You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2013/09/03 23:45:12 UTC
svn commit: r1519862 - in /hive/trunk/ql/src/test:
queries/clientpositive/list_bucket_query_multiskew_2.q
results/clientpositive/list_bucket_query_multiskew_2.q.out
Author: hashutosh
Date: Tue Sep 3 21:45:11 2013
New Revision: 1519862
URL: http://svn.apache.org/r1519862
Log:
HIVE-5145 : Fix TestCliDriver.list_bucket_query_multiskew_2.q on hadoop 0.23 (Prasanth J via Ashutosh Chauhan)
Modified:
hive/trunk/ql/src/test/queries/clientpositive/list_bucket_query_multiskew_2.q
hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out
Modified: hive/trunk/ql/src/test/queries/clientpositive/list_bucket_query_multiskew_2.q
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/queries/clientpositive/list_bucket_query_multiskew_2.q?rev=1519862&r1=1519861&r2=1519862&view=diff
==============================================================================
--- hive/trunk/ql/src/test/queries/clientpositive/list_bucket_query_multiskew_2.q (original)
+++ hive/trunk/ql/src/test/queries/clientpositive/list_bucket_query_multiskew_2.q Tue Sep 3 21:45:11 2013
@@ -30,21 +30,21 @@ SELECT count(1) FROM fact_daily WHERE ds
-- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484';
+explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484' ORDER BY key, value;
-- List Bucketing Query
-SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484';
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484' ORDER BY key, value;
-- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT key FROM fact_daily WHERE ds='1' and hr='4' and key= '406';
+explain extended SELECT key FROM fact_daily WHERE ds='1' and hr='4' and key= '406' ORDER BY key;
-- List Bucketing Query
-SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and key= '406';
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and key= '406' ORDER BY key;
-- pruner only pick up skewed-value directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238')) ;
+explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238')) ORDER BY key, value;
-- List Bucketing Query
-SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238')) ;
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238')) ORDER BY key, value;
-- clean up
-drop table fact_daily;
\ No newline at end of file
+drop table fact_daily;
Modified: hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out?rev=1519862&r1=1519861&r2=1519862&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/list_bucket_query_multiskew_2.q.out Tue Sep 3 21:45:11 2013
@@ -108,16 +108,16 @@ POSTHOOK: Lineage: fact_daily PARTITION(
500
PREHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484'
+explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484' ORDER BY key, value
PREHOOK: type: QUERY
POSTHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484'
+explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484' ORDER BY key, value
POSTHOOK: type: QUERY
POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL value) 'val_484')))))
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL value) 'val_484'))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value)))))
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -143,24 +143,19 @@ STAGE PLANS:
expr: value
type: string
outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1
- columns.types string:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ sort order: ++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -259,6 +254,27 @@ STAGE PLANS:
Truncated Path -> Alias:
/fact_daily/ds=1/hr=4/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [fact_daily]
/fact_daily/ds=1/hr=4/key=484/value=val_484 [fact_daily]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string:string
+ escape.delim \
+ hive.serialization.extend.nesting.levels true
+ serialization.format 1
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
@@ -266,13 +282,13 @@ STAGE PLANS:
PREHOOK: query: -- List Bucketing Query
-SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484'
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484' ORDER BY key, value
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
POSTHOOK: query: -- List Bucketing Query
-SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484'
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and value= 'val_484' ORDER BY key, value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
@@ -282,16 +298,16 @@ POSTHOOK: Lineage: fact_daily PARTITION(
484 val_484
PREHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT key FROM fact_daily WHERE ds='1' and hr='4' and key= '406'
+explain extended SELECT key FROM fact_daily WHERE ds='1' and hr='4' and key= '406' ORDER BY key
PREHOOK: type: QUERY
POSTHOOK: query: -- pruner only pick up default directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT key FROM fact_daily WHERE ds='1' and hr='4' and key= '406'
+explain extended SELECT key FROM fact_daily WHERE ds='1' and hr='4' and key= '406' ORDER BY key
POSTHOOK: type: QUERY
POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL key) '406')))))
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (= (TOK_TABLE_OR_COL key) '406'))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key)))))
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -315,24 +331,15 @@ STAGE PLANS:
expr: key
type: string
outputColumnNames: _col0
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0
- columns.types string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -384,6 +391,27 @@ STAGE PLANS:
name: default.fact_daily
Truncated Path -> Alias:
/fact_daily/ds=1/hr=4/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [fact_daily]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0
+ columns.types string
+ escape.delim \
+ hive.serialization.extend.nesting.levels true
+ serialization.format 1
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
@@ -391,13 +419,13 @@ STAGE PLANS:
PREHOOK: query: -- List Bucketing Query
-SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and key= '406'
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and key= '406' ORDER BY key
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
POSTHOOK: query: -- List Bucketing Query
-SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and key= '406'
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and key= '406' ORDER BY key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily
POSTHOOK: Input: default@fact_daily@ds=1/hr=4
@@ -410,16 +438,16 @@ POSTHOOK: Lineage: fact_daily PARTITION(
406 val_406
PREHOOK: query: -- pruner only pick up skewed-value directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238'))
+explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238')) ORDER BY key, value
PREHOOK: type: QUERY
POSTHOOK: query: -- pruner only pick up skewed-value directory
-- explain plan shows which directory selected: Truncated Path -> Alias
-explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238'))
+explain extended SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238')) ORDER BY key, value
POSTHOOK: type: QUERY
POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: fact_daily PARTITION(ds=1,hr=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (or (and (= (TOK_TABLE_OR_COL key) '484') (= (TOK_TABLE_OR_COL value) 'val_484')) (and (= (TOK_TABLE_OR_COL key) '238') (= (TOK_TABLE_OR_COL value) 'val_238')))))))
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME fact_daily))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL ds) '1') (= (TOK_TABLE_OR_COL hr) '4')) (or (and (= (TOK_TABLE_OR_COL key) '484') (= (TOK_TABLE_OR_COL value) 'val_484')) (and (= (TOK_TABLE_OR_COL key) '238') (= (TOK_TABLE_OR_COL value) 'val_238'))))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value)))))
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -445,24 +473,19 @@ STAGE PLANS:
expr: value
type: string
outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1
- columns.types string:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ sort order: ++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -561,6 +584,27 @@ STAGE PLANS:
Truncated Path -> Alias:
/fact_daily/ds=1/hr=4/key=238/value=val_238 [fact_daily]
/fact_daily/ds=1/hr=4/key=484/value=val_484 [fact_daily]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types string:string
+ escape.delim \
+ hive.serialization.extend.nesting.levels true
+ serialization.format 1
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
@@ -568,13 +612,13 @@ STAGE PLANS:
PREHOOK: query: -- List Bucketing Query
-SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238'))
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238')) ORDER BY key, value
PREHOOK: type: QUERY
PREHOOK: Input: default@fact_daily
PREHOOK: Input: default@fact_daily@ds=1/hr=4
#### A masked pattern was here ####
POSTHOOK: query: -- List Bucketing Query
-SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238'))
+SELECT key, value FROM fact_daily WHERE ds='1' and hr='4' and ( (key='484' and value ='val_484') or (key='238' and value= 'val_238')) ORDER BY key, value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@fact_daily
POSTHOOK: Input: default@fact_daily@ds=1/hr=4