Re: SUMMARY: Too many cfagents running. Was: Load problem with cfserv d

[David E. Nelson]

Hi Mark,

Would it be prudent to delete all *db files whenever cfengine is restarted - 
say when a host reboots or from '/etc/init.d/cfengine restart'?

Thanks,
         /\/elson


On Thu, 17 Mar 2005, Mark Burgess wrote:

> On Thu, 2005-03-17 at 09:11 -0500, Baker, Darryl wrote:
> >  -----BEGIN PGP SIGNED MESSAGE-----
> > Hash: SHA1
> >
> > Finally got all the problems fix. First I installed the latest snap
> > shot and the load dropped. We had some scripts using ssh that were
> > setting up X window tunnels for no reason. We fixed those scripts and
> > the load dropped. I switched the configuration to "schedule = (
> > Min00_05 Min30_35 )" but left the rules saying Q1 and Q3. Nothing
> > changed. Then I had an inspiration and removed /var/cfengine/*db. The
> > load and the contention for the mutex dropped like a rock. Why?
> >
> > We believe that the main problem was that the kernel mutex we were
> > spinning on is part of /dev/random and that between all the ssh
> > clients this machine spawns and the cfengine connections that it was
> > just now being able to generate enough randomness and was blocking.
> > Then why would removing those files improve things
>
>
> This is almost certainly an internal roblem in berkeley DB, probably
> caused by having mixed versions or upgrades on your system. Sleepycat
> change internals quite often and that causes problems in compatability.
>
> That is why deleting the file with incorrect format will cure the
> problem. It will then not be incompatible.
>
> M
>
>
>
> _______________________________________________
> Help-cfengine mailing list
> Help-cfengine@gnu.org
> http://lists.gnu.org/mailman/listinfo/help-cfengine

--
~~ ** ~~  If you didn't learn anything when you broke it the 1st ~~ ** ~~
                        time, then break it again.