From owner-freebsd-net@FreeBSD.ORG Fri Apr 27 19:41:45 2012 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id EE076106566B; Fri, 27 Apr 2012 19:41:45 +0000 (UTC) (envelope-from seanbru@yahoo-inc.com) Received: from mrout3.yahoo.com (mrout3.yahoo.com [216.145.54.173]) by mx1.freebsd.org (Postfix) with ESMTP id D147F8FC15; Fri, 27 Apr 2012 19:41:45 +0000 (UTC) Received: from [IPv6:::1] (proxy7.corp.yahoo.com [216.145.48.98]) by mrout3.yahoo.com (8.14.4/8.14.4/y.out) with ESMTP id q3RJTAdB060431; Fri, 27 Apr 2012 12:29:10 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=yahoo-inc.com; s=cobra; t=1335554950; bh=CJm6q0dNCAH0muvvEqoyugl/eTW4Lx5xDFXElewUyig=; h=Subject:From:To:Cc:In-Reply-To:References:Content-Type:Date: Message-ID:Mime-Version:Content-Transfer-Encoding; b=JDzjjpeOgEX56oCrzt8a4Q2b4FUpdA4MHdgGNVl9+107xdLCGfb5Y0o4RStERoQM8 YIG5IArxUGQDSNDxNarcwx8TU5SHzIPBHfs0wXGj3uwXRlC4c5H8JKl02NXv+6iRzb QZUMtg8qIeqFBiPeeKR5uHUo3aofyhkJ45j6Ae/4= From: Sean Bruno To: Juli Mallett In-Reply-To: References: <1335463643.2727.10.camel@powernoodle-l7.corp.yahoo.com> Content-Type: text/plain; charset="UTF-8" Date: Fri, 27 Apr 2012 12:29:10 -0700 Message-ID: <1335554950.9324.3.camel@powernoodle-l7.corp.yahoo.com> Mime-Version: 1.0 X-Mailer: Evolution 2.32.1 FreeBSD GNOME Team Port Content-Transfer-Encoding: 7bit Cc: "freebsd-net@freebsd.org" Subject: Re: igb(4) at peak in big purple X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 Apr 2012 19:41:46 -0000 On Thu, 2012-04-26 at 11:13 -0700, Juli Mallett wrote: > Queue splitting in Intel cards is done using a hash of protocol > headers, so this is expected behavior. This also helps with TCP and > UDP performance, in terms of keeping packets for the same protocol > control block on the same core, but for other applications it's not > ideal. If your application does not require that kind of locality, > there are things that can be done in the driver to make it easier to > balance packets between all queues about-evenly. Oh? :-) What should I be looking at to balance more evenly? sean