From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Message-ID: <42B2977F.7040906@yahoo.com.au> Date: Fri, 17 Jun 2005 19:27:27 +1000 From: Nick Piggin MIME-Version: 1.0 Subject: Re: Global spinlock vs local bit spin locks References: <1118982092.5261.44.camel@npiggin-nld.site> <20050617044611.GF3913@holomorphy.com> <42B28B44.9090606@yahoo.com.au> <20050617085426.GK31127@wotan.suse.de> In-Reply-To: <20050617085426.GK31127@wotan.suse.de> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit To: Andi Kleen Cc: William Lee Irwin III , "David S. Miller" , anton@samba.org, linux-arch@vger.kernel.org, Andrew Morton , Peter Keilty List-ID: Andi Kleen wrote: > On Fri, Jun 17, 2005 at 06:35:16PM +1000, Nick Piggin wrote: > >>William Lee Irwin III wrote: >> >> >>>I'd feel far more comfortable with this if the lockbit resided in the >>>page. Also, compare it to akpm's solution. >>> >> >>akpm's solution is alright. They perform similarly on the workload in >>question. Of course, the bitlock will scale quite a lot better if you >>pushed it and will automatically be localised per device and have NUMA >>locality, etc. > > > The buffer head is not necessarily NUMA local though - there is > some chance that a BH from a different node is reused. True, but compared to a hash which is almost guaranteed *not* to be in local memory for any medium to large NUMA system :) Though I guess on many, it is basically luck that you would get an IO submitted on the same node that takes the completion interrupt. However, on really huge systems like SGI's, they often tend to lock down devices and jobs quite tightly to nodes so I think it has some merit. -- SUSE Labs, Novell Inc. Send instant messages to your online friends http://au.messenger.yahoo.com