[Spread-users] Number of machines in a configuration

[Ryan Caudy]

Well, the limit isn't all that hard in terms of what the code can
support, in general.  You should just need to change a few things (I'm
not sure of all of them, but MAX_PROCS_RING is probably the most
important one).  However, the real limitation is the increase in token
latency this might bring.  You may have to tweak the membership.c
timeouts in order to allow your network to work with a few hundred
members.  Also, the latency to deliver many message types will be
increased proportionally to the number of daemons in your ring.

Cheers,
Ryan

On Fri, 30 Jul 2004 19:01:45 -0400, J C Lawrence <claw at kanga.nu> wrote:
> 
> How hard is the limit of 128 machines in a configuration?
> 
> I'm looking at an application where in extreme cases the total number of
> systems could be in the small thousands, typical deployments would be in
> the dozens and not-uncommon large deployments would be in the small
> hundreds...and Spread is awfully appealing...
> 
> --
> J C Lawrence
> ---------(*)                Satan, oscillate my metallic sonatas.
> claw at kanga.nu               He lived as a devil, eh?
> http://www.kanga.nu/~claw/  Evil is a name of a foeman, as I live.
> 
> _______________________________________________
> Spread-users mailing list
> Spread-users at lists.spread.org
> http://lists.spread.org/mailman/listinfo/spread-users
> 


-- 
---------------------------------------------------------------------
Ryan W. Caudy
<rcaudy at gmail.com>
---------------------------------------------------------------------
Bloomberg L.P.
<rcaudy1 at bloomberg.net>
---------------------------------------------------------------------
[Alumnus]
<caudy at cnds.jhu.edu>         
Center for Networking and Distributed Systems
Department of Computer Science
Johns Hopkins University          
---------------------------------------------------------------------