Date: Fri, 2 May 2003 04:56:20 -0700 From: David Schultz <das@FreeBSD.ORG> To: Colin Faber <cfaber@fpsn.net> Cc: "freebsd-bugs@freebsd.org" <freebsd-bugs@FreeBSD.ORG> Subject: Re: Yet another swap_pager: indefinite wait buffer problem Message-ID: <20030502115620.GB46597@HAL9000.homeunix.com> In-Reply-To: <3EA55547.23050A6D@fpsn.net> References: <3EA55547.23050A6D@fpsn.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Apr 22, 2003, Colin Faber wrote: > Every once in a while my compaq proliant 800 with smart array 221 > raid controller will totally lock up, I've replaced everything in the > system including drives, cables, and raid card. I've read in the hand > book that this is caused by possibly one of the above but am beginning > to suspect that this is happening when ever large amounts of swap are > used. > > Has anyone else run into this problem with this configuration or am > I just dealing with a lemon of a machine here? > > The exact message I'm receiving: > > swap_pager: indefinite wait buffer: device #idad/0x2001, blkno 376, > size: 4096 Alan Cox has done quite a bit in the area of page queue locking in the last few months, so there could be a bug there. Or it could be a problem with the buffer cache or a device driver. It would be helpful if you could kill the kernel to get a crash dump, then print *bp and *mreq from kgdb.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030502115620.GB46597>