blob: a2e724e9b28239999a338be47ee3166dd8c64db1 [file] [log] [blame]
PREHOOK: query: drop table t1_n28
PREHOOK: type: DROPTABLE
POSTHOOK: query: drop table t1_n28
POSTHOOK: type: DROPTABLE
PREHOOK: query: drop table t2_n19
PREHOOK: type: DROPTABLE
POSTHOOK: query: drop table t2_n19
POSTHOOK: type: DROPTABLE
PREHOOK: query: create table t1_n28 as select * from src where key < 10
PREHOOK: type: CREATETABLE_AS_SELECT
PREHOOK: Input: default@src
PREHOOK: Output: database:default
PREHOOK: Output: default@t1_n28
POSTHOOK: query: create table t1_n28 as select * from src where key < 10
POSTHOOK: type: CREATETABLE_AS_SELECT
POSTHOOK: Input: default@src
POSTHOOK: Output: database:default
POSTHOOK: Output: default@t1_n28
POSTHOOK: Lineage: t1_n28.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: t1_n28.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: create table t2_n19 as select * from src where key < 10
PREHOOK: type: CREATETABLE_AS_SELECT
PREHOOK: Input: default@src
PREHOOK: Output: database:default
PREHOOK: Output: default@t2_n19
POSTHOOK: query: create table t2_n19 as select * from src where key < 10
POSTHOOK: type: CREATETABLE_AS_SELECT
POSTHOOK: Input: default@src
POSTHOOK: Output: database:default
POSTHOOK: Output: default@t2_n19
POSTHOOK: Lineage: t2_n19.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: t2_n19.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: create table t3_n6(key string, cnt int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@t3_n6
POSTHOOK: query: create table t3_n6(key string, cnt int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@t3_n6
PREHOOK: query: create table t4_n2(value string, cnt int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@t4_n2
POSTHOOK: query: create table t4_n2(value string, cnt int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@t4_n2
PREHOOK: query: explain
from
(select * from t1_n28
union all
select * from t2_n19
) x
insert overwrite table t3_n6
select key, count(1) group by key
insert overwrite table t4_n2
select value, count(1) group by value
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n28
PREHOOK: Input: default@t2_n19
PREHOOK: Output: default@t3_n6
PREHOOK: Output: default@t4_n2
POSTHOOK: query: explain
from
(select * from t1_n28
union all
select * from t2_n19
) x
insert overwrite table t3_n6
select key, count(1) group by key
insert overwrite table t4_n2
select value, count(1) group by value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n28
POSTHOOK: Input: default@t2_n19
POSTHOOK: Output: default@t3_n6
POSTHOOK: Output: default@t4_n2
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-3 depends on stages: Stage-2
Stage-0 depends on stages: Stage-3
Stage-4 depends on stages: Stage-0
Stage-1 depends on stages: Stage-3
Stage-5 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-2
Tez
#### A masked pattern was here ####
Edges:
Map 1 <- Union 2 (CONTAINS)
Map 7 <- Union 2 (CONTAINS)
Reducer 3 <- Union 2 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
Reducer 5 <- Union 2 (SIMPLE_EDGE)
Reducer 6 <- Reducer 5 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: t1_n28
Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 20 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string)
minReductionHashAggr: 0.7
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col1
Statistics: Num rows: 20 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(1)
keys: _col1 (type: string)
minReductionHashAggr: 0.7
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 7
Map Operator Tree:
TableScan
alias: t2_n19
Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 20 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string)
minReductionHashAggr: 0.7
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col1
Statistics: Num rows: 20 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(1)
keys: _col1 (type: string)
minReductionHashAggr: 0.7
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 6 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 3
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: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t3_n6
Select Operator
expressions: _col0 (type: string), _col1 (type: int)
outputColumnNames: key, cnt
Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(length(key)), avg(COALESCE(length(key),0)), count(1), count(key), compute_bit_vector(key, 'hll'), min(cnt), max(cnt), count(cnt), compute_bit_vector(cnt, 'hll')
minReductionHashAggr: 0.8333333
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: int), _col7 (type: bigint), _col8 (type: binary)
Reducer 4
Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), min(VALUE._col5), max(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col0,0)) (type: bigint), COALESCE(_col1,0) (type: double), (_col2 - _col3) (type: bigint), COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary), 'LONG' (type: string), UDFToLong(_col5) (type: bigint), UDFToLong(_col6) (type: bigint), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 530 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: 6 Data size: 582 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t4_n2
Select Operator
expressions: _col0 (type: string), _col1 (type: int)
outputColumnNames: value, cnt
Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(length(value)), avg(COALESCE(length(value),0)), count(1), count(value), compute_bit_vector(value, 'hll'), min(cnt), max(cnt), count(cnt), compute_bit_vector(cnt, 'hll')
minReductionHashAggr: 0.8333333
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: int), _col7 (type: bigint), _col8 (type: binary)
Reducer 6
Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), min(VALUE._col5), max(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col0,0)) (type: bigint), COALESCE(_col1,0) (type: double), (_col2 - _col3) (type: bigint), COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary), 'LONG' (type: string), UDFToLong(_col5) (type: bigint), UDFToLong(_col6) (type: bigint), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 530 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
Union 2
Vertex: Union 2
Stage: Stage-3
Dependency Collection
Stage: Stage-0
Move Operator
tables:
replace: true
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t3_n6
Stage: Stage-4
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: key, cnt
Column Types: string, int
Table: default.t3_n6
Stage: Stage-1
Move Operator
tables:
replace: true
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t4_n2
Stage: Stage-5
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: value, cnt
Column Types: string, int
Table: default.t4_n2
PREHOOK: query: from
(select * from t1_n28
union all
select * from t2_n19
) x
insert overwrite table t3_n6
select key, count(1) group by key
insert overwrite table t4_n2
select value, count(1) group by value
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n28
PREHOOK: Input: default@t2_n19
PREHOOK: Output: default@t3_n6
PREHOOK: Output: default@t4_n2
POSTHOOK: query: from
(select * from t1_n28
union all
select * from t2_n19
) x
insert overwrite table t3_n6
select key, count(1) group by key
insert overwrite table t4_n2
select value, count(1) group by value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n28
POSTHOOK: Input: default@t2_n19
POSTHOOK: Output: default@t3_n6
POSTHOOK: Output: default@t4_n2
POSTHOOK: Lineage: t3_n6.cnt EXPRESSION [(t1_n28)t1_n28.null, (t2_n19)t2_n19.null, ]
POSTHOOK: Lineage: t3_n6.key EXPRESSION [(t1_n28)t1_n28.FieldSchema(name:key, type:string, comment:null), (t2_n19)t2_n19.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: t4_n2.cnt EXPRESSION [(t1_n28)t1_n28.null, (t2_n19)t2_n19.null, ]
POSTHOOK: Lineage: t4_n2.value EXPRESSION [(t1_n28)t1_n28.FieldSchema(name:value, type:string, comment:null), (t2_n19)t2_n19.FieldSchema(name:value, type:string, comment:null), ]
PREHOOK: query: select * from t3_n6
PREHOOK: type: QUERY
PREHOOK: Input: default@t3_n6
#### A masked pattern was here ####
POSTHOOK: query: select * from t3_n6
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t3_n6
#### A masked pattern was here ####
0 6
2 2
4 2
5 6
8 2
9 2
PREHOOK: query: select * from t4_n2
PREHOOK: type: QUERY
PREHOOK: Input: default@t4_n2
#### A masked pattern was here ####
POSTHOOK: query: select * from t4_n2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t4_n2
#### A masked pattern was here ####
val_0 6
val_2 2
val_4 2
val_5 6
val_8 2
val_9 2
PREHOOK: query: create table t5_n0(c1 string, cnt int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@t5_n0
POSTHOOK: query: create table t5_n0(c1 string, cnt int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@t5_n0
PREHOOK: query: create table t6_n0(c1 string, cnt int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@t6_n0
POSTHOOK: query: create table t6_n0(c1 string, cnt int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@t6_n0
PREHOOK: query: explain
from
(
select key as c1, count(1) as cnt from t1_n28 group by key
union all
select key as c1, count(1) as cnt from t2_n19 group by key
) x
insert overwrite table t5_n0
select c1, sum(cnt) group by c1
insert overwrite table t6_n0
select c1, sum(cnt) group by c1
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n28
PREHOOK: Input: default@t2_n19
PREHOOK: Output: default@t5_n0
PREHOOK: Output: default@t6_n0
POSTHOOK: query: explain
from
(
select key as c1, count(1) as cnt from t1_n28 group by key
union all
select key as c1, count(1) as cnt from t2_n19 group by key
) x
insert overwrite table t5_n0
select c1, sum(cnt) group by c1
insert overwrite table t6_n0
select c1, sum(cnt) group by c1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n28
