You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by pr...@apache.org on 2015/09/15 22:42:52 UTC
[46/51] [partial] hive git commit: HIVE-11776: LLAP: Generate golden
files for all MiniLlapCluster tests (Prasanth Jayachandran)
http://git-wip-us.apache.org/repos/asf/hive/blob/ace87818/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out
new file mode 100644
index 0000000..ae1a8d2
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_10.q.out
@@ -0,0 +1,369 @@
+PREHOOK: query: CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@tbl1
+POSTHOOK: query: CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tbl1
+PREHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@tbl2
+POSTHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tbl2
+PREHOOK: query: insert overwrite table tbl1
+select * from src where key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@tbl1
+POSTHOOK: query: insert overwrite table tbl1
+select * from src where key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@tbl1
+POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: insert overwrite table tbl2
+select * from src where key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@tbl2
+POSTHOOK: query: insert overwrite table tbl2
+select * from src where key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@tbl2
+POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- One of the subqueries contains a union, so it should not be converted to a sort-merge join.
+explain
+select count(*) from
+ (
+ select * from
+ (select a.key as key, a.value as value from tbl1 a where key < 6
+ union all
+ select a.key as key, a.value as value from tbl1 a where key < 6
+ ) usubq1 ) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- One of the subqueries contains a union, so it should not be converted to a sort-merge join.
+explain
+select count(*) from
+ (
+ select * from
+ (select a.key as key, a.value as value from tbl1 a where key < 6
+ union all
+ select a.key as key, a.value as value from tbl1 a where key < 6
+ ) usubq1 ) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 1 <- Map 5 (BROADCAST_EDGE), Union 2 (CONTAINS)
+ Map 4 <- Map 5 (BROADCAST_EDGE), Union 2 (CONTAINS)
+ Reducer 3 <- Union 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 6) (type: boolean)
+ Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ input vertices:
+ 1 Map 5
+ Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
+ 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)
+ Execution mode: llap
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 6) (type: boolean)
+ Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ input vertices:
+ 1 Map 5
+ Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
+ 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)
+ Execution mode: llap
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 6) (type: boolean)
+ Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ Reducer 3
+ Execution mode: uber
+ 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
+ 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
+ Union 2
+ Vertex: Union 2
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(*) from
+ (
+ select * from
+ (select a.key as key, a.value as value from tbl1 a where key < 6
+ union all
+ select a.key as key, a.value as value from tbl1 a where key < 6
+ ) usubq1 ) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from
+ (
+ select * from
+ (select a.key as key, a.value as value from tbl1 a where key < 6
+ union all
+ select a.key as key, a.value as value from tbl1 a where key < 6
+ ) usubq1 ) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+40
+PREHOOK: query: -- One of the subqueries contains a groupby, so it should not be converted to a sort-merge join.
+explain
+select count(*) from
+ (select a.key as key, count(*) as value from tbl1 a where key < 6 group by a.key) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- One of the subqueries contains a groupby, so it should not be converted to a sort-merge join.
+explain
+select count(*) from
+ (select a.key as key, count(*) as value from tbl1 a where key < 6 group by a.key) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 3 <- Reducer 2 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 6) (type: boolean)
+ Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ bucketGroup: true
+ keys: key (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Execution mode: llap
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 6) (type: boolean)
+ Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ input vertices:
+ 0 Reducer 2
+ Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
+ 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)
+ Execution mode: llap
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 7 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: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE
+ Reducer 4
+ Execution mode: uber
+ 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
+ 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
+ (select a.key as key, count(*) as value from tbl1 a where key < 6 group by a.key) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from
+ (select a.key as key, count(*) as value from tbl1 a where key < 6 group by a.key) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+8
http://git-wip-us.apache.org/repos/asf/hive/blob/ace87818/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_11.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_11.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_11.q.out
new file mode 100644
index 0000000..3c50dac
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_11.q.out
@@ -0,0 +1,1485 @@
+PREHOOK: query: -- small 1 part, 2 bucket & big 2 part, 4 bucket
+
+CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@bucket_small
+POSTHOOK: query: -- small 1 part, 2 bucket & big 2 part, 4 bucket
+
+CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@bucket_small
+PREHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_small
+POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_small
+POSTHOOK: Output: default@bucket_small@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_small@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_small@ds=2008-04-08
+PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@bucket_big
+POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@bucket_big
+PREHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_big
+POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_big
+POSTHOOK: Output: default@bucket_big@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_big@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_big@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_big@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_big@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_big@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_big@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_big
+POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_big
+POSTHOOK: Output: default@bucket_big@ds=2008-04-09
+PREHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_big@ds=2008-04-09
+POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_big@ds=2008-04-09
+PREHOOK: query: load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_big@ds=2008-04-09
+POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_big@ds=2008-04-09
+PREHOOK: query: load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_big@ds=2008-04-09
+POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_big@ds=2008-04-09
+PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+
+TOK_QUERY
+ TOK_FROM
+ TOK_JOIN
+ TOK_TABREF
+ TOK_TABNAME
+ bucket_small
+ a
+ TOK_TABREF
+ TOK_TABNAME
+ bucket_big
+ b
+ =
+ .
