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
doujutun3207
flink
提交
84759dad
F
flink
项目概览
doujutun3207
/
flink
与 Fork 源项目一致
从无法访问的项目Fork
通知
24
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
F
flink
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
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
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
体验新版 GitCode,发现更多精彩内容 >>
提交
84759dad
编写于
7月 14, 2014
作者:
G
gyfora
提交者:
Stephan Ewen
8月 18, 2014
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
[streaming] added support for batch partitioning to jobgraphbuilder
上级
7e7051b3
变更
6
展开全部
显示空白变更内容
内联
并排
Showing
6 changed file
with
4212 addition
and
34 deletion
+4212
-34
flink-addons/flink-streaming/src/main/java/eu/stratosphere/streaming/api/DataStream.java
...c/main/java/eu/stratosphere/streaming/api/DataStream.java
+2
-1
flink-addons/flink-streaming/src/main/java/eu/stratosphere/streaming/api/JobGraphBuilder.java
...n/java/eu/stratosphere/streaming/api/JobGraphBuilder.java
+2
-1
flink-addons/flink-streaming/src/main/java/eu/stratosphere/streaming/api/StreamExecutionEnvironment.java
...tratosphere/streaming/api/StreamExecutionEnvironment.java
+2
-0
flink-addons/flink-streaming/src/main/java/eu/stratosphere/streaming/api/streamcomponent/StreamComponentHelper.java
.../streaming/api/streamcomponent/StreamComponentHelper.java
+22
-4
flink-addons/flink-streaming/src/main/java/eu/stratosphere/streaming/util/TestDataUtil.java
...ain/java/eu/stratosphere/streaming/util/TestDataUtil.java
+0
-28
flink-addons/flink-streaming/src/test/resources/testdata/hamlet.txt
...ns/flink-streaming/src/test/resources/testdata/hamlet.txt
+4184
-0
未找到文件。
flink-addons/flink-streaming/src/main/java/eu/stratosphere/streaming/api/DataStream.java
浏览文件 @
84759dad
...
...
@@ -57,6 +57,8 @@ public class DataStream<T extends Tuple> {
}
//TODO: create copy method (or constructor) and copy datastream at every operator
private
void
initConnections
()
{
connectIDs
=
new
ArrayList
<
String
>();
connectIDs
.
add
(
getId
());
...
...
@@ -82,7 +84,6 @@ public class DataStream<T extends Tuple> {
for
(
int
i
=
0
;
i
<
batchSizes
.
size
();
i
++)
{
batchSizes
.
set
(
i
,
batchSize
);
}
context
.
setBatchSize
(
this
);
return
this
;
}
...
...
flink-addons/flink-streaming/src/main/java/eu/stratosphere/streaming/api/JobGraphBuilder.java
浏览文件 @
84759dad
...
...
@@ -306,7 +306,8 @@ public class JobGraphBuilder {
public
void
setBatchSize
(
String
componentName
,
int
batchSize
)
{
Configuration
config
=
components
.
get
(
componentName
).
getConfiguration
();
config
.
setInteger
(
"batchSize"
,
batchSize
);
config
.
setInteger
(
"batchSize_"
+
(
components
.
get
(
componentName
).
getNumberOfForwardConnections
()
-
1
),
batchSize
);
}
/**
...
...
flink-addons/flink-streaming/src/main/java/eu/stratosphere/streaming/api/StreamExecutionEnvironment.java
浏览文件 @
84759dad
...
...
@@ -91,6 +91,8 @@ public class StreamExecutionEnvironment {
}
}
this
.
setBatchSize
(
inputStream
);
}
public
<
T
extends
Tuple
,
R
extends
Tuple
>
DataStream
<
R
>
addFunction
(
String
functionName
,
...
...
flink-addons/flink-streaming/src/main/java/eu/stratosphere/streaming/api/streamcomponent/StreamComponentHelper.java
浏览文件 @
84759dad
...
...
@@ -18,6 +18,7 @@ package eu.stratosphere.streaming.api.streamcomponent;
import
java.io.ByteArrayInputStream
;
import
java.io.IOException
;
import
java.io.ObjectInputStream
;
import
java.util.ArrayList
;
import
java.util.ConcurrentModificationException
;
import
java.util.List
;
...
...
@@ -75,6 +76,12 @@ public final class StreamComponentHelper<T extends AbstractInvokable> {
private
SerializationDelegate
<
Tuple
>
outSerializationDelegate
=
null
;
public
StreamCollector
<
Tuple
>
collector
;
private
List
<
Integer
>
batchsizes_s
=
new
ArrayList
<
Integer
>();
private
List
<
Integer
>
batchsizes_f
=
new
ArrayList
<
Integer
>();
private
int
keyPosition
=
0
;
private
List
<
RecordWriter
<
StreamRecord
>>
outputs_s
=
new
ArrayList
<
RecordWriter
<
StreamRecord
>>();
private
List
<
RecordWriter
<
StreamRecord
>>
outputs_f
=
new
ArrayList
<
RecordWriter
<
StreamRecord
>>();
public
static
int
newComponent
()
{
numComponents
++;
...
