blob: e0758aa49db62496fa1c77b4b6b88303a6de4f9a [file] [log] [blame]
PREHOOK: query: CREATE TABLE dest1_n126(c1 INT, c2 STRING, c3 INT, c4 STRING) STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@dest1_n126
POSTHOOK: query: CREATE TABLE dest1_n126(c1 INT, c2 STRING, c3 INT, c4 STRING) STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@dest1_n126
PREHOOK: query: EXPLAIN
FROM (
FROM
(
FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20
) a
RIGHT OUTER JOIN
(
FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25
) b
ON (a.c1 = b.c3)
SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4
) c
INSERT OVERWRITE TABLE dest1_n126 SELECT c.c1, c.c2, c.c3, c.c4
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@dest1_n126
POSTHOOK: query: EXPLAIN
FROM (
FROM
(
FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20
) a
RIGHT OUTER JOIN
(
FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25
) b
ON (a.c1 = b.c3)
SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4
) c
INSERT OVERWRITE TABLE dest1_n126 SELECT c.c1, c.c2, c.c3, c.c4
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n126
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:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: src1
filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (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) > 15.0D)) (type: boolean)
Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 55 Data size: 9790 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: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
TableScan
alias: src2
filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean)
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 25.0D)) (type: boolean)
Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 55 Data size: 9790 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: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
Right Outer Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 55 Data size: 19580 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 55 Data size: 10450 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.dest1_n126
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string)
outputColumnNames: c1, c2, c3, c4
Statistics: Num rows: 55 Data size: 10450 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(c1), max(c1), count(1), count(c1), compute_bit_vector(c1, 'hll'), max(length(c2)), avg(COALESCE(length(c2),0)), count(c2), compute_bit_vector(c2, 'hll'), min(c3), max(c3), count(c3), compute_bit_vector(c3, 'hll'), max(length(c4)), avg(COALESCE(length(c4),0)), count(c4), compute_bit_vector(c4, 'hll')
minReductionHashAggr: 0.9818182
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16
Statistics: Num rows: 1 Data size: 792 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 792 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: int), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary)
Reducer 3
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), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8), min(VALUE._col9), max(VALUE._col10), count(VALUE._col11), compute_bit_vector(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector(VALUE._col16)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16
Statistics: Num rows: 1 Data size: 656 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'LONG' (type: string), UDFToLong(_col9) (type: bigint), UDFToLong(_col10) (type: bigint), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23
Statistics: Num rows: 1 Data size: 1060 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 1060 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.dest1_n126
Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: c1, c2, c3, c4
Column Types: int, string, int, string
Table: default.dest1_n126
PREHOOK: query: FROM (
FROM
(
FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20
) a
RIGHT OUTER JOIN
(
FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25
) b
ON (a.c1 = b.c3)
SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4
) c
INSERT OVERWRITE TABLE dest1_n126 SELECT c.c1, c.c2, c.c3, c.c4
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@dest1_n126
POSTHOOK: query: FROM (
FROM
(
FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20
) a
RIGHT OUTER JOIN
(
FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25
) b
ON (a.c1 = b.c3)
SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4
) c
INSERT OVERWRITE TABLE dest1_n126 SELECT c.c1, c.c2, c.c3, c.c4
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n126
POSTHOOK: Lineage: dest1_n126.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest1_n126.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ]
POSTHOOK: Lineage: dest1_n126.c3 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest1_n126.c4 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: SELECT dest1_n126.* FROM dest1_n126
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n126
#### A masked pattern was here ####
POSTHOOK: query: SELECT dest1_n126.* FROM dest1_n126
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n126
#### A masked pattern was here ####
17 val_17 17 val_17
18 val_18 18 val_18
18 val_18 18 val_18
18 val_18 18 val_18
18 val_18 18 val_18
19 val_19 19 val_19
NULL NULL 20 val_20
NULL NULL 24 val_24
NULL NULL 24 val_24