From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:50300) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1TtHW1-0007RR-7P for qemu-devel@nongnu.org; Thu, 10 Jan 2013 07:45:53 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1TtHVv-0006jJ-2Q for qemu-devel@nongnu.org; Thu, 10 Jan 2013 07:45:49 -0500 Received: from mail-wi0-x229.google.com ([2a00:1450:400c:c05::229]:52703) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1TtHVu-0006iO-I5 for qemu-devel@nongnu.org; Thu, 10 Jan 2013 07:45:42 -0500 Received: by mail-wi0-f169.google.com with SMTP id hq12so1214106wib.2 for ; Thu, 10 Jan 2013 04:45:41 -0800 (PST) Date: Thu, 10 Jan 2013 13:45:39 +0100 From: Stefan Hajnoczi Message-ID: <20130110124539.GG30946@stefanha-thinkpad.redhat.com> References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: Subject: Re: [Qemu-devel] livelock in iolimits List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Peter Lieven Cc: "qemu-devel@nongnu.org" On Tue, Jan 08, 2013 at 04:43:22PM +0100, Peter Lieven wrote: > i am experimenting with iolimits on a virtio block device and found a lock condition. > My plan was to monitor IOPS and/or bandwidth and kick a limit in if a vServer is exhausting > these limits too much. > However, it seems that if a limit is defined while the defined limit is exceeded no further I/O > is processed. You have sent a fix for this? Just double-checking that this email thread can be ignored in favor of your patch. Stefan