From owner-freebsd-net@FreeBSD.ORG Wed Oct 5 11:04:44 2005 Return-Path: X-Original-To: net@freebsd.org Delivered-To: freebsd-net@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B7FB516A41F for ; Wed, 5 Oct 2005 11:04:44 +0000 (GMT) (envelope-from ferdinand.goldmann@jku.at) Received: from mail2.edvz.uni-linz.ac.at (mail2.edvz.uni-linz.ac.at [140.78.3.69]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0A3AD43D48 for ; Wed, 5 Oct 2005 11:04:43 +0000 (GMT) (envelope-from ferdinand.goldmann@jku.at) Received: from emailsecure.uni-linz.ac.at (emailsecure.uni-linz.ac.at [140.78.3.66]) by mail2.edvz.uni-linz.ac.at (8.13.3/8.13.3) with ESMTP id j95B4drL043047 for ; Wed, 5 Oct 2005 13:04:39 +0200 (CEST) (envelope-from ferdinand.goldmann@jku.at) Received: from [140.78.164.13] (jku006048.edvz.uni-linz.ac.at [140.78.6.48]) by emailsecure.uni-linz.ac.at (Postfix) with ESMTP id 48808228019 for ; Wed, 5 Oct 2005 13:04:39 +0200 (CEST) Message-ID: <4343B34A.6020308@jku.at> Date: Wed, 05 Oct 2005 13:04:42 +0200 From: Ferdinand Goldmann Organization: Johannes Kepler University User-Agent: Thunderbird 1.4 (Macintosh/20050908) MIME-Version: 1.0 To: net@freebsd.org References: <4341089F.7010504@jku.at> <20051003104548.GB70355@cell.sick.ru> <4341242F.9060602@jku.at> <20051003123210.GF70355@cell.sick.ru> <43426EF3.3020404@jku.at> <9CD8C672-1EF2-42FE-A61E-83DC684C893D@dragondata.com> <43429157.90606@jku.at> <4342987D.7000200@benswebs.com> <20051004161217.GB43195@obiwan.tataz.chchile.org> In-Reply-To: <20051004161217.GB43195@obiwan.tataz.chchile.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.44 Cc: Subject: Re: dummynet, em driver, device polling issues :-(( X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: ferdinand.goldmann@jku.at List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 05 Oct 2005 11:04:44 -0000 Jeremie Le Hen wrote: >>> em0: Missed Packets = 39 >>> em0: Receive No Buffers = 2458 > > "Receive No Buffers" grows when polling is enabled and it's somewhat > a normal behaviour. After running with polling enabled for two hours, the statistics were: em0: Missed Packets = 2159959 em0: Receive No Buffers = 32458174 em0: Good Packets Rcvd = 499051709 em0: Good Packets Xmtd = 466744805 That's quite a lot of missed packets in only ~two hours :-( > I think you can slightly increase the HZ value to decrease this > error count, but I'm not sure this will improve the bandwidth in a > great order of magnitude. Hm it would be interesting how to optimize the HZ value in order to prevent lost packets, because this is not good at all. > I know that Intel GigE NICs have a smart way to to interrupt throttling > (that's what tx_int_delay, tx_abs_int_delay, rx_int_delay and > rx_abs_int_delay stand for). You should try to tune them through > dev.em.[0-9]+. sysctl tree. > These tresholds are very well explained here : > http://www.intel.com/design/network/applnots/ap450.pdf Thank you for the pointer, I will have a look at this and see whether this helps, and post the results. -- >> Ferdinand Goldmann //// | | >> EMail: Ferdinand.Goldmann@zid.uni-linz.ac.at |--00 | UNIX | >> Tel. : +43/732/2468/9398 Fax. : +43/732/2468/9397 C ^ | | >> EMail: Ferdinand.Goldmann@zid.uni-linz.ac.at \ ~/ ~~~|~~~~~~~~ >> PGP D4CF 8AA4 4B2A 7B88 65CA 5EDC 0A9B FA9A 13EA B993| |-----3