From owner-freebsd-net@freebsd.org Wed Jun 14 15:37:58 2017 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 7113BB94A5F for ; Wed, 14 Jun 2017 15:37:58 +0000 (UTC) (envelope-from mike@sentex.net) Received: from smarthost2.sentex.ca (smarthost2.sentex.ca [205.211.164.50]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (Client CN "smarthost.sentex.ca", Issuer "smarthost.sentex.ca" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 2A8E568A33; Wed, 14 Jun 2017 15:37:54 +0000 (UTC) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (lava.sentex.ca [IPv6:2607:f3e0:0:5::11]) by smarthost2.sentex.ca (8.15.2/8.15.2) with ESMTPS id v5EFKB8x060645 (version=TLSv1 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO); Wed, 14 Jun 2017 11:20:11 -0400 (EDT) (envelope-from mike@sentex.net) Received: from [192.168.43.26] (saphire3.sentex.ca [192.168.43.26]) by lava.sentex.ca (8.15.2/8.15.2) with ESMTP id v5EFK923085164; Wed, 14 Jun 2017 11:20:10 -0400 (EDT) (envelope-from mike@sentex.net) Subject: Re: state of packet forwarding in FreeBSD? To: John Jasen , FreeBSD Net References: From: Mike Tancsa Organization: Sentex Communications Message-ID: <5f2a5097-2fe5-7a21-6446-6018b55f0a68@sentex.net> Date: Wed, 14 Jun 2017 11:20:08 -0400 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.1.1 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 8bit X-Scanned-By: MIMEDefang 2.78 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: Wed, 14 Jun 2017 15:37:58 -0000 On 6/14/2017 10:48 AM, John Jasen wrote: > Our goal was to test whether or not FreeBSD currently is viable, as the > operating system platform for high speed routers and firewalls, in the > 40 to 100 GbE range. > > In our investigations, we tested 10.3, 11.0/-STABLE, -CURRENT, and a USB > stick from BSDRP using the FreeBSD routing improvements project > enhancements (https://wiki.freebsd.org/ProjectsRoutingProposal). Hi John, I am interested in your findings / test setups. I have a couple of boxes in the field running r317611 (around April 30) and r316678 (April 4) and found that r316678 does a higher PPS with zero drops and r317611 does less work, but will get random overruns on dev.cxl.0.stats.rx_ovflow0 and dev.cxl.0.stats.rx_trunc0. Same hardware, same cxl cards, both running frr as the routing daemon. Whats odd is that the errors are not anywhere peak load. Sometimes in the middle of the night when traffic is much lower. The missed packets dont seem to correlate to load-- that I can see anyways based on utilization graphs. When you were doing your tests, did you measure peak as what the box could forward without dropping packets or dropping some ? ---Mike -- ------------------- Mike Tancsa, tel +1 519 651 3400 Sentex Communications, mike@sentex.net Providing Internet services since 1994 www.sentex.net Cambridge, Ontario Canada http://www.tancsa.com/