You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by vg...@apache.org on 2017/11/07 06:27:33 UTC
[14/17] hive git commit: HIVE-17767 Rewrite correlated EXISTS/IN
subqueries into LEFT SEMI JOIN (Vineet Garg, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/aee0eaa0/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out b/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out
new file mode 100644
index 0000000..0ffbaae
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out
@@ -0,0 +1,2079 @@
+PREHOOK: query: DROP TABLE IF EXISTS part_subq
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE IF EXISTS part_subq
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE part_subq(
+ p_partkey INT,
+ p_name STRING,
+ p_mfgr STRING,
+ p_brand STRING,
+ p_type STRING,
+ p_size INT,
+ p_container STRING,
+ p_retailprice DOUBLE,
+ p_comment STRING
+)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@part_subq
+POSTHOOK: query: CREATE TABLE part_subq(
+ p_partkey INT,
+ p_name STRING,
+ p_mfgr STRING,
+ p_brand STRING,
+ p_type STRING,
+ p_size INT,
+ p_container STRING,
+ p_retailprice DOUBLE,
+ p_comment STRING
+)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@part_subq
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/part_tiny.txt' overwrite into table part_subq
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@part_subq
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/part_tiny.txt' overwrite into table part_subq
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@part_subq
+PREHOOK: query: explain
+ select key, count(*)
+from src
+group by key
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key )
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+ select key, count(*)
+from src
+group by key
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.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)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+ Reducer 4 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: key
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Filter Operator
+ predicate: (key > '9') (type: boolean)
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col1 is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: bigint)
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0 _col1 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 41 Data size: 3895 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 41 Data size: 3895 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col1
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col1 is not null (type: boolean)
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: bigint)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 41 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 41 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select s1.key, count(*) from src s1 where s1.key > '9' group by s1.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select s1.key, count(*) from src s1 where s1.key > '9' group by s1.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+90 3
+92 1
+95 2
+96 1
+97 2
+98 2
+PREHOOK: query: select key, count(*)
+from src
+group by key
+having count(*) in (select count(*) from src s1 where s1.key = '90' group by s1.key )
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key, count(*)
+from src
+group by key
+having count(*) in (select count(*) from src s1 where s1.key = '90' group by s1.key )
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0 3
+119 3
+128 3
+167 3
+187 3
+193 3
+199 3
+208 3
+273 3
+298 3
+311 3
+316 3
+318 3
+327 3
+35 3
+369 3
+384 3
+396 3
+403 3
+409 3
+417 3
+430 3
+431 3
+438 3
+454 3
+466 3
+480 3
+498 3
+5 3
+70 3
+90 3
+PREHOOK: query: explain
+select p_mfgr, avg(p_size)
+from part_subq b
+group by b.p_mfgr
+having b.p_mfgr in
+ (select p_mfgr
+ from part_subq
+ group by p_mfgr
+ having max(p_size) - min(p_size) < 20
+ )
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select p_mfgr, avg(p_size)
+from part_subq b
+group by b.p_mfgr
+having b.p_mfgr in
+ (select p_mfgr
+ from part_subq
+ group by p_mfgr
+ having max(p_size) - min(p_size) < 20
+ )
+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)
+ Reducer 3 <- Reducer 2 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE)
+ Reducer 4 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_mfgr is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(p_size)
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>)
+ Group By Operator
+ aggregations: max(p_size), min(p_size)
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col2 (type: int)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 206 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
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0), min(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col1 - _col2) < 20) (type: boolean)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select p_mfgr, avg(p_size)
+from part_subq b
+group by b.p_mfgr
+having b.p_mfgr in
+ (select p_mfgr
+ from part_subq
+ group by p_mfgr
+ having max(p_size) - min(p_size) < 20
+ )
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select p_mfgr, avg(p_size)