...
@@ -109,6 +116,7 @@ public final class StreamComponentHelper<T extends AbstractInvokable> {
List
<
RecordWriter
<
StreamRecord
>>
outputs
)
{
int
batchSize
=
taskConfiguration
.
getInteger
(
"batchSize"
,
1
);
long
batchTimeout
=
taskConfiguration
.
getLong
(
"batchTimeout"
,
1000
);
collector
=
new
StreamCollector
<
Tuple
>(
batchSize
,
batchTimeout
,
id
,
outSerializationDelegate
,
outputs
);
...
...
@@ -208,10 +216,11 @@ public final class StreamComponentHelper<T extends AbstractInvokable> {
List
<
ChannelSelector
<
StreamRecord
>>
partitioners
)
throws
StreamComponentException
{
int
numberOfOutputs
=
taskConfiguration
.
getInteger
(
"numberOfOutputs"
,
0
);
for
(
int
i
=
0
;
i
<
numberOfOutputs
;
i
++)
{
setPartitioner
(
taskConfiguration
,
i
,
partitioners
);
}
for
(
ChannelSelector
<
StreamRecord
>
outputPartitioner
:
partitioners
)
{
ChannelSelector
<
StreamRecord
>
outputPartitioner
=
partitioners
.
get
(
i
);
if
(
taskBase
instanceof
StreamTask
)
{
outputs
.
add
(
new
RecordWriter
<
StreamRecord
>((
StreamTask
)
taskBase
,
StreamRecord
.
class
,
outputPartitioner
));
...
...
@@ -221,6 +230,11 @@ public final class StreamComponentHelper<T extends AbstractInvokable> {
}
else
{
throw
new
StreamComponentException
(
"Nonsupported object passed to setConfigOutputs"
);
}
if
(
outputs_f
.
size
()
<
batchsizes_f
.
size
())
{
outputs_f
.
add
(
outputs
.
get
(
i
));
}
else
{
outputs_s
.
add
(
outputs
.
get
(
i
));
}
}
}
...
...
@@ -321,14 +335,18 @@ public final class StreamComponentHelper<T extends AbstractInvokable> {
Class
<?
extends
ChannelSelector
<
StreamRecord
>>
partitioner
=
taskConfiguration
.
getClass
(
"partitionerClass_"
+
nrOutput
,
DefaultPartitioner
.
class
,
ChannelSelector
.
class
);
Integer
batchSize
=
taskConfiguration
.
getInteger
(
"batchSize_"
+
nrOutput
,
1
);
try
{
if
(
partitioner
.
equals
(
FieldsPartitioner
.
class
))
{
int
keyPosition
=
taskConfiguration
.
getInteger
(
"partitionerIntParam_"
+
nrOutput
,
1
);
batchsizes_f
.
add
(
batchSize
);
// TODO:force one partitioning field
keyPosition
=
taskConfiguration
.
getInteger
(
"partitionerIntParam_"
+
nrOutput
,
1
);
partitioners
.
add
(
partitioner
.
getConstructor
(
int
.
class
).
newInstance
(
keyPosition
));
}
else
{
batchsizes_s
.
add
(
batchSize
);
partitioners
.
add
(
partitioner
.
newInstance
());
}
if
(
log
.
isTraceEnabled
())
{
...
...
flink-addons/flink-streaming/src/main/java/eu/stratosphere/streaming/util/TestDataUtil.java
已删除
100644 → 0
浏览文件 @
7e7051b3
package
eu.stratosphere.streaming.util
;
import
java.io.IOException
;
import
java.io.File
;
public
class
TestDataUtil
{
public
static
void
downloadIfNotExists
(
String
fileName
)
{
String
testDataDir
=
""
;
File
file
=
new
File
(
testDataDir
+
fileName
);
String
testRepoUrl
=
"info.ilab.sztaki.hu/~mbalassi/flink-streaming/testdata/"
;
if
(
file
.
exists
()){
System
.
out
.
println
(
fileName
+
" already exists"
);
}
else
{
System
.
out
.
println
(
"downloading "
+
fileName
);
try
{
String
myCommand
=
"wget -O "
+
testDataDir
+
fileName
+
" "
+
testRepoUrl
+
fileName
;
System
.
out
.
println
(
myCommand
);
Runtime
.
getRuntime
().
exec
(
myCommand
);
}
catch
(
IOException
e
)
{
// TODO Auto-generated catch block
e
.
printStackTrace
();
}
}
}
}
flink-addons/flink-streaming/src/test/resources/testdata/hamlet.txt
0 → 100644
浏览文件 @
84759dad
此差异已折叠。
点击以展开。
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