hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jd...@apache.org
Subject [03/12] hive git commit: HIVE-18208: SMB Join : Fix the unit tests to run SMB Joins. (Deepak Jaiswal, reviewed by Jason Dere)
Date Tue, 12 Dec 2017 20:51:26 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out
index 0af21e0..da28ae4 100644
--- a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out
+++ b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out
@@ -77,52 +77,40 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 2 <- Map 1 (BROADCAST_EDGE)
-        Reducer 3 <- Map 2 (SIMPLE_EDGE)
-        Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+        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: a
-                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
+                  alias: b
+                  Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean)
-                    Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
+                    Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: int)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: int)
-                        Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
-                        value expressions: _col1 (type: string)
-            Execution mode: llap
-            LLAP IO: no inputs
-        Map 2 
+                      Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE
+                  alias: a
+                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean)
-                    Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
+                    Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE
-                      Map Join Operator
+                      Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
+                      Merge Join Operator
                         condition map:
                              Inner Join 0 to 1
                         keys:
                           0 _col0 (type: int)
                           1 _col0 (type: int)
                         outputColumnNames: _col0, _col1, _col4
-                        input vertices:
-                          0 Map 1
                         Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE
                         Select Operator
                           expressions: _col0 (type: int), concat(_col1, _col4) (type: string)
@@ -135,8 +123,7 @@ STAGE PLANS:
                             Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
                             value expressions: _col1 (type: string)
             Execution mode: llap
-            LLAP IO: no inputs
-        Reducer 3 
+        Reducer 2 
             Execution mode: llap
             Reduce Operator Tree:
               Select Operator
@@ -167,7 +154,7 @@ STAGE PLANS:
                       Map-reduce partition columns: _col0 (type: string)
                       Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
                       value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
-        Reducer 4 
+        Reducer 3 
             Execution mode: llap
             Reduce Operator Tree:
               Group By Operator
@@ -302,52 +289,40 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 2 <- Map 1 (BROADCAST_EDGE)
-        Reducer 3 <- Map 2 (SIMPLE_EDGE)
-        Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+        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: test_table1
-                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
+                  alias: test_table2
+                  Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean)
-                    Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
+                    Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: int)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: int)
-                        Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
-                        value expressions: _col1 (type: string)
-            Execution mode: llap
-            LLAP IO: no inputs
-        Map 2 
+                      Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
             Map Operator Tree:
                 TableScan
-                  alias: test_table2
-                  Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE
+                  alias: test_table1
+                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean)
-                    Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
+                    Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
-                      Map Join Operator
+                      Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
+                      Merge Join Operator
                         condition map:
                              Inner Join 0 to 1
                         keys:
                           0 _col0 (type: int)
                           1 _col0 (type: int)
                         outputColumnNames: _col0, _col1, _col3
-                        input vertices:
-                          0 Map 1
                         Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE
                         Select Operator
                           expressions: _col0 (type: int), concat(_col1, _col3) (type: string)
@@ -360,8 +335,7 @@ STAGE PLANS:
                             Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
                             value expressions: _col1 (type: string)
             Execution mode: llap
-            LLAP IO: no inputs
-        Reducer 3 
+        Reducer 2 
             Execution mode: llap
             Reduce Operator Tree:
               Select Operator
@@ -392,7 +366,7 @@ STAGE PLANS:
                       Map-reduce partition columns: _col0 (type: string)
                       Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
                       value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
-        Reducer 4 
+        Reducer 3 
             Execution mode: llap
             Reduce Operator Tree:
               Group By Operator
@@ -533,52 +507,40 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 2 <- Map 1 (BROADCAST_EDGE)
-        Reducer 3 <- Map 2 (SIMPLE_EDGE)
-        Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+        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: test_table1