+from part_subq b
+group by b.p_mfgr
+having b.p_mfgr in
+ (select p_mfgr
+ from part_subq
+ group by p_mfgr
+ having max(p_size) - min(p_size) < 20
+ )
+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)
+ Reducer 3 <- Reducer 2 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE)
+ Reducer 4 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_mfgr is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(p_size)
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>)
+ Group By Operator
+ aggregations: max(p_size), min(p_size)
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col2 (type: int)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 206 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
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0), min(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col1 - _col2) < 20) (type: boolean)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select b.key, min(b.value)
+from src b
+group by b.key
+having b.key in ( select a.key
+ from src a
+ where a.value > 'val_9' and a.value = min(b.value)
+ )
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select b.key, min(b.value)
+from src b
+group by b.key
+having b.key in ( select a.key
+ from src a
+ where a.value > 'val_9' and a.value = min(b.value)
+ )
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+90 val_90
+92 val_92
+95 val_95
+96 val_96
+97 val_97
+98 val_98
+PREHOOK: query: explain
+select key, value, count(*)
+from src b
+where b.key in (select key from src where src.key > '8')
+group by key, value
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key )
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select key, value, count(*)
+from src b
+where b.key in (select key from src where src.key > '8')
+group by key, value
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.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), Reducer 6 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key > '8') (type: boolean)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key > '8') (type: boolean)
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key > '9') (type: boolean)
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col2 is not null (type: boolean)
+ Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col2 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: bigint)
+ Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0 _col2 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 32 Data size: 5952 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 32 Data size: 5952 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col1
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col1 is not null (type: boolean)
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: bigint)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 41 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 41 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select key, value, count(*)
+from src b
+where b.key in (select key from src where src.key > '8')
+group by key, value
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key )
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key, value, count(*)
+from src b
+where b.key in (select key from src where src.key > '8')
+group by key, value
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key )
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+80 val_80 1
+82 val_82 1
+83 val_83 2
+84 val_84 2
+85 val_85 1
+86 val_86 1
+87 val_87 1
+9 val_9 1
+90 val_90 3
+92 val_92 1
+95 val_95 2
+96 val_96 1
+97 val_97 2
+98 val_98 2
+PREHOOK: query: explain
+select key, value, count(*)
+from src b
+where b.key in (select key from src where src.key > '8')
+group by key, value
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key )
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select key, value, count(*)
+from src b
+where b.key in (select key from src where src.key > '8')
+group by key, value
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.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:
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (BROADCAST_EDGE)
+ Reducer 4 <- Map 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key > '8') (type: boolean)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key > '8') (type: boolean)
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key > '9') (type: boolean)
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col2 is not null (type: boolean)
+ Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0 _col2 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ input vertices:
+ 1 Reducer 4
+ Statistics: Num rows: 32 Data size: 5952 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 32 Data size: 5952 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col1
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col1 is not null (type: boolean)
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: bigint)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 41 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 41 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain
