linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
To: cgroups@vger.kernel.org
Cc: "linux-mm@kvack.org" <linux-mm@kvack.org>,
	Michal Hocko <mhocko@kernel.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	"n.fahldieck@profihost.ag" <n.fahldieck@profihost.ag>,
	Daniel Aberger - Profihost AG <d.aberger@profihost.ag>,
	p.kramme@profihost.ag
Subject: No memory reclaim while reaching MemoryHigh
Date: Thu, 25 Jul 2019 15:17:17 +0200	[thread overview]
Message-ID: <496dd106-abdd-3fca-06ad-ff7abaf41475@profihost.ag> (raw)

Hello all,

i hope i added the right list and people - if i missed someone i would
be happy to know.

While using kernel 4.19.55 and cgroupv2 i set a MemoryHigh value for a
varnish service.

It happens that the varnish.service cgroup reaches it's MemoryHigh value
and stops working due to throttling.

But i don't understand is that the process itself only consumes 40% of
it's cgroup usage.

So the other 60% is dirty dentries and inode cache. If i issue an
echo 3 > /proc/sys/vm/drop_caches

the varnish cgroup memory usage drops to the 50% of the pure process.

I thought that the kernel would trigger automatic memory reclaim if a
cgroup reaches is memory high value to drop caches.

Isn't it? does it needs a special flag or tuning? Is this expected?

Before drop caches:
   Memory: 13.1G (high: 13.0G)

After drop caches:
   Memory: 5.8G (high: 13.0G)

Greets,
Stefan


             reply	other threads:[~2019-07-25 13:17 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-25 13:17 Stefan Priebe - Profihost AG [this message]
2019-07-25 14:01 ` Michal Hocko
2019-07-25 21:37   ` Stefan Priebe - Profihost AG
2019-07-26  7:45     ` Michal Hocko
2019-07-26 18:30       ` Stefan Priebe - Profihost AG
2019-07-28 21:11         ` Stefan Priebe - Profihost AG
2019-07-28 21:39           ` Chris Down
2019-07-29  5:34             ` Stefan Priebe - Profihost AG
2019-07-29  7:07           ` Stefan Priebe - Profihost AG
2019-07-29  7:45             ` Stefan Priebe - Profihost AG
2019-07-31 13:03               ` Michal Hocko
2019-07-25 14:53 ` Chris Down
2019-07-25 21:42   ` Stefan Priebe - Profihost AG

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=496dd106-abdd-3fca-06ad-ff7abaf41475@profihost.ag \
    --to=s.priebe@profihost.ag \
    --cc=cgroups@vger.kernel.org \
    --cc=d.aberger@profihost.ag \
    --cc=hannes@cmpxchg.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=n.fahldieck@profihost.ag \
    --cc=p.kramme@profihost.ag \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox