All of lore.kernel.org
 help / color / mirror / Atom feed
From: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>,
	Michal Hocko <mhocko@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/7] mm: memcontrol: charge swap to cgroup2
Date: Thu, 17 Dec 2015 11:46:27 +0900	[thread overview]
Message-ID: <56722203.5030604@jp.fujitsu.com> (raw)
In-Reply-To: <20151216110912.GA29816@cmpxchg.org>

On 2015/12/16 20:09, Johannes Weiner wrote:
> On Wed, Dec 16, 2015 at 12:18:30PM +0900, Kamezawa Hiroyuki wrote:
>> Hmm, my requests are
>>   - set the same capabilities as mlock() to set swap.limit=0
>
> Setting swap.max is already privileged operation.
>
Sure.

>>   - swap-full notification via vmpressure or something mechanism.
>
> Why?
>

I think it's a sign of unhealthy condition, starting file cache drop rate to rise.
But I forgot that there are resource threshold notifier already. Does the notifier work
for swap.usage ?

>>   - OOM-Killer's available memory calculation may be corrupted, please check.
>
> Vladimir updated mem_cgroup_get_limit().
>
I'll check it.

>>   - force swap-in at reducing swap.limit
>
> Why?
>
If full, swap.limit cannot be reduced even if there are available memory in a cgroup.
Another cgroup cannot make use of the swap resource while it's occupied by other cgroup.
The job scheduler should have a chance to fix the situation.

Thanks,
-Kame

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>,
	Michal Hocko <mhocko@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/7] mm: memcontrol: charge swap to cgroup2
Date: Thu, 17 Dec 2015 11:46:27 +0900	[thread overview]
Message-ID: <56722203.5030604@jp.fujitsu.com> (raw)
In-Reply-To: <20151216110912.GA29816@cmpxchg.org>

On 2015/12/16 20:09, Johannes Weiner wrote:
> On Wed, Dec 16, 2015 at 12:18:30PM +0900, Kamezawa Hiroyuki wrote:
>> Hmm, my requests are
>>   - set the same capabilities as mlock() to set swap.limit=0
>
> Setting swap.max is already privileged operation.
>
Sure.

>>   - swap-full notification via vmpressure or something mechanism.
>
> Why?
>

I think it's a sign of unhealthy condition, starting file cache drop rate to rise.
But I forgot that there are resource threshold notifier already. Does the notifier work
for swap.usage ?

>>   - OOM-Killer's available memory calculation may be corrupted, please check.
>
> Vladimir updated mem_cgroup_get_limit().
>
I'll check it.

>>   - force swap-in at reducing swap.limit
>
> Why?
>
If full, swap.limit cannot be reduced even if there are available memory in a cgroup.
Another cgroup cannot make use of the swap resource while it's occupied by other cgroup.
The job scheduler should have a chance to fix the situation.

Thanks,
-Kame


  reply	other threads:[~2015-12-17  2:47 UTC|newest]

