From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751475AbXB0EOW (ORCPT ); Mon, 26 Feb 2007 23:14:22 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751477AbXB0EOW (ORCPT ); Mon, 26 Feb 2007 23:14:22 -0500 Received: from x35.xmailserver.org ([64.71.152.41]:1483 "EHLO x35.xmailserver.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751475AbXB0EOV (ORCPT ); Mon, 26 Feb 2007 23:14:21 -0500 X-AuthUser: davidel@xmailserver.org Date: Mon, 26 Feb 2007 20:14:15 -0800 (PST) From: Davide Libenzi X-X-Sender: davide@alien.or.mcafeemobile.com To: Linus Torvalds cc: Linux Kernel Mailing List , Andrew Morton Subject: Re: [patch] epoll reduced (to 1) number of passes over the ready set ... In-Reply-To: Message-ID: References: X-GPG-FINGRPRINT: CFAE 5BEE FD36 F65E E640 56FE 0974 BF23 270F 474E X-GPG-PUBLIC_KEY: http://www.xmailserver.org/davidel.asc MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 26 Feb 2007, Linus Torvalds wrote: > On Mon, 26 Feb 2007, Davide Libenzi wrote: > > > > Epoll is doing multiple passes over the ready set at the moment, because > > of the constraints over the f_op->poll() call. Looking at the code again, > > I noticed that we already hold the epoll semaphore in read, and this > > (together with other locking conditions that hold while doing an > > epoll_wait()) can lead to a smarter way to "ship" events to userspace (in > > a single pass). > > Ok, this looks fine, but I think it makes more sense with (a) a sign-off > line and perhaps a slightly expanded explanation, and (b) keeping it in > -mm until after 2.6.21 is out, and merging it then. > > Yes? No? Linus is on some crazy drugs again? Let me do more testing. My post was to have more eyes looking at it. Once I feel confident about it, and if no objections come from review, I'll sign and repost. - Davide