Return-path: Received: from nbd.name ([46.4.11.11]:47990 "EHLO nbd.name" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753142Ab3B1EcM (ORCPT ); Wed, 27 Feb 2013 23:32:12 -0500 Message-ID: <512EDDC5.7020901@openwrt.org> (sfid-20130228_053216_486230_0D4DA527) Date: Thu, 28 Feb 2013 05:32:05 +0100 From: Felix Fietkau MIME-Version: 1.0 To: Sujith Manoharan CC: Adrian Chadd , "Luis R. Rodriguez" , Paul Stewart , linux-wireless Subject: Re: [RFC] ath9k: remove ath9k_rate_control References: <1360329197-72631-1-git-send-email-nbd@openwrt.org> <20757.1753.863278.858198@gargle.gargle.HOWL> <511508A6.8020104@openwrt.org> <51152D9E.1040106@openwrt.org> <20130227192030.GW12537@pogo> <512ECE01.8010102@openwrt.org> <20782.54505.239733.82364@gargle.gargle.HOWL> In-Reply-To: <20782.54505.239733.82364@gargle.gargle.HOWL> Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-wireless-owner@vger.kernel.org List-ID: On 2013-02-28 4:54 AM, Sujith Manoharan wrote: > Felix Fietkau wrote: >> I don't see the point in keeping that algorithm around. It has known >> design flaws that make it perform poorly in several scenarios, and >> fixing some of the flaws require basically rewriting it. > > I ran some comparison throughput tests between minstrel_ht and ath9k RC > and minstrel showed lower numbers (~10Mbps difference). This is in a clean > environment (OTA). IMO, we can switch the default to minstrel_ht, but keep > the ath9k RC until the perf. gap is fixed. I think this was Google's concern too, > a drop in the average throughput. This was in the STA->AP direction. What was the distance and what was the rate used? > In the AP->STA direction (AP: DB120, STA: AR9280), the numbers were really low. > The highest that I could see was ~165 Mbps, while with WNDR3700 (stock FW), the > average throughput was ~185 Mbps and an occasional high of 190 and above. Comparing against stock FW (especially with different devices) is not useful, it could be anything. - Felix