From owner-freebsd-wireless@FreeBSD.ORG Mon Nov 28 16:20:46 2011 Return-Path: Delivered-To: freebsd-wireless@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id ED93E106564A for ; Mon, 28 Nov 2011 16:20:46 +0000 (UTC) (envelope-from gperez@entel.upc.edu) Received: from violet.upc.es (violet.upc.es [147.83.2.51]) by mx1.freebsd.org (Postfix) with ESMTP id 6E2CA8FC0C for ; Mon, 28 Nov 2011 16:20:45 +0000 (UTC) Received: from ackerman2.upc.es (ackerman2.upc.es [147.83.2.244]) by violet.upc.es (8.14.1/8.13.1) with ESMTP id pASGKhu9013783 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=FAIL); Mon, 28 Nov 2011 17:20:43 +0100 Received: from portgus.lan (141.Red-81-39-182.dynamicIP.rima-tde.net [81.39.182.141]) (authenticated bits=0) by ackerman2.upc.es (8.14.4/8.14.4) with ESMTP id pASGKcDG026538 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO); Mon, 28 Nov 2011 17:20:42 +0100 Message-ID: <4ED3B4D1.3020701@entel.upc.edu> Date: Mon, 28 Nov 2011 17:20:33 +0100 From: =?ISO-8859-1?Q?Gustau_P=E9rez?= User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111111 Thunderbird/8.0 MIME-Version: 1.0 To: Adrian Chadd References: <3d4d2d249836fafc6acd885693c02198@webmail.entel.upc.edu> <4ECFCDAB.1080407@entel.upc.edu> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.70 on 147.83.2.244 X-Mail-Scanned: Criba 2.0 + Clamd X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-3.0 (violet.upc.es [147.83.2.51]); Mon, 28 Nov 2011 17:20:43 +0100 (CET) Cc: freebsd-wireless@freebsd.org Subject: Re: Big delays between an AR5416 AP and its clients X-BeenThere: freebsd-wireless@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: "Discussions of 802.11 stack, tools device driver development." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 28 Nov 2011 16:20:47 -0000 On 28/11/2011 11:08, Adrian Chadd wrote: > Just run athstats a few times whilst you're pinging in the background > and you see spikes of latency. > > In fact, try doing something like "ping -i 0.1", that way it > sends out 10 pings a second. That'll hopefully bump up the counters > even further. > > Thanks, > > > Adrian I see little increase in the counters. I hope you can see what happens from them, because I have no idea. I did 5 runs of 300 pings with 0,1 seconds before each one. The client and the iphone are half a meter far from the AR5416 box. Before each run I collected the counters with athstats, I labeled each file as: athstats_1client_pinging_iphone_assoc_before_runX.txt where X is the run. Then I collected the state of the card while pinging the AP with the AR5416, I labeled eash file as: athstats_1client_pinging_iphone_assoc_runX.txt I collected the info while pinging with: athstats -i 1 | tee athstats_1client_pinging_iphone_assoc_runX.txt I'm also adding the output of the ping command. The file is: ping_0.1_delays.txt As you may see, the problem has a frequency of about 8,5 seconds. That is to say that after 8,5 seconds the delays fall one order of magnitude. However the minimum value of the delays is about 10ms which is 3 orders of magnitude bigger than the normal values (which are of 0,1ms). You can fetch the results from: https://www-entel.upc.edu/gus/ath_delay_values.zip