mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: SJ Park <sj@kernel.org>
Cc: SJ Park <sj@kernel.org>, "Liam R. Howlett" <liam@infradead.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	David Hildenbrand <david@kernel.org>,
	Jonathan Corbet <corbet@lwn.net>,
	Lorenzo Stoakes <ljs@kernel.org>, Michal Hocko <mhocko@suse.com>,
	Mike Rapoport <rppt@kernel.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Vlastimil Babka <vbabka@kernel.org>,
	damon@lists.linux.dev, linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [RFC PATCH 0/8] mm/damon: introduce hugepage_size probe filter
Date: Sun, 13 Sep 2026 10:11:22 -0700	[thread overview]
Message-ID: <20260913171133.102366-1-sj@kernel.org> (raw)

Knowing whether a given memory is backed by a hugepage of specific size
is useful for efficient utilization of hugepages.  For easy monitoring
of the information, introduce a new data attribute probe filter type,
hugepage_size.  It works similar to the DAMOS filter of the same name.
It works for memory that is backed by a hugepage of a given size range.

Patch 1 introduces the new probe filter type to DAMON API and extends
related data structures.  Patch 2 updates probe filter commit logic to
handle the size range.  Patch 3 Updates the filtering logic to support
the new type.  Patch 4 adds new DAMON sysfs files for the size range.
Patch 5 updates DAMON sysfs interface to fully support the new filter
type.  Patches 6-8 updates design, usage and ABI documents for the new
feature.

Test
====

Set THP always and start a test workload using masim [1].

    $ echo always | sudo tee /sys/kernel/mm/transparent_hugepage/enabled
    $ ./masim.py run --config_file ./configs/stairs-500mb.cfg --repeat 10

Using the DAMON user-space tool, damo [2], start DAMON with two probes.
The primary probe monitors access.  The secondary probe monitors 2 MiB
sized hugepages.  The region adjustment weight is given to only the
primary probe.  That is, this setup is for showing access temperature
and additionally how many 2 MiB hugepages are being used for the region
of the access temperature.

    $ sudo ./damo start $(pidof masim) \
            --probe_prep set_pgidle --probe_filter allow pgidle_unset \
            --probe_filter allow hugepage_size 2M 2M --probe_weight 1 0 \
            --nr_probe_preps 1 0 --nr_probe_filters 1 1 --nr_probes 2

Show the monitoring results.

    $ sudo ./damo report attrs
    heatmap: 000004[...]666666668988888888888844444430000000000000000000000000000000000000000000014[...]8
    # min/max temperatures: -470,000,000, 10,000,500, column size: 64.119 MiB
    probes
    - prep: set_pgidle, filter: allow pgidle_unset (weight: 1)
    - allow hugepage_size [2.000 MiB, 2.000 MiB] (weight: 0)
    intervals: sample 5 ms aggr 100 ms (max probe hits 20)
    #   size         address       age           probe_hits
    0   354.039 MiB  85.833 TiB    4.700 s       0 0
    1   1.843 GiB    127.724 TiB   4.700 s       0 6
    2   936.781 MiB  127.726 TiB   4.600 s       0 16
    [...]
    25  44.000 KiB   127.723 TiB   0 ns          15 20
    26  11.492 MiB   127.723 TiB   0 ns          16 20
    27  2.160 MiB    127.723 TiB   0 ns          19 20
    [...]
    47  376.000 KiB  127.723 TiB   300 ms        1 20
    48  48.000 KiB   127.723 TiB   400 ms        2 20
    49  812.000 KiB  127.723 TiB   500 ms        9 20
    memory bw estimate: 0 B per second
    total size: 5.009 GiB
    record DAMON intervals: sample 5 ms, aggr 100 ms

The first probe_hits count and the age show the access temperature of
each region.  The second probe_hits count shows the ratio of 2 MiB
hugepages in the region.

For example, region 2, which has 936 MiB size, is quite cold (not
accessed for 4.6 seconds) but uses 2 MiB THP for ~80% (16/20) of the
region.  Maybe not a very efficient use of THP.

On the other hand, region 49, which is 812 KiB size, is somewhat hot
(accessed about 9 times per 100 ms for the last 500 ms) and fully backed
by 2 MiB hugepage.  Maybe this is a good use of THP.

[1] https://github.com/sjp38/masim
[2] https://github.com/damonitor/damo

SJ Park (8):
  mm/damon/api: introduce DAMON_FILTER_TYPE_HUGEPAGE_SIZE
  mm/damon/core: commit hugepage_size type damon filter
  mm/damon/ops-common: support hugepage_size damon filter matching
  mm/damon/sysfs: add min,max files under probe filter directory
  mm/damon/sysfs: support hugepage_size probe filter
  Docs/mm/damon/design: update for hugepage_size probe filter
  Docs/admin-guide/mm/damon/usage: update for hugepage_size
  Docs/ABI/damon: update for hugepage_size probe filter

 .../ABI/testing/sysfs-kernel-mm-damon         | 14 +++++
 Documentation/admin-guide/mm/damon/usage.rst  |  4 +-
 Documentation/mm/damon/design.rst             |  2 +
 include/linux/damon.h                         |  8 +++
 mm/damon/core.c                               | 20 +++++--
 mm/damon/ops-common.c                         | 10 ++++
 mm/damon/sysfs.c                              | 55 +++++++++++++++++++
 7 files changed, 107 insertions(+), 6 deletions(-)


base-commit: 91c120b49e83b867e29684fd229c3e1f07190071
-- 
2.47.3

             reply	other threads:[~2026-09-13 17:11 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-13 17:11 SJ Park [this message]
2026-09-13 17:11 ` [RFC PATCH 1/8] mm/damon/api: introduce DAMON_FILTER_TYPE_HUGEPAGE_SIZE SJ Park
2026-09-13 17:11 ` [RFC PATCH 2/8] mm/damon/core: commit hugepage_size type damon filter SJ Park
2026-09-13 17:11 ` [RFC PATCH 3/8] mm/damon/ops-common: support hugepage_size damon filter matching SJ Park
2026-09-13 17:11 ` [RFC PATCH 4/8] mm/damon/sysfs: add min,max files under probe filter directory SJ Park
2026-09-13 17:11 ` [RFC PATCH 5/8] mm/damon/sysfs: support hugepage_size probe filter SJ Park
2026-09-13 17:11 ` [RFC PATCH 6/8] Docs/mm/damon/design: update for " SJ Park
2026-09-13 17:11 ` [RFC PATCH 7/8] Docs/admin-guide/mm/damon/usage: update for hugepage_size SJ Park
2026-09-13 17:11 ` [RFC PATCH 8/8] Docs/ABI/damon: update for hugepage_size probe filter SJ 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=20260913171133.102366-1-sj@kernel.org \
    --to=sj@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=corbet@lwn.net \
    --cc=damon@lists.linux.dev \
    --cc=david@kernel.org \
    --cc=liam@infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=mhocko@suse.com \
    --cc=rdunlap@infradead.org \
    --cc=rppt@kernel.org \
    --cc=skhan@linuxfoundation.org \
    --cc=surenb@google.com \
    --cc=vbabka@kernel.org \
    /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

all inboxes | Powered by JetHome®