http://git-wip-us.apache.org/repos/asf/hive/blob/f562dfb5/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out
b/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out
new file mode 100644
index 0000000..cafdf5d
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/smb_mapjoin_14.q.out
@@ -0,0 +1,1709 @@
+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: -- The mapjoin is being performed as part of sub-query. It
should be converted to a sort-merge join
+explain
+select count(*) from (
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+) subq1
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The mapjoin is being performed as part of sub-query. It
should be converted to a sort-merge join
+explain
+select count(*) from (
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+) subq1
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 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 is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE
Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ Statistics: Num rows: 11 Data size: 77 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
+ Execution mode: llap
+ 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.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(*) from (
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+) subq1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from (
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+) subq1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+22
+PREHOOK: query: -- The mapjoin is being performed as part of sub-query. It
should be converted to a sort-merge join
+-- Add a order by at the end to make the results deterministic.
+explain
+select key, count(*) from
+(
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+) subq1
+group by key
+order by key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The mapjoin is being performed as part of sub-query. It
should be converted to a sort-merge join
+-- Add a order by at the end to make the results deterministic.
+explain
+select key, count(*) from
+(
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+) subq1
+group by key
+order by 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
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 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 is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE
Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE
Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 11 Data size: 77 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: 11 Data size: 77 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reducer 3
+ 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: 5 Data size: 35 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int), VALUE._col0
(type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE
Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE
Column stats: NONE
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select key, count(*) from
+(
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+) subq1
+group by key
+order by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select key, count(*) from
+(
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+) subq1
+group by key
+order by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+0 9
+2 1
+4 1
+5 9
+8 1
+9 1
+PREHOOK: query: -- The mapjoin is being performed as part of more than one
sub-query. It should be converted to a sort-merge join
+explain
+select count(*) from
+(
+ select key, count(*) from
+ (
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+ ) subq1
+ group by key
+) subq2
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The mapjoin is being performed as part of more than one
sub-query. It should be converted to a sort-merge join
+explain
+select count(*) from
+(
+ select key, count(*) from
+ (
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+ ) subq1
+ group by key
+) subq2
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 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 is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE
Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE
Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 11 Data size: 77 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: 11 Data size: 77 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reducer 3
+ 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: 5 Data size: 35 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE
Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 16 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE
Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE
Column stats: NONE
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(*) from
+(
+ select key, count(*) from
+ (
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+ ) subq1
+ group by key
+) subq2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from
+(
+ select key, count(*) from
+ (
+ select /*+mapjoin(a)*/ a.key as key, a.value as val1, b.value as val2 from
tbl1 a join tbl2 b on a.key = b.key
+ ) subq1
+ group by key
+) subq2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+6
+PREHOOK: query: -- The subquery itself is being map-joined. Since the
sub-query only contains selects and filters, it should
+-- be converted to a sort-merge join.
+explain
+select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) 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: -- The subquery itself is being map-joined. Since the
sub-query only contains selects and filters, it should
+-- be converted to a sort-merge join.
+explain
+select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) 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
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 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
+ 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
+ LLAP IO: no inputs
+ 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
+ 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
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 23 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
+ Execution mode: llap
+ 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.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) 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 /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) 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 ####
+20
+PREHOOK: query: -- The subquery itself is being map-joined. Since the
sub-query only contains selects and filters, it should
+-- be converted to a sort-merge join, although there is more than one level of
sub-query
+explain
+select /*+mapjoin(subq2)*/ count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join tbl2 b
+ on subq2.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The subquery itself is being map-joined. Since the
sub-query only contains selects and filters, it should
+-- be converted to a sort-merge join, although there is more than one level of
sub-query
+explain
+select /*+mapjoin(subq2)*/ count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join tbl2 b
+ on subq2.key = b.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 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 < 8) and (key < 6)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (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
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE
Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ Statistics: Num rows: 11 Data size: 77 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
+ Execution mode: llap
+ 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.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select /*+mapjoin(subq2)*/ count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join tbl2 b
+ on subq2.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select /*+mapjoin(subq2)*/ count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join tbl2 b
+ on subq2.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+20
+PREHOOK: query: -- Both the big table and the small table are nested
sub-queries i.e more then 1 level of sub-query.
