From owner-freebsd-current@FreeBSD.ORG Mon Sep 26 15:16:40 2011 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 35084106564A; Mon, 26 Sep 2011 15:16:40 +0000 (UTC) (envelope-from jhb@freebsd.org) Received: from cyrus.watson.org (cyrus.watson.org [65.122.17.42]) by mx1.freebsd.org (Postfix) with ESMTP id 0A7AE8FC14; Mon, 26 Sep 2011 15:16:40 +0000 (UTC) Received: from bigwig.baldwin.cx (66.111.2.69.static.nyinternet.net [66.111.2.69]) by cyrus.watson.org (Postfix) with ESMTPSA id B3CFD46B23; Mon, 26 Sep 2011 11:16:39 -0400 (EDT) Received: from jhbbsd.localnet (unknown [209.249.190.124]) by bigwig.baldwin.cx (Postfix) with ESMTPSA id 543308A02E; Mon, 26 Sep 2011 11:16:39 -0400 (EDT) From: John Baldwin To: Adrian Chadd Date: Mon, 26 Sep 2011 10:53:30 -0400 User-Agent: KMail/1.13.5 (FreeBSD/8.2-CBSD-20110617; KDE/4.5.5; amd64; ; ) References: <201109260917.44236.jhb@freebsd.org> In-Reply-To: MIME-Version: 1.0 Content-Type: Text/Plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Message-Id: <201109261053.30410.jhb@freebsd.org> X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.2.6 (bigwig.baldwin.cx); Mon, 26 Sep 2011 11:16:39 -0400 (EDT) Cc: Alexander Motin , freebsd-current@freebsd.org Subject: Re: ath / 802.11n performance issues and timer code X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 26 Sep 2011 15:16:40 -0000 On Monday, September 26, 2011 10:10:27 am Adrian Chadd wrote: > On 26 September 2011 21:17, John Baldwin wrote: > > On Sunday, September 25, 2011 5:48:31 am Adrian Chadd wrote: > >> Nope, it has the opposite effect: > >> > >> * Increased latency may make aggregation better (for TX) but it limits > >> throughput because TCP senses a latency increase; > > > > I suspect this matters more. Have you tried comparing UDP throughput in the > > two cases? > > Yes, UDP performance from the MIPS boards (running iperf) is just > plain silly and low. > > It's better from the i386 based eeepc (I can get around 200mbit before > things croak it, but I _should_ be able to schedule ~ 250mbit with > maximum aggregation and no airtime errors / retries, which I _can_ > achieve in controlled conditions.) I meant do the timer settings affect UDP performance? I.e. does idletick=1 change UDP performance at all? > > One behavioral difference of a periodic timer vs a deadline timer is that if > > you ask to delay for "1 clock tick", that can be anywhere from 0us to 1000us > > (with hz == 1000) when using the periodic timer (because you can set the > > callout at any time within a tick, but the callout will fire at the start of > > the next tick). However, for a deadline timer, the TCP timer will always fire > > 1000us after you set the timer. > > Right. Hm, what about scheduling in general though? Ie, if I'm > scheduling a taskqueue run, the taskqueue caller does: > > * lock queue > * schedule next task queue > * call wakeup_one > > Which should wake up a/the taskqueue thread in question and have it > immediately run the next task on the queue. The taskqueue doesn't have > any form of timer/callout; it's just a "submit this to get run." When > will it be run? I hope not at the next tick, not if the CPU is free. No, that scheduling is synchronous. Anytime a thread is scheduled the scheduler will check if it should preempt the current thread to run the new thread. -- John Baldwin