-                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
+                  alias: test_table2
+                  Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((key = 0) or (key = 5)) and (key < 8)) (type: boolean)
-                    Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE
+                    Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: int)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: int)
-                        Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE
-                        value expressions: _col1 (type: string)
-            Execution mode: llap
-            LLAP IO: no inputs
-        Map 2 
+                      Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
             Map Operator Tree:
                 TableScan
-                  alias: test_table2
-                  Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE
+                  alias: test_table1
+                  Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
                   Filter Operator
                     predicate: (((key = 0) or (key = 5)) and (key < 8)) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
+                    Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
-                      Map Join Operator
+                      Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE
+                      Merge Join Operator
                         condition map:
                              Inner Join 0 to 1
                         keys:
                           0 _col0 (type: int)
                           1 _col0 (type: int)
                         outputColumnNames: _col0, _col1, _col3
-                        input vertices:
-                          0 Map 1
                         Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE
                         Select Operator
                           expressions: _col0 (type: int), concat(_col1, _col3) (type: string)
@@ -591,8 +553,7 @@ STAGE PLANS:
                             Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
                             value expressions: _col1 (type: string)
             Execution mode: llap
-            LLAP IO: no inputs
-        Reducer 3 
+        Reducer 2 
             Execution mode: llap
             Reduce Operator Tree:
               Select Operator
@@ -623,7 +584,7 @@ STAGE PLANS:
                       Map-reduce partition columns: _col0 (type: string)
                       Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE
                       value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
-        Reducer 4 
+        Reducer 3 
             Execution mode: llap
             Reduce Operator Tree:
               Group By Operator

http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/llap/quotedid_smb.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/quotedid_smb.q.out b/ql/src/test/results/clientpositive/llap/quotedid_smb.q.out
index 8e850f5..97721d0 100644
--- a/ql/src/test/results/clientpositive/llap/quotedid_smb.q.out
+++ b/ql/src/test/results/clientpositive/llap/quotedid_smb.q.out
@@ -42,6 +42,69 @@ POSTHOOK: Input: default@src
 POSTHOOK: Output: default@src_b2
 POSTHOOK: Lineage: src_b2.!@#$%^&*()_q SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
 POSTHOOK: Lineage: src_b2.x+1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: explain select a.`x+1`, a.`!@#$%^&*()_q`, b.`x+1`, b.`!@#$%^&*()_q`
+from src_b a join src_b2 b on a.`!@#$%^&*()_q` = b.`!@#$%^&*()_q`
+where a.`x+1` < '11'
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select a.`x+1`, a.`!@#$%^&*()_q`, b.`x+1`, b.`!@#$%^&*()_q`
+from src_b a join src_b2 b on a.`!@#$%^&*()_q` = b.`!@#$%^&*()_q`
+where a.`x+1` < '11'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: !@#$%^&*()_q is not null (type: boolean)
+                    Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: x+1 (type: string), !@#$%^&*()_q (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (!@#$%^&*()_q is not null and (x+1 < '11')) (type: boolean)
+                    Statistics: Num rows: 141 Data size: 49397 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: x+1 (type: string), !@#$%^&*()_q (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 141 Data size: 49397 Basic stats: COMPLETE Column stats: NONE
+                      Merge Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        keys:
+                          0 _col1 (type: string)
+                          1 _col1 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Statistics: Num rows: 522 Data size: 183049 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 522 Data size: 183049 Basic stats: COMPLETE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Execution mode: llap
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
 PREHOOK: query: select a.`x+1`, a.`!@#$%^&*()_q`, b.`x+1`, b.`!@#$%^&*()_q`
 from src_b a join src_b2 b on a.`!@#$%^&*()_q` = b.`!@#$%^&*()_q`
 where a.`x+1` < '11'
@@ -56,15 +119,6 @@ POSTHOOK: type: QUERY
 POSTHOOK: Input: default@src_b
 POSTHOOK: Input: default@src_b2
 #### A masked pattern was here ####
-10	val_10	10	val_10
-100	val_100	100	val_100
-100	val_100	100	val_100
-100	val_100	100	val_100
-100	val_100	100	val_100
-104	val_104	104	val_104
-104	val_104	104	val_104
-104	val_104	104	val_104
-104	val_104	104	val_104
 0	val_0	0	val_0
 0	val_0	0	val_0
 0	val_0	0	val_0
@@ -79,3 +133,12 @@ POSTHOOK: Input: default@src_b2
 103	val_103	103	val_103
 103	val_103	103	val_103
 105	val_105	105	val_105
+10	val_10	10	val_10
+100	val_100	100	val_100
+100	val_100	100	val_100
+100	val_100	100	val_100
+100	val_100	100	val_100
+104	val_104	104	val_104
+104	val_104	104	val_104
+104	val_104	104	val_104
+104	val_104	104	val_104

http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/llap/smb_cache.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/smb_cache.q.out b/ql/src/test/results/clientpositive/llap/smb_cache.q.out
index defade5..7614cf5 100644
--- a/ql/src/test/results/clientpositive/llap/smb_cache.q.out
+++ b/ql/src/test/results/clientpositive/llap/smb_cache.q.out
@@ -200,43 +200,86 @@ t1.userid,
   from bug_201_input_b as t1
   join bug_201_input_a as fa on (t1.userid = fa.userid)
 POSTHOOK: type: QUERY
-Plan optimized by CBO.
