From owner-freebsd-arch@FreeBSD.ORG Wed Jul 16 12:14:11 2014 Return-Path: Delivered-To: freebsd-arch@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 668B4BB for ; Wed, 16 Jul 2014 12:14:11 +0000 (UTC) Received: from zxy.spb.ru (zxy.spb.ru [195.70.199.98]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 21F8F20FE for ; Wed, 16 Jul 2014 12:14:10 +0000 (UTC) Received: from slw by zxy.spb.ru with local (Exim 4.82 (FreeBSD)) (envelope-from ) id 1X7O63-000Hfn-JL for freebsd-arch@freebsd.org; Wed, 16 Jul 2014 16:14:07 +0400 Date: Wed, 16 Jul 2014 16:14:07 +0400 From: Slawa Olhovchenkov To: freebsd-arch@freebsd.org Subject: Re: ixgbe and igb - how many queues? Message-ID: <20140716121407.GA67137@zxy.spb.ru> References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.23 (2014-03-12) X-SA-Exim-Connect-IP: X-SA-Exim-Mail-From: slw@zxy.spb.ru X-SA-Exim-Scanned: No (on zxy.spb.ru); SAEximRunCond expanded to false X-BeenThere: freebsd-arch@freebsd.org X-Mailman-Version: 2.1.18 Precedence: list List-Id: Discussion related to FreeBSD architecture List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 16 Jul 2014 12:14:11 -0000 On Tue, Jul 15, 2014 at 03:52:42PM -0700, Adrian Chadd wrote: > How many queues does the ixgbe and igb hardware support? > > The documentation reflects many more transmit and receive queues than > the 8 currently auto-configured. > > For RSS configuration I'd like to expand it out to the 16 that I > _think_ the hardware supports, but I'd like some confirmation that the > documentation mostly reflects the reality out there and I wouldn't be > breaking things on other peoples obscure/onboard/laptop/etc intel > platforms. I am configure ixgbe queues count to half of cores (all cores of one chip). Other chip fully occupied by nginx. Now I am read http://sigops.org/sosp/sosp13/papers/p33-david.pdf and wish try more optimize solution with fully locale memory reservation.