From mboxrd@z Thu Jan 1 00:00:00 1970 From: Marcelo Tosatti Subject: Re: [PATCH v8 3/4] block: add block timer and throttling algorithm Date: Fri, 9 Sep 2011 11:44:03 -0300 Message-ID: <20110909144403.GB19459@amt.cnet> References: <1315476668-19812-1-git-send-email-wuzhy@linux.vnet.ibm.com> <1315476668-19812-4-git-send-email-wuzhy@linux.vnet.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org, stefanha@linux.vnet.ibm.com, aliguori@us.ibm.com, ryanh@us.ibm.com, zwu.kernel@gmail.com, kwolf@redhat.com, pair@us.ibm.com To: Zhi Yong Wu Return-path: Received: from mx1.redhat.com ([209.132.183.28]:63223 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751492Ab1IIOo3 (ORCPT ); Fri, 9 Sep 2011 10:44:29 -0400 Content-Disposition: inline In-Reply-To: <1315476668-19812-4-git-send-email-wuzhy@linux.vnet.ibm.com> Sender: kvm-owner@vger.kernel.org List-ID: On Thu, Sep 08, 2011 at 06:11:07PM +0800, Zhi Yong Wu wrote: > Note: > 1.) When bps/iops limits are specified to a small value such as 511 bytes/s, this VM will hang up. We are considering how to handle this senario. You can increase the length of the slice, if the request is larger than slice_time * bps_limit. > 2.) When "dd" command is issued in guest, if its option bs is set to a large value such as "bs=1024K", the result speed will slightly bigger than the limits. Why? There is lots of debugging leftovers in the patch. From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([140.186.70.92]:38972) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1R22Jn-0007D1-Kk for qemu-devel@nongnu.org; Fri, 09 Sep 2011 10:44:36 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1R22Jg-0003wV-SH for qemu-devel@nongnu.org; Fri, 09 Sep 2011 10:44:35 -0400 Received: from mx1.redhat.com ([209.132.183.28]:17418) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1R22Jg-0003wD-KV for qemu-devel@nongnu.org; Fri, 09 Sep 2011 10:44:28 -0400 Date: Fri, 9 Sep 2011 11:44:03 -0300 From: Marcelo Tosatti Message-ID: <20110909144403.GB19459@amt.cnet> References: <1315476668-19812-1-git-send-email-wuzhy@linux.vnet.ibm.com> <1315476668-19812-4-git-send-email-wuzhy@linux.vnet.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1315476668-19812-4-git-send-email-wuzhy@linux.vnet.ibm.com> Subject: Re: [Qemu-devel] [PATCH v8 3/4] block: add block timer and throttling algorithm List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Zhi Yong Wu Cc: kwolf@redhat.com, aliguori@us.ibm.com, stefanha@linux.vnet.ibm.com, kvm@vger.kernel.org, qemu-devel@nongnu.org, pair@us.ibm.com, zwu.kernel@gmail.com, ryanh@us.ibm.com On Thu, Sep 08, 2011 at 06:11:07PM +0800, Zhi Yong Wu wrote: > Note: > 1.) When bps/iops limits are specified to a small value such as 511 bytes/s, this VM will hang up. We are considering how to handle this senario. You can increase the length of the slice, if the request is larger than slice_time * bps_limit. > 2.) When "dd" command is issued in guest, if its option bs is set to a large value such as "bs=1024K", the result speed will slightly bigger than the limits. Why? There is lots of debugging leftovers in the patch.