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
 
-Vertex dependency in root stage
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Edges:
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: t1
+                  Statistics: Num rows: 130 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE
+                  Filter Operator
+                    predicate: userid is not null (type: boolean)
+                    Statistics: Num rows: 130 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE
+                    Select Operator
+                      expressions: userid (type: int)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 130 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: int)
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: int)
+                        Statistics: Num rows: 130 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE
+            Execution mode: llap
+            LLAP IO: no inputs
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: fa
+                  Statistics: Num rows: 527 Data size: 2108 Basic stats: COMPLETE Column stats: COMPLETE
+                  Filter Operator
+                    predicate: userid is not null (type: boolean)
+                    Statistics: Num rows: 527 Data size: 2108 Basic stats: COMPLETE Column stats: COMPLETE
+                    Select Operator
+                      expressions: userid (type: int)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 527 Data size: 2108 Basic stats: COMPLETE Column stats: COMPLETE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: int)
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: int)
+                        Statistics: Num rows: 527 Data size: 2108 Basic stats: COMPLETE Column stats: COMPLETE
+            Execution mode: llap
+            LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Merge Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 130 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 130 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
-Stage-0
-  Fetch Operator
-    limit:-1
-    Stage-1
-      Reducer 2 llap
-      File Output Operator [FS_10]
-        Merge Join Operator [MERGEJOIN_15] (rows=130 width=8)
-          Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col1"]
-        <-Map 1 [SIMPLE_EDGE] llap
-          SHUFFLE [RS_6]
-            PartitionCols:_col0
-            Select Operator [SEL_2] (rows=130 width=4)
-              Output:["_col0"]
-              Filter Operator [FIL_13] (rows=130 width=4)
-                predicate:userid is not null
-                TableScan [TS_0] (rows=130 width=4)
-                  default@bug_201_input_b,t1,Tbl:COMPLETE,Col:COMPLETE,Output:["userid"]
-        <-Map 3 [SIMPLE_EDGE] llap
-          SHUFFLE [RS_7]
-            PartitionCols:_col0
-            Select Operator [SEL_5] (rows=527 width=4)
-              Output:["_col0"]
-              Filter Operator [FIL_14] (rows=527 width=4)
-                predicate:userid is not null
-                TableScan [TS_3] (rows=527 width=4)
-                  default@bug_201_input_a,fa,Tbl:COMPLETE,Col:COMPLETE,Output:["userid"]
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
 
 PREHOOK: query: select
 t1.userid,
   fa.userid   as  fa_userid 
   from bug_201_input_b as t1
-  join bug_201_input_a as fa on (t1.userid = fa.userid)
+  join bug_201_input_a as fa on (t1.userid = fa.userid) order by t1.userid, fa.userid
 PREHOOK: type: QUERY
 PREHOOK: Input: default@bug_201_input_a
 PREHOOK: Input: default@bug_201_input_b
@@ -245,7 +288,7 @@ POSTHOOK: query: select
 t1.userid,
   fa.userid   as  fa_userid 
   from bug_201_input_b as t1
-  join bug_201_input_a as fa on (t1.userid = fa.userid)
+  join bug_201_input_a as fa on (t1.userid = fa.userid) order by t1.userid, fa.userid
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@bug_201_input_a
 POSTHOOK: Input: default@bug_201_input_b
@@ -265,7 +308,6 @@ POSTHOOK: Input: default@bug_201_input_b
 162031843	162031843
 181554703	181554703
 182530846	182530846
-Warning: Value had a \n character in it.
 PREHOOK: query: explain
 select
 t1.userid,
@@ -280,43 +322,66 @@ t1.userid,
   from bug_201_input_b as t1
   join bug_201_input_a as fa on (t1.userid = fa.userid)
 POSTHOOK: type: QUERY
-Plan optimized by CBO.
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
 
-Vertex dependency in root stage
-Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
+            Map Operator Tree:
+                TableScan
+                  alias: t1
+                  Statistics: Num rows: 130 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE
+                  Filter Operator
+                    predicate: userid is not null (type: boolean)
+                    Statistics: Num rows: 130 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE
+                    Select Operator
+                      expressions: userid (type: int)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 130 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE
+            Map Operator Tree:
+                TableScan
+                  alias: fa
+                  Statistics: Num rows: 527 Data size: 2108 Basic stats: COMPLETE Column stats: COMPLETE
+                  Filter Operator
+                    predicate: userid is not null (type: boolean)
+                    Statistics: Num rows: 527 Data size: 2108 Basic stats: COMPLETE Column stats: COMPLETE
+                    Select Operator
+                      expressions: userid (type: int)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 527 Data size: 2108 Basic stats: COMPLETE Column stats: COMPLETE
+                      Merge Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        keys:
+                          0 _col0 (type: int)
+                          1 _col0 (type: int)
+                        outputColumnNames: _col0, _col1
+                        Statistics: Num rows: 130 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 130 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
+                          table:
+                              input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Execution mode: llap
 
-Stage-0
-  Fetch Operator
-    limit:-1
-    Stage-1
-      Reducer 2 llap
-      File Output Operator [FS_10]
-        Merge Join Operator [MERGEJOIN_15] (rows=130 width=8)
-          Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col1"]
-        <-Map 1 [SIMPLE_EDGE] llap
-          SHUFFLE [RS_6]
-            PartitionCols:_col0
-            Select Operator [SEL_2] (rows=130 width=4)
-              Output:["_col0"]
-              Filter Operator [FIL_13] (rows=130 width=4)
-                predicate:userid is not null
-                TableScan [TS_0] (rows=130 width=4)
-                  default@bug_201_input_b,t1,Tbl:COMPLETE,Col:COMPLETE,Output:["userid"]
-        <-Map 3 [SIMPLE_EDGE] llap
-          SHUFFLE [RS_7]
-            PartitionCols:_col0
-            Select Operator [SEL_5] (rows=527 width=4)
-              Output:["_col0"]
-              Filter Operator [FIL_14] (rows=527 width=4)
-                predicate:userid is not null
-                TableScan [TS_3] (rows=527 width=4)
-                  default@bug_201_input_a,fa,Tbl:COMPLETE,Col:COMPLETE,Output:["userid"]
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
 
 PREHOOK: query: select
 t1.userid,
   fa.userid   as  fa_userid 
   from bug_201_input_b as t1
-  join bug_201_input_a as fa on (t1.userid = fa.userid)
