[OpenAFS-devel] Updated redhat workaround patch

[Derrick J Brashear]

On Tue, 22 Oct 2002, Hartmut Reuter wrote:

> Derrick J Brashear wrote:
>
> > We *may* need:
> > -rx performance enhancements. nobody has yet quantified that it's really
> > rx and not a client or server issue, but i suspect what Hartmut has
> > pointed at indicates a direction: SMP linux kernel on UP machine performs
> > better.
>
> I must admit this was not an rx-problem, but for some reason with the
> SMP kernel the network interface came up full duplex and with the single
> processor kernel only half duplex!. But, anyway, it seems other
> protocols are less sensitive to such misconfigurations: when I mounted
> AFS via NFS on this machine I got much better performance than with the
> AFS-client. There seems to be more bi-directional traffic with AFS than
> with NFS.

Not a huge shock, really, though. If it's misconfiguration it's not really
an issue we should be worrying overly about, but there are still other
complaints of Rx performance about, none of which have been particularly
well quantified.