From owner-freebsd-current Wed Jan 21 04:01:47 1998 Return-Path: Received: (from daemon@localhost) by hub.freebsd.org (8.8.8/8.8.8) id EAA17929 for current-outgoing; Wed, 21 Jan 1998 04:01:47 -0800 (PST) (envelope-from owner-freebsd-current) Received: from dyson.iquest.net (dyson.iquest.net [198.70.144.127]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id EAA17924 for ; Wed, 21 Jan 1998 04:01:42 -0800 (PST) (envelope-from toor@dyson.iquest.net) Received: (from root@localhost) by dyson.iquest.net (8.8.8/8.8.8) id HAA00803; Wed, 21 Jan 1998 07:01:17 -0500 (EST) (envelope-from toor) Message-Id: <199801211201.HAA00803@dyson.iquest.net> Subject: Re: Panic while clustered I/O In-Reply-To: <19980121201543Z.kato@gneiss.eps.nagoya-u.ac.jp> from KATO Takenori at "Jan 21, 98 08:15:43 pm" To: kato@migmatite.eps.nagoya-u.ac.jp (KATO Takenori) Date: Wed, 21 Jan 1998 07:01:17 -0500 (EST) Cc: current@FreeBSD.ORG From: "John S. Dyson" Reply-To: dyson@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL32 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-current@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk KATO Takenori said: > Please help me. > > How to repeat: > mount_union foo /usr/obj > make world > > Workarround: disabling clustered I/O in ufs_readwrite.c :-(. > The VFS layering is being worked on aggressively right now. Hopefully, it will be more possible to fix the problem, after I get done with my part of the layering issues. PHK has started working on it, and I am working on the VFS/VM interface. Once we all get done with it, I think that it will be much easier to debug these problems. Note that the specific problem that you are seeing is likely partially due to the problems with (lack of) resource reservation. It appears that you are running out of bounce-buffers (obvious.) Even if you get rid of the use of bounces, there will still likely eventually be problems. Note that it appears that clustering is putting to much pressure on the bounce buffer code. You *might* try increasing the size of the bounce space, and see if things work better. Also, Justin is working on the new FreeBSD bus mgmt code. That also might be a component of a "real" fix. -- John | Never try to teach a pig to sing, dyson@freebsd.org | it just makes you look stupid, jdyson@nc.com | and it irritates the pig.