+  join bug_201_input_a as fa on (t1.userid = fa.userid) order by t1.userid, fa.userid
 PREHOOK: type: QUERY
 PREHOOK: Input: default@bug_201_input_a
 PREHOOK: Input: default@bug_201_input_b
@@ -325,7 +390,7 @@ POSTHOOK: query: select
 t1.userid,
   fa.userid   as  fa_userid 
   from bug_201_input_b as t1
-  join bug_201_input_a as fa on (t1.userid = fa.userid)
+  join bug_201_input_a as fa on (t1.userid = fa.userid) order by t1.userid, fa.userid
 POSTHOOK: type: QUERY
 POSTHOOK: Input: default@bug_201_input_a
 POSTHOOK: Input: default@bug_201_input_b

http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_1.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_1.q.out
index e6038b8..86c10aa 100644
--- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_1.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_1.q.out
@@ -520,96 +520,10 @@ PREHOOK: type: QUERY
 POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
 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
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                  GatherStats: false
-                  Filter Operator
-                    isSamplingPred: false
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: key (type: string)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                      Spark HashTable Sink Operator
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                        Position of Big Table: 0
-            Local Work:
-              Map Reduce Local Work
-                Bucket Mapjoin Context:
-                    Alias Bucket File Name Mapping:
-#### A masked pattern was here ####
-                    Alias Bucket Output File Name Mapping:
-#### A masked pattern was here ####
-            Path -> Alias:
-#### A masked pattern was here ####
-            Path -> Partition:
-#### A masked pattern was here ####
-                Partition
-                  base file name: ds=2008-04-08
-                  input format: org.apache.hadoop.mapred.TextInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                  partition values:
-                    ds 2008-04-08
-                  properties:
-                    bucket_count 2
-                    bucket_field_name key
-                    column.name.delimiter ,
-                    columns key,value
-                    columns.comments 
-                    columns.types string:string
-#### A masked pattern was here ####
-                    name default.bucket_small
-                    numFiles 2
-                    numRows 0
-                    partition_columns ds
-                    partition_columns.types string
-                    rawDataSize 0
-                    serialization.ddl struct bucket_small { string key, string value}
-                    serialization.format 1
-                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 114
-#### A masked pattern was here ####
-                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                
-                    input format: org.apache.hadoop.mapred.TextInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                    properties:
-                      SORTBUCKETCOLSPREFIX TRUE
-                      bucket_count 2
-                      bucket_field_name key
-                      column.name.delimiter ,
-                      columns key,value
-                      columns.comments 
-                      columns.types string:string
-#### A masked pattern was here ####
-                      name default.bucket_small
-                      partition_columns ds
-                      partition_columns.types string
-                      serialization.ddl struct bucket_small { string key, string value}
-                      serialization.format 1
-                      serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
-                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.bucket_small
-                  name: default.bucket_small
-            Truncated Path -> Alias:
-              /bucket_small/ds=2008-04-08 [$hdt$_1:b]
-
   Stage: Stage-1
     Spark
       Edges:
@@ -630,14 +544,12 @@ STAGE PLANS:
                       expressions: key (type: string)
                       outputColumnNames: _col0
                       Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
+                      Sorted Merge Bucket Map Join Operator
                         condition map:
                              Inner Join 0 to 1
                         keys:
                           0 _col0 (type: string)
                           1 _col0 (type: string)
-                        input vertices:
-                          1 Map 3
                         Position of Big Table: 0
                         Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
                         BucketMapJoin: true
@@ -653,13 +565,6 @@ STAGE PLANS:
                             tag: -1
                             value expressions: _col0 (type: bigint)
                             auto parallelism: false
-            Local Work:
-              Map Reduce Local Work
-                Bucket Mapjoin Context:
-                    Alias Bucket File Name Mapping:
-#### A masked pattern was here ####
-                    Alias Bucket Output File Name Mapping:
-#### A masked pattern was here ####
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:

http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out
index ff9a0f4..3db099a 100644
--- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out
@@ -134,19 +134,22 @@ POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket3out
 POSTHOOK: type: LOAD
 #### A masked pattern was here ####
 POSTHOOK: Output: default@bucket_medium@ds=2008-04-08
-Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[17][tables = [$hdt$_1, $hdt$_2, $hdt$_0, $hdt$_3]] in Work 'Reducer 3' is a cross product
 PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key
 PREHOOK: type: QUERY
 POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key
 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
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2), Map 6 (PARTITION-LEVEL SORT, 2)
+        Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
+        Reducer 4 <- Reducer 3 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -163,14 +166,14 @@ STAGE PLANS:
                       expressions: key (type: string)
                       outputColumnNames: _col0
                       Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                      Spark HashTable Sink Operator
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                          2 _col0 (type: string)
-                        Position of Big Table: 2
-            Local Work:
-              Map Reduce Local Work
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        null sort order: a
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                        tag: 0
+                        auto parallelism: false
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -225,7 +228,7 @@ STAGE PLANS:
                   name: default.bucket_small
             Truncated Path -> Alias:
               /bucket_small/ds=2008-04-08 [$hdt$_1:a]
-        Map 2 
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -239,14 +242,14 @@ STAGE PLANS:
                       expressions: key (type: string)
                       outputColumnNames: _col0
                       Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
-                      Spark HashTable Sink Operator
