From owner-svn-src-all@freebsd.org Wed Jan 18 18:04:42 2017 Return-Path: Delivered-To: svn-src-all@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 AE4EECB65EF; Wed, 18 Jan 2017 18:04:42 +0000 (UTC) (envelope-from hps@selasky.org) Received: from mail.turbocat.net (turbocat.net [IPv6:2a01:4f8:c17:6c4b::2]) (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 744F0184B; Wed, 18 Jan 2017 18:04:42 +0000 (UTC) (envelope-from hps@selasky.org) Received: from hps2016.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 C12361FE025; Wed, 18 Jan 2017 19:04:22 +0100 (CET) Subject: Re: svn commit: r312379 - in head: lib/libc/sys sbin/ifconfig sys/conf sys/kern sys/modules/if_lagg sys/modules/if_vlan sys/net sys/netinet sys/netinet6 sys/sys To: Gleb Smirnoff References: <201701181331.v0IDVHWf048428@repo.freebsd.org> <20170118173132.GD2611@FreeBSD.org> Cc: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org, Meny Yossefi , Navdeep Parhar From: Hans Petter Selasky Message-ID: Date: Wed, 18 Jan 2017 19:04:05 +0100 User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:45.0) Gecko/20100101 Thunderbird/45.4.0 MIME-Version: 1.0 In-Reply-To: <20170118173132.GD2611@FreeBSD.org> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit X-BeenThere: svn-src-all@freebsd.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: "SVN commit messages for the entire src tree \(except for " user" and " projects" \)" List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 18 Jan 2017 18:04:42 -0000 On 01/18/17 18:31, Gleb Smirnoff wrote: > there were no production testing of the feature, > that will prove that the idea actually works. Hi Gleb, This feature has been tested small scale in production environments and it for sure saves CPU versus doing rate limiting all in software. Mellanox plans to checkin support for the mlx5en driver which starts using this feature soon and I believe np@ has similar plans for cxgbe. I'll reply to your other questions tomorrow. --HPS