+select key, value, count(*)
+from src b
+where b.key in (select key from src where src.value = b.value)
+group by key, value
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key )
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select key, value, count(*)
+from src b
+where b.key in (select key from src where src.value = b.value)
+group by key, value
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.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:
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (BROADCAST_EDGE)
+ Reducer 5 <- Map 4 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: s1
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key > '9') (type: boolean)
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col2 is not null (type: boolean)
+ Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0 _col2 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ input vertices:
+ 1 Reducer 5
+ Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 41 Data size: 7626 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+ Reducer 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col1
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col1 is not null (type: boolean)
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 83 Data size: 664 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: bigint)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 41 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 41 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select key, value, count(*)
+from src b
+where b.key in (select key from src where src.value = b.value)
+group by key, value
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key )
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key, value, count(*)
+from src b
+where b.key in (select key from src where src.value = b.value)
+group by key, value
+having count(*) in (select count(*) from src s1 where s1.key > '9' group by s1.key )
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0 val_0 3
+10 val_10 1
+100 val_100 2
+103 val_103 2
+104 val_104 2
+105 val_105 1
+11 val_11 1
+111 val_111 1
+113 val_113 2
+114 val_114 1
+116 val_116 1
+118 val_118 2
+119 val_119 3
+12 val_12 2
+120 val_120 2
+125 val_125 2
+126 val_126 1
+128 val_128 3
+129 val_129 2
+131 val_131 1
+133 val_133 1
+134 val_134 2
+136 val_136 1
+137 val_137 2
+143 val_143 1
+145 val_145 1
+146 val_146 2
+149 val_149 2
+15 val_15 2
+150 val_150 1
+152 val_152 2
+153 val_153 1
+155 val_155 1
+156 val_156 1
+157 val_157 1
+158 val_158 1
+160 val_160 1
+162 val_162 1
+163 val_163 1
+164 val_164 2
+165 val_165 2
+166 val_166 1
+167 val_167 3
+168 val_168 1
+17 val_17 1
+170 val_170 1
+172 val_172 2
+174 val_174 2
+175 val_175 2
+176 val_176 2
+177 val_177 1
+178 val_178 1
+179 val_179 2
+18 val_18 2
+180 val_180 1
+181 val_181 1
+183 val_183 1
+186 val_186 1
+187 val_187 3
+189 val_189 1
+19 val_19 1
+190 val_190 1
+191 val_191 2
+192 val_192 1
+193 val_193 3
+194 val_194 1
+195 val_195 2
+196 val_196 1
+197 val_197 2
+199 val_199 3
+2 val_2 1
+20 val_20 1
+200 val_200 2
+201 val_201 1
+202 val_202 1
+203 val_203 2
+205 val_205 2
+207 val_207 2
+208 val_208 3
+209 val_209 2
+213 val_213 2
+214 val_214 1
+216 val_216 2
+217 val_217 2
+218 val_218 1
+219 val_219 2
+221 val_221 2
+222 val_222 1
+223 val_223 2
+224 val_224 2
+226 val_226 1
+228 val_228 1
+229 val_229 2
+233 val_233 2
+235 val_235 1
+237 val_237 2
+238 val_238 2
+239 val_239 2
+24 val_24 2
+241 val_241 1
+242 val_242 2
+244 val_244 1
+247 val_247 1
+248 val_248 1
+249 val_249 1
+252 val_252 1
+255 val_255 2
+256 val_256 2
+257 val_257 1
+258 val_258 1
+26 val_26 2
+260 val_260 1
+262 val_262 1
+263 val_263 1
+265 val_265 2
+266 val_266 1
+27 val_27 1
+272 val_272 2
+273 val_273 3
+274 val_274 1
+275 val_275 1
+278 val_278 2
+28 val_28 1
+280 val_280 2
+281 val_281 2
+282 val_282 2
+283 val_283 1
+284 val_284 1
+285 val_285 1
+286 val_286 1
+287 val_287 1
+288 val_288 2
+289 val_289 1
+291 val_291 1
+292 val_292 1
+296 val_296 1
+298 val_298 3
+30 val_30 1
+302 val_302 1
+305 val_305 1
+306 val_306 1
+307 val_307 2
+308 val_308 1
+309 val_309 2
+310 val_310 1
+311 val_311 3
+315 val_315 1
+316 val_316 3
+317 val_317 2
+318 val_318 3
+321 val_321 2
+322 val_322 2
+323 val_323 1
+325 val_325 2
+327 val_327 3
+33 val_33 1
+331 val_331 2
+332 val_332 1
+333 val_333 2
+335 val_335 1
+336 val_336 1
+338 val_338 1
+339 val_339 1
+34 val_34 1
+341 val_341 1
+342 val_342 2
+344 val_344 2
+345 val_345 1
+35 val_35 3
+351 val_351 1
+353 val_353 2
+356 val_356 1
+360 val_360 1
+362 val_362 1
+364 val_364 1
+365 val_365 1
+366 val_366 1
+367 val_367 2
+368 val_368 1
+369 val_369 3
+37 val_37 2
+373 val_373 1
+374 val_374 1
+375 val_375 1
+377 val_377 1
+378 val_378 1
+379 val_379 1
+382 val_382 2
+384 val_384 3
+386 val_386 1
+389 val_389 1
+392 val_392 1
+393 val_393 1
+394 val_394 1
+395 val_395 2
+396 val_396 3
+397 val_397 2
+399 val_399 2
+4 val_4 1
+400 val_400 1
+402 val_402 1
+403 val_403 3
+404 val_404 2
+407 val_407 1
+409 val_409 3
+41 val_41 1
+411 val_411 1
