|
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 is a root stage
STAGE PLANS:
Stage: Stage-1
Map Reduce
Alias -> Map Operator Tree:
logs
TableScan // 扫描表
alias: logs
Select Operator //选择字段
expressions:
expr: uid
type: string
expr: count
type: int
outputColumnNames: uid, count
Group By Operator //在map端先做一次聚合,减少shuffle数据量
aggregations:
expr: sum(count) //聚合函数
bucketGroup: false
keys:
expr: uid
type: string
mode: hash
outputColumnNames: _col0, _col1
Reduce Output Operator //输出key,value给reduce
key expressions:
expr: _col0
type: string
sort order: +
Map-reduce partition columns:
expr: _col0
type: string
tag: -1
value expressions:
expr: _col1
type: bigint
Reduce Operator Tree:
Group By Operator
aggregations:
expr: sum(VALUE._col0) //聚合
bucketGroup: false
keys:
expr: KEY._col0
type: string
mode: mergepartial
outputColumnNames: _col0, _col1
Select Operator //选择字段
expressions:
expr: _col0
type: string
expr: _col1
type: bigint
outputColumnNames: _col0, _col1
File Output Operator //输出到文件
compressed: false
GlobalTableId: 0
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
Stage: Stage-0
Fetch Operator
limit: -1
|
|
|