Re: [PATCH v5 00/11] Introduce huge zero page

2012-11-14 Thread Kirill A. Shutemov
On Wed, Nov 14, 2012 at 01:33:42PM -0800, Andrew Morton wrote: > On Wed, 7 Nov 2012 17:00:52 +0200 > "Kirill A. Shutemov" wrote: > > > Andrew, here's updated huge zero page patchset. > > There is still a distinct lack of reviewed-by's and acked-by's on this > patchset. > > On 13 Sep, Andrea di

Re: [PATCH v5 00/11] Introduce huge zero page

2012-11-14 Thread David Rientjes
On Wed, 14 Nov 2012, Andrew Morton wrote: > For this reason and for general ease-of-testing: can and should we add > a knob which will enable users to disable the feature at runtime? That > way if it causes problems or if we suspect it's causing problems, we > can easily verify the theory and off

Re: [PATCH v5 00/11] Introduce huge zero page

2012-11-14 Thread H. Peter Anvin
On 11/14/2012 03:32 PM, Andrew Morton wrote: > > The current code does the latter, by freeing the page via a > "slab"-shrinker callback. > > But I do suspect that with the right combination of use/unuse and > memory pressure, we could still get into the high-frequency scenario. > There probably

Re: [PATCH v5 00/11] Introduce huge zero page

2012-11-14 Thread Andrew Morton
On Wed, 14 Nov 2012 23:20:13 + Alan Cox wrote: > > I'm still a bit concerned over the possibility that some workloads will > > cause a high-frequency free/alloc/memset cycle on that huge zero page. > > We'll see how it goes... > > That is easy enough to fix - we can delay the freeing by a r

Re: [PATCH v5 00/11] Introduce huge zero page

2012-11-14 Thread Alan Cox
> I'm still a bit concerned over the possibility that some workloads will > cause a high-frequency free/alloc/memset cycle on that huge zero page. > We'll see how it goes... That is easy enough to fix - we can delay the freeing by a random time or until memory pressure is applied. Alan -- To uns

Re: [PATCH v5 00/11] Introduce huge zero page

2012-11-14 Thread Andrew Morton
On Wed, 7 Nov 2012 17:00:52 +0200 "Kirill A. Shutemov" wrote: > Andrew, here's updated huge zero page patchset. There is still a distinct lack of reviewed-by's and acked-by's on this patchset. On 13 Sep, Andrea did indicate that he "reviewed the whole patchset and it looks fine to me". But th

[PATCH v5 00/11] Introduce huge zero page

2012-11-07 Thread Kirill A. Shutemov
From: "Kirill A. Shutemov" Hi, Andrew, here's updated huge zero page patchset. Please consider applying. = During testing I noticed big (up to 2.5 times) memory consumption overhead on some workloads (e.g. ft.A from NPB) if THP is enabled. The main reason for that big differe