hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject [10/50] [abbrv] hive git commit: HIVE-11606: Bucket map joins fail at hash table construction time (Vikram Dixit K, reviewed by Sergey Shelukhin)
Date Wed, 16 Sep 2015 19:18:28 GMT
HIVE-11606: Bucket map joins fail at hash table construction time (Vikram Dixit K, reviewed
by Sergey Shelukhin)


Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/9fe8802c
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/9fe8802c
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/9fe8802c

Branch: refs/heads/spark
Commit: 9fe8802cb83e05c0392b11b8dcfe354fecfda786
Parents: 4ea8e29
Author: vikram <vikram@hortonworks.com>
Authored: Thu Sep 10 13:29:34 2015 -0700
Committer: vikram <vikram@hortonworks.com>
Committed: Thu Sep 10 13:30:24 2015 -0700

----------------------------------------------------------------------
 .../apache/hadoop/hive/ql/exec/Operator.java    |   3 +-
 .../ql/optimizer/ReduceSinkMapJoinProc.java     |  11 +-
 .../clientpositive/bucket_map_join_tez1.q       |  22 ++
 .../spark/bucket_map_join_tez1.q.out            | 226 +++++++++++++++++++
 .../tez/bucket_map_join_tez1.q.out              | 210 +++++++++++++++++
 5 files changed, 469 insertions(+), 3 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/hive/blob/9fe8802c/ql/src/java/org/apache/hadoop/hive/ql/exec/Operator.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/Operator.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/Operator.java
index acbe504..92e5446 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/exec/Operator.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/Operator.java
@@ -319,6 +319,7 @@ public abstract class Operator<T extends OperatorDesc> implements
Serializable,C
   @SuppressWarnings("unchecked")
   public final void initialize(Configuration hconf, ObjectInspector[] inputOIs)
       throws HiveException {
+    this.done = false;
     if (state == State.INIT) {
       return;
     }
@@ -369,7 +370,7 @@ public abstract class Operator<T extends OperatorDesc> implements
Serializable,C
     }
 
     if (isLogInfoEnabled) {
-      LOG.info("Initialization Done " + id + " " + getName());
+      LOG.info("Initialization Done " + id + " " + getName() + " done is reset.");
     }
 
     initializeChildren(hconf);

http://git-wip-us.apache.org/repos/asf/hive/blob/9fe8802c/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ReduceSinkMapJoinProc.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ReduceSinkMapJoinProc.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ReduceSinkMapJoinProc.java
index 71c766f..757ff5e 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ReduceSinkMapJoinProc.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ReduceSinkMapJoinProc.java
@@ -215,8 +215,15 @@ public class ReduceSinkMapJoinProc implements NodeProcessor {
         tableSize /= bucketCount;
       }
     }
-    LOG.info("Mapjoin " + mapJoinOp + ", pos: " + pos + " --> " + parentWork.getName()
+ " ("
-      + keyCount + " keys estimated from " + rowCount + " rows, " + bucketCount + " buckets)");
+    if (keyCount == 0) {
+      keyCount = 1;
+    }
+    if (tableSize == 0) {
+      tableSize = 1;
+    }
+    LOG.info("Mapjoin " + mapJoinOp + "(bucket map join = )" + joinConf.isBucketMapJoin()
+        + ", pos: " + pos + " --> " + parentWork.getName() + " (" + keyCount
+        + " keys estimated from " + rowCount + " rows, " + bucketCount + " buckets)");
     joinConf.getParentToInput().put(pos, parentWork.getName());
     if (keyCount != Long.MAX_VALUE) {
       joinConf.getParentKeyCounts().put(pos, keyCount);

http://git-wip-us.apache.org/repos/asf/hive/blob/9fe8802c/ql/src/test/queries/clientpositive/bucket_map_join_tez1.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/bucket_map_join_tez1.q b/ql/src/test/queries/clientpositive/bucket_map_join_tez1.q
index 0f9dd6d..8546e78 100644
--- a/ql/src/test/queries/clientpositive/bucket_map_join_tez1.q
+++ b/ql/src/test/queries/clientpositive/bucket_map_join_tez1.q
@@ -95,3 +95,25 @@ explain select a.key, b.key from tab_part a join tab_part c on a.key =
c.key joi
 explain
 select a.key, a.value, b.value
 from tab a join tab_part b on a.key = b.key and a.ds = b.ds;
+
+set hive.mapjoin.hybridgrace.hashtable = false;
+insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin where key = 411;
+
+explain
+select count(*)
+from tab_part a join tab b on a.key = b.key;
+
+select count(*)
+from tab_part a join tab b on a.key = b.key;
+
+set hive.mapjoin.hybridgrace.hashtable = false;
+insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin where key = 411;
+
+explain
+select count(*)
+from tab_part a join tab b on a.key = b.key;
+
+select count(*)
+from tab_part a join tab b on a.key = b.key;