POSTHOOK: Input: default@t2_n19
POSTHOOK: Output: default@t5_n0
POSTHOOK: Output: default@t6_n0
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-3 depends on stages: Stage-2
Stage-0 depends on stages: Stage-3
Stage-4 depends on stages: Stage-0
Stage-1 depends on stages: Stage-3
Stage-5 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-2
Tez
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS)
Reducer 4 <- Union 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE)
Reducer 6 <- Reducer 4 (CUSTOM_SIMPLE_EDGE)
Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 3 (CONTAINS)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: t1_n28
Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: key (type: string)
minReductionHashAggr: 0.5
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 7
Map Operator Tree:
TableScan
alias: t2_n19
Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: key (type: string)
minReductionHashAggr: 0.5
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 4
Execution mode: llap
Reduce Operator Tree:
Forward
Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(VALUE._col0)
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t5_n0
Select Operator
expressions: _col0 (type: string), _col1 (type: int)
outputColumnNames: c1, cnt
Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(length(c1)), avg(COALESCE(length(c1),0)), count(1), count(c1), compute_bit_vector(c1, 'hll'), min(cnt), max(cnt), count(cnt), compute_bit_vector(cnt, 'hll')
minReductionHashAggr: 0.8
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: int), _col7 (type: bigint), _col8 (type: binary)
Group By Operator
aggregations: sum(VALUE._col0)
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t6_n0
Select Operator
expressions: _col0 (type: string), _col1 (type: int)
outputColumnNames: c1, cnt
Statistics: Num rows: 5 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(length(c1)), avg(COALESCE(length(c1),0)), count(1), count(c1), compute_bit_vector(c1, 'hll'), min(cnt), max(cnt), count(cnt), compute_bit_vector(cnt, 'hll')
minReductionHashAggr: 0.8
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: int), _col7 (type: bigint), _col8 (type: binary)
Reducer 5
Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), min(VALUE._col5), max(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col0,0)) (type: bigint), COALESCE(_col1,0) (type: double), (_col2 - _col3) (type: bigint), COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary), 'LONG' (type: string), UDFToLong(_col5) (type: bigint), UDFToLong(_col6) (type: bigint), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 530 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: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), min(VALUE._col5), max(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col0,0)) (type: bigint), COALESCE(_col1,0) (type: double), (_col2 - _col3) (type: bigint), COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary), 'LONG' (type: string), UDFToLong(_col5) (type: bigint), UDFToLong(_col6) (type: bigint), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 530 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 8
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Union 3
Vertex: Union 3
Stage: Stage-3
Dependency Collection
Stage: Stage-0
Move Operator
tables:
replace: true
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t5_n0
Stage: Stage-4
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: c1, cnt
Column Types: string, int
Table: default.t5_n0
Stage: Stage-1
Move Operator
tables:
replace: true
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t6_n0
Stage: Stage-5
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: c1, cnt
Column Types: string, int
Table: default.t6_n0
PREHOOK: query: from
(
select key as c1, count(1) as cnt from t1_n28 group by key
union all
select key as c1, count(1) as cnt from t2_n19 group by key
) x
insert overwrite table t5_n0
select c1, sum(cnt) group by c1
insert overwrite table t6_n0
select c1, sum(cnt) group by c1
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n28
PREHOOK: Input: default@t2_n19
PREHOOK: Output: default@t5_n0
PREHOOK: Output: default@t6_n0
POSTHOOK: query: from
(
select key as c1, count(1) as cnt from t1_n28 group by key
union all
select key as c1, count(1) as cnt from t2_n19 group by key
) x
insert overwrite table t5_n0
select c1, sum(cnt) group by c1
insert overwrite table t6_n0
select c1, sum(cnt) group by c1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n28
POSTHOOK: Input: default@t2_n19
POSTHOOK: Output: default@t5_n0
POSTHOOK: Output: default@t6_n0
POSTHOOK: Lineage: t5_n0.c1 EXPRESSION [(t1_n28)t1_n28.FieldSchema(name:key, type:string, comment:null), (t2_n19)t2_n19.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: t5_n0.cnt EXPRESSION [(t1_n28)t1_n28.null, (t2_n19)t2_n19.null, ]
