Messages in this thread | | | Date | Mon, 21 Mar 2011 15:06:22 -0700 | From | Andrew Morton <> | Subject | Re: [PATCH] mm: optimize replace_page_cache_page |
| |
On Thu, 24 Feb 2011 11:56:55 +0100 Miklos Szeredi <mszeredi@suse.cz> wrote:
> On Thu, 2011-02-24 at 08:37 +0900, Minchan Kim wrote: > > On Thu, Feb 24, 2011 at 7:44 AM, Andrew Morton > > <akpm@linux-foundation.org> wrote: > > > On Sun, 20 Feb 2011 08:41:21 +0900 > > > Minchan Kim <minchan.kim@gmail.com> wrote: > > > > > >> Resend. > > > > > > Reignore. > > > > > >> he patch is based on mmotm-2011-02-04 + > > >> mm-add-replace_page_cache_page-function-add-freepage-hook.patch. > > >> > > >> On Fri, Feb 11, 2011 at 01:33:46AM +0900, Minchan Kim wrote: > > >> > This patch optmizes replace_page_cache_page. > > >> > > > >> > 1) remove radix_tree_preload > > >> > 2) single radix_tree_lookup_slot and replace radix tree slot > > >> > 3) page accounting optimization if both pages are in same zone. > > >> > > > >> > Cc: Miklos Szeredi <mszeredi@suse.cz> > > >> > Cc: Rik van Riel <riel@redhat.com> > > >> > Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> > > >> > Cc: Mel Gorman <mel@csn.ul.ie> > > >> > Signed-off-by: Minchan Kim <minchan.kim@gmail.com> > > >> > --- > > >> > mm/filemap.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++++--------- > > >> > 1 files changed, 51 insertions(+), 10 deletions(-) > > >> > > > >> > Hi Miklos, > > >> > This patch is totally not tested. > > >> > Could you test this patch? > > > > > > ^^^ Because of this. > > > > > > Is it tested yet? > > > > > > > Miklos. Could you test this? > > If you are busy, let me know how to test it. I will. > > Thanks. > > Grab git version of libfuse and do something like this: > > fuse/example/fusexmp_fh -obig_writes /mnt/fuse/ > dd if=/tmp/random0 of=/mnt/fuse/tmp/random1 bs=1M > md5sum /tmp/radom0 /tmp/random1 > > This should exercise the page moving. > > I'll review and test the patch when I have some time. >
Too late. It took months to half-finish Miklos's patch and now I'm sitting on other patches which depend on it, so it's going in.
| |