You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2014/10/27 20:57:03 UTC
svn commit: r1634671 [37/46] - in /hive/branches/spark:
itests/src/test/resources/ ql/src/test/results/clientpositive/spark/
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_17.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_17.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_17.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_17.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,1118 @@
+PREHOOK: query: -- Create bucketed and sorted tables
+CREATE TABLE test_table1 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table1
+POSTHOOK: query: -- Create bucketed and sorted tables
+CREATE TABLE test_table1 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table1
+PREHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table2
+POSTHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table2
+PREHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table3
+POSTHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table3
+PREHOOK: query: CREATE TABLE test_table4 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table4
+POSTHOOK: query: CREATE TABLE test_table4 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table4
+PREHOOK: query: CREATE TABLE test_table5 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table5
+POSTHOOK: query: CREATE TABLE test_table5 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table5
+PREHOOK: query: CREATE TABLE test_table6 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table6
+POSTHOOK: query: CREATE TABLE test_table6 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table6
+PREHOOK: query: CREATE TABLE test_table7 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table7
+POSTHOOK: query: CREATE TABLE test_table7 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table7
+PREHOOK: query: CREATE TABLE test_table8 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table8
+POSTHOOK: query: CREATE TABLE test_table8 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table8
+PREHOOK: query: INSERT OVERWRITE TABLE test_table1
+SELECT * FROM src WHERE key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table1
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table1
+SELECT * FROM src WHERE key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table1
+POSTHOOK: Lineage: test_table1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: INSERT OVERWRITE TABLE test_table2
+SELECT * FROM src WHERE key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table2
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table2
+SELECT * FROM src WHERE key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table2
+POSTHOOK: Lineage: test_table2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: INSERT OVERWRITE TABLE test_table3
+SELECT * FROM src WHERE key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table3
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table3
+SELECT * FROM src WHERE key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table3
+POSTHOOK: Lineage: test_table3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: INSERT OVERWRITE TABLE test_table4
+SELECT * FROM src WHERE key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table4
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table4
+SELECT * FROM src WHERE key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table4
+POSTHOOK: Lineage: test_table4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: INSERT OVERWRITE TABLE test_table5
+SELECT * FROM src WHERE key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table5
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table5
+SELECT * FROM src WHERE key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table5
+POSTHOOK: Lineage: test_table5.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table5.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: INSERT OVERWRITE TABLE test_table6
+SELECT * FROM src WHERE key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table6
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table6
+SELECT * FROM src WHERE key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table6
+POSTHOOK: Lineage: test_table6.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table6.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: INSERT OVERWRITE TABLE test_table7
+SELECT * FROM src WHERE key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table7
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table7
+SELECT * FROM src WHERE key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table7
+POSTHOOK: Lineage: test_table7.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table7.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: INSERT OVERWRITE TABLE test_table8
+SELECT * FROM src WHERE key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table8
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table8
+SELECT * FROM src WHERE key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table8
+POSTHOOK: Lineage: test_table8.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table8.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- Mapjoin followed by a aggregation should be performed in a single MR job upto 7 tables
+EXPLAIN
+SELECT /*+ mapjoin(b, c, d, e, f, g) */ count(*)
+FROM test_table1 a JOIN test_table2 b ON a.key = b.key
+JOIN test_table3 c ON a.key = c.key
+JOIN test_table4 d ON a.key = d.key
+JOIN test_table5 e ON a.key = e.key
+JOIN test_table6 f ON a.key = f.key
