LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: David Rientjes <rientjes@google.com>
To: "Li,Rongqing" <lirongqing@baidu.com>
Cc: Michal Hocko <mhocko@kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"cgroups@vger.kernel.org" <cgroups@vger.kernel.org>,
	"hannes@cmpxchg.org" <hannes@cmpxchg.org>,
	Andrey Ryabinin <aryabinin@virtuozzo.com>
Subject: Re: 答复: 答复: [PATCH] mm/memcontrol.c: speed up to force empty a memory cgroup
Date: Mon, 19 Mar 2018 10:51:57 -0700 (PDT)	[thread overview]
Message-ID: <alpine.DEB.2.20.1803191044310.177918@chino.kir.corp.google.com> (raw)
In-Reply-To: <2AD939572F25A448A3AE3CAEA61328C2374589DC@BC-MAIL-M28.internal.baidu.com>

On Mon, 19 Mar 2018, Li,Rongqing wrote:

> > > Although SWAP_CLUSTER_MAX is used at the lower level, but the call
> > > stack of try_to_free_mem_cgroup_pages is too long, increase the
> > > nr_to_reclaim can reduce times of calling
> > > function[do_try_to_free_pages, shrink_zones, hrink_node ]
> > >
> > > mem_cgroup_resize_limit
> > > --->try_to_free_mem_cgroup_pages:  .nr_to_reclaim = max(1024,
> > > --->SWAP_CLUSTER_MAX),
> > >    ---> do_try_to_free_pages
> > >      ---> shrink_zones
> > >       --->shrink_node
> > >        ---> shrink_node_memcg
> > >          ---> shrink_list          <-------loop will happen in this place
> > [times=1024/32]
> > >            ---> shrink_page_list
> > 
> > Can you actually measure this to be the culprit. Because we should rethink
> > our call path if it is too complicated/deep to perform well.
> > Adding arbitrary batch sizes doesn't sound like a good way to go to me.
> 
> Ok, I will try
> 

Looping in mem_cgroup_resize_limit(), which takes memcg_limit_mutex on 
every iteration which contends with lowering limits in other cgroups (on 
our systems, thousands), calling try_to_free_mem_cgroup_pages() with less 
than SWAP_CLUSTER_MAX is lame.  It would probably be best to limit the 
nr_pages to the amount that needs to be reclaimed, though, rather than 
over reclaiming.

If you wanted to be invasive, you could change page_counter_limit() to 
return the count - limit, fix up the callers that look for -EBUSY, and 
then use max(val, SWAP_CLUSTER_MAX) as your nr_pages.

  reply	other threads:[~2018-03-19 17:52 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-19  8:29 Li RongQing
2018-03-19  8:53 ` Michal Hocko
     [not found]   ` <2AD939572F25A448A3AE3CAEA61328C23745764B@BC-MAIL-M28.internal.baidu.com>
2018-03-19 10:37     ` 答复: " Michal Hocko
2018-03-19 10:51       ` 答复: " Li,Rongqing
2018-03-19 17:51         ` David Rientjes [this message]
2018-03-20  8:39           ` Michal Hocko
2018-03-20 20:29             ` David Rientjes
2018-03-20 22:08               ` Andrey Ryabinin
2018-03-20 22:15                 ` David Rientjes
2018-03-20 22:35                   ` Andrey Ryabinin
2018-03-20 22:45                     ` David Rientjes
2018-03-21  9:59                     ` Michal Hocko
2018-03-23  2:58         ` Li,Rongqing
2018-03-23 10:08           ` Michal Hocko
2018-03-23 12:04             ` 答复: " Li,Rongqing
2018-03-23 12:29               ` Michal Hocko
2018-03-23 10:34 ` Michal Hocko

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=alpine.DEB.2.20.1803191044310.177918@chino.kir.corp.google.com \
    --to=rientjes@google.com \
    --cc=aryabinin@virtuozzo.com \
    --cc=cgroups@vger.kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lirongqing@baidu.com \
    --cc=mhocko@kernel.org \
    --subject='Re: 答复: 答复: [PATCH] mm/memcontrol.c: speed up to force empty a memory cgroup' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).