From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:37415) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1VC5Eb-0003kZ-TP for qemu-devel@nongnu.org; Wed, 21 Aug 2013 06:01:54 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1VC5EW-0005m7-MT for qemu-devel@nongnu.org; Wed, 21 Aug 2013 06:01:49 -0400 Received: from mx1.redhat.com ([209.132.183.28]:62085) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1VC5EW-0005m2-EE for qemu-devel@nongnu.org; Wed, 21 Aug 2013 06:01:44 -0400 Message-ID: <52148FCF.5070309@redhat.com> Date: Wed, 21 Aug 2013 12:00:47 +0200 From: Paolo Bonzini MIME-Version: 1.0 References: <1376960839-13033-1-git-send-email-gaowanlong@cn.fujitsu.com> <52137284.9070402@redhat.com> <52141657.1020209@cn.fujitsu.com> <521481B9.9070604@redhat.com> <5214838A.3090501@cn.fujitsu.com> <521486DB.1010601@redhat.com> <521489B0.3010605@cn.fujitsu.com> In-Reply-To: <521489B0.3010605@cn.fujitsu.com> Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH V8 00/11] Add support for binding guest numa nodes to host numa nodes List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: gaowanlong@cn.fujitsu.com Cc: aliguori@us.ibm.com, ehabkost@redhat.com, lersek@redhat.com, qemu-devel@nongnu.org, lcapitulino@redhat.com, bsd@redhat.com, hutao@cn.fujitsu.com, y-goto@jp.fujitsu.com, peter.huangpeng@huawei.com, afaerber@suse.de Il 21/08/2013 11:34, Wanlong Gao ha scritto: > On 08/21/2013 05:22 PM, Paolo Bonzini wrote: >> Il 21/08/2013 11:08, Wanlong Gao ha scritto: >>>>>> Also, do you still need a "-m" option if you use "-numa mem"? >>>>> >>>>> The "-m" options will be used to compute the memory size of each node >>>>> if the memory size of each node is not set by "-numa mem" option. This >>>>> is also be consistent with the original concept. >>>> >>>> Ok. You didn't answer my exact question though---could you run the >>>> above command line without "-m 2048"? >>> >>> Sorry :( >> >> No problem! >> >>> Sure not. And if the memory size assigned by "-m" option is not equal >>> the total memory size assigned by "-numa mem,", the ACPI will write the >>> wrong table, then the guest kernel will detect this and ignore the wrong >>> ACPI numa table and assume that all of the memory are belong to one node. >> >> Can you make the code print a warning in this case, or fail to start the >> VM (if there is "-numa mem" but the total doesn't match "-m"? > > You mean this? http://lists.nongnu.org/archive/html/qemu-devel/2013-05/msg03065.html > I sent a patch previously to do this, if you like I can merge to this patch set. Yes! >> >>> Would you like to run without "-m" option in mind? >> >> This would definitely be nice to have, if it's not too complicated. >> Otherwise, the above idea will do. > > Yeah, but more complicated since we should make "-numa mem,size" and "-m" > options both optional. Yes. Paolo