hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From vg...@apache.org
Subject [1/7] hive git commit: HIVE-17308: Improvement in join cardinality estimation (Vineet Garg, reviewed by Ashutosh Chauhan)
Date Tue, 22 Aug 2017 18:25:52 GMT
Repository: hive
Updated Branches:
  refs/heads/master 2dd984444 -> ff30a1ebf


http://git-wip-us.apache.org/repos/asf/hive/blob/ff30a1eb/ql/src/test/results/clientpositive/spark/join_cond_pushdown_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_4.q.out b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_4.q.out
index 9c3aed8..d1bcf20 100644
--- a/ql/src/test/results/clientpositive/spark/join_cond_pushdown_4.q.out
+++ b/ql/src/test/results/clientpositive/spark/join_cond_pushdown_4.q.out
@@ -154,30 +154,30 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
-        Reducer 3 <- Map 6 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT,
2)
-        Reducer 4 <- Map 7 (PARTITION-LEVEL SORT, 2), Reducer 3 (PARTITION-LEVEL SORT,
2)
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
+        Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT,
2)
+        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 2), Map 7 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: p1
+                  alias: p3
                   Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats:
NONE
                   Filter Operator
-                    predicate: (p_name is not null and p_partkey is not null) (type: boolean)
+                    predicate: p_name is not null (type: boolean)
                     Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
                       expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type:
string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type:
string), p_retailprice (type: double), p_comment (type: string)
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6,
_col7, _col8
                       Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column
stats: NONE
                       Reduce Output Operator
-                        key expressions: _col1 (type: string), _col0 (type: int)
-                        sort order: ++
-                        Map-reduce partition columns: _col1 (type: string), _col0 (type:
int)
+                        key expressions: _col1 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col1 (type: string)
                         Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column
stats: NONE
-                        value expressions: _col2 (type: string), _col3 (type: string), _col4
(type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type:
string)
-        Map 5 
+                        value expressions: _col0 (type: int), _col2 (type: string), _col3
(type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type:
double), _col8 (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: p2
@@ -190,29 +190,29 @@ STAGE PLANS:
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6,
_col7, _col8
                       Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column
stats: NONE
                       Reduce Output Operator
-                        key expressions: _col1 (type: string), _col0 (type: int)
-                        sort order: ++
-                        Map-reduce partition columns: _col1 (type: string), _col0 (type:
int)
+                        key expressions: _col1 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col1 (type: string)
                         Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column
stats: NONE
-                        value expressions: _col2 (type: string), _col3 (type: string), _col4
(type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type:
string)
-        Map 6 
+                        value expressions: _col0 (type: int), _col2 (type: string), _col3
(type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type:
double), _col8 (type: string)
+        Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: p3
+                  alias: p1
                   Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats:
NONE
                   Filter Operator
-                    predicate: p_name is not null (type: boolean)
+                    predicate: (p_name is not null and p_partkey is not null) (type: boolean)
                     Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
                       expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type:
string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type:
string), p_retailprice (type: double), p_comment (type: string)
                       outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6,
_col7, _col8
                       Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column
stats: NONE
                       Reduce Output Operator
-                        key expressions: _col1 (type: string)
+                        key expressions: _col0 (type: int)
                         sort order: +
-                        Map-reduce partition columns: _col1 (type: string)
+                        Map-reduce partition columns: _col0 (type: int)
                         Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column
stats: NONE
-                        value expressions: _col0 (type: int), _col2 (type: string), _col3
(type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type:
double), _col8 (type: string)
+                        value expressions: _col1 (type: string), _col2 (type: string), _col3
(type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type:
double), _col8 (type: string)
         Map 7 
             Map Operator Tree:
                 TableScan
@@ -237,33 +237,38 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 keys:
-                  0 _col1 (type: string), _col0 (type: int)
-                  1 _col1 (type: string), _col0 (type: int)
+                  0 _col1 (type: string)
+                  1 _col1 (type: string)
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7,
_col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
                 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats:
NONE
                 Reduce Output Operator
-                  key expressions: _col10 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col10 (type: string)
+                  key expressions: _col9 (type: int), _col10 (type: string)
+                  sort order: ++
+                  Map-reduce partition columns: _col9 (type: int), _col10 (type: string)
                   Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats:
NONE
-                  value expressions: _col0 (type: int), _col1 (type: string), _col2 (type:
string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string),
_col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12
(type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type:
double), _col17 (type: string)
+                  value expressions: _col0 (type: int), _col1 (type: string), _col2 (type:
string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string),
_col7 (type: double), _col8 (type: string), _col11 (type: string), _col12 (type: string),
_col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17
(type: string)
         Reducer 3 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Inner Join 0 to 1
                 keys:
-                  0 _col10 (type: string)
-                  1 _col1 (type: string)
-                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7,
_col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19,
_col20, _col21, _col22, _col23, _col24, _col25, _col26
+                  0 _col9 (type: int), _col10 (type: string)
+                  1 _col0 (type: int), _col1 (type: string)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7,
_col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19,
_col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31,
_col32, _col33, _col34, _col35
                 Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats:
NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: int)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: int)
+                Select Operator
+                  expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string),
_col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25
(type: double), _col26 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type:
string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string),
_col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2
(type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type:
string), _col7 (type: double), _col8 (type: string), _col27 (type: int), _col28 (type: string),
_col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33
(type: string), _col34 (type: double), _col35 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7,
_col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19,
_col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31,
_col32, _col33, _col34, _col35
                   Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats:
NONE
-                  value expressions: _col1 (type: string), _col2 (type: string), _col3 (type:
string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double),
_col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12
(type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type:
double), _col17 (type: string), _col18 (type: int), _col19 (type: string), _col20 (type: string),
_col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25
(type: double), _col26 (type: string)
-        Reducer 4 
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 30 Data size: 3807 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
+        Reducer 6 
             Reduce Operator Tree:
               Join Operator
                 condition map:
@@ -271,15 +276,14 @@ STAGE PLANS:
                 keys:
                   0 _col0 (type: int)
                   1 _col0 (type: int)
-                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7,
_col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19,
_col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31,
_col32, _col33, _col34, _col35
-                Statistics: Num rows: 33 Data size: 4187 Basic stats: COMPLETE Column stats:
NONE
-                File Output Operator
-                  compressed: false
-                  Statistics: Num rows: 33 Data size: 4187 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
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7,
_col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
+                Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats:
NONE
+                Reduce Output Operator
+                  key expressions: _col0 (type: int), _col1 (type: string)
+                  sort order: ++
+                  Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
+                  Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats:
NONE
+                  value expressions: _col2 (type: string), _col3 (type: string), _col4 (type:
string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string),
_col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13
(type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type:
string)
 
