From mboxrd@z Thu Jan 1 00:00:00 1970 Date: Wed, 19 Sep 2007 15:23:01 -0700 (PDT) From: Christoph Lameter Subject: Re: [PATCH] Fix NUMA Memory Policy Reference Counting In-Reply-To: <1190239421.5301.72.camel@localhost> Message-ID: References: <20070830185053.22619.96398.sendpatchset@localhost> <1190055637.5460.105.camel@localhost> <1190057885.5460.134.camel@localhost> <1190239421.5301.72.camel@localhost> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-linux-mm@kvack.org Return-Path: To: Lee Schermerhorn Cc: linux-mm@kvack.org, akpm@linux-foundation.org, ak@suse.de, eric.whitney@hp.com, Mel Gorman List-ID: On Wed, 19 Sep 2007, Lee Schermerhorn wrote: > Bottom line: the run to run variability seems greater than the > difference between 23-rc4-mm1 with and without the patch. Also, it > appears that the contention on the page table, and perhaps the > radix-tree in the shmem case, overshadow any differences due to the > reference counting. Take a look and see what you think. Looks good. Thanks. Makes sense that the radix tree overshadows it. There are lots of reasons to not use shmem. -- 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