Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
PaddlePaddle
Paddle
提交
9b11e17d
P
Paddle
项目概览
PaddlePaddle
/
Paddle
1 年多 前同步成功
通知
2302
Star
20931
Fork
5422
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1423
列表
看板
标记
里程碑
合并请求
543
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
1,423
Issue
1,423
列表
看板
标记
里程碑
合并请求
543
合并请求
543
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
提交
9b11e17d
编写于
5月 25, 2017
作者:
H
Helin Wang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix according to comments
上级
6ce7c8bc
变更
4
隐藏空白更改
内联
并排
Showing
4 changed file
with
45 addition
and
25 deletion
+45
-25
paddle/go/cmd/master/master.go
paddle/go/cmd/master/master.go
+28
-13
paddle/go/cmd/pserver/pserver.go
paddle/go/cmd/pserver/pserver.go
+3
-2
paddle/go/master/service.go
paddle/go/master/service.go
+6
-7
paddle/go/master/service_internal_test.go
paddle/go/master/service_internal_test.go
+8
-3
未找到文件。
paddle/go/cmd/master/master.go
浏览文件 @
9b11e17d
package
main
import
(
"f
lag
"
"f
mt
"
"net"
"net/http"
"net/rpc"
"os"
"path/filepath"
"strconv"
"strings"
"time"
"github.com/namsral/flag"
"github.com/PaddlePaddle/Paddle/paddle/go/master"
"github.com/PaddlePaddle/Paddle/paddle/go/recordio"
)
const
(
taskTimeoutDur
=
20
*
time
.
Minute
taskTimeoutMax
=
3
)
func
main
()
{
port
:=
flag
.
Int
(
"p"
,
0
,
"port of the master server"
)
dataset
:=
flag
.
String
(
"d"
,
""
,
"dataset: comma separated path to RecordIO files"
)
faultTolerant
:=
flag
.
Bool
(
"fault-tolerance"
,
false
,
"enable fault tolerance (requires etcd)."
)
port
:=
flag
.
Int
(
"port"
,
8080
,
"port of the master server."
)
dataset
:=
flag
.
String
(
"training_dataset"
,
""
,
"dataset: comma separated path to RecordIO paths, supports golb patterns."
)
faultTolerance
:=
flag
.
Bool
(
"fault_tolerance"
,
false
,
"enable fault tolerance (requires etcd)."
)
taskTimeoutDur
:=
flag
.
Duration
(
"task_timout_dur"
,
20
*
time
.
Minute
,
"task timout duration."
)
taskTimeoutMax
:=
flag
.
Int
(
"task_timeout_max"
,
3
,
"max timtout count for each task before it being declared failed task."
)
chunkPerTask
:=
flag
.
Int
(
"chunk_per_task"
,
10
,
"chunk per task."
)
flag
.
Parse
()
if
*
dataset
==
""
{
panic
(
"no dataset specified."
)
}
if
*
faultToleran
t
{
panic
(
"fault tolerna
t
not implemented."
)
if
*
faultToleran
ce
{
panic
(
"fault tolerna
nce
not implemented."
)
}
var
chunks
[]
master
.
Chunk
paths
:=
strings
.
Split
(
*
dataset
,
","
)
var
paths
[]
string
ss
:=
strings
.
Split
(
*
dataset
,
","
)
fmt
.
Println
(
ss
)
for
_
,
s
:=
range
ss
{
match
,
err
:=
filepath
.
Glob
(
s
)
if
err
!=
nil
{
panic
(
err
)
}
paths
=
append
(
paths
,
match
...
)
}
if
len
(
paths
)
==
0
{
panic
(
"no valid datset specified."
)
}
idx
:=
0
for
_
,
path
:=
range
paths
{
f
,
err
:=
os
.
Open
(
path
)
...
...
@@ -59,7 +74,7 @@ func main() {
}
}
s
:=
master
.
NewService
(
chunks
,
taskTimeoutDur
,
taskTimeoutMax
)
s
:=
master
.
