From owner-freebsd-current@FreeBSD.ORG Fri Nov 16 01:08:20 2007 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 C293116A41A for ; Fri, 16 Nov 2007 01:08:20 +0000 (UTC) (envelope-from kip.macy@gmail.com) Received: from rn-out-0102.google.com (rn-out-0910.google.com [64.233.170.189]) by mx1.freebsd.org (Postfix) with ESMTP id 6B18313C46B for ; Fri, 16 Nov 2007 01:08:20 +0000 (UTC) (envelope-from kip.macy@gmail.com) Received: by rn-out-0102.google.com with SMTP id s42so618708rnb for ; Thu, 15 Nov 2007 17:08:19 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=beta; h=domainkey-signature:received:received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=496dyub4Ghj/Qlbkn30ZGJcnzZv0swD5zFiCysx3qiw=; b=BFXvluDqgQUhvdkRPh70hPc8gJSSaUWPeq0mLLfNC4NJXKIT8+2pdkO/A/3RXqK4CR6/ZtEYZLSd5LkRbdDrRL+5scJOkhJmrqxqx0lDJMH1bu6vfgURh7QC+pjX+mPXcMfqwdMV9pCBf2P/yUK90MAqI2Z/6h7JVEhUPvgS0wo= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=KUPOHVGcaZXpNrf76CnLEXJbzb4xa3CxAi7gJE4S4zQNA0H8SqiX6G8IqFGpyAiQKTXKl/zUVnY+0NXuMcUN1leK7X6TP8YIX039VpH/v/Ez0jMbMJwXSA1OiUV0QSPpFJZW1EmsDDKjHCbkDSWnbSJyMyn6MSJUTPy1peDLs8c= Received: by 10.142.240.9 with SMTP id n9mr481838wfh.1195175298759; Thu, 15 Nov 2007 17:08:18 -0800 (PST) Received: by 10.142.230.18 with HTTP; Thu, 15 Nov 2007 17:08:18 -0800 (PST) Message-ID: Date: Thu, 15 Nov 2007 17:08:18 -0800 From: "Kip Macy" To: "Jack Vogel" In-Reply-To: <2a41acea0711151625q5a994cf3ja0d5f14b0670ca3@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <200711151729.lAFHTbiq024351@ambrisko.com> <473CE2B9.8010201@freebsd.org> <2a41acea0711151625q5a994cf3ja0d5f14b0670ca3@mail.gmail.com> Cc: Andre Oppermann , freebsd-net@freebsd.org, Scott Ullrich , freebsd-current@freebsd.org, Julian Elischer , "Wilkinson, Alex" Subject: Re: I/OAT ... Coming Soon ? 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: Fri, 16 Nov 2007 01:08:20 -0000 On Nov 15, 2007 4:25 PM, Jack Vogel wrote: > On Nov 15, 2007 4:22 PM, Andre Oppermann wrote: > > > > Scott Ullrich wrote: > > > On 11/15/07, Doug Ambrisko wrote: > > >> Hmm, I forgot about the 2970 which are AMD based. Can you check the > > >> BIOS to see if there is an option to turn it on? I think this is an > > >> Intel feature. AMD might have something close? We have one 2970 > > >> that we've played with a little but not much. I can't say for sure > > >> if it has it. > > > > > > Right you are. As of BIOS 1.2.2 I do not see a I/OAT option. Guess > > > I will need to pick up a different server as we are interested in what > > > kind of packet forwarding rate increase that this feature might bring > > > on a heavily loaded firewall. > > > > Not much. Unless your firewall is in usermode. Otherwise the data > > stays in the kernel and I/OAT is of not help as no copying happens. > > Your CPU is probably spending half of its clock cycles waiting on > > cache misses from newly arrived packets. Some Intel chipset integrated > > gige ports have a cache prefetch feature (duno whether our driver > > supports it) that would help quite a bit for your case. > > What might help this is multiqueue support on the receive AND send, > and stack support for the same. Not sure what the stack changes > would look like, but I know there's interest in this sort of thing, so > naturally I'd be into it :) I have support for this already in my ethng branch. I'll be adding support for zero-copy send and receive for TOE to my toestack branch as soon as I feel better :-(. It would probably not be that hard to generalize it to I/OAT. -Kip