   Stage: Stage-0
     Fetch Operator

http://git-wip-us.apache.org/repos/asf/hive/blob/ff30a1eb/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out
index bf0708b..6b7fecf 100644
--- a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out
+++ b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out
@@ -1759,11 +1759,11 @@ Stage-0
     Stage-1
       Reducer 3
       File Output Operator [FS_18]
-        Select Operator [SEL_17] (rows=250 width=178)
+        Select Operator [SEL_17] (rows=183 width=178)
           Output:["_col0","_col1"]
-          Filter Operator [FIL_16] (rows=250 width=178)
+          Filter Operator [FIL_16] (rows=183 width=179)
             predicate:_col4 is null
-            Join Operator [JOIN_15] (rows=250 width=178)
+            Join Operator [JOIN_15] (rows=250 width=179)
               Output:["_col0","_col1","_col4"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0,
_col1","1":"_col0, _col1"}
             <-Reducer 2 [PARTITION-LEVEL SORT]
               PARTITION-LEVEL SORT [RS_13]
@@ -1835,7 +1835,7 @@ Stage-0
     Stage-1
       Reducer 2
       File Output Operator [FS_11]
-        Join Operator [JOIN_9] (rows=1 width=178)
+        Join Operator [JOIN_9] (rows=134 width=178)
           Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0,
_col1","1":"_col0, _col1"}
         <-Map 1 [PARTITION-LEVEL SORT]
           PARTITION-LEVEL SORT [RS_7]
@@ -1885,7 +1885,7 @@ Stage-0
     Stage-1
       Reducer 2
       File Output Operator [FS_11]
-        Join Operator [JOIN_9] (rows=1 width=178)
+        Join Operator [JOIN_9] (rows=134 width=178)
           Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0,
_col1","1":"_col0, _col1"}
         <-Map 1 [PARTITION-LEVEL SORT]
           PARTITION-LEVEL SORT [RS_7]


Mime
View raw message