Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756160Ab0HCMCd (ORCPT ); Tue, 3 Aug 2010 08:02:33 -0400 Received: from soto.provo.novell.com ([137.65.250.214]:58048 "EHLO soto.provo.novell.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755971Ab0HCMCb convert rfc822-to-8bit (ORCPT ); Tue, 3 Aug 2010 08:02:31 -0400 X-Greylist: delayed 1209 seconds by postgrey-1.27 at vger.kernel.org; Tue, 03 Aug 2010 08:02:31 EDT Message-Id: <4C57C8580200005A0006E50B@soto.provo.novell.com> X-Mailer: Novell GroupWise Internet Agent 8.0.2 Date: Tue, 03 Aug 2010 05:42:16 -0600 From: "Gregory Haskins" To: "Bjoern Brandenburg" , "Peter Zijlstra" Cc: , "Nicola Manica" , "Luca Abeni" , "Harald Gustafsson" , "Song Yuan" , "Claudio Scordino" , "Dmitry Adamushko" , "rostedt" , "Thomas Gleixner" , "Raistlin" , "Giuseppe Lipari" , "linux-kernel" Subject: Re: periods and deadlines in SCHED_DEADLINE References: <1278682707.6083.227.camel@Palantir> <1278685133.1900.201.camel@laptop> <51F8E441-58D7-45E1-B7A0-7A717EDF08B5@email.unc.edu> <1278745706.4390.2.camel@Palantir> <21AA2C13-8831-47A2-9464-28E84DBD72B0@email.unc.edu> <1280823360.1923.419.camel@laptop> In-Reply-To: <1280823360.1923.419.camel@laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 8BIT Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1190 Lines: 28 Hello Peter, Steven, Thomas, et al. ! Its been a while. >>> On 8/3/2010 at 04:16 AM, in message <1280823360.1923.419.camel@laptop>, Peter Zijlstra wrote: [snip] > > So we replace the global lock with cmpxchg like loops using 2 per-cpu > locks. Our current SCHED_FIFO balancer does just this and is found to be > a very good approximation of global-fifo (iirc there's one funny case, > but I can't remember, maybe Steve or Gregory can remember the details). The only thing I remember at the moment is that Steven and I found one last remaining bug in an extreme corner case where priority order may be violated. Sadly, I can no longer recall the exact specifics and would have to dig into the code to remember. The good news is I believe the issue is fixable. Its just a matter of impl+test, which neither of us ever seem to have found the time to properly dedicate. Perhaps this will be the catalyst ;) -Greg -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/