POSTHOOK: Lineage: t6_n0.c1 EXPRESSION [(t1_n28)t1_n28.FieldSchema(name:key, type:string, comment:null), (t2_n19)t2_n19.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: t6_n0.cnt EXPRESSION [(t1_n28)t1_n28.null, (t2_n19)t2_n19.null, ]
PREHOOK: query: select * from t5_n0
PREHOOK: type: QUERY
PREHOOK: Input: default@t5_n0
#### A masked pattern was here ####
POSTHOOK: query: select * from t5_n0
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t5_n0
#### A masked pattern was here ####
0 6
2 2
4 2
5 6
8 2
9 2
PREHOOK: query: select * from t6_n0
PREHOOK: type: QUERY
PREHOOK: Input: default@t6_n0
#### A masked pattern was here ####
POSTHOOK: query: select * from t6_n0
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t6_n0
#### A masked pattern was here ####
0 6
2 2
4 2
5 6
8 2
9 2
PREHOOK: query: drop table t1_n28
PREHOOK: type: DROPTABLE
PREHOOK: Input: default@t1_n28
PREHOOK: Output: default@t1_n28
POSTHOOK: query: drop table t1_n28
POSTHOOK: type: DROPTABLE
POSTHOOK: Input: default@t1_n28
POSTHOOK: Output: default@t1_n28
PREHOOK: query: drop table t2_n19
PREHOOK: type: DROPTABLE
PREHOOK: Input: default@t2_n19
PREHOOK: Output: default@t2_n19
POSTHOOK: query: drop table t2_n19
POSTHOOK: type: DROPTABLE
POSTHOOK: Input: default@t2_n19
POSTHOOK: Output: default@t2_n19
PREHOOK: query: create table t1_n28 as select * from src where key < 10
PREHOOK: type: CREATETABLE_AS_SELECT
PREHOOK: Input: default@src
PREHOOK: Output: database:default
PREHOOK: Output: default@t1_n28
POSTHOOK: query: create table t1_n28 as select * from src where key < 10
POSTHOOK: type: CREATETABLE_AS_SELECT
POSTHOOK: Input: default@src
POSTHOOK: Output: database:default
POSTHOOK: Output: default@t1_n28
POSTHOOK: Lineage: t1_n28.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: t1_n28.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: create table t2_n19 as select key, count(1) as cnt from src where key < 10 group by key
PREHOOK: type: CREATETABLE_AS_SELECT
PREHOOK: Input: default@src
PREHOOK: Output: database:default
PREHOOK: Output: default@t2_n19
POSTHOOK: query: create table t2_n19 as select key, count(1) as cnt from src where key < 10 group by key
POSTHOOK: type: CREATETABLE_AS_SELECT
POSTHOOK: Input: default@src
POSTHOOK: Output: database:default
POSTHOOK: Output: default@t2_n19
POSTHOOK: Lineage: t2_n19.cnt EXPRESSION [(src)src.null, ]
POSTHOOK: Lineage: t2_n19.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
PREHOOK: query: create table t7_n1(c1 string, cnt int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@t7_n1
POSTHOOK: query: create table t7_n1(c1 string, cnt int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@t7_n1
PREHOOK: query: create table t8_n0(c1 string, cnt int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@t8_n0
POSTHOOK: query: create table t8_n0(c1 string, cnt int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@t8_n0
PREHOOK: query: explain
from
(
select key as c1, count(1) as cnt from t1_n28 group by key
union all
select key as c1, cnt from t2_n19
) x
insert overwrite table t7_n1
select c1, count(1) group by c1
insert overwrite table t8_n0
select c1, count(1) group by c1
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n28
PREHOOK: Input: default@t2_n19
PREHOOK: Output: default@t7_n1
PREHOOK: Output: default@t8_n0
POSTHOOK: query: explain
from
(
select key as c1, count(1) as cnt from t1_n28 group by key
union all
select key as c1, cnt from t2_n19
) x
insert overwrite table t7_n1
select c1, count(1) group by c1
insert overwrite table t8_n0
select c1, count(1) group by c1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n28
POSTHOOK: Input: default@t2_n19
POSTHOOK: Output: default@t7_n1
POSTHOOK: Output: default@t8_n0
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-3 depends on stages: Stage-2
Stage-0 depends on stages: Stage-3
Stage-4 depends on stages: Stage-0
Stage-1 depends on stages: Stage-3
Stage-5 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-2
Tez
#### A masked pattern was here ####
Edges:
Map 7 <- Union 3 (CONTAINS)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS)
Reducer 4 <- Union 3 (SIMPLE_EDGE)
Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE)
Reducer 6 <- Reducer 4 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: t1_n28
Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
Statistics: Num rows: 10 Data size: 850 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: key (type: string)
minReductionHashAggr: 0.5
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 7
Map Operator Tree:
TableScan
alias: t2_n19
Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 11 Data size: 975 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 11 Data size: 975 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 11 Data size: 975 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: z
