From mboxrd@z Thu Jan 1 00:00:00 1970 From: Wei Liu Subject: Re: [PATCH net-next 2/3] xen-netback: switch to per-cpu scratch space Date: Fri, 24 May 2013 13:31:30 +0100 Message-ID: <20130524123130.GB16745__32114.7044924603$1369398808$gmane$org@zion.uk.xensource.com> References: <1369391553-16835-1-git-send-email-wei.liu2@citrix.com> <1369391553-16835-3-git-send-email-wei.liu2@citrix.com> <519F5C09.3030502@citrix.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: <519F5C09.3030502@citrix.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: David Vrabel Cc: netdev@vger.kernel.org, konrad.wilk@oracle.com, Wei Liu , ian.campbell@citrix.com, xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org On Fri, May 24, 2013 at 01:24:41PM +0100, David Vrabel wrote: > On 24/05/13 11:32, Wei Liu wrote: > > There are maximum nr_onlie_cpus netback threads running. We can make use of > > per-cpu scratch space to reduce the size of buffer space when we move to 1:1 > > model. > > How much memory does this actually save? At first glance the savings > don't seem worth it for the extra complexity wrt hotplugged VCPUs etc. > It would not save any for the old model netback. But if we switch to 1:1 model the saving depends on how many vifs you run. This can be calculated by: (nr_vifs - nr_cpus) * sizeof(scratch space) Wei. > David