+JOIN test_table7 g ON a.key = g.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Mapjoin followed by a aggregation should be performed in a single MR job upto 7 tables
+EXPLAIN
+SELECT /*+ mapjoin(b, c, d, e, f, g) */ count(*)
+FROM test_table1 a JOIN test_table2 b ON a.key = b.key
+JOIN test_table3 c ON a.key = c.key
+JOIN test_table4 d ON a.key = d.key
+JOIN test_table5 e ON a.key = e.key
+JOIN test_table6 f ON a.key = f.key
+JOIN test_table7 g ON a.key = g.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1), Map 8 (GROUP PARTITION-LEVEL SORT, 1), Map 9 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: f
+ Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 40 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: 10 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: g
+ Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 40 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: 10 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 40 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: 10 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: e
+ Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 40 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: 10 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 40 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: 10 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 40 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: 10 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 40 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: 10 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ Inner Join 0 to 3
+ Inner Join 0 to 4
+ Inner Join 0 to 5
+ Inner Join 0 to 6
+ condition expressions:
+ 0
+ 1
+ 2
+ 3
+ 4
+ 5
+ 6
+ Statistics: Num rows: 66 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 66 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ 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 /*+ mapjoin(b, c, d, e, f, g) */ count(*)
+FROM test_table1 a JOIN test_table2 b ON a.key = b.key
+JOIN test_table3 c ON a.key = c.key
+JOIN test_table4 d ON a.key = d.key
+JOIN test_table5 e ON a.key = e.key
+JOIN test_table6 f ON a.key = f.key
+JOIN test_table7 g ON a.key = g.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table4
+PREHOOK: Input: default@test_table5
+PREHOOK: Input: default@test_table6
+PREHOOK: Input: default@test_table7
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT /*+ mapjoin(b, c, d, e, f, g) */ count(*)
+FROM test_table1 a JOIN test_table2 b ON a.key = b.key
+JOIN test_table3 c ON a.key = c.key
+JOIN test_table4 d ON a.key = d.key
+JOIN test_table5 e ON a.key = e.key
+JOIN test_table6 f ON a.key = f.key
+JOIN test_table7 g ON a.key = g.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table4
+POSTHOOK: Input: default@test_table5
+POSTHOOK: Input: default@test_table6
+POSTHOOK: Input: default@test_table7
+#### A masked pattern was here ####
+4378
+PREHOOK: query: -- It should be automatically converted to a sort-merge join followed by a groupby in
+-- a single MR job
+EXPLAIN
+SELECT count(*)
+FROM test_table1 a LEFT OUTER JOIN test_table2 b ON a.key = b.key
+LEFT OUTER JOIN test_table3 c ON a.key = c.key
+LEFT OUTER JOIN test_table4 d ON a.key = d.key
+LEFT OUTER JOIN test_table5 e ON a.key = e.key
+LEFT OUTER JOIN test_table6 f ON a.key = f.key
+LEFT OUTER JOIN test_table7 g ON a.key = g.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- It should be automatically converted to a sort-merge join followed by a groupby in
+-- a single MR job
+EXPLAIN
+SELECT count(*)
+FROM test_table1 a LEFT OUTER JOIN test_table2 b ON a.key = b.key
+LEFT OUTER JOIN test_table3 c ON a.key = c.key
+LEFT OUTER JOIN test_table4 d ON a.key = d.key
+LEFT OUTER JOIN test_table5 e ON a.key = e.key
+LEFT OUTER JOIN test_table6 f ON a.key = f.key
+LEFT OUTER JOIN test_table7 g ON a.key = g.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1), Map 8 (GROUP PARTITION-LEVEL SORT, 1), Map 9 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: f
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: g
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: e
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Left Outer Join0 to 2
+ Left Outer Join0 to 3
+ Left Outer Join0 to 4
+ Left Outer Join0 to 5
+ Left Outer Join0 to 6
+ condition expressions:
+ 0
+ 1
+ 2
+ 3
+ 4
+ 5
+ 6
+ Statistics: Num rows: 132 Data size: 528 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 132 Data size: 528 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ 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 test_table1 a LEFT OUTER JOIN test_table2 b ON a.key = b.key
+LEFT OUTER JOIN test_table3 c ON a.key = c.key
+LEFT OUTER JOIN test_table4 d ON a.key = d.key
+LEFT OUTER JOIN test_table5 e ON a.key = e.key
+LEFT OUTER JOIN test_table6 f ON a.key = f.key
+LEFT OUTER JOIN test_table7 g ON a.key = g.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table4
+PREHOOK: Input: default@test_table5
+PREHOOK: Input: default@test_table6
+PREHOOK: Input: default@test_table7
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT count(*)
+FROM test_table1 a LEFT OUTER JOIN test_table2 b ON a.key = b.key
+LEFT OUTER JOIN test_table3 c ON a.key = c.key
+LEFT OUTER JOIN test_table4 d ON a.key = d.key
+LEFT OUTER JOIN test_table5 e ON a.key = e.key
+LEFT OUTER JOIN test_table6 f ON a.key = f.key
+LEFT OUTER JOIN test_table7 g ON a.key = g.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table4
+POSTHOOK: Input: default@test_table5