http://git-wip-us.apache.org/repos/asf/hive/blob/9fe8802c/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
index 34ddc90..2c14065 100644
--- a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
@@ -1424,3 +1424,229 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
+PREHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin where key = 411
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcbucket_mapjoin
+PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin where key = 411
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcbucket_mapjoin
+POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+POSTHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key,
type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value,
type:string, comment:null), ]
+PREHOOK: query: explain
+select count(*)
+from tab_part a join tab b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select count(*)
+from tab_part a join tab 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-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: 11 Basic stats: COMPLETE Column stats:
NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats:
NONE
+                    Spark HashTable Sink Operator
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Reducer 2 <- Map 1 (GROUP, 1)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column
stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      input vertices:
+                        1 Map 3
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+                      Reduce Output Operator
+                        sort order: 
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+            Local Work:
+              Map Reduce Local Work
+        Reducer 2 
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count()
+                mode: complete
+                outputColumnNames: _col0
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: select count(*)
+from tab_part a join tab b on a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tab
+PREHOOK: Input: default@tab@ds=2008-04-08
+PREHOOK: Input: default@tab_part
+PREHOOK: Input: default@tab_part@ds=2008-04-08
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*)
+from tab_part a join tab b on a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tab
+POSTHOOK: Input: default@tab@ds=2008-04-08
+POSTHOOK: Input: default@tab_part
+POSTHOOK: Input: default@tab_part@ds=2008-04-08
+#### A masked pattern was here ####
+1
+PREHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin where key = 411
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcbucket_mapjoin
+PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin where key = 411
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcbucket_mapjoin
+POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+POSTHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key,
type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value,
type:string, comment:null), ]
+PREHOOK: query: explain
+select count(*)
+from tab_part a join tab b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select count(*)
+from tab_part a join tab 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-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: 11 Basic stats: COMPLETE Column stats:
NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats:
NONE
+                    Spark HashTable Sink Operator
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Reducer 2 <- Map 1 (GROUP, 1)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column
stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      input vertices:
+                        1 Map 3
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+                      Reduce Output Operator
+                        sort order: 
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+            Local Work:
+              Map Reduce Local Work
+        Reducer 2 
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count()
+                mode: complete
+                outputColumnNames: _col0
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: select count(*)
+from tab_part a join tab b on a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tab
+PREHOOK: Input: default@tab@ds=2008-04-08
+PREHOOK: Input: default@tab_part
+PREHOOK: Input: default@tab_part@ds=2008-04-08
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*)
+from tab_part a join tab b on a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tab
+POSTHOOK: Input: default@tab@ds=2008-04-08
+POSTHOOK: Input: default@tab_part
+POSTHOOK: Input: default@tab_part@ds=2008-04-08
+#### A masked pattern was here ####
+1

http://git-wip-us.apache.org/repos/asf/hive/blob/9fe8802c/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out
index 8338672..af5e6e6 100644
--- a/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out
+++ b/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out
@@ -1350,3 +1350,213 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
+PREHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin where key = 411
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcbucket_mapjoin
+PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin where key = 411
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcbucket_mapjoin
+POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+POSTHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key,
type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value,
type:string, comment:null), ]
+PREHOOK: query: explain
+select count(*)
+from tab_part a join tab b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select count(*)
+from tab_part a join tab b on a.key = b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Edges:
+        Map 1 <- Map 3 (CUSTOM_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column
stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      input vertices:
+                        1 Map 3
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+                      Reduce Output Operator
+                        sort order: 
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats:
NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats:
NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column
stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count()
+                mode: complete
+                outputColumnNames: _col0
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: select count(*)
+from tab_part a join tab b on a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tab
+PREHOOK: Input: default@tab@ds=2008-04-08
+PREHOOK: Input: default@tab_part
+PREHOOK: Input: default@tab_part@ds=2008-04-08
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*)
+from tab_part a join tab b on a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tab
+POSTHOOK: Input: default@tab@ds=2008-04-08
+POSTHOOK: Input: default@tab_part
+POSTHOOK: Input: default@tab_part@ds=2008-04-08
+#### A masked pattern was here ####
+1
+PREHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin where key = 411
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcbucket_mapjoin
+PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin where key = 411
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcbucket_mapjoin
+POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+POSTHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key,
type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value,
type:string, comment:null), ]
+PREHOOK: query: explain
+select count(*)
+from tab_part a join tab b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select count(*)
+from tab_part a join tab b on a.key = b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Edges:
+        Map 1 <- Map 3 (CUSTOM_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column
stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      input vertices:
+                        1 Map 3
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+                      Reduce Output Operator
+                        sort order: 
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats:
NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats:
NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column
stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count()
+                mode: complete
+                outputColumnNames: _col0
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats:
NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+
+PREHOOK: query: select count(*)
+from tab_part a join tab b on a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tab
+PREHOOK: Input: default@tab@ds=2008-04-08
+PREHOOK: Input: default@tab_part
+PREHOOK: Input: default@tab_part@ds=2008-04-08
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*)
+from tab_part a join tab b on a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tab
+POSTHOOK: Input: default@tab@ds=2008-04-08
+POSTHOOK: Input: default@tab_part
+POSTHOOK: Input: default@tab_part@ds=2008-04-08
+#### A masked pattern was here ####
+1


Mime
View raw message