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.

Hartmut
-----------------------------------------------------------------
Hartmut Reuter e-mail [EMAIL PROTECTED]
phone +49-89-3299-1328
RZG (Rechenzentrum Garching) fax +49-89-3299-1301
Computing Center of the Max-Planck-Gesellschaft (MPG) and the
Institut fuer Plasmaphysik (IPP)
-----------------------------------------------------------------

_______________________________________________
OpenAFS-devel mailing list
[EMAIL PROTECTED]
https://lists.openafs.org/mailman/listinfo/openafs-devel


Reply via email to