On Thu, 23 Sep 2004 22:00:18 +0100, Steve Woodford <scw@netbsd.org> wrote:
> 
> 
> On Thursday 23 September 2004 08:43, matthew green wrote:
> > my ultra10/440 experienced the sleep forever bug twice a couple of
> > weeks ago.  it happens on any sparc64 box.  it seems to be more
> > likely to occur if the disk and network are busy (eg, both the
> > above happened when i started writing and read heavily over NFS
> > at the same time.)
> 
> Just on a whim, can someone try out the attached patch to
> sys/arch/sparc64/include/psl.h to see if it cures the sleep forever
> bug?
> 
> There's a chance that gcc is reordering instructions around some spl*
> calls. The patch should address this.

Well, the problem is, I haven't found a way to trigger the bug. Other
people have stated that heavy network/disk IO seem to cause it, but
yesterday I threw a gig and a half over my network to my Ultra 5, over
FTP then over NFS, and it handled it just fine (although NFS was about
25% slower than FTP, obviously...)

Once I get my main workstation back up (its AGP slot (or video card)
died yesterday when putting in a faster cpu) I'll be happy to do more
testing, but for now the only machines I have running are my Ultra 1
which is doing NAT, and my mother's dell windows XP box. (I've got a
sparcbook 3gx going in my room, but 10baseT/HDX is hardly enough for
testing network speeds on a 100mbit lan...)


-- 
Sean