Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753460AbWKFRH7 (ORCPT ); Mon, 6 Nov 2006 12:07:59 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753461AbWKFRH7 (ORCPT ); Mon, 6 Nov 2006 12:07:59 -0500 Received: from brick.kernel.dk ([62.242.22.158]:63755 "EHLO kernel.dk") by vger.kernel.org with ESMTP id S1753460AbWKFRH7 (ORCPT ); Mon, 6 Nov 2006 12:07:59 -0500 Date: Mon, 6 Nov 2006 18:10:05 +0100 From: Jens Axboe To: Phillip Susi Cc: Brent Baccala , linux-kernel@vger.kernel.org Subject: Re: async I/O seems to be blocking on 2.6.15 Message-ID: <20061106171005.GA19471@kernel.dk> References: <20061103122055.GE13555@kernel.dk> <20061103160212.GK13555@kernel.dk> <20061106160250.GY13555@kernel.dk> <454F6B19.8010701@cfl.rr.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <454F6B19.8010701@cfl.rr.com> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1339 Lines: 31 On Mon, Nov 06 2006, Phillip Susi wrote: > Jens Axboe wrote: > >You could optimistically retry when you had reaped some completed > >events, or use some controlled way of blocking for free request > >notification. There are many ways, most of them share the fact that the > >time between notification and new io_submit() may change the picture, in > >which case you'd get EAGAIN once more. > > > >The important bit is imho to make the blocking at least deterministic. > >At some point you _have_ to block for resources, but it's not very > >polite to be blocking for a considerable time indeterministically. > > > > Right, but there currently exists no mechanism for waiting until there > is room in the queue is there? My point was that this would be required > in order to return EAGAIN. No mechanism exists, since we don't return EAGAIN for this condition right now. I wouldn't say it's required, just retrying when you have reaped one (or more) completed events should be good enough. You can't do much better than that anyway, with others beating on the disk as well. -- Jens Axboe - 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/