+POSTHOOK: Input: default@test_table6
+POSTHOOK: Input: default@test_table7
+#### A masked pattern was here ####
+4378
+PREHOOK: query: EXPLAIN
+SELECT count(*)
+FROM test_table1 a LEFT OUTER JOIN test_table2 b ON a.key = b.key
+LEFT OUTER JOIN test_table3 c ON a.key = c.key
+LEFT OUTER JOIN test_table4 d ON a.key = d.key
+LEFT OUTER JOIN test_table5 e ON a.key = e.key
+LEFT OUTER JOIN test_table6 f ON a.key = f.key
+LEFT OUTER JOIN test_table7 g ON a.key = g.key
+LEFT OUTER JOIN test_table8 h ON a.key = h.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT count(*)
+FROM test_table1 a LEFT OUTER JOIN test_table2 b ON a.key = b.key
+LEFT OUTER JOIN test_table3 c ON a.key = c.key
+LEFT OUTER JOIN test_table4 d ON a.key = d.key
+LEFT OUTER JOIN test_table5 e ON a.key = e.key
+LEFT OUTER JOIN test_table6 f ON a.key = f.key
+LEFT OUTER JOIN test_table7 g ON a.key = g.key
+LEFT OUTER JOIN test_table8 h ON a.key = h.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 10 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1), Map 8 (GROUP PARTITION-LEVEL SORT, 1), Map 9 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: f
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: h
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: g
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: e
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Left Outer Join0 to 2
+ Left Outer Join0 to 3
+ Left Outer Join0 to 4
+ Left Outer Join0 to 5
+ Left Outer Join0 to 6
+ Left Outer Join0 to 7
+ condition expressions:
+ 0
+ 1
+ 2
+ 3
+ 4
+ 5
+ 6
+ 7
+ Statistics: Num rows: 154 Data size: 616 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 154 Data size: 616 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ 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 test_table1 a LEFT OUTER JOIN test_table2 b ON a.key = b.key
+LEFT OUTER JOIN test_table3 c ON a.key = c.key
+LEFT OUTER JOIN test_table4 d ON a.key = d.key
+LEFT OUTER JOIN test_table5 e ON a.key = e.key
+LEFT OUTER JOIN test_table6 f ON a.key = f.key
+LEFT OUTER JOIN test_table7 g ON a.key = g.key
+LEFT OUTER JOIN test_table8 h ON a.key = h.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table3
+PREHOOK: Input: default@test_table4
+PREHOOK: Input: default@test_table5
+PREHOOK: Input: default@test_table6
+PREHOOK: Input: default@test_table7
+PREHOOK: Input: default@test_table8
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT count(*)
+FROM test_table1 a LEFT OUTER JOIN test_table2 b ON a.key = b.key
+LEFT OUTER JOIN test_table3 c ON a.key = c.key
+LEFT OUTER JOIN test_table4 d ON a.key = d.key
+LEFT OUTER JOIN test_table5 e ON a.key = e.key
+LEFT OUTER JOIN test_table6 f ON a.key = f.key
+LEFT OUTER JOIN test_table7 g ON a.key = g.key
+LEFT OUTER JOIN test_table8 h ON a.key = h.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table3
+POSTHOOK: Input: default@test_table4
+POSTHOOK: Input: default@test_table5
+POSTHOOK: Input: default@test_table6
+POSTHOOK: Input: default@test_table7
+POSTHOOK: Input: default@test_table8
+#### A masked pattern was here ####
+13126
+PREHOOK: query: -- outer join with max 16 aliases
+EXPLAIN
+SELECT a.*
+FROM test_table1 a
+LEFT OUTER JOIN test_table2 b ON a.key = b.key
+LEFT OUTER JOIN test_table3 c ON a.key = c.key
+LEFT OUTER JOIN test_table4 d ON a.key = d.key
+LEFT OUTER JOIN test_table5 e ON a.key = e.key
+LEFT OUTER JOIN test_table6 f ON a.key = f.key
+LEFT OUTER JOIN test_table7 g ON a.key = g.key
+LEFT OUTER JOIN test_table8 h ON a.key = h.key
+LEFT OUTER JOIN test_table4 i ON a.key = i.key
+LEFT OUTER JOIN test_table5 j ON a.key = j.key
+LEFT OUTER JOIN test_table6 k ON a.key = k.key
+LEFT OUTER JOIN test_table7 l ON a.key = l.key
+LEFT OUTER JOIN test_table8 m ON a.key = m.key
+LEFT OUTER JOIN test_table7 n ON a.key = n.key
+LEFT OUTER JOIN test_table8 o ON a.key = o.key
+LEFT OUTER JOIN test_table4 p ON a.key = p.key
+LEFT OUTER JOIN test_table5 q ON a.key = q.key
+LEFT OUTER JOIN test_table6 r ON a.key = r.key
+LEFT OUTER JOIN test_table7 s ON a.key = s.key
+LEFT OUTER JOIN test_table8 t ON a.key = t.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- outer join with max 16 aliases
+EXPLAIN
+SELECT a.*
+FROM test_table1 a
+LEFT OUTER JOIN test_table2 b ON a.key = b.key
+LEFT OUTER JOIN test_table3 c ON a.key = c.key
+LEFT OUTER JOIN test_table4 d ON a.key = d.key
+LEFT OUTER JOIN test_table5 e ON a.key = e.key
+LEFT OUTER JOIN test_table6 f ON a.key = f.key
+LEFT OUTER JOIN test_table7 g ON a.key = g.key
+LEFT OUTER JOIN test_table8 h ON a.key = h.key
+LEFT OUTER JOIN test_table4 i ON a.key = i.key
+LEFT OUTER JOIN test_table5 j ON a.key = j.key
+LEFT OUTER JOIN test_table6 k ON a.key = k.key
+LEFT OUTER JOIN test_table7 l ON a.key = l.key
+LEFT OUTER JOIN test_table8 m ON a.key = m.key
+LEFT OUTER JOIN test_table7 n ON a.key = n.key
+LEFT OUTER JOIN test_table8 o ON a.key = o.key
+LEFT OUTER JOIN test_table4 p ON a.key = p.key
+LEFT OUTER JOIN test_table5 q ON a.key = q.key
+LEFT OUTER JOIN test_table6 r ON a.key = r.key
+LEFT OUTER JOIN test_table7 s ON a.key = s.key
+LEFT OUTER JOIN test_table8 t ON a.key = t.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 10 (GROUP PARTITION-LEVEL SORT, 1), Map 11 (GROUP PARTITION-LEVEL SORT, 1), Map 12 (GROUP PARTITION-LEVEL SORT, 1), Map 13 (GROUP PARTITION-LEVEL SORT, 1), Map 14 (GROUP PARTITION-LEVEL SORT, 1), Map 15 (GROUP PARTITION-LEVEL SORT, 1), Map 16 (GROUP PARTITION-LEVEL SORT, 1), Map 17 (GROUP PARTITION-LEVEL SORT, 1), Map 22 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1), Map 8 (GROUP PARTITION-LEVEL SORT, 1), Map 9 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Map 18 (GROUP PARTITION-LEVEL SORT, 1), Map 19 (GROUP PARTITION-LEVEL SORT, 1), Map 20 (GROUP PARTITION-LEVEL SORT, 1), Map 21 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: f