+-- The join should be converted to a sort-merge join
+explain
+select /*+mapjoin(subq2)*/ count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq3
+ where key < 6
+ ) subq4
+ on subq2.key = subq4.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Both the big table and the small table are nested
sub-queries i.e more then 1 level of sub-query.
+-- The join should be converted to a sort-merge join
+explain
+select /*+mapjoin(subq2)*/ count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq3
+ where key < 6
+ ) subq4
+ on subq2.key = subq4.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
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 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 < 8) and (key < 6)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (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
+ Execution mode: llap
+ LLAP IO: no inputs
+ 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 < 8) and (key < 6)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (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
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 7 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
+ Execution mode: llap
+ 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.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select /*+mapjoin(subq2)*/ count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq3
+ where key < 6
+ ) subq4
+ on subq2.key = subq4.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+#### A masked pattern was here ####
+POSTHOOK: query: select /*+mapjoin(subq2)*/ count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq3
+ where key < 6
+ ) subq4
+ on subq2.key = subq4.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+#### A masked pattern was here ####
+20
+PREHOOK: query: -- The subquery itself is being map-joined. Since the
sub-query only contains selects and filters and the join key
+-- is not getting modified, it should be converted to a sort-merge join. Note
that the sub-query modifies one
+-- item, but that is not part of the join key.
+explain
+select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, concat(a.value, a.value) as value from tbl1 a where
key < 8) subq1
+ join
+ (select a.key as key, concat(a.value, a.value) as value from tbl2 a where
key < 8) subq2
+ on subq1.key = subq2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The subquery itself is being map-joined. Since the
sub-query only contains selects and filters and the join key
+-- is not getting modified, it should be converted to a sort-merge join. Note
that the sub-query modifies one
+-- item, but that is not part of the join key.
+explain
+select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, concat(a.value, a.value) as value from tbl1 a where
key < 8) subq1
+ join
+ (select a.key as key, concat(a.value, a.value) as value from tbl2 a where
key < 8) 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
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 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 < 8) (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
+ Execution mode: llap
+ LLAP IO: no inputs
+ 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 < 8) (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
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 23 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
+ Execution mode: llap
+ 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.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, concat(a.value, a.value) as value from tbl1 a where
key < 8) subq1
+ join
+ (select a.key as key, concat(a.value, a.value) as value from tbl2 a where
key < 8) 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 /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, concat(a.value, a.value) as value from tbl1 a where
key < 8) subq1
+ join
+ (select a.key as key, concat(a.value, a.value) as value from tbl2 a where
key < 8) subq2
+ on subq1.key = subq2.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+20
+PREHOOK: query: -- Since the join key is modified by the sub-query, neither
sort-merge join not bucketized map-side
+-- join should be performed
+explain
+select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key +1 as key, concat(a.value, a.value) as value from tbl1 a)
subq1
+ join
+ (select a.key +1 as key, concat(a.value, a.value) as value from tbl2 a) subq2
+ on subq1.key = subq2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Since the join key is modified by the sub-query, neither
sort-merge join not bucketized map-side
+-- join should be performed
+explain
+select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key +1 as key, concat(a.value, a.value) as value from tbl1 a)
subq1
+ join
+ (select a.key +1 as key, concat(a.value, a.value) as value from tbl2 a) 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
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 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
+ Select Operator
+ expressions: (key + 1) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: (key + 1) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 11 Data size: 77 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
+ Execution mode: llap
+ 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.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key +1 as key, concat(a.value, a.value) as value from tbl1 a)
subq1
+ join
+ (select a.key +1 as key, concat(a.value, a.value) as value from tbl2 a) 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 /*+mapjoin(subq1)*/ count(*) from
+ (select a.key +1 as key, concat(a.value, a.value) as value from tbl1 a)
subq1
+ join
+ (select a.key +1 as key, concat(a.value, a.value) as value from tbl2 a) subq2
+ on subq1.key = subq2.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+22
+PREHOOK: query: -- The small table is a sub-query and the big table is not.
