[Linux-HA] Question about limits around resources .
nozawat
nozawat at gmail.com
Sun Dec 12 22:08:38 MST 2010
Hi,
I sent a half-finished email. I'm sorry.
FYI,I dont simply that from my experience.
> 2 and 4 node clusters running 1.0.x should easily handle 200 resources or
so.
> Clusters running >= 1.1.4 should be able to go even higher.
12 and 16 node clusters not running from pm-1.0.x(12 * 16 = 192).
I think that many elements coil themselves.
I think that various elements intertwine with each other.
It is really important that I confirm it by oneself.
Regards,
Tomo
2010/12/9 Andrew Beekhof <andrew at beekhof.net>
> On Thu, Dec 9, 2010 at 9:06 AM, Alain.Moulle <Alain.Moulle at bull.net>
> wrote:
> > Hi,
> >
> > I wonder if there are some limits with Pacemaker in terms of :
> >
> > nb of resources (primitives, groups, clones etc.) in the whole HA
> > Cluster with 2 or 4 nodes ?
> >
> > nb of resources (primitives, groups, clones etc.) per node in a HA
> Cluster ?
>
> The limit is a factor of N * R, where N = number of nodes and R =
> number of resources.
> 2 and 4 node clusters running 1.0.x should easily handle 200 resources or
> so.
> Clusters running >= 1.1.4 should be able to go even higher.
> _______________________________________________
> Linux-HA mailing list
> Linux-HA at lists.linux-ha.org
> http://lists.linux-ha.org/mailman/listinfo/linux-ha
> See also: http://linux-ha.org/ReportingProblems
>
More information about the Linux-HA
mailing list