[Linux-cluster] Load peaks - caused by the cluster?

[Lon Hohberger]

On Mon, Aug 13, 2007 at 12:07:04PM +0300, Janne Peltonen wrote:
> 
> Next, I think I'm going to put an exit 0 to the status checks of ip.sh
> (and see if the elfs go away). Then I'm going to start wondering if the
> cluster'd notice our server room falling apart... ;)

There are certainly plenty of exec()s in ip.sh.

> Any suggestions? At this point, I'm not any more even certain whether
> the problem lies within the cluster. On the other hand, since I see no
> difference at the process level during peak and no-peak time, the
> difference must (as far as I understand) be inside kernel. So it can't
> be my application. So it must be the cluster, mustn't it?


One other thing you could do is spread out the check intervals for
resources.  For example:

  <service name="test">
   <fs name="foo" device="..." ...>
      <action name="status" depth="*" interval="3600" />
   </fs>
  </service>

If you do find that it's ip.sh, note that in your bz about fs.sh
actually.

I don't understand why it happens in 11-hour cycles though.

-- 
Lon Hohberger - Software Engineer - Red Hat, Inc.