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: n
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 11
+ Map Operator Tree:
+ TableScan
+ alias: o
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 12
+ Map Operator Tree:
+ TableScan
+ alias: l
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 13
+ Map Operator Tree:
+ TableScan
+ alias: m
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 14
+ Map Operator Tree:
+ TableScan
+ alias: j
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 15
+ Map Operator Tree:
+ TableScan
+ alias: k
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 16
+ Map Operator Tree:
+ TableScan
+ alias: h
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 17
+ Map Operator Tree:
+ TableScan
+ alias: i
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 18
+ Map Operator Tree:
+ TableScan
+ alias: t
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 19
+ Map Operator Tree:
+ TableScan
+ alias: s
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 20
+ Map Operator Tree:
+ TableScan
+ alias: r
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 21
+ Map Operator Tree:
+ TableScan
+ alias: q
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 22
+ Map Operator Tree:
+ TableScan
+ alias: p
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: g
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: e
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 20 Data size: 80 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: 20 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 80 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 0 Data size: 80 Basic stats: PARTIAL Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Left Outer Join0 to 2
+ Left Outer Join0 to 3
+ Left Outer Join0 to 4
+ Left Outer Join0 to 5
+ Left Outer Join0 to 6
+ Left Outer Join0 to 7
+ Left Outer Join0 to 8
+ Left Outer Join0 to 9
+ Left Outer Join0 to 10
+ Left Outer Join0 to 11
+ Left Outer Join0 to 12
+ Left Outer Join0 to 13
+ Left Outer Join0 to 14
+ Left Outer Join0 to 15
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1
+ 2
+ 3
+ 4
+ 5
+ 6
+ 7
+ 8
+ 9
+ 10
+ 11
+ 12
+ 13
+ 14
+ 15
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 330 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 330 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Left Outer Join0 to 2
+ Left Outer Join0 to 3
+ Left Outer Join0 to 4
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1
+ 2
+ 3
+ 4
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1452 Data size: 5808 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1452 Data size: 5808 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1452 Data size: 5808 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
+
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_18.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_18.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_18.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_18.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,468 @@
+PREHOOK: query: -- Create two bucketed and sorted tables
+CREATE TABLE test_table1 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table1
+POSTHOOK: query: -- Create two bucketed and sorted tables
+CREATE TABLE test_table1 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table1
+PREHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table2
+POSTHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table2
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT *
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table1@ds=1
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT *
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table1@ds=1
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
+-- This should be a map-only operation
+EXPLAIN
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
+-- This should be a map-only operation
+EXPLAIN
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 55 Data size: 5812 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
+ name: default.test_table2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: true
+ 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
+ name: default.test_table2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+PREHOOK: Output: default@test_table2@ds=1
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+POSTHOOK: Output: default@test_table2@ds=1
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select count(*) from test_table1 where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+500
+PREHOOK: query: select count(*) from test_table1 where ds = '1' and hash(key) % 2 = 0
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 where ds = '1' and hash(key) % 2 = 0
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+247
+PREHOOK: query: select count(*) from test_table1 where ds = '1' and hash(key) % 2 = 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 where ds = '1' and hash(key) % 2 = 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+253
+PREHOOK: query: select count(*) from test_table1 tablesample (bucket 1 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 tablesample (bucket 1 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+247
