From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Ky Srinivasan" Subject: Re: VCPU affinity Date: Mon, 18 Dec 2006 10:08:13 -0700 Message-ID: <45867529.E57C.0030.0@novell.com> References: <4586644F.E57C.0030.0@novell.com> <0951ba397e5752bf7a54f5ecaf67ad4e@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <0951ba397e5752bf7a54f5ecaf67ad4e@gmail.com> Content-Disposition: inline List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Emmanuel Ackaouy Cc: xen-devel@lists.xensource.com List-Id: xen-devel@lists.xenproject.org I am chasing a bug we seem to be hitting where we are not able to specify the binding; will let you know once I know more. Regards, K. Y >>> On Mon, Dec 18, 2006 at 11:01 AM, in message <0951ba397e5752bf7a54f5ecaf67ad4e@gmail.com>, Emmanuel Ackaouy wrote: > On Dec 18, 2006, at 16:56, Ky Srinivasan wrote: >> What is the best way to pin VCPUs. It looks like the implementation of >> affinity currently is at best only "soft". >> >> Regards, > > VCPU affinity should not be soft. By the time the set affinity hypercall > returns, the VCPU in question should be running on a physical CPU > set in its affinity mask. > > If it's not behaving this way then something is broken. Can you send > more details?