graphite-dev team mailing list archive

[Brian Hatfield <question216675@xxxxxxxxxxxxxxxxxxxxx>]

Question #216675 on Graphite changed:
https://answers.launchpad.net/graphite/+question/216675

    Status: Open => Answered

Brian Hatfield proposed the following answer:
David,

Some bullet-point thoughts:

   - You can try adjusting the IO Scheduler on your boxes to determine if
   that helps prevent one cache from starving the others
   - You can try reducing the size of your caches to ensure that the caches
   attempt to write smaller chunks more frequently.
   - You can turn on the "WHISPER_AUTOFLUSH" option to see if you're
   hitting PDFlush barriers that are causing your system to have spiky IO and
   never recover

But ultimately,

   - You probably have more IO than your system can keep up with.
      - SSDs would help, but be aware that graphite is the worst-case
      pattern for SSD durability
      - Perhaps consider scaling-out your hosts further.


On Thu, Dec 13, 2012 at 1:20 AM, David Gillies <
question216675@xxxxxxxxxxxxxxxxxxxxx> wrote:

> Question #216675 on Graphite changed:
> https://answers.launchpad.net/graphite/+question/216675
>
> David Gillies gave more information on the question:
> And here's a screenshot of the carbon-caches and the IO that one of them
> is gobbling up:
>
> http://imgur.com/R32Yd
>
> --
> You received this question notification because you are a member of
> graphite-dev, which is an answer contact for Graphite.
>
> _______________________________________________
> Mailing list: https://launchpad.net/~graphite-dev
> Post to     : graphite-dev@xxxxxxxxxxxxxxxxxxx
> Unsubscribe : https://launchpad.net/~graphite-dev
> More help   : https://help.launchpad.net/ListHelp
>

-- 
You received this question notification because you are a member of
graphite-dev, which is an answer contact for Graphite.