+-- It should be converted to a sort-merge join.
+explain
+select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join tbl2 a on subq1.key = a.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The small table is a sub-query and the big table is not.
+-- It should be converted to a sort-merge join.
+explain
+select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join tbl2 a on subq1.key = a.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
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 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
+ 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
+ LLAP IO: no inputs
+ 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 is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ Statistics: Num rows: 11 Data size: 77 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
+ Execution mode: llap
+ 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.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join tbl2 a on subq1.key = a.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select /*+mapjoin(subq1)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join tbl2 a on subq1.key = a.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+20
+PREHOOK: query: -- The big table is a sub-query and the small table is not.
+-- It should be converted to a sort-merge join.
+explain
+select /*+mapjoin(a)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join tbl2 a on subq1.key = a.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The big table is a sub-query and the small table is not.
+-- It should be converted to a sort-merge join.
+explain
+select /*+mapjoin(a)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join tbl2 a on subq1.key = a.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
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 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
+ 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
+ LLAP IO: no inputs
+ 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 is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ Statistics: Num rows: 11 Data size: 77 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
+ Execution mode: llap
+ 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.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select /*+mapjoin(a)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join tbl2 a on subq1.key = a.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select /*+mapjoin(a)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join tbl2 a on subq1.key = a.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+20
+PREHOOK: query: -- There are more than 2 inputs to the join, all of them being
sub-queries.
+-- It should be converted to to a sort-merge join
+explain
+select /*+mapjoin(subq1, subq2)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on (subq1.key = subq2.key)
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq3
+ on (subq1.key = subq3.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- There are more than 2 inputs to the join, all of them
being sub-queries.
+-- It should be converted to to a sort-merge join
+explain
+select /*+mapjoin(subq1, subq2)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on (subq1.key = subq2.key)
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq3
+ on (subq1.key = subq3.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
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5
(SIMPLE_EDGE)
+ Reducer 3 <- Reducer 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
+ 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
+ LLAP IO: no inputs
+ 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
+ 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
+ LLAP IO: no inputs
+ 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
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ 2 _col0 (type: int)
+ Statistics: Num rows: 6 Data size: 46 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
+ Execution mode: llap
+ 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.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select /*+mapjoin(subq1, subq2)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq3
+ on (subq1.key = subq3.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select /*+mapjoin(subq1, subq2)*/ count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq3
+ on (subq1.key = subq3.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+56
+PREHOOK: query: -- The mapjoin is being performed on a nested sub-query, and
an aggregation is performed after that.
+-- The join should be converted to a sort-merge join
+explain
+select count(*) from (
+ select /*+mapjoin(subq2)*/ subq2.key as key, subq2.value as value1, b.value
as value2 from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+join tbl2 b
+on subq2.key = b.key) a
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The mapjoin is being performed on a nested sub-query, and
an aggregation is performed after that.
+-- The join should be converted to a sort-merge join
+explain
+select count(*) from (
+ select /*+mapjoin(subq2)*/ subq2.key as key, subq2.value as value1, b.value
as value2 from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+join tbl2 b
+on subq2.key = b.key) a
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 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 < 8) and (key < 6)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (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
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE
Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 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: 70 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ Statistics: Num rows: 11 Data size: 77 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
+ Execution mode: llap
+ 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.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(*) from (
+ select /*+mapjoin(subq2)*/ subq2.key as key, subq2.value as value1, b.value
as value2 from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+join tbl2 b
+on subq2.key = b.key) a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from (
+ select /*+mapjoin(subq2)*/ subq2.key as key, subq2.value as value1, b.value
as value2 from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+join tbl2 b
+on subq2.key = b.key) a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+20
