From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:43944) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1V1eGp-0008Hl-Gw for qemu-devel@nongnu.org; Tue, 23 Jul 2013 11:13:02 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1V1eGo-0004L2-8M for qemu-devel@nongnu.org; Tue, 23 Jul 2013 11:12:59 -0400 Received: from nodalink.pck.nerim.net ([62.212.105.220]:47561 helo=paradis.irqsave.net) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1V1eGo-0004Ki-0a for qemu-devel@nongnu.org; Tue, 23 Jul 2013 11:12:58 -0400 Date: Tue, 23 Jul 2013 17:14:43 +0200 From: =?iso-8859-1?Q?Beno=EEt?= Canet Message-ID: <20130723151443.GF5002@irqsave.net> References: <1374582067-9063-1-git-send-email-benoit@irqsave.net> <1374582067-9063-3-git-send-email-benoit@irqsave.net> <20130723145906.GB14190@stefanha-thinkpad.redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline In-Reply-To: <20130723145906.GB14190@stefanha-thinkpad.redhat.com> Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] [PATCH V2 for-1.6 2/5] block: Modify the throttling code to implement the leaky bucket algorithm. List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Stefan Hajnoczi Cc: kwolf@redhat.com, qemu-devel@nongnu.org, stefanha@redhat.com > 1. Can we activate the timer only when requests are actually pending? > Imagine a host with 1000 guests, even a 1 second timer becomes > wasteful. I will try to do this. > 2. You don't vary the wait time, does this mean a throttled request mus= t > wait for max 1 second? If yes, then it introduces a big variance on > request latency. If iops or bps request where done on a negligible time (very fast storage backend) yes. We could make the timer frequency higher though to mitigate this. Best regards Beno=EEt