Thread overview: 78+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-12-10 11:39 [PATCH 0/7] Add swap accounting to cgroup2 Vladimir Davydov
2015-12-10 11:39 ` Vladimir Davydov
2015-12-10 11:39 ` [PATCH 1/7] mm: memcontrol: charge swap " Vladimir Davydov
2015-12-10 11:39   ` Vladimir Davydov
2015-12-10 16:00   ` Johannes Weiner
2015-12-10 16:00     ` Johannes Weiner
2015-12-10 17:00     ` Vladimir Davydov
2015-12-10 17:00       ` Vladimir Davydov
2015-12-11  2:48   ` Kamezawa Hiroyuki
2015-12-11  2:48     ` Kamezawa Hiroyuki
2015-12-11  7:39     ` Vladimir Davydov
2015-12-11  7:39       ` Vladimir Davydov
2015-12-14 15:30   ` Michal Hocko
2015-12-14 15:30     ` Michal Hocko
2015-12-14 15:48     ` Johannes Weiner
2015-12-14 15:48       ` Johannes Weiner
2015-12-14 19:42     ` Vladimir Davydov
2015-12-14 19:42       ` Vladimir Davydov
2015-12-14 19:52       ` One Thousand Gnomes
2015-12-14 19:52         ` One Thousand Gnomes
2015-12-15  3:22       ` Kamezawa Hiroyuki
2015-12-15  3:22         ` Kamezawa Hiroyuki
2015-12-15 11:02         ` Vladimir Davydov
2015-12-15 11:02           ` Vladimir Davydov
2015-12-16  2:44           ` Kamezawa Hiroyuki
2015-12-16  2:44             ` Kamezawa Hiroyuki
2015-12-15 14:50         ` Johannes Weiner
2015-12-15 14:50           ` Johannes Weiner
2015-12-16  3:18           ` Kamezawa Hiroyuki
2015-12-16  3:18             ` Kamezawa Hiroyuki
2015-12-16 11:09             ` Johannes Weiner
2015-12-16 11:09               ` Johannes Weiner
2015-12-17  2:46               ` Kamezawa Hiroyuki [this message]
2015-12-17  2:46                 ` Kamezawa Hiroyuki
2015-12-17  3:32                 ` Johannes Weiner
2015-12-17  3:32                   ` Johannes Weiner
2015-12-17  4:29                   ` Kamezawa Hiroyuki
2015-12-17  4:29                     ` Kamezawa Hiroyuki
2015-12-15 17:21       ` Michal Hocko
2015-12-15 17:21         ` Michal Hocko
2015-12-15 20:22         ` Johannes Weiner
2015-12-15 20:22           ` Johannes Weiner
2015-12-16  3:57         ` Kamezawa Hiroyuki
2015-12-16  3:57           ` Kamezawa Hiroyuki
2015-12-15  3:12     ` Kamezawa Hiroyuki
2015-12-15  3:12       ` Kamezawa Hiroyuki
2015-12-15  8:30       ` Vladimir Davydov
2015-12-15  8:30         ` Vladimir Davydov
2015-12-15  9:29         ` Kamezawa Hiroyuki
2015-12-15  9:29           ` Kamezawa Hiroyuki
2015-12-10 11:39 ` [PATCH 2/7] mm: vmscan: pass memcg to get_scan_count() Vladimir Davydov
2015-12-10 11:39   ` Vladimir Davydov
2015-12-11 19:24   ` Johannes Weiner
2015-12-11 19:24     ` Johannes Weiner
2015-12-10 11:39 ` [PATCH 3/7] mm: memcontrol: replace mem_cgroup_lruvec_online with mem_cgroup_online Vladimir Davydov
2015-12-10 11:39   ` Vladimir Davydov
2015-12-11 19:25   ` Johannes Weiner
2015-12-11 19:25     ` Johannes Weiner
2015-12-10 11:39 ` [PATCH 4/7] swap.h: move memcg related stuff to the end of the file Vladimir Davydov
2015-12-10 11:39   ` Vladimir Davydov
2015-12-11 19:25   ` Johannes Weiner
2015-12-11 19:25     ` Johannes Weiner
2015-12-10 11:39 ` [PATCH 5/7] mm: vmscan: do not scan anon pages if memcg swap limit is hit Vladimir Davydov
2015-12-10 11:39   ` Vladimir Davydov
2015-12-11 19:27   ` Johannes Weiner
2015-12-11 19:27     ` Johannes Weiner
2015-12-10 11:39 ` [PATCH 6/7] mm: free swap cache aggressively if memcg swap is full Vladimir Davydov
2015-12-10 11:39   ` Vladimir Davydov
2015-12-11 19:33   ` Johannes Weiner
2015-12-11 19:33     ` Johannes Weiner
2015-12-12 16:18     ` Vladimir Davydov
2015-12-12 16:18       ` Vladimir Davydov
2015-12-10 11:39 ` [PATCH 7/7] Documentation: cgroup: add memory.swap.{current,max} description Vladimir Davydov
2015-12-10 11:39   ` Vladimir Davydov
2015-12-11 19:42   ` Johannes Weiner
2015-12-11 19:42     ` Johannes Weiner
2015-12-12 16:19     ` Vladimir Davydov
2015-12-12 16:19       ` Vladimir Davydov

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=56722203.5030604@jp.fujitsu.com \
    --to=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=vdavydov@virtuozzo.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.