+413 val_413 2
+414 val_414 2
+417 val_417 3
+418 val_418 1
+419 val_419 1
+42 val_42 2
+421 val_421 1
+424 val_424 2
+427 val_427 1
+429 val_429 2
+43 val_43 1
+430 val_430 3
+431 val_431 3
+432 val_432 1
+435 val_435 1
+436 val_436 1
+437 val_437 1
+438 val_438 3
+439 val_439 2
+44 val_44 1
+443 val_443 1
+444 val_444 1
+446 val_446 1
+448 val_448 1
+449 val_449 1
+452 val_452 1
+453 val_453 1
+454 val_454 3
+455 val_455 1
+457 val_457 1
+458 val_458 2
+459 val_459 2
+460 val_460 1
+462 val_462 2
+463 val_463 2
+466 val_466 3
+467 val_467 1
+47 val_47 1
+470 val_470 1
+472 val_472 1
+475 val_475 1
+477 val_477 1
+478 val_478 2
+479 val_479 1
+480 val_480 3
+481 val_481 1
+482 val_482 1
+483 val_483 1
+484 val_484 1
+485 val_485 1
+487 val_487 1
+490 val_490 1
+491 val_491 1
+492 val_492 2
+493 val_493 1
+494 val_494 1
+495 val_495 1
+496 val_496 1
+497 val_497 1
+498 val_498 3
+5 val_5 3
+51 val_51 2
+53 val_53 1
+54 val_54 1
+57 val_57 1
+58 val_58 2
+64 val_64 1
+65 val_65 1
+66 val_66 1
+67 val_67 2
+69 val_69 1
+70 val_70 3
+72 val_72 2
+74 val_74 1
+76 val_76 2
+77 val_77 1
+78 val_78 1
+8 val_8 1
+80 val_80 1
+82 val_82 1
+83 val_83 2
+84 val_84 2
+85 val_85 1
+86 val_86 1
+87 val_87 1
+9 val_9 1
+90 val_90 3
+92 val_92 1
+95 val_95 2
+96 val_96 1
+97 val_97 2
+98 val_98 2
+PREHOOK: query: explain
+select p_mfgr, p_name, avg(p_size)
+from part_subq
+group by p_mfgr, p_name
+having p_name in
+ (select first_value(p_name) over(partition by p_mfgr order by p_size) from part_subq)
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select p_mfgr, p_name, avg(p_size)
+from part_subq
+group by p_mfgr, p_name
+having p_name in
+ (select first_value(p_name) over(partition by p_mfgr order by p_size) from part_subq)
+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), Reducer 4 (BROADCAST_EDGE)
+ Reducer 4 <- Map 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_subq
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(p_size)
+ keys: p_name (type: string), p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: struct<count:bigint,sum:double,input:int>)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: part_subq
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_size (type: int)
+ sort order: ++
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col0 (type: string), _col2 (type: double)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ input vertices:
+ 1 Reducer 4
+ Statistics: Num rows: 1 Data size: 409 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 409 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
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int)
+ outputColumnNames: _col1, _col2, _col5
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col1: string, _col2: string, _col5: int
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col5 ASC NULLS FIRST
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: first_value_window_0
+ arguments: _col1
+ name: first_value
+ window function: GenericUDAFFirstValueEvaluator
+ window frame: RANGE PRECEDING(MAX)~CURRENT
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: first_value_window_0 is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: first_value_window_0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 372 Basic stats: COMPLETE Column stats: NONE
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: CREATE TABLE src_null (key STRING COMMENT 'default', value STRING COMMENT 'default') STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@src_null
+POSTHOOK: query: CREATE TABLE src_null (key STRING COMMENT 'default', value STRING COMMENT 'default') STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@src_null
+PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/kv1.txt" INTO TABLE src_null
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@src_null
+POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/kv1.txt" INTO TABLE src_null
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@src_null
+PREHOOK: query: INSERT INTO src_null values('5444', null)
+PREHOOK: type: QUERY
+PREHOOK: Output: default@src_null
+POSTHOOK: query: INSERT INTO src_null values('5444', null)
+POSTHOOK: type: QUERY
+POSTHOOK: Output: default@src_null
+POSTHOOK: Lineage: src_null.key SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
+POSTHOOK: Lineage: src_null.value SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
+Warning: Map Join MAPJOIN[123][bigTable=?] in task 'Map 1' is a cross product
+Warning: Map Join MAPJOIN[124][bigTable=?] in task 'Map 1' is a cross product
+Warning: Map Join MAPJOIN[126][bigTable=?] in task 'Map 1' is a cross product
+Warning: Shuffle Join MERGEJOIN[125][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[127][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 6' is a cross product
+PREHOOK: query: explain
+select key, value, count(*)
+from src_null b
+where NOT EXISTS (select key from src_null where src_null.value <> b.value)
+group by key, value
+having count(*) not in (select count(*) from src_null s1 where s1.key > '9' and s1.value <> b.value group by s1.key )