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 11 Data size: 975 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 4
Execution mode: llap
Reduce Operator Tree:
Forward
Statistics: Num rows: 11 Data size: 975 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(1)
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t7_n1
Select Operator
expressions: _col0 (type: string), _col1 (type: int)
outputColumnNames: c1, cnt
Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(length(c1)), avg(COALESCE(length(c1),0)), count(1), count(c1), compute_bit_vector(c1, 'hll'), min(cnt), max(cnt), count(cnt), compute_bit_vector(cnt, 'hll')
minReductionHashAggr: 0.8333333
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: int), _col7 (type: bigint), _col8 (type: binary)
Group By Operator
aggregations: count(1)
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t8_n0
Select Operator
expressions: _col0 (type: string), _col1 (type: int)
outputColumnNames: c1, cnt
Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(length(c1)), avg(COALESCE(length(c1),0)), count(1), count(c1), compute_bit_vector(c1, 'hll'), min(cnt), max(cnt), count(cnt), compute_bit_vector(cnt, 'hll')
minReductionHashAggr: 0.8333333
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: int), _col7 (type: bigint), _col8 (type: binary)
Reducer 5
Execution mode: llap
Reduce Operator Tree:
Group By Operator
aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), min(VALUE._col5), max(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col0,0)) (type: bigint), COALESCE(_col1,0) (type: double), (_col2 - _col3) (type: bigint), COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary), 'LONG' (type: string), UDFToLong(_col5) (type: bigint), UDFToLong(_col6) (type: bigint), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 530 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: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), min(VALUE._col5), max(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col0,0)) (type: bigint), COALESCE(_col1,0) (type: double), (_col2 - _col3) (type: bigint), COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary), 'LONG' (type: string), UDFToLong(_col5) (type: bigint), UDFToLong(_col6) (type: bigint), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 530 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
Union 3
Vertex: Union 3
Stage: Stage-3
Dependency Collection
Stage: Stage-0
Move Operator
tables:
replace: true
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t7_n1
Stage: Stage-4
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: c1, cnt
Column Types: string, int
Table: default.t7_n1
Stage: Stage-1
Move Operator
tables:
replace: true
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.t8_n0
Stage: Stage-5
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: c1, cnt
Column Types: string, int
Table: default.t8_n0
PREHOOK: query: from
(
select key as c1, count(1) as cnt from t1_n28 group by key
union all
select key as c1, cnt from t2_n19
) x
insert overwrite table t7_n1
select c1, count(1) group by c1
insert overwrite table t8_n0
select c1, count(1) group by c1
PREHOOK: type: QUERY
PREHOOK: Input: default@t1_n28
PREHOOK: Input: default@t2_n19
PREHOOK: Output: default@t7_n1
PREHOOK: Output: default@t8_n0
POSTHOOK: query: from
(
select key as c1, count(1) as cnt from t1_n28 group by key
union all
select key as c1, cnt from t2_n19
) x
insert overwrite table t7_n1
select c1, count(1) group by c1
insert overwrite table t8_n0
select c1, count(1) group by c1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1_n28
POSTHOOK: Input: default@t2_n19
POSTHOOK: Output: default@t7_n1
POSTHOOK: Output: default@t8_n0
POSTHOOK: Lineage: t7_n1.c1 EXPRESSION [(t1_n28)t1_n28.FieldSchema(name:key, type:string, comment:null), (t2_n19)t2_n19.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: t7_n1.cnt EXPRESSION [(t1_n28)t1_n28.null, (t2_n19)t2_n19.null, ]
POSTHOOK: Lineage: t8_n0.c1 EXPRESSION [(t1_n28)t1_n28.FieldSchema(name:key, type:string, comment:null), (t2_n19)t2_n19.FieldSchema(name:key, type:string, comment:null), ]
POSTHOOK: Lineage: t8_n0.cnt EXPRESSION [(t1_n28)t1_n28.null, (t2_n19)t2_n19.null, ]
PREHOOK: query: select * from t7_n1
PREHOOK: type: QUERY
PREHOOK: Input: default@t7_n1
#### A masked pattern was here ####
POSTHOOK: query: select * from t7_n1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t7_n1
#### A masked pattern was here ####
0 2
2 2
4 2
5 2
8 2
9 2
PREHOOK: query: select * from t8_n0
PREHOOK: type: QUERY
PREHOOK: Input: default@t8_n0
#### A masked pattern was here ####
POSTHOOK: query: select * from t8_n0
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t8_n0
#### A masked pattern was here ####
0 2
2 2
4 2
5 2
8 2
9 2