From mboxrd@z Thu Jan 1 00:00:00 1970 Date: Fri, 15 Sep 2006 18:36:04 -0700 From: Andrew Morton Subject: Re: [PATCH] GFP_THISNODE for the slab allocator Message-Id: <20060915183604.11a8d045.akpm@osdl.org> In-Reply-To: <20060915170455.f8b98784.pj@sgi.com> References: <20060914220011.2be9100a.akpm@osdl.org> <20060914234926.9b58fd77.pj@sgi.com> <20060915002325.bffe27d1.akpm@osdl.org> <20060915004402.88d462ff.pj@sgi.com> <20060915010622.0e3539d2.akpm@osdl.org> <20060915170455.f8b98784.pj@sgi.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-linux-mm@kvack.org Return-Path: To: Paul Jackson Cc: David Rientjes , clameter@sgi.com, linux-mm@kvack.org List-ID: On Fri, 15 Sep 2006 17:04:55 -0700 Paul Jackson wrote: > Thanks for doing this, David. > > > I used numa=fake=64 for 64 nodes of 48M each (with my numa=fake fix). I > > created a 2G cpuset with 43 nodes (43*48M = ~2G) and attached 'usemem -m > > 1500 -s 10000000 &' to it for 1.5G of anonymous memory. I then used > > readprofile to time and profile a kernel build of 2.6.18-rc5 with x86_64 > > defconfig in the remaining 21 nodes. > > I got confused here. Was the kernel build running in the > 2G cpuset (which only had 0.5G remaining free), or was it > running on the remaining 21 nodes, outside the 2G cpuset? The former. > Separate question - would it be easy to run this again, with > a little patch from me that open coded cpuset_zone_allowed() > in get_page_from_freelist()? I guess it would, but that'll be a next-week thing. I need to get David's stuff working on my machine, but you know how it is.. > The patch I have in mind would > not be acceptable for the real kernel, but it would give us > an idea of whether just a local code change might be sufficient > here. I doubt it - if we still hit z->zone_pgdat->node_id for all 40-odd zones, I expect the cost will be comparable. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org