Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1418278

Re: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page arrival

From Michal Hocko <mhocko@kernel.org>
Newsgroups linux.kernel
Subject Re: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page arrival
Date 2016-06-09 14:30 +0200
Message-ID <rI7fX-6hH-7@gated-at.bofh.it> (permalink)
References <rHMOe-1mm-23@gated-at.bofh.it> <rHNKh-1Yh-3@gated-at.bofh.it> <rHOdj-2nA-13@gated-at.bofh.it> <rHOGl-2xG-15@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On Wed 08-06-16 09:34:01, Dave Hansen wrote:
> On 06/08/2016 09:06 AM, Michal Hocko wrote:
> >> > Do we have any statistics that tell us how many pages are sitting the
> >> > lru pvecs?  Although this helps the problem overall, don't we still have
> >> > a problem with memory being held in such an opaque place?
> > Is it really worth bothering when we are talking about 56kB per CPU
> > (after this patch)?
> 
> That was the logic why we didn't have it up until now: we didn't
> *expect* it to get large.  A code change blew it up by 512x, and we had
> no instrumentation to tell us where all the memory went.
> 
> I guess we don't have any other ways to group pages than compound pages,
> and _that_ one is covered now...

exactly and that is why I am not sure it is needed. I do not expect we
would ever change the pagevec size or have a different way of grouping
pages on the LRU list.

That being said I am not objecting to the counter, I am just not sure it
is worth it.

> for one of the 5 classes of pvecs.
> 
> Is there a good reason we don't have to touch the other 4 pagevecs, btw?

I agree it would be better to do the same for others as well. Even if
this is not an immediate problem for those.

-- 
Michal Hocko
SUSE Labs

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread


Thread

[PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page arrival Lukasz Odzioba <lukasz.odzioba@intel.com> - 2016-06-08 16:40 +0200
  Re: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page  arrival Michal Hocko <mhocko@kernel.org> - 2016-06-08 17:10 +0200
    RE: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page  arrival "Odzioba, Lukasz" <lukasz.odzioba@intel.com> - 2016-06-09 10:10 +0200
  Re: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page  arrival Dave Hansen <dave.hansen@intel.com> - 2016-06-08 17:40 +0200
    Re: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page  arrival Michal Hocko <mhocko@kernel.org> - 2016-06-08 18:10 +0200
      Re: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page  arrival Dave Hansen <dave.hansen@intel.com> - 2016-06-08 18:40 +0200
        Re: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page  arrival Michal Hocko <mhocko@kernel.org> - 2016-06-09 14:30 +0200
    RE: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page  arrival "Odzioba, Lukasz" <lukasz.odzioba@intel.com> - 2016-06-09 11:00 +0200
      Re: [PATCH 1/1] mm/swap.c: flush lru_add pvecs on compound page  arrival Dave Hansen <dave.hansen@intel.com> - 2016-06-09 17:50 +0200

csiph-web