From mboxrd@z Thu Jan 1 00:00:00 1970 From: Keir Fraser Subject: Re: [RFC PATCH 2/2] gnttab: refactor locking for better scalability Date: Tue, 12 Nov 2013 14:24:50 +0000 Message-ID: References: <528245120200007800102642@nat28.tlf.novell.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail6.bemta3.messagelabs.com ([195.245.230.39]) by lists.xen.org with esmtp (Exim 4.72) (envelope-from ) id 1VgEtq-0007aS-Uv for xen-devel@lists.xenproject.org; Tue, 12 Nov 2013 14:25:03 +0000 Received: by mail-wg0-f44.google.com with SMTP id k14so4416067wgh.23 for ; Tue, 12 Nov 2013 06:25:00 -0800 (PST) In-Reply-To: <528245120200007800102642@nat28.tlf.novell.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: Jan Beulich Cc: Felipe Franciosi , Anthony Liguori , Andrew Cooper , David Vrabel , Matt Wilson , Matt Wilson , xen-devel@lists.xenproject.org, roger.pau@citrix.com List-Id: xen-devel@lists.xenproject.org On 12/11/2013 14:11, "Jan Beulich" wrote: >>>> On 12.11.13 at 14:58, Keir Fraser wrote: >> On 12/11/2013 13:42, "Keir Fraser" wrote: >> >>>> And indeed I think we should be making our rwlocks fair for writers >>>> before pushing in the change here; I've been meaning to get to this >>>> for a while, but other stuff continues to require attention. I'm also >>>> of the opinion that we should switch to ticket spinlocks. >>> >>> Would queuing spinlocks (e.g. MCS locks) be even more preferable? Two atomic >>> ops (cmpxchg) per critical region in the uncontended case. Each CPU spins on >>> its own location so there's no cacheline carnage in the highly contended >>> case (a problem with simple ticket spinlocks). And it builds on cmpxchg so >>> the spinlock implementation has no arch-specific component (apart from >>> cmpxchg, which we already have). >>> >>> I have a queue-based rwlock design too, does require a spinlock lock/unlock >>> per rwlock op though (i.e., 4 atomic ops per critical region in the >>> uncontended case). >> >> Actually MCS has a multi-reader extension we could use, or there is another >> alternative by Krieger et al. My own design was intended to build on pthread >> primitives and wouldn't be as good as the existing solutions in the >> literature for purely spinning waiters. > > Sounds nice - are you going to spend time on implementing this then? Yes I'll look into it. Amazon's benchmarking of grant-table throughput will be a good testbed for performance of a different lock implementation. -- Keir > Jan >