lkml.org 
[lkml]   [2020]   [Mar]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] mm,page_alloc,cma: conditionally prefer cma pageblocks for movable allocations
On Thu, Mar 12, 2020 at 10:41:28AM +0900, Joonsoo Kim wrote:
> Hello, Roman.

Hello, Joonsoo!

>
> 2020년 3월 12일 (목) 오전 2:35, Roman Gushchin <guro@fb.com>님이 작성:
> >
> > On Wed, Mar 11, 2020 at 09:51:07AM +0100, Vlastimil Babka wrote:
> > > On 3/6/20 9:01 PM, Rik van Riel wrote:
> > > > Posting this one for Roman so I can deal with any upstream feedback and
> > > > create a v2 if needed, while scratching my head over the next piece of
> > > > this puzzle :)
> > > >
> > > > ---8<---
> > > >
> > > > From: Roman Gushchin <guro@fb.com>
> > > >
> > > > Currently a cma area is barely used by the page allocator because
> > > > it's used only as a fallback from movable, however kswapd tries
> > > > hard to make sure that the fallback path isn't used.
> > >
> > > Few years ago Joonsoo wanted to fix these kinds of weird MIGRATE_CMA corner
> > > cases by using ZONE_MOVABLE instead [1]. Unfortunately it was reverted due to
> > > unresolved bugs. Perhaps the idea could be resurrected now?
> >
> > Hi Vlastimil!
> >
> > Thank you for this reminder! I actually looked at it and also asked Joonsoo in private
> > about the state of this patch(set). As I understand, Joonsoo plans to resubmit
> > it later this year.
> >
> > What Rik and I are suggesting seems to be much simpler, however it's perfectly
> > possible that Joonsoo's solution is preferable long-term.
> >
> > So if the proposed patch looks ok for now, I'd suggest to go with it and return
> > to this question once we'll have a new version of ZONE_MOVABLE solution.
>
> Hmm... utilization is not the only matter for CMA user. The more
> important one is
> success guarantee of cma_alloc() and this patch would have a bad impact on it.
>
> A few years ago, I have tested this kind of approach and found that increasing
> utilization increases cma_alloc() failure. Reason is that the page
> allocated with
> __GFP_MOVABLE, especially, by sb_bread(), is sometimes pinned by someone.
>
> Until now, cma memory isn't used much so this problem doesn't occur easily.
> However, with this patch, it would happen.

Sure, but the whole point of cma is to be able to use the cma area
effectively by movable pages. Otherwise we can just reserve it and
have 100% reliability.

So I'd focus on fixing page migration issues, rather than trying
to keep it empty most of the time.

Btw, I've fixed two issues, which dramatically increased the success
rate of 1 GB page allocation in my case:

https://patchwork.kernel.org/patch/11420997/
https://lore.kernel.org/patchwork/patch/1202868/

(They both are on the way to upstream, but not there yet)

Can you, please, pull them and try?

Thanks!

Roman

\
 
 \ /
  Last update: 2020-03-12 03:41    [W:0.094 / U:2.068 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site