-                        Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                        Spark Partition Pruning Sink Operator
-                          partition key expr: ds
-                          Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE
-                          target column name: ds
-                          target work: Map 1
+                Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  keys: _col0 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 2 Data size: 368 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: 368 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 5 <- Map 4 (GROUP, 1)
-        Reducer 7 <- Map 6 (GROUP, 1)
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2)
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2)
         Reducer 3 <- Reducer 2 (GROUP, 2)
+        Reducer 5 <- Map 4 (GROUP, 1)
+        Reducer 6 <- Reducer 5 (GROUP, 2), Reducer 8 (GROUP, 2)
+        Reducer 8 <- Map 7 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: srcpart
-                  filterExpr: ds is not null (type: boolean)
                   Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: ds (type: string)
@@ -3650,12 +3595,12 @@ STAGE PLANS:
                       aggregations: max(ds)
                       mode: hash
                       outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         sort order: 
-                        Statistics

<TRUNCATED>

Mime
View raw message