NewService
(
chunks
,
*
chunkPerTask
,
*
taskTimeoutDur
,
*
taskTimeoutMax
)
err
:=
rpc
.
Register
(
s
)
if
err
!=
nil
{
panic
(
err
)
...
...
paddle/go/cmd/pserver/pserver.go
浏览文件 @
9b11e17d
package
main
import
(
"flag"
"net"
"net/http"
"net/rpc"
"strconv"
"github.com/namsral/flag"
"github.com/PaddlePaddle/Paddle/paddle/go/pserver"
)
func
main
()
{
port
:=
flag
.
Int
(
"p"
,
0
,
"port of the pserver"
)
port
:=
flag
.
Int
(
"p
ort
"
,
0
,
"port of the pserver"
)
flag
.
Parse
()
s
:=
pserver
.
NewService
()
...
...
paddle/go/master/service.go
浏览文件 @
9b11e17d
...
...
@@ -34,17 +34,16 @@ func Recover() (*Service, error) {
return
nil
,
nil
}
func
partition
(
chunks
[]
Chunk
,
targetTaskCount
int
)
[]
taskEntry
{
func
partition
(
chunks
[]
Chunk
,
chunksPerTask
int
)
[]
taskEntry
{
id
:=
0
chunkPerTask
:=
len
(
chunks
)
/
targetTaskCount
if
chunkPerTask
<=
0
{
chunkPerTask
=
1
if
chunksPerTask
<=
0
{
chunksPerTask
=
1
}
var
result
[]
taskEntry
var
cur
taskEntry
for
i
,
c
:=
range
chunks
{
if
i
%
chunkPerTask
==
0
&&
len
(
cur
.
Task
.
Chunks
)
>
0
{
if
i
%
chunk
s
PerTask
==
0
&&
len
(
cur
.
Task
.
Chunks
)
>
0
{
cur
.
Task
.
ID
=
id
id
++
result
=
append
(
result
,
cur
)
...
...
@@ -64,13 +63,13 @@ func partition(chunks []Chunk, targetTaskCount int) []taskEntry {
}
// NewService creates a new service.
func
NewService
(
chunks
[]
Chunk
,
timeoutDur
time
.
Duration
,
timeoutMax
int
)
*
Service
{
func
NewService
(
chunks
[]
Chunk
,
chunksPerTask
int
,
timeoutDur
time
.
Duration
,
timeoutMax
int
)
*
Service
{
s
:=
&
Service
{}
s
.
timeoutDur
=
timeoutDur
s
.
timeoutMax
=
timeoutMax
s
.
taskQueues
=
taskQueues
{}
s
.
taskQueues
.
Pending
=
make
(
map
[
int
]
taskEntry
)
s
.
taskQueues
.
Todo
=
partition
(
chunks
,
targetTaskCount
)
s
.
taskQueues
.
Todo
=
partition
(
chunks
,
chunksPerTask
)
return
s
}
...
...
paddle/go/master/service_internal_test.go
浏览文件 @
9b11e17d
...
...
@@ -4,18 +4,23 @@ import "testing"
func
TestPartitionCount
(
t
*
testing
.
T
)
{
cs
:=
make
([]
Chunk
,
100
)
ts
:=
partition
(
cs
,
20
)
ts
:=
partition
(
cs
,
5
)
if
len
(
ts
)
!=
20
{
t
.
Error
(
len
(
ts
))
}
cs
=
make
([]
Chunk
,
101
)
ts
=
partition
(
cs
,
20
)
ts
=
partition
(
cs
,
5
)
if
len
(
ts
)
!=
21
{
t
.
Error
(
len
(
ts
))
}
ts
=
partition
(
cs
,
200
)
ts
=
partition
(
cs
,
1
)
if
len
(
ts
)
!=
101
{
t
.
Error
(
len
(
ts
))
}
ts
=
partition
(
cs
,
0
)
if
len
(
ts
)
!=
101
{
t
.
Error
(
len
(
ts
))
}
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录