Return-path: Received: from mail-ww0-f44.google.com ([74.125.82.44]:36184 "EHLO mail-ww0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932625Ab0JLOPw (ORCPT ); Tue, 12 Oct 2010 10:15:52 -0400 Received: by wwj40 with SMTP id 40so5082308wwj.1 for ; Tue, 12 Oct 2010 07:15:51 -0700 (PDT) Date: Tue, 12 Oct 2010 16:15:47 +0200 From: Ido Yariv To: Johannes Berg Cc: Luciano Coelho , linux-wireless@vger.kernel.org Subject: Re: [PATCH v3 3/4] wl1271: Allocate TX descriptors more efficiently Message-ID: <20101012141547.GC1836@WorkStation> References: <1286887752-19321-1-git-send-email-ido@wizery.com> <1286887752-19321-4-git-send-email-ido@wizery.com> <1286888188.3753.4.camel@jlt3.sipsolutions.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <1286888188.3753.4.camel@jlt3.sipsolutions.net> Sender: linux-wireless-owner@vger.kernel.org List-ID: On Tue, Oct 12, 2010 at 02:56:28PM +0200, Johannes Berg wrote: > This is all under some lock, right? (If that isn't the case, it's racy) Right. > Therefore, you need not use atomic bitops which will be fairly > expensive... > > Have you actually measured this? It seems that it con't have a huge > effect, and the atomic bitops you use now might even negate it. Like I mentioned in the cover letter, this is more of a cosmetic change than a real optimization. It doesn't really improve performance, but the code looks nicer. Using non atomic bitops cannot hurt, I guess. Thanks, Ido.