+ TOK_TABLE_OR_COL
+ a
+ key
+ .
+ TOK_TABLE_OR_COL
+ b
+ key
+ TOK_INSERT
+ TOK_DESTINATION
+ TOK_DIR
+ TOK_TMP_FILE
+ TOK_SELECT
+ TOK_SELEXPR
+ TOK_FUNCTIONSTAR
+ count
+
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 2 <- Map 1 (BROADCAST_EDGE)
+ Reducer 3 <- Map 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ auto parallelism: true
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 114
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_small/ds=2008-04-08 [a]
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Estimated key counts: Map 1 => 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ input vertices:
+ 0 Map 1
+ Position of Big Table: 1
+ Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
+ 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
+ tag: -1
+ value expressions: _col0 (type: bigint)
+ auto parallelism: false
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+ Truncated Path -> Alias:
+ /bucket_big/ds=2008-04-08 [b]
+ /bucket_big/ds=2008-04-09 [b]
+ Reducer 3
+ Execution mode: uber
+ Needs Tagging: false
+ 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
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+#### 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 bigint
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bucket_big
+PREHOOK: Input: default@bucket_big@ds=2008-04-08
+PREHOOK: Input: default@bucket_big@ds=2008-04-09
+PREHOOK: Input: default@bucket_small
+PREHOOK: Input: default@bucket_small@ds=2008-04-08
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bucket_big
+POSTHOOK: Input: default@bucket_big@ds=2008-04-08
+POSTHOOK: Input: default@bucket_big@ds=2008-04-09
+POSTHOOK: Input: default@bucket_small
+POSTHOOK: Input: default@bucket_small@ds=2008-04-08
+#### A masked pattern was here ####
+38
+PREHOOK: query: -- Since size is being used to find the big table, the order of the tables in the join does not matter
+-- The tables are only bucketed and not sorted, the join should not be converted
+-- Currenly, a join is only converted to a sort-merge join without a hint, automatic conversion to
+-- bucketized mapjoin is not done
+explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Since size is being used to find the big table, the order of the tables in the join does not matter
+-- The tables are only bucketed and not sorted, the join should not be converted
+-- Currenly, a join is only converted to a sort-merge join without a hint, automatic conversion to
+-- bucketized mapjoin is not done
+explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+
+TOK_QUERY
+ TOK_FROM
+ TOK_JOIN
+ TOK_TABREF
+ TOK_TABNAME
+ bucket_small
+ a
+ TOK_TABREF
+ TOK_TABNAME
+ bucket_big
+ b
+ =
+ .
+ TOK_TABLE_OR_COL
+ a
+ key
+ .
+ TOK_TABLE_OR_COL
+ b
+ key
+ TOK_INSERT
+ TOK_DESTINATION
+ TOK_DIR
+ TOK_TMP_FILE
+ TOK_SELECT
+ TOK_SELEXPR
+ TOK_FUNCTIONSTAR
+ count
+
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 2 <- Map 1 (BROADCAST_EDGE)
+ Reducer 3 <- Map 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ auto parallelism: true
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 114
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_small/ds=2008-04-08 [a]
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Estimated key counts: Map 1 => 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ input vertices:
+ 0 Map 1
+ Position of Big Table: 1
+ Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
+ 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
+ tag: -1
+ value expressions: _col0 (type: bigint)
+ auto parallelism: false
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+ Truncated Path -> Alias:
+ /bucket_big/ds=2008-04-08 [b]
+ /bucket_big/ds=2008-04-09 [b]
+ Reducer 3
+ Execution mode: uber
+ Needs Tagging: false
+ 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
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+#### 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 bigint
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bucket_big
+PREHOOK: Input: default@bucket_big@ds=2008-04-08
+PREHOOK: Input: default@bucket_big@ds=2008-04-09
+PREHOOK: Input: default@bucket_small
+PREHOOK: Input: default@bucket_small@ds=2008-04-08
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bucket_big
+POSTHOOK: Input: default@bucket_big@ds=2008-04-08
+POSTHOOK: Input: default@bucket_big@ds=2008-04-09
+POSTHOOK: Input: default@bucket_small
+POSTHOOK: Input: default@bucket_small@ds=2008-04-08
+#### A masked pattern was here ####
+38
+PREHOOK: query: -- The join is converted to a bucketed mapjoin with a mapjoin hint
+explain extended select /*+ mapjoin(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The join is converted to a bucketed mapjoin with a mapjoin hint
+explain extended select /*+ mapjoin(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+
+TOK_QUERY
+ TOK_FROM
+ TOK_JOIN
+ TOK_TABREF
+ TOK_TABNAME
+ bucket_small
+ a
+ TOK_TABREF
+ TOK_TABNAME
+ bucket_big
+ b
+ =
+ .
+ TOK_TABLE_OR_COL
+ a
+ key
+ .