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select key, value, count(*)
+from src_null b
+where NOT EXISTS (select key from src_null where src_null.value <> b.value)
+group by key, value
+having count(*) not in (select count(*) from src_null s1 where s1.key > '9' and s1.value <> b.value group by s1.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:
+ Map 1 <- Reducer 11 (BROADCAST_EDGE), Reducer 12 (BROADCAST_EDGE), Reducer 13 (BROADCAST_EDGE)
+ Reducer 11 <- Map 10 (SIMPLE_EDGE)
+ Reducer 12 <- Map 10 (SIMPLE_EDGE)
+ Reducer 13 <- Map 10 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (BROADCAST_EDGE), Reducer 8 (BROADCAST_EDGE)
+ Reducer 3 <- Map 1 (XPROD_EDGE), Reducer 5 (XPROD_EDGE)
+ Reducer 4 <- Reducer 3 (SIMPLE_EDGE)
+ Reducer 5 <- Map 1 (SIMPLE_EDGE)
+ Reducer 6 <- Map 1 (XPROD_EDGE), Reducer 9 (XPROD_EDGE)
+ Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
+ Reducer 8 <- Reducer 7 (SIMPLE_EDGE)
+ Reducer 9 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Reducer 11
+ residual filter predicates: {(_col1 <> _col2)}
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col3 is null (type: boolean)
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col1 (type: string), _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ Filter Operator
+ predicate: (key > '9') (type: boolean)
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Reducer 12
+ residual filter predicates: {(_col1 <> _col2)}
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col3 is null (type: boolean)
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col1 (type: string), _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key > '9') (type: boolean)
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Reducer 13
+ residual filter predicates: {(_col1 <> _col2)}
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col3 is null (type: boolean)
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col1 (type: string), _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: src_null
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: value (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 11
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), true (type: boolean)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: boolean)
+ Reducer 12
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), true (type: boolean)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: boolean)
+ Reducer 13
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), true (type: boolean)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: boolean)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col0 (type: string), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col4, _col5
+ input vertices:
+ 1 Reducer 4
+ Statistics: Num rows: 1 Data size: 608 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col1 (type: string), _col2 (type: bigint)
+ 1 _col1 (type: string), _col0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col8
+ input vertices:
+ 1 Reducer 8
+ Statistics: Num rows: 1 Data size: 668 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (not CASE WHEN ((_col4 = 0)) THEN (false) WHEN (_col4 is null) THEN (false) WHEN (_col8 is not null) THEN (true) WHEN (_col2 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (true) ELSE (false) END) (type: boolean)
+ Statistics: Num rows: 1 Data size: 668 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 668 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 668 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
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2
+ residual filter predicates: {(_col1 <> _col2)}
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col2 (type: string), _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: bigint)
+ outputColumnNames: _col1, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(), count(_col2)
+ keys: _col1 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint), _col2 (type: bigint)
+ Reducer 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col1
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col1 (type: string)
+ mode: complete
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 553 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2
+ residual filter predicates: {(_col1 <> _col2)}
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col2 (type: string), _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: bigint)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: bigint)
+ outputColumnNames: _col1, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col1 (type: string), _col2 (type: bigint)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: bigint)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Reducer 8
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: bigint), _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint), _col1 (type: string), true (type: boolean)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 922 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string), _col0 (type: bigint)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: string), _
<TRUNCATED>