[OpenAFS-devel] AFS goes to WAIT on alpha_dux40

[Atro Tossavainen]

Harald,

> V4.0F is not the freshest. We have mostly V5.0A.

I know.  If you think upgrading the OS would perhaps help solve the
problem, I suppose that wouldn't be impossible.

> I'm not that fluent with Alpha models: Multi or single CPU?

Both XP1000 and the PWS500au are single CPU.

> Do you really need to serve NFS from your AFS client WS? I'd rather not
> and eliminate one more possibe problem.

We do indeed, at least up until such time as all of the NFS shares
have been eliminated from the two computers in question, which (due
to internal politics) is even hairier :(

For the record, we have been successfully running AFS 3.6 GA (2.0) on
both of them from Aug 2000 until late 2003, when these problems started,
and have been serving NFS on both of them at the same time.  There were
never any problems like this until now.  We've had both memcaches and
disk caches on the clients depending on whether a spare partition has
been available.

> You can debug this with syscall traces and the like. I'm curious, but
> this seems extremely hairy. Do you need the 64 addr space or can you
> replace the Alpha with a PC? That might be more efficient.

We've got plenty of peecees, but we want to be able to use all of our
existing hardware for as long as the hardware is functional and useful
to any degree.

-- 
Atro Tossavainen (Mr.)               / The Institute of Biotechnology at
Systems Analyst, Techno-Amish &     / the University of Helsinki, Finland,
+358-9-19158939  UNIX Dinosaur     / employs me, but my opinions are my own.
< URL : http : / / www . helsinki . fi / %7E atossava / > NO FILE ATTACHMENTS