+ TOK_TABLE_OR_COL
+ b
+ key
+ TOK_INSERT
+ TOK_DESTINATION
+ TOK_DIR
+ TOK_TMP_FILE
+ TOK_SELECT
+ TOK_HINTLIST
+ TOK_HINT
+ TOK_MAPJOIN
+ TOK_HINTARGLIST
+ a
+ TOK_SELEXPR
+ TOK_FUNCTIONSTAR
+ count
+
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 2 <- Map 1 (BROADCAST_EDGE)
+ Reducer 3 <- Map 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ auto parallelism: true
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 114
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_small/ds=2008-04-08 [a]
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Estimated key counts: Map 1 => 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ input vertices:
+ 0 Map 1
+ Position of Big Table: 1
+ Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
+ 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
+ tag: -1
+ value expressions: _col0 (type: bigint)
+ auto parallelism: false
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+ Truncated Path -> Alias:
+ /bucket_big/ds=2008-04-08 [b]
+ /bucket_big/ds=2008-04-09 [b]
+ Reducer 3
+ Execution mode: uber
+ Needs Tagging: false
+ 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
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+#### 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 bigint
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select /*+ mapjoin(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bucket_big
+PREHOOK: Input: default@bucket_big@ds=2008-04-08
+PREHOOK: Input: default@bucket_big@ds=2008-04-09
+PREHOOK: Input: default@bucket_small
+PREHOOK: Input: default@bucket_small@ds=2008-04-08
+#### A masked pattern was here ####
+POSTHOOK: query: select /*+ mapjoin(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bucket_big
+POSTHOOK: Input: default@bucket_big@ds=2008-04-08
+POSTHOOK: Input: default@bucket_big@ds=2008-04-09
+POSTHOOK: Input: default@bucket_small
+POSTHOOK: Input: default@bucket_small@ds=2008-04-08
+#### A masked pattern was here ####
+38
+PREHOOK: query: -- HIVE-7023
+explain extended select /* + MAPJOIN(a,b) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key JOIN bucket_big c ON a.key = c.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- HIVE-7023
+explain extended select /* + MAPJOIN(a,b) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key JOIN bucket_big c ON a.key = c.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+
+TOK_QUERY
+ TOK_FROM
+ TOK_JOIN
+ TOK_JOIN
+ TOK_TABREF
+ TOK_TABNAME
+ bucket_small
+ a
+ TOK_TABREF
+ TOK_TABNAME
+ bucket_big
+ b
+ =
+ .
+ TOK_TABLE_OR_COL
+ a
+ key
+ .
+ TOK_TABLE_OR_COL
+ b
+ key
+ TOK_TABREF
+ TOK_TABNAME
+ bucket_big
+ c
+ =
+ .
+ TOK_TABLE_OR_COL
+ a
+ key
+ .
+ TOK_TABLE_OR_COL
+ c
+ key
+ TOK_INSERT
+ TOK_DESTINATION
+ TOK_DIR
+ TOK_TMP_FILE
+ TOK_SELECT
+ TOK_HINTLIST
+ TOK_HINT
+ TOK_MAPJOIN
+ TOK_HINTARGLIST
+ a
+ b
+ TOK_SELEXPR
+ TOK_FUNCTIONSTAR
+ count
+
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 2 <- Map 1 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE)
+ Reducer 3 <- Map 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ auto parallelism: true
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 114
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_small/ds=2008-04-08 [a]
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ Estimated key counts: Map 1 => 1, Map 4 => 58
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ input vertices:
+ 0 Map 1
+ 2 Map 4
+ Position of Big Table: 1
+ Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
+ 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
+ tag: -1
+ value expressions: _col0 (type: bigint)
+ auto parallelism: false
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+ Truncated Path -> Alias:
+ /bucket_big/ds=2008-04-08 [b]
+ /bucket_big/ds=2008-04-09 [b]
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ tag: 2
+ auto parallelism: true
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+ Truncated Path -> Alias:
+ /bucket_big/ds=2008-04-08 [c]
+ /bucket_big/ds=2008-04-09 [c]
+ Reducer 3
+ Execution mode: uber
+ Needs Tagging: false
+ 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
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+#### 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 bigint
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select /* + MAPJOIN(a,b) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key JOIN bucket_big c ON a.key = c.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bucket_big
+PREHOOK: Input: default@bucket_big@ds=2008-04-08
+PREHOOK: Input: default@bucket_big@ds=2008-04-09
+PREHOOK: Input: default@bucket_small
+PREHOOK: Input: default@bucket_small@ds=2008-04-08
+#### A masked pattern was here ####
+POSTHOOK: query: select /* + MAPJOIN(a,b) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key JOIN bucket_big c ON a.key = c.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bucket_big
+POSTHOOK: Input: default@bucket_big@ds=2008-04-08
+POSTHOOK: Input: default@bucket_big@ds=2008-04-09
+POSTHOOK: Input: default@bucket_small
+POSTHOOK: Input: default@bucket_small@ds=2008-04-08
+#### A masked pattern was here ####
+180