答复: Slow flink checkpoint

Posted by makeyang on
URL: http://deprecated-apache-flink-user-mailing-list-archive.369.s1.nabble.com/Slow-flink-checkpoint-tp18946p19537.html

Fabian:
    thanks for u replay.
    I have create a jira issue:
https://issues.apache.org/jira/browse/FLINK-9182?jql=project%20%3D%20FLINK%20AND%20issuetype%20%3D%20Improvement%20AND%20created%20%3E%3D%20-10m

   I'll pull the code ASAP.

MaKeyang

TIG.JD.COM

京东基础架构 tig.jd.com TIG官网

---

发件人: Fabian Hueske <[hidden email]>
发送时间: 2018年4月16日 16:21
收件人: makeyang
抄送: user; Aljoscha Krettek
主题: Re: Slow flink checkpoint

 

Hi everybody,

Thanks so much for looking into this issue and posting the detailed description of your approach.

As said before, improving the checkpointing performance for timers is a very important improvement for Flink.

I'm not familiar with the internals of the timer service checkpointing, but adding an add and delete version field and perform async checkpoints based on these fields seems like a good approach to me.

IIRC, Aljoscha (in CC) implemented the timer service and its checkpointing. He might have more comments.

I'd suggest to create a JIRA (everybody can do that) and repost the description of your approach there.

If you have the code ready, you can also open a PR and reference the JIRA.

Best, Fabian

2018-04-16 9:03 GMT+02:00 makeyang <[hidden email]>:

since flink forward SF has done.
can you guys give some minutes to take a look at this issue and give some
thoughts on it? help to review/comments on my desgin? or give us a design so
that I can help to implement it.

thanks a lot.

--
Sent from: http://apache-flink-user-mailing-list-archive.2336050.n4.nabble.com/