[OpenAFS] Re: Performance issues

Andrew Deason adeason@sinenomine.net
Wed, 24 Aug 2011 10:43:58 -0500


On Wed, 24 Aug 2011 01:10:04 +0200
Jaap Winius <jwinius@umrk.nl> wrote:

> > ... I would guess that this has more to do with the bandwidth and
> > latency, but unless there are more dropped or reordered packets or
> > something, I'm not sure either way what we would see from the
> > OpenAFS fileserver point of view besides worse bandwidth/latency.
> 
> After both the fs and db servers were moved from the virtual hosts
> (and from behind the firewall and NAT) to the bare metal, we saw a
> marked improvement in local performance. For example, certain
> applications, particularly the Iceweasel (Firefox) browser, only
> became usable after the fs server was moved. But as I said, after the
> changes we've seen no performance improvement for when the user
> volumes are accessed remotely.

Yes... and that suggests a change in bandwidth and/or latency (or
packets getting dropped, getting reordered, etc etc) Whether that is
caused by the number of firewalls or whatever or by the characteristics
of the connection... to OpenAFS it is the same.

What I mean is, this isn't OpenAFS specific. You can just measure the
differences in throughput and delays of UDP packets to see if there's
any differences in the setup. For the purposes of sustained throughput,
we have no idea what routers, firewalls, NATs, etc that we're going
through, so it doesn't make a difference to us.

-- 
Andrew Deason
adeason@sinenomine.net