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                          2 _col0 (type: string)
-                        Position of Big Table: 2
-            Local Work:
-              Map Reduce Local Work
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        null sort order: a
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+                        tag: 1
+                        auto parallelism: false
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -301,21 +304,28 @@ STAGE PLANS:
                   name: default.bucket_medium
             Truncated Path -> Alias:
               /bucket_medium/ds=2008-04-08 [$hdt$_2:b]
-        Map 5 
+        Map 6 
             Map Operator Tree:
                 TableScan
-                  alias: d
-                  Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL Column stats: NONE
+                  alias: c
+                  Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
-                  Select Operator
-                    Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 
-                        1 
-                      Position of Big Table: 0
-            Local Work:
-              Map Reduce Local Work
+                  Filter Operator
+                    isSamplingPred: false
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        null sort order: a
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+                        tag: 2
+                        auto parallelism: false
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -327,23 +337,23 @@ STAGE PLANS:
                   partition values:
                     ds 2008-04-08
                   properties:
-                    bucket_count 3
+                    bucket_count 4
                     bucket_field_name key
                     column.name.delimiter ,
                     columns key,value
                     columns.comments 
                     columns.types string:string
 #### A masked pattern was here ####
-                    name default.bucket_medium
-                    numFiles 3
+                    name default.bucket_big
+                    numFiles 4
                     numRows 0
                     partition_columns ds
                     partition_columns.types string
                     rawDataSize 0
-                    serialization.ddl struct bucket_medium { string key, string value}
+                    serialization.ddl struct bucket_big { string key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 170
+                    totalSize 5812
 #### A masked pattern was here ####
                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                 
@@ -351,93 +361,30 @@ STAGE PLANS:
                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                     properties:
                       SORTBUCKETCOLSPREFIX TRUE
-                      bucket_count 3
+                      bucket_count 4
                       bucket_field_name key
                       column.name.delimiter ,
                       columns key,value
                       columns.comments 
                       columns.types string:string
 #### A masked pattern was here ####
-                      name default.bucket_medium
+                      name default.bucket_big
                       partition_columns ds
                       partition_columns.types string
-                      serialization.ddl struct bucket_medium { string key, string value}
+                      serialization.ddl struct bucket_big { string key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.bucket_medium
-                  name: default.bucket_medium
-            Truncated Path -> Alias:
-              /bucket_medium/ds=2008-04-08 [$hdt$_3:d]
-
-  Stage: Stage-1
-    Spark
-      Edges:
-        Reducer 4 <- Map 3 (GROUP, 1)
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
-            Map Operator Tree:
-                TableScan
-                  alias: c
-                  Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                  GatherStats: false
-                  Filter Operator
-                    isSamplingPred: false
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: key (type: string)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                             Inner Join 1 to 2
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                          2 _col0 (type: string)
-                        input vertices:
-                          0 Map 1
-                          1 Map 2
-                        Position of Big Table: 2
-                        Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE
-                        Map Join Operator
-                          condition map:
-                               Inner Join 0 to 1
-                          keys:
-                            0 
-                            1 
-                          input vertices:
-                            1 Map 5
-                          Position of Big Table: 0
-                          Statistics: Num rows: 255 Data size: 69177 Basic stats: PARTIAL Column stats: NONE
-                          Group By Operator
-                            aggregations: count()
-                            mode: hash
-                            outputColumnNames: _col0
-                            Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
-                            Reduce Output Operator
-                              null sort order: 
-                              sort order: 
-                              Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
-                              tag: -1
-                              value expressions: _col0 (type: bigint)
-                              auto parallelism: false
-            Local Work:
-              Map Reduce Local Work
-            Path -> Alias:
-#### A masked pattern was here ####
-            Path -> Partition:
+                    name: default.bucket_big
+                  name: default.bucket_big
 #### A masked pattern was here ####
                 Partition
-                  base file name: ds=2008-04-08
+                  base file name: ds=2008-04-09
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   partition values:
-                    ds 2008-04-08
+                    ds 2008-04-09
                   properties:
                     bucket_count 4
                     bucket_field_name key
@@ -480,31 +427,51 @@ STAGE PLANS:
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     name: default.bucket_big
                   name: default.bucket_big
+            Truncated Path -> Alias:
+              /bucket_big/ds=2008-04-08 [$hdt$_0:c]
+              /bucket_big/ds=2008-04-09 [$hdt$_0:c]
+        Map 7 
+            Map Operator Tree:
+                TableScan
+                  alias: d
+                  Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL Column stats: NONE
+                  GatherStats: false
+                  Select Operator
+                    Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL Column stats: NONE
+                    Reduce Output Operator
+                      null sort order: 
+                      sort order: 
+                      Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL Column stats: NONE
+                      tag: 1
+                      auto parallelism: false
+            Path -> Alias:
+#### A masked pattern was here ####
