blob: c1c2098ba9492e84d5fdf450875e6beafa2dd732 [file] [log] [blame]
PREHOOK: query: show partitions srcpart
PREHOOK: type: SHOWPARTITIONS
PREHOOK: Input: default@srcpart
POSTHOOK: query: show partitions srcpart
POSTHOOK: type: SHOWPARTITIONS
POSTHOOK: Input: default@srcpart
ds=2008-04-08/hr=11
ds=2008-04-08/hr=12
ds=2008-04-09/hr=11
ds=2008-04-09/hr=12
PREHOOK: query: create table if not exists nzhang_part13 like srcpart
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@nzhang_part13
POSTHOOK: query: create table if not exists nzhang_part13 like srcpart
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@nzhang_part13
PREHOOK: query: describe extended nzhang_part13
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@nzhang_part13
POSTHOOK: query: describe extended nzhang_part13
POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@nzhang_part13
key string default
value string default
ds string
hr string
# Partition Information
# col_name data_type comment
ds string
hr string
#### A masked pattern was here ####
PREHOOK: query: explain
insert overwrite table nzhang_part13 partition (ds="2010-03-03", hr)
select * from (
select key, value, '22'
from src
where key < 20
union all
select key, value, '33'
from src
where key > 20 and key < 40) s
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@nzhang_part13@ds=2010-03-03
POSTHOOK: query: explain
insert overwrite table nzhang_part13 partition (ds="2010-03-03", hr)
select * from (
select key, value, '22'
from src
where key < 20
union all
select key, value, '33'
from src
where key > 20 and key < 40) s
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
Edges:
Map 1 <- Union 2 (CONTAINS)
Map 4 <- Union 2 (CONTAINS)
Reducer 3 <- Union 2 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: src
filterExpr: (UDFToDouble(key) < 20.0D) (type: boolean)
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (UDFToDouble(key) < 20.0D) (type: boolean)
Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string), '22' (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 166 Data size: 43824 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 221 Data size: 58344 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.nzhang_part13
Select Operator
expressions: _col0 (type: string), _col1 (type: string), '2010-03-03' (type: string), _col2 (type: string)
outputColumnNames: key, value, ds, hr
Statistics: Num rows: 221 Data size: 79118 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'), max(length(value)), avg(COALESCE(length(value),0)), count(value), compute_bit_vector(value, 'hll')
keys: ds (type: string), hr (type: string)
minReductionHashAggr: 0.99
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
Statistics: Num rows: 1 Data size: 652 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: 1 Data size: 652 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: int), _col3 (type: struct<count:bigint,sum:double,input:int>), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: binary), _col7 (type: int), _col8 (type: struct<count:bigint,sum:double,input:int>), _col9 (type: bigint), _col10 (type: binary)
Execution mode: llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
TableScan
alias: src
filterExpr: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(key) < 40.0D)) (type: boolean)
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(key) > 20.0D) and (UDFToDouble(key) < 40.0D)) (type: boolean)
Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string), '33' (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 55 Data size: 14520 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 221 Data size: 58344 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.nzhang_part13
Select Operator
expressions: _col0 (type: string), _col1 (type: string), '2010-03-03' (type: string), _col2 (type: string)
outputColumnNames: key, value, ds, hr
Statistics: Num rows: 221 Data size: 79118 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'), max(length(value)), avg(COALESCE(length(value),0)), count(value), compute_bit_vector(value, 'hll')
keys: ds (type: string), hr (type: string)
minReductionHashAggr: 0.99
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
