blob: a597c2b575310f5cc37183ec352300e846e0fb50 [file] [log] [blame]
PREHOOK: query: CREATE TABLE dest_j1(key INT, cnt INT)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@dest_j1
POSTHOOK: query: CREATE TABLE dest_j1(key INT, cnt INT)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@dest_j1
PREHOOK: query: EXPLAIN
INSERT OVERWRITE TABLE dest_j1
SELECT x.key, count(1) FROM src1 x JOIN src y ON (x.key = y.key) group by x.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
PREHOOK: Output: default@dest_j1
POSTHOOK: query: EXPLAIN
INSERT OVERWRITE TABLE dest_j1
SELECT x.key, count(1) FROM src1 x JOIN src y ON (x.key = y.key) group by x.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
POSTHOOK: Output: default@dest_j1
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 2 <- Map 1 (BROADCAST_EDGE)
Reducer 3 <- Map 2 (SIMPLE_EDGE)
Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: x
filterExpr: key is not null (type: boolean)
Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 2
Map Operator Tree:
TableScan
alias: y
filterExpr: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0
input vertices:
0 Map 1
Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
minReductionHashAggr: 0.5897436
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 16 Data size: 1504 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: 16 Data size: 1504 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: 16 Data size: 1504 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 16 Data size: 128 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.dest_j1
Select Operator
expressions: _col0 (type: int), _col1 (type: int)
outputColumnNames: key, cnt
Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(key), max(key), count(1), count(key), compute_bit_vector(key, 'hll'), min(cnt), max(cnt), count(cnt), compute_bit_vector(cnt, 'hll')
minReductionHashAggr: 0.9375
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 328 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: 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: min(VALUE._col0), max(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: 328 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'LONG' (type: string), UDFToLong(_col0) (type: bigint), UDFToLong(_col1) (type: bigint), (_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: 528 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 528 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-2
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.dest_j1
Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: key, cnt
Column Types: int, int
Table: default.dest_j1
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT x.key, count(1) FROM src1 x JOIN src y ON (x.key = y.key) group by x.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
PREHOOK: Output: default@dest_j1
POSTHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT x.key, count(1) FROM src1 x JOIN src y ON (x.key = y.key) group by x.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
POSTHOOK: Output: default@dest_j1
POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, (src)y.null, ]
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
PREHOOK: query: select * from dest_j1
PREHOOK: type: QUERY
PREHOOK: Input: default@dest_j1
#### A masked pattern was here ####
POSTHOOK: query: select * from dest_j1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest_j1
#### A masked pattern was here ####
128 3
146 2
150 1
213 2
224 2
238 2
255 2
273 3
278 2
311 3
369 3
401 5
406 4
66 1
98 2