Date: Fri, 16 Aug 2002 11:50:03 -0700 (PDT) From: Nate Lawson <nate@root.org> To: freebsd-bugs@FreeBSD.org Subject: Re: kern/37043: Latest stable causes SCSI bus freeze on sym0 when running SMP Message-ID: <200208161850.g7GIo3dp047717@freefall.freebsd.org>
next in thread | raw e-mail | index | archive | help
The following reply was made to PR kern/37043; it has been noted by GNATS.
From: Nate Lawson <nate@root.org>
To: freebsd-gnats-submit@FreeBSD.org
Cc:
Subject: Re: kern/37043: Latest stable causes SCSI bus freeze on sym0 when
running SMP
Date: Fri, 16 Aug 2002 11:41:41 -0700 (PDT)
Followup directly from user, resent.
---------- Forwarded message ----------
Date: Fri, 16 Aug 2002 10:40:44 +0100
From: Pete French <pfrench@firstcallgroup.co.uk>
To: freebsd-bugs@FreeBSD.org, holger.kipp@alogis.com, njl@FreeBSD.org,
webadmin@firstcallgroup.co.uk
Subject: Re: kern/37043: Latest stable causes SCSI bus freeze on sym0 when
running SMP
[note to Holger - I've copied you in because this is the same problem
you were having with the fxp0 hangs, this is in relation to my original PR]
> Synopsis: Latest stable causes SCSI bus freeze on sym0 when running SMP
> Are you still having trouble? This sounds like an SMP problem.
> http://www.freebsd.org/cgi/query-pr.cgi?pr=37043
There was a discussion on -STABLE about this. The cause of the
hanging was identified to sym0 stopping servicing interrupts. The author of
that driver gave us a patch to detect this and poll for interrupts which
showed up the problem. I dont know if tats been commited or not, but it
was always more of a workaround than a fix - polling a SCSI interface because
the interrupt servicing has died under suspicious circumstances is hardly
ideal after all :-) (though the patch was extremely welcome as it did make
the machine usable again)
More investigation showed that the problem only occurs when interrupts are
shared on the machine - several other people had the same problem sharing
interrupts between ether cards and scsi cards. In my case the interrupt
was shared with the ata interface. The Compaq bios does not let me fix
this, but as I do not have any ATA devices I simply removed the ata driver
from the kernel.
This appears to have fixed the problem for me.
Unsure what conclusions to draw - consensus seems to be that there is some
problem with shared interrupts (as opposed to the sym0 driver) which only
manifest themselves on an SMP system. Thats about as much information as I
can give you I'm afraid. The best other person to talk to about this would
be holger.kipp@alogis.com who put in most of the effort at finding a fix
for this. I have copied him in on this reply.
cheers,
-pete french.
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-bugs" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200208161850.g7GIo3dp047717>