From owner-freebsd-wireless@FreeBSD.ORG Mon Oct 31 01:12:11 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 AE002106564A; Mon, 31 Oct 2011 01:12:11 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-vw0-f54.google.com (mail-vw0-f54.google.com [209.85.212.54]) by mx1.freebsd.org (Postfix) with ESMTP id 58C268FC08; Mon, 31 Oct 2011 01:12:11 +0000 (UTC) Received: by vws11 with SMTP id 11so7044646vws.13 for ; Sun, 30 Oct 2011 18:12:10 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; bh=S7eNCZtUnh36cCYFTWdqvfwYXG+pRFSmE8UdpPTl+qM=; b=SBNf4RJaPKS2X/2Y1ZE3sw6oy852F0N04o0JDsaYrKMy/C/wgimyVKXIbqUhKkYb3t tx9v5o+8B+FVqIwi7EhFgeul5AjV/XnFDnnJ3bacTo3mQwsc3ogqhVB1pJ2w2okYto57 M3ZSuQ1U6GgtUHoMjMo4vRqfXp/jmtd60PEac= MIME-Version: 1.0 Received: by 10.52.38.99 with SMTP id f3mr2992393vdk.117.1320023530711; Sun, 30 Oct 2011 18:12:10 -0700 (PDT) Sender: adrian.chadd@gmail.com Received: by 10.52.164.101 with HTTP; Sun, 30 Oct 2011 18:12:10 -0700 (PDT) In-Reply-To: <591784976.20111030232455@serebryakov.spb.ru> References: <872994138.20111026222719@serebryakov.spb.ru> <723076644.20111030221555@serebryakov.spb.ru> <591784976.20111030232455@serebryakov.spb.ru> Date: Mon, 31 Oct 2011 12:12:10 +1100 X-Google-Sender-Auth: TBPYt8cXea0yaO6vtbBLbX1jo0A Message-ID: From: Adrian Chadd To: Lev Serebryakov Content-Type: text/plain; charset=ISO-8859-1 Cc: freebsd-wireless@freebsd.org Subject: Re: AR9280: very strange upload speed 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, 31 Oct 2011 01:12:11 -0000 Hi, Please do this: * sysctl dev.ath.0.sample_stats then past the dmesg output here, so I can see what kind of TX failures you're seeing. * UDP iperf only gives useful stats on the RX side, so you have to do this: + RX side: iperf -su -i 1 + TX side: iperf -c x.x.x.x -u -b 100m -i 5 -t 10 (just so you see it running) + watch the RX side Do that in both directions, see which direction works better. TCP is difficult as the throughput depends upon both TX/RX behaviour. I expect that the TX side is great, the RX side sucks, and you're getting lots of stuck beacons. Try my patch from another email thread and see if that helps things. Finally, try changing channels. I had some very strange behaviour where some channels would work great and some wouldn't. I really need to find someone to sit down and finish the channel usage code. :( adrian