From owner-freebsd-current@FreeBSD.ORG Sat Dec 12 10:03:39 2009 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 79B6A106566C for ; Sat, 12 Dec 2009 10:03:39 +0000 (UTC) (envelope-from ltning@anduin.net) Received: from mail.anduin.net (mail.anduin.net [213.225.74.249]) by mx1.freebsd.org (Postfix) with ESMTP id 33E0E8FC0C for ; Sat, 12 Dec 2009 10:03:38 +0000 (UTC) Received: from [212.62.248.150] (helo=[192.168.2.110]) by mail.anduin.net with esmtpsa (TLSv1:AES128-SHA:128) (Exim 4.69 (FreeBSD)) (envelope-from ) id 1NJOp6-0004Zh-3J; Sat, 12 Dec 2009 11:03:36 +0100 Mime-Version: 1.0 (Apple Message framework v1077) Content-Type: text/plain; charset=iso-8859-1 From: =?iso-8859-1?Q?Eirik_=D8verby?= In-Reply-To: Date: Sat, 12 Dec 2009 11:03:35 +0100 Content-Transfer-Encoding: quoted-printable Message-Id: <22EC170C-2A92-40C6-9AA2-696742CBE64A@anduin.net> References: <20091129013026.GA1355@michelle.cdnetworks.com> <74BFE523-4BB3-4748-98BA-71FBD9829CD5@anduin.net> <34AD565D-814A-446A-B9CA-AC16DD762E1B@anduin.net> <18778B61-797C-4A38-94E6-AC6A2A453F17@anduin.net> To: Rick Macklem X-Mailer: Apple Mail (2.1077) Cc: freebsd-current@freebsd.org Subject: Re: FreeBSD 8.0 - network stack crashes? X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 12 Dec 2009 10:03:39 -0000 On 10. des. 2009, at 17.21, Rick Macklem wrote: >=20 >=20 > On Thu, 10 Dec 2009, Eirik =C3~Xverby wrote: >=20 >> Hi, >>=20 >> this applies to 8.0-RELEASE? >>=20 > It should. sys/rpc/svc_dg.c hasn't changed in a while. >=20 >> I'll try to test today. >>=20 > Thanks. I have no idea if it will help, but there was a case that = could > leak mbufs, if it ever occurs, that is fixed by this. It didn't seem to help by much, anyway. After a couple of backup runs = the mbuf cluster allocation had gone from ~4k to ~25k, and as I had = reverted the sysctl to default, it wedged right there. I'll have to go back to TCP mounts from the OpenBSD box again I guess ;) /Eirik > Good luck with it, rick No luck with it, unfortunately :) But thanks for trying. Any other = ideas? /Eirik=