From owner-freebsd-net@freebsd.org Wed Aug 19 07:42:25 2015 Return-Path: Delivered-To: freebsd-net@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 019E09BDAF2; Wed, 19 Aug 2015 07:42:25 +0000 (UTC) (envelope-from pyunyh@gmail.com) Received: from mail-pa0-x22d.google.com (mail-pa0-x22d.google.com [IPv6:2607:f8b0:400e:c03::22d]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id C08CBE09; Wed, 19 Aug 2015 07:42:24 +0000 (UTC) (envelope-from pyunyh@gmail.com) Received: by paccq16 with SMTP id cq16so108134730pac.1; Wed, 19 Aug 2015 00:42:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=from:date:to:cc:subject:message-id:reply-to:references:mime-version :content-type:content-disposition:in-reply-to:user-agent; bh=S0ZZmoyRQiijWzna4W8TD4lopx6A6yFnDneAQwWxdZ0=; b=c6MrsZlVkTXk65TXNgwoj0qpu1Vn8yZQi7Iwh5AuPlHY12Fvjt+lc3qdrCzcBX5Z75 V8HHCQDe4XVxqluirLR3sOsREh5CITl1IaCdCmr6dQrmQDxRqkt+y5OPBYZWReMLyjq+ 7vCUP14XLg5z7GzZvx1+uZFQg+PyTUEGWTh1zQ85zzAxlhUn2xKURMlH6xcrhu9ku+oe +OE4qqeTy1FjqtgPkNc8H8jie6D2affav8JZFODIwK80OWG3LIpdDI0FFmFWckv0yt+L WuebY3qhtVuxBbzn+PjEn3tOzO8+0LyWw/e1/l0TGCWmjAqoG7s/4YEuB4gI0GjDIrDn pSVQ== X-Received: by 10.69.0.166 with SMTP id az6mr21689907pbd.168.1439970144299; Wed, 19 Aug 2015 00:42:24 -0700 (PDT) Received: from pyunyh@gmail.com ([106.247.248.2]) by smtp.gmail.com with ESMTPSA id r1sm2419947pdm.31.2015.08.19.00.42.19 (version=TLSv1 cipher=RC4-SHA bits=128/128); Wed, 19 Aug 2015 00:42:23 -0700 (PDT) From: Yonghyeon PYUN X-Google-Original-From: "Yonghyeon PYUN" Received: by pyunyh@gmail.com (sSMTP sendmail emulation); Wed, 19 Aug 2015 16:42:12 +0900 Date: Wed, 19 Aug 2015 16:42:12 +0900 To: Hans Petter Selasky Cc: Rick Macklem , Daniel Braniss , FreeBSD Net , Slawa Olhovchenkov , FreeBSD stable , Christopher Forgeron Subject: Re: ix(intel) vs mlxen(mellanox) 10Gb performance Message-ID: <20150819074212.GB964@michelle.fasterthan.com> Reply-To: pyunyh@gmail.com References: <1D52028A-B39F-4F9B-BD38-CB1D73BF5D56@cs.huji.ac.il> <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> <1325951625.25292515.1439934848268.JavaMail.zimbra@uoguelph.ca> <55D429A4.3010407@selasky.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <55D429A4.3010407@selasky.org> User-Agent: Mutt/1.4.2.3i X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 19 Aug 2015 07:42:25 -0000 On Wed, Aug 19, 2015 at 09:00:52AM +0200, Hans Petter Selasky wrote: > On 08/18/15 23:54, Rick Macklem wrote: > >Ouch! Yes, I now see that the code that counts the # of mbufs is before the > >code that adds the tcp/ip header mbuf. > > > >In my opinion, this should be fixed by setting if_hw_tsomaxsegcount to > >whatever > >the driver provides - 1. It is not the driver's responsibility to know if > >a tcp/ip > >header mbuf will be added and is a lot less confusing that expecting the > >driver > >author to know to subtract one. (I had mistakenly thought that > >tcp_output() had > >added the tc/ip header mbuf before the loop that counts mbufs in the list. > >Btw, > >this tcp/ip header mbuf also has leading space for the MAC layer header.) > > > > Hi Rick, > > Your question is good. With the Mellanox hardware we have separate > so-called inline data space for the TCP/IP headers, so if the TCP stack > subtracts something, then we would need to add something to the limit, > because then the scatter gather list is only used for the data part. > I think all drivers in tree don't subtract 1 for if_hw_tsomaxsegcount. Probably touching Mellanox driver would be simpler than fixing all other drivers in tree. > Maybe it can be controlled by some kind of flag, if all the three TSO > limits should include the TCP/IP/ethernet headers too. I'm pretty sure > we want both versions. > Hmm, I'm afraid it's already complex. Drivers have to tell almost the same information to both bus_dma(9) and network stack.