From owner-freebsd-stable@freebsd.org Tue Aug 18 14:09:50 2015 Return-Path: Delivered-To: freebsd-stable@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 218D39BC532; Tue, 18 Aug 2015 14:09:50 +0000 (UTC) (envelope-from danny@cs.huji.ac.il) Received: from kabab.cs.huji.ac.il (kabab.cs.huji.ac.il [132.65.116.210]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C6EE6118; Tue, 18 Aug 2015 14:09:48 +0000 (UTC) (envelope-from danny@cs.huji.ac.il) Received: from chamsa.cs.huji.ac.il ([132.65.80.19]) by kabab.cs.huji.ac.il with esmtp id 1ZRhaA-000Ac9-LX; Tue, 18 Aug 2015 17:09:42 +0300 Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 8.2 \(2104\)) Subject: Re: ix(intel) vs mlxen(mellanox) 10Gb performance From: Daniel Braniss In-Reply-To: <55D333D6.5040102@selasky.org> Date: Tue, 18 Aug 2015 17:09:41 +0300 Cc: Rick Macklem , FreeBSD Net , Slawa Olhovchenkov , FreeBSD stable , Christopher Forgeron Content-Transfer-Encoding: quoted-printable Message-Id: <47EC9292-082C-4801-B52F-4BD6B8310F99@cs.huji.ac.il> References: <1D52028A-B39F-4F9B-BD38-CB1D73BF5D56@cs.huji.ac.il> <20150817094145.GB3158@zxy.spb.ru> <17871443-E105-4434-80B1-6939306A865F@cs.huji.ac.il> <473274181.23263108.1439814072514.JavaMail.zimbra@uoguelph.ca> <7F892C70-9C04-4468-9514-EDBFE75CF2C6@cs.huji.ac.il> <805850043.24018217.1439848150695.JavaMail.zimbra@uoguelph.ca> <9D8B0503-E8FA-43CA-88F0-01F184F84D9B@cs.huji.ac.il> <1721122651.24481798.1439902381663.JavaMail.zimbra@uoguelph.ca> <55D333D6.5040102@selasky.org> To: Hans Petter Selasky X-Mailer: Apple Mail (2.2104) X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 18 Aug 2015 14:09:50 -0000 sorry, it=E2=80=99s been a tough day, we had a major meltdown, caused by = a faulty gbic :-( anyways, could you tell me what to do? comment out, fix the off by one? the machine is not yet production. thanks, danny > On 18 Aug 2015, at 16:32, Hans Petter Selasky wrote: >=20 > On 08/18/15 14:53, Rick Macklem wrote: >> 2572 ifp->if_hw_tsomax =3D 65518; >>> >2573 ifp->if_hw_tsomaxsegcount =3D = IXGBE_82599_SCATTER; >>> >2574 ifp->if_hw_tsomaxsegsize =3D 2048; >=20 > Hi, >=20 > If IXGBE_82599_SCATTER is the maximum scatter/gather entries the = hardware can do, remember to subtract one fragment for the TCP/IP-header = mbuf! >=20 > I think there is an off-by-one here: >=20 > ifp->if_hw_tsomax =3D 65518; > ifp->if_hw_tsomaxsegcount =3D IXGBE_82599_SCATTER - 1; > ifp->if_hw_tsomaxsegsize =3D 2048; >=20 > Refer to: >=20 >> * >> * NOTE: The TSO limits only apply to the data payload part of >> * a TCP/IP packet. That means there is no need to subtract >> * space for ethernet-, vlan-, IP- or TCP- headers from the >> * TSO limits unless the hardware driver in question requires >> * so. >=20 > In sys/net/if_var.h >=20 > Thank you! >=20 > --HPS >=20