+            Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: ds=2008-04-09
+                  base file name: ds=2008-04-08
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   partition values:
-                    ds 2008-04-09
+                    ds 2008-04-08
                   properties:
-                    bucket_count 4
+                    bucket_count 3
                     bucket_field_name key
                     column.name.delimiter ,
                     columns key,value
                     columns.comments 
                     columns.types string:string
 #### A masked pattern was here ####
-                    name default.bucket_big
-                    numFiles 4
+                    name default.bucket_medium
+                    numFiles 3
                     numRows 0
                     partition_columns ds
                     partition_columns.types string
                     rawDataSize 0
-                    serialization.ddl struct bucket_big { string key, string value}
+                    serialization.ddl struct bucket_medium { string key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 5812
+                    totalSize 170
 #### A masked pattern was here ####
                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                 
@@ -512,26 +479,65 @@ STAGE PLANS:
                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                     properties:
                       SORTBUCKETCOLSPREFIX TRUE
-                      bucket_count 4
+                      bucket_count 3
                       bucket_field_name key
                       column.name.delimiter ,
                       columns key,value
                       columns.comments 
                       columns.types string:string
 #### A masked pattern was here ####
-                      name default.bucket_big
+                      name default.bucket_medium
                       partition_columns ds
                       partition_columns.types string
-                      serialization.ddl struct bucket_big { string key, string value}
+                      serialization.ddl struct bucket_medium { string key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.bucket_big
-                  name: default.bucket_big
+                    name: default.bucket_medium
+                  name: default.bucket_medium
             Truncated Path -> Alias:
-              /bucket_big/ds=2008-04-08 [$hdt$_0:c]
-              /bucket_big/ds=2008-04-09 [$hdt$_0:c]
+              /bucket_medium/ds=2008-04-08 [$hdt$_3:d]
+        Reducer 2 
+            Needs Tagging: true
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 1 to 2
+                keys:
+                  0 _col0 (type: string)
+                  1 _col0 (type: string)
+                  2 _col0 (type: string)
+                Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE
+                Reduce Output Operator
+                  null sort order: 
+                  sort order: 
+                  Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE
+                  tag: 0
+                  auto parallelism: false
+        Reducer 3 
+            Needs Tagging: true
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                keys:
+                  0 
+                  1 
+                Statistics: Num rows: 255 Data size: 69177 Basic stats: PARTIAL Column stats: NONE
+                Group By Operator
+                  aggregations: count()
+                  mode: hash
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
+                  Reduce Output Operator
+                    null sort order: 
+                    sort order: 
+                    Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
+                    tag: -1
+                    value expressions: _col0 (type: bigint)
+                    auto parallelism: false
         Reducer 4 
             Needs Tagging: false
             Reduce Operator Tree:
@@ -569,7 +575,7 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
-Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[17][tables = [$hdt$_1, $hdt$_2, $hdt$_0, $hdt$_3]] in Work 'Reducer 3' is a cross product
 PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key
 PREHOOK: type: QUERY
 PREHOOK: Input: default@bucket_big

http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_14.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_14.q.out
index 8c0d506..5c73ddb 100644
--- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_14.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_14.q.out
@@ -41,31 +41,10 @@ POSTHOOK: query: explain
 select count(*) FROM tbl1 a LEFT OUTER JOIN tbl2 b ON a.key = b.key
 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
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-                  Select Operator
-                    expressions: key (type: int)
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 _col0 (type: int)
-                        1 _col0 (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
       Edges:
@@ -81,14 +60,12 @@ STAGE PLANS:
                     expressions: key (type: int)
                     outputColumnNames: _col0
                     Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
+                    Sorted Merge Bucket Map Join Operator
                       condition map:
                            Left Outer Join 0 to 1
                       keys:
                         0 _col0 (type: int)
                         1 _col0 (type: int)
-                      input vertices:
-                        1 Map 3
                       Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count()
@@ -99,8 +76,6 @@ STAGE PLANS:
                           sort order: 
                           Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col0 (type: bigint)
-            Local Work:
-              Map Reduce Local Work
         Reducer 2 
             Reduce Operator Tree:
               Group By Operator
@@ -150,38 +125,17 @@ POSTHOOK: query: explain
 select count(*) FROM tbl1 a RIGHT OUTER JOIN tbl2 b ON a.key = b.key
 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
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
-                  Select Operator
-                    expressions: key (type: int)
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 _col0 (type: int)
-                        1 _col0 (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 3 <- Map 2 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -190,14 +144,12 @@ STAGE PLANS:
                     expressions: key (type: int)
                     outputColumnNames: _col0
                     Statistics: Num rows: 189 Data size: 1891 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
+                    Sorted Merge Bucket Map Join Operator
                       condition map:
                            Right Outer Join 0 to 1
                       keys:
                         0 _col0 (type: int)
                         1 _col0 (type: int)
-                      input vertices:
-                        0 Map 1
                       Statistics: Num rows: 207 Data size: 2080 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count()
@@ -208,9 +160,7 @@ STAGE PLANS:
                           sort order: 
                           Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col0 (type: bigint)
-            Local Work:
-              Map Reduce Local Work
-        Reducer 3 
