From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:33437) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1dfmtK-0008Pv-Dh for qemu-devel@nongnu.org; Thu, 10 Aug 2017 08:48:47 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1dfmtG-0003i1-Dl for qemu-devel@nongnu.org; Thu, 10 Aug 2017 08:48:46 -0400 Received: from mx1.redhat.com ([209.132.183.28]:42252) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1dfmtG-0003fk-7Y for qemu-devel@nongnu.org; Thu, 10 Aug 2017 08:48:42 -0400 Date: Thu, 10 Aug 2017 14:41:03 +0200 From: Radim =?utf-8?B?S3LEjW3DocWZ?= Message-ID: <20170810124102.GA21850@flask> References: <1502359687-25370-1-git-send-email-tianyu.lan@intel.com> <20170810102649.GF12980@redhat.com> <00cb01a4-5c27-fc69-d3ae-0653aa54b121@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: <00cb01a4-5c27-fc69-d3ae-0653aa54b121@intel.com> Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] [PATCH] x86: Increase max vcpu number to 352 List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Lan Tianyu Cc: "Daniel P. Berrange" , pbonzini@redhat.com, mst@redhat.com, qemu-devel@nongnu.org, ehabkost@redhat.com, rth@twiddle.net 2017-08-10 19:02+0800, Lan Tianyu: > On 2017=E5=B9=B408=E6=9C=8810=E6=97=A5 18:26, Daniel P. Berrange wrote: >> On Thu, Aug 10, 2017 at 06:08:07PM +0800, Lan Tianyu wrote: >>> Intel Xeon phi chip will support 352 logical threads. For HPC >>> usage case, it will create a huge VM with vcpus number as same as hos= t >>> cpus. This patch is to increase max vcpu number to 352. >>=20 >> If we pick arbitray limits based on size of physical CPUs that happen >> to be shipping today, we'll continue the cat+mouse game forever traili= ng >> latest CPUs that vendors ship. >>=20 >> IMHO we should pick a higher number influenced by technical constraint= s >> of the q35 impl instead. eg can we go straight to something like 512 o= r >> 1024 ? >=20 > Sure. 512 should be enough and some arrays is defined according to max > vcpu number. Hm, which arrays are that? I was thinking it is safe to bump it to INT_MAX as the number is only used when setting global max_cpus. Thanks.