From owner-freebsd-net@freebsd.org Fri Sep 30 13:37:30 2016 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 6BF67C02DFF for ; Fri, 30 Sep 2016 13:37:30 +0000 (UTC) (envelope-from hps@selasky.org) Received: from mail.turbocat.net (heidi.turbocat.net [88.198.202.214]) (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 33736BA7 for ; Fri, 30 Sep 2016 13:37:29 +0000 (UTC) (envelope-from hps@selasky.org) Received: from laptop015.home.selasky.org (unknown [62.141.129.119]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by mail.turbocat.net (Postfix) with ESMTPSA id DC37D1FE022 for ; Fri, 30 Sep 2016 15:37:20 +0200 (CEST) To: "freebsd-net@freebsd.org" From: Hans Petter Selasky Subject: [RFC] [D3687] SO_MAX_PACING_RATE and FreeBSD Message-ID: Date: Fri, 30 Sep 2016 15:42:13 +0200 User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:45.0) Gecko/20100101 Thunderbird/45.3.0 MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.23 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, 30 Sep 2016 13:37:30 -0000 Hi, After some time of discussions going forth and back I think there is a very good proposal for implementing support for the SO_MAX_PACING_RATE socket option at: https://reviews.freebsd.org/D3687 Since last time the solution was discussed there has been added RSS awareness to the internal APIs, to better utilize CPU offloading when applying rate limiting. By default, unless options RATELIMIT is defined, there are no functional changes in the current TCP/IP code. I'd like some people from the network group to have a fresh look at the patch and if everything is fine, be able to push something by end of October. At Mellanox we are currently doing final testing of the SO_MAX_PACING_RATE feature. --HPS