+        Reducer 2 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)

http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_15.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_15.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_15.q.out
index b005bda..fbbe01d 100644
--- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_15.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_15.q.out
@@ -41,31 +41,10 @@ POSTHOOK: query: explain
 select count(*) FROM tbl1 a LEFT OUTER JOIN tbl2 b ON a.key = b.key
 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
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-                  Select Operator
-                    expressions: key (type: int)
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 _col0 (type: int)
-                        1 _col0 (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
       Edges:
@@ -81,14 +60,12 @@ STAGE PLANS:
                     expressions: key (type: int)
                     outputColumnNames: _col0
                     Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
+                    Sorted Merge Bucket Map Join Operator
                       condition map:
                            Left Outer Join 0 to 1
                       keys:
                         0 _col0 (type: int)
                         1 _col0 (type: int)
-                      input vertices:
-                        1 Map 3
                       Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count()
@@ -99,8 +76,6 @@ STAGE PLANS:
                           sort order: 
                           Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col0 (type: bigint)
-            Local Work:
-              Map Reduce Local Work
         Reducer 2 
             Reduce Operator Tree:
               Group By Operator
@@ -129,38 +104,17 @@ POSTHOOK: query: explain
 select count(*) FROM tbl1 a RIGHT OUTER JOIN tbl2 b ON a.key = b.key
 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
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
-                  Select Operator
-                    expressions: key (type: int)
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      keys:
-                        0 _col0 (type: int)
-                        1 _col0 (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 3 <- Map 2 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -169,14 +123,12 @@ STAGE PLANS:
                     expressions: key (type: int)
                     outputColumnNames: _col0
                     Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
+                    Sorted Merge Bucket Map Join Operator
                       condition map:
                            Right Outer Join 0 to 1
                       keys:
                         0 _col0 (type: int)
                         1 _col0 (type: int)
-                      input vertices:
-                        0 Map 1
                       Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count()
@@ -187,9 +139,7 @@ STAGE PLANS:
                           sort order: 
                           Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col0 (type: bigint)
-            Local Work:
-              Map Reduce Local Work
-        Reducer 3 
+        Reducer 2 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)

http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out
index 025d0d2..6c25da4 100644
--- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out
@@ -294,96 +294,10 @@ PREHOOK: type: QUERY
 POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
 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
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE
-                  GatherStats: false
-                  Filter Operator
-                    isSamplingPred: false
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: key (type: string)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE
-                      Spark HashTable Sink Operator
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                        Position of Big Table: 0
-            Local Work:
-              Map Reduce Local Work
-                Bucket Mapjoin Context:
-                    Alias Bucket File Name Mapping:
-#### A masked pattern was here ####
-                    Alias Bucket Output File Name Mapping:
-#### A masked pattern was here ####
-            Path -> Alias:
-#### A masked pattern was here ####
-            Path -> Partition:
-#### A masked pattern was here ####
-                Partition
-                  base file name: ds=2008-04-08
-                  input format: org.apache.hadoop.mapred.TextInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                  partition values:
-                    ds 2008-04-08
-                  properties:
-                    bucket_count 4
-                    bucket_field_name key
-                    column.name.delimiter ,
-                    columns key,value
-                    columns.comments 
-                    columns.types string:string
-#### A masked pattern was here ####
-                    name default.bucket_small
-                    numFiles 4
-                    numRows 0
-                    partition_columns ds
-                    partition_columns.types string
-                    rawDataSize 0
-                    serialization.ddl struct bucket_small { string key, string value}
-                    serialization.format 1
-                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 226
-#### A masked pattern was here ####
-                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                
-                    input format: org.apache.hadoop.mapred.TextInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                    properties:
-                      SORTBUCKETCOLSPREFIX TRUE
-                      bucket_count 4
-                      bucket_field_name key
-                      column.name.delimiter ,
-                      columns key,value
-                      columns.comments 
-                      columns.types string:string
-#### A masked pattern was here ####
-                      name default.bucket_small
-                      partition_columns ds
-                      partition_columns.types string
-                      serialization.ddl struct bucket_small { string key, string value}
-                      serialization.format 1
-                      serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
-                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.bucket_small
-                  name: default.bucket_small
-            Truncated Path -> Alias:
-              /bucket_small/ds=2008-04-08 [$hdt$_1:b]
-
   Stage: Stage-1
     Spark
       Edges:
@@ -404,14 +318,12 @@ STAGE PLANS:
                       expressions: key (type: string)
                       outputColumnNames: _col0
                       Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
+                      Sorted Merge Bucket Map Join Operator
                         condition map:
                              Inner Join 0 to 1
                         keys:
                           0 _col0 (type: string)
                           1 _col0 (type: string)
-                        input vertices:
-                          1 Map 3
                         Position of Big Table: 0
                         Statistics: Num rows: 59 Data size: 6050 Basic stats: COMPLETE Column stats: NONE