Statistics: Num rows: 1 Data size: 652 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: 1 Data size: 652 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: int), _col3 (type: struct<count:bigint,sum:double,input:int>), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: binary), _col7 (type: int), _col8 (type: struct<count:bigint,sum:double,input:int>), _col9 (type: bigint), _col10 (type: binary)
Execution mode: llap
LLAP IO: all inputs
Reducer 3
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), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8)
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
Statistics: Num rows: 1 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col2,0)) (type: bigint), COALESCE(_col3,0) (type: double), (_col4 - _col5) (type: bigint), COALESCE(ndv_compute_bit_vector(_col6),0) (type: bigint), _col6 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col7,0)) (type: bigint), COALESCE(_col8,0) (type: double), (_col4 - _col9) (type: bigint), COALESCE(ndv_compute_bit_vector(_col10),0) (type: bigint), _col10 (type: binary), _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
Statistics: Num rows: 1 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 712 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-2
Dependency Collection
Stage: Stage-0
Move Operator
tables:
partition:
ds 2010-03-03
hr
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.nzhang_part13
Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: key, value
Column Types: string, string
Table: default.nzhang_part13
PREHOOK: query: insert overwrite table nzhang_part13 partition (ds="2010-03-03", hr)
select * from (
select key, value, '22'
from src
where key < 20
union all
select key, value, '33'
from src
where key > 20 and key < 40) s
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@nzhang_part13@ds=2010-03-03
POSTHOOK: query: insert overwrite table nzhang_part13 partition (ds="2010-03-03", hr)
select * from (
select key, value, '22'
from src
where key < 20
union all
select key, value, '33'
from src
where key > 20 and key < 40) s
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@nzhang_part13@ds=2010-03-03/hr=22
POSTHOOK: Output: default@nzhang_part13@ds=2010-03-03/hr=33
POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=22).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=22).value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=33).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: nzhang_part13 PARTITION(ds=2010-03-03,hr=33).value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: show partitions nzhang_part13
PREHOOK: type: SHOWPARTITIONS
PREHOOK: Input: default@nzhang_part13
POSTHOOK: query: show partitions nzhang_part13
POSTHOOK: type: SHOWPARTITIONS
POSTHOOK: Input: default@nzhang_part13
ds=2010-03-03/hr=22
ds=2010-03-03/hr=33
PREHOOK: query: select * from nzhang_part13 where ds is not null and hr is not null
PREHOOK: type: QUERY
PREHOOK: Input: default@nzhang_part13
PREHOOK: Input: default@nzhang_part13@ds=2010-03-03/hr=22
PREHOOK: Input: default@nzhang_part13@ds=2010-03-03/hr=33
#### A masked pattern was here ####
POSTHOOK: query: select * from nzhang_part13 where ds is not null and hr is not null
POSTHOOK: type: QUERY
POSTHOOK: Input: default@nzhang_part13
POSTHOOK: Input: default@nzhang_part13@ds=2010-03-03/hr=22
POSTHOOK: Input: default@nzhang_part13@ds=2010-03-03/hr=33
#### A masked pattern was here ####
15 val_15 2010-03-03 22
17 val_17 2010-03-03 22
0 val_0 2010-03-03 22
4 val_4 2010-03-03 22
12 val_12 2010-03-03 22
8 val_8 2010-03-03 22
0 val_0 2010-03-03 22
0 val_0 2010-03-03 22
15 val_15 2010-03-03 22
19 val_19 2010-03-03 22
10 val_10 2010-03-03 22
5 val_5 2010-03-03 22
11 val_11 2010-03-03 22
5 val_5 2010-03-03 22
2 val_2 2010-03-03 22
12 val_12 2010-03-03 22
5 val_5 2010-03-03 22
18 val_18 2010-03-03 22
9 val_9 2010-03-03 22
18 val_18 2010-03-03 22
27 val_27 2010-03-03 33
37 val_37 2010-03-03 33
35 val_35 2010-03-03 33
24 val_24 2010-03-03 33
26 val_26 2010-03-03 33
35 val_35 2010-03-03 33
34 val_34 2010-03-03 33
30 val_30 2010-03-03 33
33 val_33 2010-03-03 33
35 val_35 2010-03-03 33
24 val_24 2010-03-03 33
26 val_26 2010-03-03 33
28 val_28 2010-03-03 33
37 val_37 2010-03-03 33