From owner-freebsd-hackers@FreeBSD.ORG Thu Jan 17 23:11:34 2013 Return-Path: Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by hub.freebsd.org (Postfix) with ESMTP id 911181E7; Thu, 17 Jan 2013 23:11:34 +0000 (UTC) (envelope-from Devin.Teske@fisglobal.com) Received: from mx1.fisglobal.com (mx1.fisglobal.com [199.200.24.190]) by mx1.freebsd.org (Postfix) with ESMTP id 5DA23B6D; Thu, 17 Jan 2013 23:11:34 +0000 (UTC) Received: from smtp.fisglobal.com ([10.132.206.16]) by ltcfislmsgpa06.fnfis.com (8.14.5/8.14.5) with ESMTP id r0HNBXqK006787 (version=TLSv1/SSLv3 cipher=AES128-SHA bits=128 verify=NOT); Thu, 17 Jan 2013 17:11:33 -0600 Received: from dtwin (10.14.152.22) by smtp.fisglobal.com (10.132.206.16) with Microsoft SMTP Server (TLS) id 14.2.309.2; Thu, 17 Jan 2013 17:11:29 -0600 From: Sender: Devin Teske To: "'Damien Fleuriot'" , "'Devin Teske'" References: <9A20C472-593A-4AAB-A0C0-FE6375011DAD@fisglobal.com> <201301171103.41013.jhb@freebsd.org> <796BC3D0-522A-4E1E-8BC6-96741D96E0A4@fisglobal.com> <259B53A09C4141E384BBA78217DD2BBD@multiplay.co.uk> <39477686-B5CC-439B-82A8-EEECBE358A9F@my.gd> In-Reply-To: <39477686-B5CC-439B-82A8-EEECBE358A9F@my.gd> Subject: RE: disadvantages of running 8.3 kernel on freebsd 8.2 system Date: Thu, 17 Jan 2013 15:11:28 -0800 Message-ID: <0bbf01cdf507$fddd7e20$f9987a60$@freebsd.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-Mailer: Microsoft Outlook 14.0 Thread-Index: AQG17F+kvLKaGGKXIYo9KMIouDrtrgFs29LrAqoL0fECPIraMwFae7ZjAjia+0EB63lyHZgfpf3w Content-Language: en-us X-Originating-IP: [10.14.152.22] X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:5.9.8327, 1.0.431, 0.0.0000 definitions=2013-01-17_09:2013-01-17,2013-01-17,1970-01-01 signatures=0 Cc: =?UTF-8?Q?'Ali_Okan_Y=C3=9CKSEL'?= , freebsd-hackers@freebsd.org, 'Devin Teske' , 'Steven Hartland' X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 17 Jan 2013 23:11:34 -0000 > -----Original Message----- > From: Damien Fleuriot [mailto:ml@my.gd] > Sent: Thursday, January 17, 2013 2:54 PM > To: Devin Teske > Cc: Steven Hartland; freebsd-hackers@freebsd.org; Devin Teske; Ali Okan > Y=C3=9CKSEL > Subject: Re: disadvantages of running 8.3 kernel on freebsd 8.2 system >=20 >=20 > On 17 Jan 2013, at 20:27, Devin Teske wrote: >=20 > > > > On Jan 17, 2013, at 11:14 AM, Steven Hartland wrote: > > > >> ----- Original Message ----- From: "Devin Teske" > >>> You're the perfect person to help us figure out why when we: > >>> > >>> 1. back-port mfi(4) from stable/8 into releng/8.3 (8.3-RELEASE-p5 at = the time > of back-port) > >>> > >>> 2. Succeed in getting 8.3 to boot on Thunderbolt card > >>> > >>> 3. mfiutil produces Inappropriate ioctl for device > >>> > >>> Even after=E2=80=A6 > >>> > >>> 4. Recompiling mfiutil from stable/8 (albeit in a releng/8.3 build en= vironment > -- back ported headers applied for new macros even) > >>> > >>> Any hints on where to go next to restore mfiutil access? > >> > >> You also need to backport mfiutil too. > >> > >> I have a patch set for 8.3 which include latest mfi driver, mfiutil and > >> a large set of mfi driver fixes, even head has some rather serious iss= ues > >> although mainly around error handling on tbolt cards. > >> > >> We're running this in production so believe its a good stable set. > >> > >> If you would like the patch set just let me know. > >> > > > > I can't resist when you combine words like "production" and "8.3" (smil= es) > > >=20 > ? >=20 > Are you saying 8.3 isn't production worthy ? With the right hardware, yes, that's what we're experiencing with latent ha= rdware that we've been tasked with benchmarking. > Works like a charm here for us. 50+ boxes running 8.x, most of which are = 8-stable. >=20 But I bet you're not sitting 88 units of Thunderbolt cards that don't work = in 8.3. 8.3 is also exhibiting major problems with the igb-based NICs on those same= 88 units. > No offence meant, but I'd take 8.3 over 9.x any day. > Any night too, for that matter. >=20 (smiles) > YMMV but PF + pfsync + carp (and some boxes with nginx or relayd on top) = is > pretty good for our workload on 8.3. I do indeed appreciate the vote of confidence. The hope is that when we get= through our mfi and igb problems that 8.3 will be a slammin' victory on th= is hardware (but until then, we're fighting the good fight). --=20 Devin _____________ The information contained in this message is proprietary and/or confidentia= l. If you are not the intended recipient, please: (i) delete the message an= d all copies; (ii) do not disclose, distribute or use the message in any ma= nner; and (iii) notify the sender immediately. In addition, please be aware= that any message addressed to our domain is subject to archiving and revie= w by persons other than the intended recipient. Thank you.