                         BucketMapJoin: true
@@ -427,13 +339,6 @@ STAGE PLANS:
                             tag: -1
                             value expressions: _col0 (type: bigint)
                             auto parallelism: false
-            Local Work:
-              Map Reduce Local Work
-                Bucket Mapjoin Context:
-                    Alias Bucket File Name Mapping:
-#### A masked pattern was here ####
-                    Alias Bucket Output File Name Mapping:
-#### A masked pattern was here ####
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:

http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out
index 3ad950a..624a730 100644
--- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out
@@ -402,146 +402,10 @@ PREHOOK: type: QUERY
 POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
 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
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                  GatherStats: false
-                  Filter Operator
-                    isSamplingPred: false
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: key (type: string)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                      Spark HashTable Sink Operator
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                        Position of Big Table: 0
-            Local Work:
-              Map Reduce Local Work
-                Bucket Mapjoin Context:
-                    Alias Bucket File Name Mapping:
-#### A masked pattern was here ####
-                    Alias Bucket Output File Name Mapping:
-#### A masked pattern was here ####
-            Path -> Alias:
-#### A masked pattern was here ####
-            Path -> Partition:
-#### A masked pattern was here ####
-                Partition
-                  base file name: ds=2008-04-08
-                  input format: org.apache.hadoop.mapred.TextInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                  partition values:
-                    ds 2008-04-08
-                  properties:
-                    bucket_count 2
-                    bucket_field_name key
-                    column.name.delimiter ,
-                    columns key,value
-                    columns.comments 
-                    columns.types string:string
-#### A masked pattern was here ####
-                    name default.bucket_small
-                    numFiles 2
-                    numRows 0
-                    partition_columns ds
-                    partition_columns.types string
-                    rawDataSize 0
-                    serialization.ddl struct bucket_small { string key, string value}
-                    serialization.format 1
-                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 114
-#### A masked pattern was here ####
-                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                
-                    input format: org.apache.hadoop.mapred.TextInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                    properties:
-                      SORTBUCKETCOLSPREFIX TRUE
-                      bucket_count 2
-                      bucket_field_name key
-                      column.name.delimiter ,
-                      columns key,value
-                      columns.comments 
-                      columns.types string:string
-#### A masked pattern was here ####
-                      name default.bucket_small
-                      partition_columns ds
-                      partition_columns.types string
-                      serialization.ddl struct bucket_small { string key, string value}
-                      serialization.format 1
-                      serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
-                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.bucket_small
-                  name: default.bucket_small
-#### A masked pattern was here ####
-                Partition
-                  base file name: ds=2008-04-09
-                  input format: org.apache.hadoop.mapred.TextInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                  partition values:
-                    ds 2008-04-09
-                  properties:
-                    bucket_count 2
-                    bucket_field_name key
-                    column.name.delimiter ,
-                    columns key,value
-                    columns.comments 
-                    columns.types string:string
-#### A masked pattern was here ####
-                    name default.bucket_small
-                    numFiles 2
-                    numRows 0
-                    partition_columns ds
-                    partition_columns.types string
-                    rawDataSize 0
-                    serialization.ddl struct bucket_small { string key, string value}
-                    serialization.format 1
-                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 114
-#### A masked pattern was here ####
-                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                
-                    input format: org.apache.hadoop.mapred.TextInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                    properties:
-                      SORTBUCKETCOLSPREFIX TRUE
-                      bucket_count 2
-                      bucket_field_name key
-                      column.name.delimiter ,
-                      columns key,value
-                      columns.comments 
-                      columns.types string:string
-#### A masked pattern was here ####
-                      name default.bucket_small
-                      partition_columns ds
-                      partition_columns.types string
-                      serialization.ddl struct bucket_small { string key, string value}
-                      serialization.format 1
-                      serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
-                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.bucket_small
-                  name: default.bucket_small
-            Truncated Path -> Alias:
-              /bucket_small/ds=2008-04-08 [$hdt$_1:b]
-              /bucket_small/ds=2008-04-09 [$hdt$_1:b]
-
   Stage: Stage-1
     Spark
       Edges:
@@ -562,14 +426,12 @@ STAGE PLANS:
                       expressions: key (type: string)
                       outputColumnNames: _col0
                       Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
+                      Sorted Merge Bucket Map Join Operator
                         condition map:
                              Inner Join 0 to 1
                         keys:
                           0 _col0 (type: string)
                           1 _col0 (type: string)
-                        input vertices:
-                          1 Map 3
                         Position of Big Table: 0
                         Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                         BucketMapJoin: true
@@ -585,13 +447,6 @@ STAGE PLANS:
                             tag: -1
                             value expressions: _col0 (type: bigint)
                             auto parallelism: false
-            Local Work:
-              Map Reduce Local Work
-                Bucket Mapjoin Context:
-                    Alias Bucket File Name Mapping:
-#### A masked pattern was here ####
-                    Alias Bucket Output File Name Mapping:
-#### A masked pattern was here ####
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:


Mime
View raw message