From owner-freebsd-net@FreeBSD.ORG Mon Oct 5 17:23:57 2009 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D5B8E1065672 for ; Mon, 5 Oct 2009 17:23:57 +0000 (UTC) (envelope-from rihad@mail.ru) Received: from mx39.mail.ru (mx39.mail.ru [94.100.176.53]) by mx1.freebsd.org (Postfix) with ESMTP id 8DC638FC0C for ; Mon, 5 Oct 2009 17:23:57 +0000 (UTC) Received: from [217.25.27.27] (port=15152 helo=[217.25.27.27]) by mx39.mail.ru with asmtp id 1MurHw-000HKg-00; Mon, 05 Oct 2009 21:23:56 +0400 Message-ID: <4ACA2BA6.40709@mail.ru> Date: Mon, 05 Oct 2009 22:23:50 +0500 From: rihad User-Agent: Mozilla-Thunderbird 2.0.0.22 (X11/20090706) MIME-Version: 1.0 To: Julian Elischer References: <4AC8A76B.3050502@mail.ru> <20091005025521.GA52702@svzserv.kemerovo.su> <20091005061025.GB55845@onelab2.iet.unipi.it> <4AC9B400.9020400@mail.ru> <20091005090102.GA70430@svzserv.kemerovo.su> <4AC9BC5A.50902@mail.ru> <20091005095600.GA73335@svzserv.kemerovo.su> <20091005100446.GA60244@onelab2.iet.unipi.it> <4ACA26D4.2080102@elischer.org> In-Reply-To: <4ACA26D4.2080102@elischer.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Spam: Not detected X-Mras: Ok Cc: Eugene Grosbein , Luigi Rizzo , freebsd-net@freebsd.org Subject: Re: dummynet dropping too many packets X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 05 Oct 2009 17:23:57 -0000 Julian Elischer wrote: > Luigi Rizzo wrote: > >>> Taildrop does not really help with this. GRED does much better. >> >> i think the first problem here is figure out _why_ we have >> the drops, as the original poster said that queues are configured >> with a very large amount of buffer (and i think there is a >> misconfiguration somewhere because the mbuf stats do not make >> sense) > > it all depends on the characteristics of the traffic > > you need different queue lengths if it is just a small number of high > speeed sessions (and mayne a large number of slow speed sessions), > or if it is a larger number of medium speed sessions. > > Is it possible to know what sessions are losing packets? > Yes, of course, by running ipfw pipe show ;-) There's one confusing thing, though: net.inet.ip.dummynet.io_pkt_drop isn't increasing while around 800-1000 packets per second are being dropped right now. And so "ipfw pipe show" Drp column wouldn't grow either. So it's either not dummynet dropping packets, or a bug (?).