blob: c285f8e66883106facf7ffe3bcb7c528a38c66b1 [file] [log] [blame]
PREHOOK: query: CREATE TABLE dest1_n81(key INT, value STRING) STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@dest1_n81
POSTHOOK: query: CREATE TABLE dest1_n81(key INT, value STRING) STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@dest1_n81
PREHOOK: query: EXPLAIN
FROM (
FROM src_thrift
SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
USING 'cat' AS (tkey, tvalue)
CLUSTER BY tkey
) tmap
INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
PREHOOK: type: QUERY
PREHOOK: Input: default@src_thrift
PREHOOK: Output: default@dest1_n81
POSTHOOK: query: EXPLAIN
FROM (
FROM src_thrift
SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
USING 'cat' AS (tkey, tvalue)
CLUSTER BY tkey
) tmap
INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src_thrift
POSTHOOK: Output: default@dest1_n81
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)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: src_thrift
Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (aint + lint[0]) (type: int), lintstring[0] (type: struct<myint:int,mystring:string,underscore_int:int>)
outputColumnNames: _col0, _col1
Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
Transform Operator
command: cat
output info:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: a
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: string), _col1 (type: string)
Reducer 2
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
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_n81
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
Statistics: Num rows: 11 Data size: 29524 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(key), max(key), count(1), count(key), compute_bit_vector(key, 'hll'), max(length(value)), avg(COALESCE(length(value),0)), count(value), compute_bit_vector(value, 'hll')
minReductionHashAggr: 0.99
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 3084 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
null sort order:
sort order:
Statistics: Num rows: 1 Data size: 3084 Basic stats: COMPLETE Column stats: NONE
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)
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)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 3084 Basic stats: COMPLETE Column stats: NONE
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)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
Statistics: Num rows: 1 Data size: 3084 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 3084 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-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_n81
Stage: Stage-3
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: key, value
Column Types: int, string
Table: default.dest1_n81
PREHOOK: query: FROM (
FROM src_thrift
SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
USING 'cat' AS (tkey, tvalue)
CLUSTER BY tkey
) tmap
INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
PREHOOK: type: QUERY
PREHOOK: Input: default@src_thrift
PREHOOK: Output: default@dest1_n81
POSTHOOK: query: FROM (
FROM src_thrift
SELECT TRANSFORM(src_thrift.aint + src_thrift.lint[0], src_thrift.lintstring[0])
USING 'cat' AS (tkey, tvalue)
CLUSTER BY tkey
) tmap
INSERT OVERWRITE TABLE dest1_n81 SELECT tmap.tkey, tmap.tvalue
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src_thrift
POSTHOOK: Output: default@dest1_n81
POSTHOOK: Lineage: dest1_n81.key SCRIPT [(src_thrift)src_thrift.FieldSchema(name:aint, type:int, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lint, type:array<int>, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lintstring, type:array<struct<myint:int,mystring:string,underscore_int:int>>, comment:from deserializer), ]
POSTHOOK: Lineage: dest1_n81.value SCRIPT [(src_thrift)src_thrift.FieldSchema(name:aint, type:int, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lint, type:array<int>, comment:from deserializer), (src_thrift)src_thrift.FieldSchema(name:lintstring, type:array<struct<myint:int,mystring:string,underscore_int:int>>, comment:from deserializer), ]
PREHOOK: query: SELECT dest1_n81.* FROM dest1_n81
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n81
PREHOOK: Output: hdfs://### HDFS PATH ###
POSTHOOK: query: SELECT dest1_n81.* FROM dest1_n81
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n81
POSTHOOK: Output: hdfs://### HDFS PATH ###
-1461153966 {"myint":49,"mystring":"343","underscore_int":7}
-1952710705 {"myint":25,"mystring":"125","underscore_int":5}
-734328905 {"myint":16,"mystring":"64","underscore_int":4}
-751827636 {"myint":4,"mystring":"8","underscore_int":2}
1244525196 {"myint":36,"mystring":"216","underscore_int":6}
1638581586 {"myint":64,"mystring":"512","underscore_int":8}
1712634731 {"myint":0,"mystring":"0","underscore_int":0}
336964422 {"myint":81,"mystring":"729","underscore_int":9}
465985201 {"myint":1,"mystring":"1","underscore_int":1}
477111225 {"myint":9,"mystring":"27","underscore_int":3}
NULL NULL