[jira] [Created] (FLINK-5892) Recover job state at the granularity of operator

MaGuowei created FLINK-5892: --- Summary: Recover job state at the granularity of operator Key: FLINK-5892 URL: https://issues.apache.org/jira/browse/FLINK-5892 Project: Flink Issue Type: New Feature

[jira] [Created] (FLINK-5222) Rename StateBackend interface to StateBinder

MaGuowei created FLINK-5222: --- Summary: Rename StateBackend interface to StateBinder Key: FLINK-5222 URL: https://issues.apache.org/jira/browse/FLINK-5222 Project: Flink Issue Type: Improvement

[jira] [Created] (FLINK-3628) ChainingOutput and CopyingChainingOutput setKeyContextElement1 is no use

MaGuowei created FLINK-3628: --- Summary: ChainingOutput and CopyingChainingOutput setKeyContextElement1 is no use Key: FLINK-3628 URL: https://issues.apache.org/jira/browse/FLINK-3628 Project: Flink

RE: A Question About Execution Schedule

Thanks Till! > Date: Wed, 19 Aug 2015 09:31:49 +0200 > Subject: Re: A Question About Execution Schedule > From: trohrm...@apache.org > To: dev@flink.apache.org > > Hi MaGuoWei, > > this is not a problem. If you look at the implementation of > SlotAllocationFuture.setFu

A Question About Execution Schedule

Hi,guysThere are some codes in scheduleForExecution Function in Execution.java: 1. SlotAllocationFuture future = scheduler.scheduleQueued(toSchedule); 2. future.setFutureAction(new SlotAllocationFutureAction() {..}) When scheduler finds some slot between line1 and line 2 the sc

RE: question about SlidingPreReducer.java

the reducer will be called > with the next element (else branch). > ​ > > On Thu, Jul 30, 2015 at 11:54 AM, MaGuoWei wrote: > > > hi till > > I mean the branch of the if statement is never execute. > > thanks > > > > 发自我的 iPhone > > > >

Re: question about SlidingPreReducer.java

hi till I mean the branch of the if statement is never execute. thanks 发自我的 iPhone > 在 2015年7月30日，下午5:51，Till Rohrmann 写道： > > Hi MaGuoWei, > > do you mean that the branch of the if statement (line 130) is never > executed? Or are you looking for an example which uses the

question about SlidingPreReducer.java

hi guysThere is a function updateCurrent() in this class(SlidingPreReducer).I think there is no chance to run the following code in this function:currentReduced = reducer.reduce(serializer.copy(currentReduced), element);Can any one give me a example that can run this code. (I have already see

streaming iteration

Hi,guysI am reading the code about streaming iteration.I find there is no StreamEdge the StreamIterationHead and StreamIterationTail.Why? Because the graph can't have any ring?Or any other concerns? thanks

RE: add some new api to the scheduler in the job manager

. > From: rmetz...@apache.org > Date: Mon, 27 Jul 2015 14:01:11 +0200 > Subject: Re: add some new api to the scheduler in the job manager > To: dev@flink.apache.org > > Hi MaGuoWei, > > would you like to have done automatically by Flink or based on some user > inpu

RE: add some new api to the scheduler in the job manager

0.9/setup/yarn_setup.html#run-a-single-flink-job-on-hadoop-yarn > > Cheers, > Aljoscha > > On Mon, 27 Jul 2015 at 03:51 MaGuoWei wrote: > > > hi guysFlink must take over all the resources all the time. That wastes > > resources sometime especially in the sharing cl

add some new api to the scheduler in the job manager

hi guysFlink must take over all the resources all the time. That wastes resources sometime especially in the sharing cluster.For example when using Flink on Yarn the resource can't be returned back to RM even if no graph is running.So I want to know: Is it possible to add some apis in the sche