Date: Wed, 28 Nov 2001 19:24:57 -0500 (EST) From: Andrew Gallatin <gallatin@cs.duke.edu> To: Paul Herman <pherman@frenchfries.net> Cc: FreeBSD Alpha <freebsd-alpha@FreeBSD.ORG> Message-ID: <15365.32857.392495.737510@grasshopper.cs.duke.edu> In-Reply-To: <200111282233.fASMXUA01849@tick.sc.omation.com> References: <200111282233.fASMXUA01849@tick.sc.omation.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Paul Herman writes: > Hi, > > My 4.4-RELEASE (alpha) paniced 4 times in a row today and all at > the same place. I don't know what to make of it, so I thought I'd > start here. > > It happens when I do a lot of NFS traffic (like "pkg_add > /nfs/mount/package.tgz") What is XentUna? Is that a trap for > unaligned access? If so, what does fxdr_unsigned() do, and why > would XentUna fail? Or does it not try to correct it? I do have > machdep.unaligned_fix=1 if that makes a difference. For a more complete response.. XentUna is the unaligned access trap entry point. Eg, where the PALcode jumps to when there's an unaligned access. All unaligned accesses in kernel mode are fatal, regardless of machdep.unaligned_fix settings. Can you characterize your environment a little more? What's the NFS server running? Are you running NFS over TCP or UDP? What mount size? Is it any file or access pattern that causes this, or just special ones? Can you get a tcpdump of the traffic that causes the crash (from the server side, obviously). There's definately a bug in the code. Perhaps we could work around it by altering your environment. At Duke, I had FreeBSD/alpha (4.0 -> 4.3) running NFSv3 over UDP against Tru64 4.0f, Solaris (2.5 -> 2.8), and FreeBSD/i386 (4.0 -> 4.3) NFS servers. I never saw this panic. I hope this helps some.. Drew To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?15365.32857.392495.737510>