From owner-freebsd-stable Fri Aug 20 12:21: 6 1999 Delivered-To: freebsd-stable@freebsd.org Received: from salmon.maths.tcd.ie (salmon.maths.tcd.ie [134.226.81.11]) by hub.freebsd.org (Postfix) with SMTP id 2B10714CA1 for ; Fri, 20 Aug 1999 12:21:02 -0700 (PDT) (envelope-from dwmalone@maths.tcd.ie) Received: from lanczos.maths.tcd.ie by salmon.maths.tcd.ie with SMTP id ; 20 Aug 1999 20:18:29 +0100 (BST) Date: Fri, 20 Aug 1999 20:18:27 +0100 From: David Malone To: freebsd-stable@freebsd.org Subject: Re: vm_fault: pager read error on NFS filesystems. Message-ID: <19990820201827.A22891@lanczos.maths.tcd.ie> References: <199908171256.aa44534@salmon.maths.tcd.ie> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.95.6i In-Reply-To: <199908171256.aa44534@salmon.maths.tcd.ie>; from David Malone on Tue, Aug 17, 1999 at 12:56:17PM +0100 Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On Tue, Aug 17, 1999 at 12:56:17PM +0100, David Malone wrote: > When a user deletes/changes a running executable over NFS it results > in lots of "vm_fault: pager read error" messages. However, the > program seems to keep running indefinitely, and logging messages. > Someone running a parrallel program recompiled and added 184888 > lines to /var/log/messages in a little over an hour. Following up my own message on this. On two machines on which we had a "vm_fault: pager read error" problem init ended up stuck in state vmopar while reaping one of the processes! Eventually the machine became overwhelemed by Zombies (Sounds very "Night of the Living Dead"), and we had to reboot. If it happens again I'll try to get a dump. I do have the output of ps for a stuck machine if anyone wants to see it, but basically a process whose image was changed overs NFS is the lowest numbered zombie and there are loads of processes waiting for init to reap them. David. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message