From: Pasha Tatashin <pasha.tatashin@soleen.com>
To: David Hildenbrand <david@redhat.com>
Cc: akpm@linux-foundation.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-cxl@vger.kernel.org,
cerasuolodomenico@gmail.com, hannes@cmpxchg.org,
j.granados@samsung.com, lizhijian@fujitsu.com,
muchun.song@linux.dev, nphamcs@gmail.com, rientjes@google.com,
rppt@kernel.org, souravpanda@google.com, vbabka@suse.cz,
willy@infradead.org, dan.j.williams@intel.com,
yi.zhang@redhat.com, alison.schofield@intel.com,
yosryahmed@google.com
Subject: Re: [PATCH v3 3/4] mm: add system wide stats items category
Date: Thu, 8 Aug 2024 15:01:46 -0400 [thread overview]
Message-ID: <CA+CK2bD-8W7AP+Oedm0m9EROQZ4euLjZBhqaZJARLW02HWd6iw@mail.gmail.com> (raw)
In-Reply-To: <9cf6cbc1-67c0-4ae5-ae5e-5033631e61b6@redhat.com>
On Thu, Aug 8, 2024 at 2:20 PM David Hildenbrand <david@redhat.com> wrote:
>
> On 08.08.24 17:42, Pasha Tatashin wrote:
> > /proc/vmstat contains events and stats, events can only grow, but stats
> > can grow and srhink.
>
> s/shrink/
Thanks, fixed.
>
> I think we discussed exposing this in /proc/meminfo. There, it would be
> much easier to simply have a global variable, print it, and be done with
> it. Like we do with TotalCma.
Originally, Sourav had proposed adding per-page metadata stat to
/proc/meminfo, but it was decided against, because all the other stats
in /proc/meminfo are part of MemTotal, but memmap allocations are not
always part of MemTotal which makes things confusing.
This is why it makes sense to keep nr_memmap only in /proc/vmstat.
next prev parent reply other threads:[~2024-08-08 19:02 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-08 15:42 [PATCH v3 0/4] Fixes for memmap accounting Pasha Tatashin
2024-08-08 15:42 ` [PATCH v3 1/4] mm: update the memmap stat before page is freed Pasha Tatashin
2024-08-08 17:17 ` Yosry Ahmed
2024-08-08 17:20 ` Yosry Ahmed
2024-08-08 17:37 ` Pasha Tatashin
2024-08-08 17:17 ` Fan Ni
2024-08-08 15:42 ` [PATCH v3 2/4] mm: don't account memmap on failure Pasha Tatashin
2024-08-08 17:18 ` Yosry Ahmed
2024-08-08 17:19 ` Fan Ni
2024-08-08 18:12 ` David Hildenbrand
2024-08-08 18:54 ` Pasha Tatashin
2024-08-08 15:42 ` [PATCH v3 3/4] mm: add system wide stats items category Pasha Tatashin
2024-08-08 18:20 ` David Hildenbrand
2024-08-08 19:01 ` Pasha Tatashin [this message]
2024-08-08 15:42 ` [PATCH v3 4/4] mm: don't account memmap per-node Pasha Tatashin
2024-08-08 18:26 ` David Hildenbrand
2024-08-08 19:03 ` Pasha Tatashin
2024-08-08 18:55 ` Alison Schofield
2024-08-08 19:05 ` Pasha Tatashin
2024-08-08 21:12 ` Alison Schofield
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=CA+CK2bD-8W7AP+Oedm0m9EROQZ4euLjZBhqaZJARLW02HWd6iw@mail.gmail.com \
--to=pasha.tatashin@soleen.com \
--cc=akpm@linux-foundation.org \
--cc=alison.schofield@intel.com \
--cc=cerasuolodomenico@gmail.com \
--cc=dan.j.williams@intel.com \
--cc=david@redhat.com \
--cc=hannes@cmpxchg.org \
--cc=j.granados@samsung.com \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizhijian@fujitsu.com \
--cc=muchun.song@linux.dev \
--cc=nphamcs@gmail.com \
--cc=rientjes@google.com \
--cc=rppt@kernel.org \
--cc=souravpanda@google.com \
--cc=vbabka@suse.cz \
--cc=willy@infradead.org \
--cc=yi.zhang@redhat.com \
--cc=yosryahmed@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