Re: [PATCH] mm: use pagevec to rotate reclaimable page

2007-09-19 Thread Andrew Morton
On Tue, 18 Sep 2007 19:41:14 +0900 Hisashi Hifumi <[EMAIL PROTECTED]> wrote: > > > >So I do think that for safety and sanity's sake, we should be taking a ref > >on the pages when they are in a pagevec. That's going to hurt your nice > >performance numbers :( > > > > I did ping test again t

Re: [PATCH] mm: use pagevec to rotate reclaimable page

2007-09-18 Thread Andrew Morton
On Tue, 18 Sep 2007 11:47:44 +1000 Nick Piggin <[EMAIL PROTECTED]> wrote: > On Wednesday 19 September 2007 03:44, Andrew Morton wrote: > > On Tue, 18 Sep 2007 11:29:50 +1000 Nick Piggin <[EMAIL PROTECTED]> > wrote: > > > It would be interesting to test -mm kernels. They have a patch which > > > r

Re: [PATCH] mm: use pagevec to rotate reclaimable page

2007-09-18 Thread Nick Piggin
On Wednesday 19 September 2007 03:44, Andrew Morton wrote: > On Tue, 18 Sep 2007 11:29:50 +1000 Nick Piggin <[EMAIL PROTECTED]> wrote: > > It would be interesting to test -mm kernels. They have a patch which > > reduces zone lock contention quite a lot. > > They do? Which patch? Hmm... mm-buffer

Re: [PATCH] mm: use pagevec to rotate reclaimable page

2007-09-18 Thread Andrew Morton
On Tue, 18 Sep 2007 11:29:50 +1000 Nick Piggin <[EMAIL PROTECTED]> wrote: > It would be interesting to test -mm kernels. They have a patch which reduces > zone lock contention quite a lot. They do? Which patch? > I think your patch is a nice idea, and with less zone lock contention in other > a

Re: [PATCH] mm: use pagevec to rotate reclaimable page

2007-09-18 Thread Nick Piggin
On Tuesday 18 September 2007 20:41, Hisashi Hifumi wrote: > I modified my patch based on your comment. > > At 11:37 07/09/14, Andrew Morton wrote: > >So I do think that for safety and sanity's sake, we should be taking a > > ref on the pages when they are in a pagevec. That's going to hurt your

Re: [PATCH] mm: use pagevec to rotate reclaimable page

2007-09-18 Thread Hisashi Hifumi
I modified my patch based on your comment. At 11:37 07/09/14, Andrew Morton wrote: > >So I do think that for safety and sanity's sake, we should be taking a ref >on the pages when they are in a pagevec. That's going to hurt your nice >performance numbers :( > I did ping test again to observe pe

Re: [PATCH] mm: use pagevec to rotate reclaimable page

2007-09-14 Thread Hisashi Hifumi
Thank you for your comment. At 11:37 07/09/14, Andrew Morton wrote: >The page_count() test here is a bit of a worry, too. Why do we need it? >The caller must have pinned the page in some fashion else we couldn't use >it safely in this function at all. > >I assume that you discovered that once w

Re: [PATCH] mm: use pagevec to rotate reclaimable page

2007-09-13 Thread Andrew Morton
On Tue, 11 Sep 2007 18:31:12 +0900 Hisashi Hifumi <[EMAIL PROTECTED]> wrote: > Hi. > While running some memory intensive load, system response > deteriorated just after swap-out started. > > The cause of this problem is that when a PG_reclaim page is > moved to the tail of the inactive LRU list i