From mboxrd@z Thu Jan 1 00:00:00 1970 From: Keir Fraser Subject: Re: Re: [PATCH] Add hypercall to mark superpages to improve performance Date: Sun, 2 May 2010 17:03:23 -0700 Message-ID: References: Mime-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Dave McCracken Cc: Jeremy Fitzhardinge , Xen Developers List List-Id: xen-devel@lists.xenproject.org On 02/05/2010 16:54, "Keir Fraser" wrote: >> What are your thoughts? It seems fairly simple and elegant to me, and at >> this >> point I don't see any big holes in it. > > It does mean that creating/destroying pagetable pages causes an extra locked > read-modify-write cycle on a non-local cacheline (superpage_info refcount). > Would this be significant? Not sure. I guess we'd only be doing it for > guests with the superpage capability configured, and we could do some > performance comparisons with the capability enabled/disabled. I think > overall I quite like your suggestion. Oh, now I think about it, although your suggestion deals with type conflicts, it doesn't handle page lifetimes. What if a page is only mapped as a superpage? The page->count_info would not be incremented by the superpage mappings, and the page would be erroneously freed to the Xen free pools? So I'm not so sure we can so easily avoid the mess-with-every-page's-refcount on first mapping of a superpage... :-( -- Keir