From: Minchan Kim <minchan@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
linux-mm <linux-mm@kvack.org>,
linux-api@vger.kernel.org, oleksandr@redhat.com,
Suren Baghdasaryan <surenb@google.com>,
Tim Murray <timmurray@google.com>,
Daniel Colascione <dancol@google.com>,
Sandeep Patil <sspatil@google.com>,
Sonny Rao <sonnyrao@google.com>,
Brian Geffon <bgeffon@google.com>, Michal Hocko <mhocko@suse.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Shakeel Butt <shakeelb@google.com>,
John Dias <joaodias@google.com>, Minchan Kim <minchan@kernel.org>
Subject: [PATCH 4/4] mm/madvise: allow KSM hints for remote API
Date: Fri, 10 Jan 2020 13:34:33 -0800 [thread overview]
Message-ID: <20200110213433.94739-5-minchan@kernel.org> (raw)
In-Reply-To: <20200110213433.94739-1-minchan@kernel.org>
From: Oleksandr Natalenko <oleksandr@redhat.com>
It all began with the fact that KSM works only on memory that is marked
by madvise(). And the only way to get around that is to either:
* use LD_PRELOAD; or
* patch the kernel with something like UKSM or PKSM.
(i skip ptrace can of worms here intentionally)
To overcome this restriction, lets employ a new remote madvise API. This
can be used by some small userspace helper daemon that will do auto-KSM
job for us.
I think of two major consumers of remote KSM hints:
* hosts, that run containers, especially similar ones and especially in
a trusted environment, sharing the same runtime like Node.js;
* heavy applications, that can be run in multiple instances, not
limited to opensource ones like Firefox, but also those that cannot be
modified since they are binary-only and, maybe, statically linked.
Speaking of statistics, more numbers can be found in the very first
submission, that is related to this one [1]. For my current setup with
two Firefox instances I get 100 to 200 MiB saved for the second instance
depending on the amount of tabs.
1 FF instance with 15 tabs:
$ echo "$(cat /sys/kernel/mm/ksm/pages_sharing) * 4 / 1024" | bc
410
2 FF instances, second one has 12 tabs (all the tabs are different):
$ echo "$(cat /sys/kernel/mm/ksm/pages_sharing) * 4 / 1024" | bc
592
At the very moment I do not have specific numbers for containerised
workload, but those should be comparable in case the containers share
similar/same runtime.
[1] https://lore.kernel.org/patchwork/patch/1012142/
Signed-off-by: Oleksandr Natalenko <oleksandr@redhat.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
mm/madvise.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/mm/madvise.c b/mm/madvise.c
index eb42b2b7f49b..3aa9aec6bfd9 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1000,6 +1000,8 @@ process_madvise_behavior_valid(int behavior)
switch (behavior) {
case MADV_COLD:
case MADV_PAGEOUT:
+ case MADV_MERGEABLE:
+ case MADV_UNMERGEABLE:
return true;
default:
return false;
--
2.25.0.rc1.283.g88dfdc4193-goog
next prev parent reply other threads:[~2020-01-10 21:34 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-10 21:34 [PATCH 0/4] introduce memory hinting API for external process Minchan Kim
2020-01-10 21:34 ` [PATCH 1/4] mm: factor out madvise's core functionality Minchan Kim
2020-01-11 7:37 ` SeongJae Park
2020-01-13 18:11 ` Minchan Kim
2020-01-13 18:22 ` SeongJae Park
2020-01-10 21:34 ` [PATCH 2/4] mm: introduce external memory hinting API Minchan Kim
2020-01-11 7:34 ` SeongJae Park
2020-01-13 18:02 ` Minchan Kim
2020-01-13 8:47 ` Kirill Tkhai
2020-01-13 10:42 ` Christian Brauner
2020-01-13 18:44 ` Minchan Kim
2020-01-13 19:10 ` Christian Brauner
2020-01-13 19:27 ` Daniel Colascione
2020-01-13 20:42 ` Christian Brauner
2020-01-13 21:04 ` Daniel Colascione
2020-01-14 19:20 ` Christian Brauner
2020-01-14 18:59 ` Minchan Kim
2020-01-14 19:22 ` Christian Brauner
2020-01-13 18:39 ` Minchan Kim
2020-01-13 19:18 ` Daniel Colascione
2020-01-14 8:39 ` Kirill Tkhai
2020-01-14 19:12 ` Minchan Kim
2020-01-15 9:38 ` Kirill Tkhai
2020-01-10 21:34 ` [PATCH 3/4] mm/madvise: employ mmget_still_valid for write lock Minchan Kim
2020-01-10 21:34 ` Minchan Kim [this message]
2020-01-11 7:42 ` [PATCH 4/4] mm/madvise: allow KSM hints for remote API SeongJae Park
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=20200110213433.94739-5-minchan@kernel.org \
--to=minchan@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=bgeffon@google.com \
--cc=dancol@google.com \
--cc=hannes@cmpxchg.org \
--cc=joaodias@google.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=oleksandr@redhat.com \
--cc=shakeelb@google.com \
--cc=sonnyrao@google.com \
--cc=sspatil@google.com \
--cc=surenb@google.com \
--cc=timmurray@google.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 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).