+PREHOOK: query: select count(*) from test_table1 tablesample (bucket 2 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 tablesample (bucket 2 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+253
+PREHOOK: query: select count(*) from test_table2 where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+500
+PREHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 0
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 0
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+247
+PREHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+253
+PREHOOK: query: select count(*) from test_table2 tablesample (bucket 1 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 1 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+247
+PREHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+253
+PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
+-- This should be a map-only operation, one of the buckets should be empty
+
+EXPLAIN
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1' and a.key = 238
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
+-- This should be a map-only operation, one of the buckets should be empty
+
+EXPLAIN
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1' and a.key = 238
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key = 238) (type: boolean)
+ Statistics: Num rows: 27 Data size: 2853 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 2853 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 27 Data size: 2853 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
+ name: default.test_table2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2
+ replace: true
+ 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
+ name: default.test_table2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1' and a.key = 238
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+PREHOOK: Output: default@test_table2@ds=2
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1' and a.key = 238
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+POSTHOOK: Output: default@test_table2@ds=2
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select count(*) from test_table2 where ds = '2'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '2'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=2
+#### A masked pattern was here ####
+2
+PREHOOK: query: select count(*) from test_table2 where ds = '2' and hash(key) % 2 = 0
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '2' and hash(key) % 2 = 0
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=2
+#### A masked pattern was here ####
+2
+PREHOOK: query: select count(*) from test_table2 where ds = '2' and hash(key) % 2 = 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '2' and hash(key) % 2 = 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=2
+#### A masked pattern was here ####
+0
+PREHOOK: query: select count(*) from test_table2 tablesample (bucket 1 out of 2) s where ds = '2'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 1 out of 2) s where ds = '2'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=2
+#### A masked pattern was here ####
+2
+PREHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s where ds = '2'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s where ds = '2'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=2
+#### A masked pattern was here ####
+0
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '3')
+SELECT a.key, a.value FROM test_table2 a WHERE a.ds = '2'
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '3')
+SELECT a.key, a.value FROM test_table2 a WHERE a.ds = '2'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 24 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 0 Data size: 24 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 24 Basic stats: PARTIAL 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
+ name: default.test_table2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 3
+ replace: true
+ 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
+ name: default.test_table2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2')
+SELECT a.key, a.value FROM test_table2 a WHERE a.ds = '2'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=2
+PREHOOK: Output: default@test_table2@ds=2
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2')
+SELECT a.key, a.value FROM test_table2 a WHERE a.ds = '2'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=2
+POSTHOOK: Output: default@test_table2@ds=2
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).key SIMPLE [(test_table2)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=2).value SIMPLE [(test_table2)a.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select count(*) from test_table2 where ds = '3'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '3'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+#### A masked pattern was here ####
+0
+PREHOOK: query: select count(*) from test_table2 where ds = '3' and hash(key) % 2 = 0
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '3' and hash(key) % 2 = 0
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+#### A masked pattern was here ####
+0
+PREHOOK: query: select count(*) from test_table2 where ds = '3' and hash(key) % 2 = 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '3' and hash(key) % 2 = 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+#### A masked pattern was here ####
+0
+PREHOOK: query: select count(*) from test_table2 tablesample (bucket 1 out of 2) s where ds = '3'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 1 out of 2) s where ds = '3'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+#### A masked pattern was here ####
+0
+PREHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s where ds = '3'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s where ds = '3'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+#### A masked pattern was here ####
+0
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_19.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_19.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_19.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_19.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,263 @@
+PREHOOK: query: -- Create two bucketed and sorted tables
+CREATE TABLE test_table1 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 16 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table1
+POSTHOOK: query: -- Create two bucketed and sorted tables
+CREATE TABLE test_table1 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 16 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table1
+PREHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 16 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_table2
+POSTHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 16 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_table2
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT *
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_table1@ds=1
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT *
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_table1@ds=1
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
+-- This should be a map-only operation
+EXPLAIN
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table
+-- This should be a map-only operation
+EXPLAIN
+INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 55 Data size: 5812 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
+ name: default.test_table2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ replace: true
+ 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
+ name: default.test_table2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+PREHOOK: Output: default@test_table2@ds=1
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1')
+SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+POSTHOOK: Output: default@test_table2@ds=1
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select count(*) from test_table1 where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+500
+PREHOOK: query: select count(*) from test_table1 where ds = '1' and hash(key) % 16 = 0
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 where ds = '1' and hash(key) % 16 = 0
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+36
+PREHOOK: query: select count(*) from test_table1 where ds = '1' and hash(key) % 16 = 5
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 where ds = '1' and hash(key) % 16 = 5
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+40
+PREHOOK: query: select count(*) from test_table1 where ds = '1' and hash(key) % 16 = 12
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 where ds = '1' and hash(key) % 16 = 12
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+29
+PREHOOK: query: select count(*) from test_table1 tablesample (bucket 1 out of 16) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 tablesample (bucket 1 out of 16) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+36
+PREHOOK: query: select count(*) from test_table1 tablesample (bucket 6 out of 16) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 tablesample (bucket 6 out of 16) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+40
+PREHOOK: query: select count(*) from test_table1 tablesample (bucket 13 out of 16) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table1
+PREHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table1 tablesample (bucket 13 out of 16) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table1
+POSTHOOK: Input: default@test_table1@ds=1
+#### A masked pattern was here ####
+29
+PREHOOK: query: select count(*) from test_table2 where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+500
+PREHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 16 = 0
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 16 = 0
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+36
+PREHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 16 = 5
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 16 = 5
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+40
+PREHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 16 = 12
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 16 = 12
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+29
+PREHOOK: query: select count(*) from test_table2 tablesample (bucket 1 out of 16) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 1 out of 16) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+36
+PREHOOK: query: select count(*) from test_table2 tablesample (bucket 6 out of 16) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 6 out of 16) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+40
+PREHOOK: query: select count(*) from test_table2 tablesample (bucket 13 out of 16) s where ds = '1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_table2
+PREHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 13 out of 16) s where ds = '1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_table2
+POSTHOOK: Input: default@test_table2@ds=1
+#### A masked pattern was here ####
+29