Date: Mon, 22 Sep 2003 10:07:19 +0100 From: David Malone <dwmalone@maths.tcd.ie> To: Aleksey Ovcharenko <alexovch@ic.kharkov.ua> Cc: stable@FreeBSD.ORG Subject: Re: 4.9 stability update Message-ID: <20030922090719.GA23435@walton.maths.tcd.ie> In-Reply-To: <200309221018.18036.alexovch@ic.kharkov.ua> References: <3F6A98F3.7080801@freebsd.org> <200309221018.18036.alexovch@ic.kharkov.ua>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Sep 22, 2003 at 10:18:18AM +0300, Aleksey Ovcharenko wrote: > Ok, how about dirhash problem http://www.freebsd.org/cgi/query-pr.cgi?pr=51016 This problem predates PAE in -stable, just in case there is any confusion. > It's still same even on 4.9-PRERELEASE. On high load with ~4k virtual users on > mail server with ufs_dirhash turned on it cause kernel panic. I remember looking at this for you before, and it looked tricky to resolve. It had many of the traits of a hardware problem or a general memory corruption problem. It wasn't clear to me if dirhash was the problem or just detecting it. Did I suggested running with "sysctl vfs.ufs.dirhash_docheck=1"? It might change the panic to be closer to when the corruption occurs. If you can give me access to the vmcore and debugging kernel you have, I can have another look, but I'm not optimistic. David.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030922090719.GA23435>