blob: e6d800fed739bf86e4f5a96bef1d29fa3a71945a [file] [log] [blame]
PREHOOK: query: CREATE TABLE T1_n81(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@T1_n81
POSTHOOK: query: CREATE TABLE T1_n81(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@T1_n81
PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets.txt' INTO TABLE T1_n81
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@t1_n81
POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets.txt' INTO TABLE T1_n81
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@t1_n81
PREHOOK: query: EXPLAIN
SELECT a, b, count(*) from T1_n81 group by a, b with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n81
#### A masked pattern was here ####
POSTHOOK: query: EXPLAIN
SELECT a, b, count(*) from T1_n81 group by a, b with cube
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n81
#### A masked pattern was here ####
Explain
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)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: t1_n81
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: a (type: string), b (type: string)
outputColumnNames: a, b
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: a (type: string), b (type: string)
minReductionHashAggr: 0.99
mode: hash
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
null sort order: zz
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Execution mode: llap
LLAP IO: all 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), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
null sort order: zzz
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (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), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 2 Data size: 736 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: EXPLAIN
SELECT a, b, count(*) from T1_n81 group by cube(a, b)
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n81
#### A masked pattern was here ####
POSTHOOK: query: EXPLAIN
SELECT a, b, count(*) from T1_n81 group by cube(a, b)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n81
#### A masked pattern was here ####
Explain
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)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: t1_n81
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: a (type: string), b (type: string)
outputColumnNames: a, b
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: a (type: string), b (type: string)
minReductionHashAggr: 0.99
mode: hash
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
null sort order: zz
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Execution mode: llap
LLAP IO: all 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), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
null sort order: zzz
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (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), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 2 Data size: 736 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 a, b, count(*) from T1_n81 group by a, b with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n81
#### A masked pattern was here ####
POSTHOOK: query: SELECT a, b, count(*) from T1_n81 group by a, b with cube
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n81
#### A masked pattern was here ####
a b _c2
1 1 1
1 NULL 1
2 2 1
2 3 1
2 NULL 2
3 2 1
3 NULL 1
5 2 1
5 NULL 1
8 1 1
8 NULL 1
NULL 1 2
NULL 2 3
NULL 3 1
NULL NULL 6
PREHOOK: query: EXPLAIN
SELECT a, b, sum(c) from T1_n81 group by a, b with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n81
#### A masked pattern was here ####
POSTHOOK: query: EXPLAIN
SELECT a, b, sum(c) from T1_n81 group by a, b with cube
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n81
#### A masked pattern was here ####
Explain
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)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: t1_n81
Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: a (type: string), b (type: string), c (type: string)
outputColumnNames: a, b, c
Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(c)
keys: a (type: string), b (type: string)
minReductionHashAggr: 0.99
mode: hash
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
null sort order: zz
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: double)
Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 4 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
null sort order: zzz
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
Statistics: Num rows: 4 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: double)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: double)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 2 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 2 Data size: 1104 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 a, b, sum(c) from T1_n81 group by a, b with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n81
#### A masked pattern was here ####
POSTHOOK: query: SELECT a, b, sum(c) from T1_n81 group by a, b with cube
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n81
#### A masked pattern was here ####
a b _c2
1 1 3.0
1 NULL 3.0
2 2 4.0
2 3 5.0
2 NULL 9.0
3 2 8.0
3 NULL 8.0
5 2 2.0
5 NULL 2.0
8 1 1.0
8 NULL 1.0
NULL 1 4.0
NULL 2 14.0
NULL 3 5.0
NULL NULL 23.0
PREHOOK: query: CREATE TABLE T2_n50(a STRING, b STRING, c int, d int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@T2_n50
POSTHOOK: query: CREATE TABLE T2_n50(a STRING, b STRING, c int, d int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@T2_n50
PREHOOK: query: INSERT OVERWRITE TABLE T2_n50
SELECT a, b, c, c from T1_n81
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n81
PREHOOK: Output: default@t2_n50
POSTHOOK: query: INSERT OVERWRITE TABLE T2_n50
SELECT a, b, c, c from T1_n81
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n81
POSTHOOK: Output: default@t2_n50
POSTHOOK: Lineage: t2_n50.a SIMPLE [(t1_n81)t1_n81.FieldSchema(name:a, type:string, comment:null), ]
POSTHOOK: Lineage: t2_n50.b SIMPLE [(t1_n81)t1_n81.FieldSchema(name:b, type:string, comment:null), ]
POSTHOOK: Lineage: t2_n50.c EXPRESSION [(t1_n81)t1_n81.FieldSchema(name:c, type:string, comment:null), ]
POSTHOOK: Lineage: t2_n50.d EXPRESSION [(t1_n81)t1_n81.FieldSchema(name:c, type:string, comment:null), ]
_col0 _col1 _col2 _col3
PREHOOK: query: EXPLAIN
SELECT a, b, sum(c+d) from T2_n50 group by a, b with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t2_n50
#### A masked pattern was here ####
POSTHOOK: query: EXPLAIN
SELECT a, b, sum(c+d) from T2_n50 group by a, b with cube
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t2_n50
#### A masked pattern was here ####
Explain
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)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: t2_n50
Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: string), b (type: string), (c + d) (type: int)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col2)
keys: _col0 (type: string), _col1 (type: string)
minReductionHashAggr: 0.16666669
mode: hash
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
null sort order: zz
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: bigint)
Execution mode: llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
null sort order: zzz
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 12 Data size: 2136 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
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
ListSink
PREHOOK: query: SELECT a, b, sum(c+d) from T2_n50 group by a, b with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t2_n50
#### A masked pattern was here ####
POSTHOOK: query: SELECT a, b, sum(c+d) from T2_n50 group by a, b with cube
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t2_n50
#### A masked pattern was here ####
a b _c2
1 1 6
1 NULL 6
2 2 8
2 3 10
2 NULL 18
3 2 16
3 NULL 16
5 2 4
5 NULL 4
8 1 2
8 NULL 2
NULL 1 8
NULL 2 28
NULL 3 10
NULL NULL 46