linux-doc.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: SeongJae Park <sj@kernel.org>
Cc: SeongJae Park <sj@kernel.org>,
	"Liam R. Howlett" <Liam.Howlett@oracle.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	David Hildenbrand <david@kernel.org>,
	Jonathan Corbet <corbet@lwn.net>,
	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
	Michal Hocko <mhocko@suse.com>, Mike Rapoport <rppt@kernel.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Vlastimil Babka <vbabka@suse.cz>,
	damon@lists.linux.dev, linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [RFC PATCH v3 24/37] Docs/mm/damon/design: document sample filters
Date: Sun,  7 Dec 2025 22:29:28 -0800	[thread overview]
Message-ID: <20251208062943.68824-25-sj@kernel.org> (raw)
In-Reply-To: <20251208062943.68824-1-sj@kernel.org>

Update DAMON design document for the access sample results filtering.

Signed-off-by: SeongJae Park <sj@kernel.org>
---
 Documentation/mm/damon/design.rst | 42 +++++++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

diff --git a/Documentation/mm/damon/design.rst b/Documentation/mm/damon/design.rst
index a21973b33bc3..9a4679de437f 100644
--- a/Documentation/mm/damon/design.rst
+++ b/Documentation/mm/damon/design.rst
@@ -146,12 +146,17 @@ do the access check using monitoring-purpose page fault events in a way similar
 to NUMA balancing hinting faults.  When it is being used, ``paddr`` installs
 the page protection in a way similar to that of NUMA balancing hinting faults.
 Then the page fault handler reports the faults happend by the installed page
-protection to DAMON core layer.
+protection to DAMON core layer.  Compared to the accessed-bit based one, this
+approach gives more information to DAMON, such as the access-generated
+CPU.
 
 ``paddr`` uses :ref:`accessed-bit based check
 <damon_design_pte_accessed_bit_access_check>` by default, and users can change
 it to use this page faults based one, using :ref:`access sampling primitives
-selection <damon_design_sampling_primitives_selection>`.
+selection <damon_design_sampling_primitives_selection>`.  Also, the addtional
+information can be used for doing monitoring of only specific type accesses,
+using :ref:`access sampling results filters
+<damon_design_sampling_results_filters>`.
 
 .. _damon_design_addr_unit:
 
@@ -277,6 +282,39 @@ support from the operations set implementation for virtual address spaces
 
 At the moment, only exclusive use of the primitives is supported.
 
+.. _damon_design_sampling_results_filters:
+
+Access Sampling Results Filter
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Depending on the access sampling primitives that used, the sampling results
+could inform more than whether an access is made, such as the CPU or the thread
+the sampled access was made from, and whether the sampled access was for
+writing or reading.  By filtering the results based on the additional
+information, DAMON can perform for more detailed access monitoring, such as
+per-CPUs/threads or read/write-only monitoring.
+
+For such special types of monitoring, DAMON provides a feature called "sampling
+results filter".  The feature allows users to set an arbitrary number of
+filters for the sampling results.  Each of the filters specifies
+
+- a type of the additional information (``type``),
+- whether it is for the sampling results of the type or all except the type
+  (``matching``), and
+- whether it is to allow (include) or reject (exclude) consuming of the type of
+  sampling results.
+
+Each filter is applied in the order of the installation.  Only sampling results
+that allowed by previous filters are continue to be evaluated by the next
+filters.  If a sampling result is decided to be rejected by a filter, it is
+just discarded and no later filter is applied.
+
+Below ``type`` of access sampling results filter are currently supported.
+
+- cpumask
+    - Whether the sampled access was generated by a cpu that included in a
+      given cpumask.
+
 
 .. _damon_design_age_tracking:
 
-- 
2.47.3

  parent reply	other threads:[~2025-12-08  6:30 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-08  6:29 [RFC PATCH v3 00/37] mm/damon: introduce per-CPUs/threads/write/read monitoring SeongJae Park
2025-12-08  6:29 ` [RFC PATCH v3 11/37] Docs/mm/damon/design: document page fault sampling primitive SeongJae Park
2025-12-08  6:29 ` [RFC PATCH v3 12/37] Docs/admin-guide/mm/damon/usage: document sample primitives dir SeongJae Park
2025-12-08  6:29 ` SeongJae Park [this message]
2025-12-08  6:29 ` [RFC PATCH v3 25/37] Docs/admin-guide/mm/damon/usage: document sample filters dir SeongJae Park
2025-12-08  6:29 ` [RFC PATCH v3 31/37] Docs/mm/damon/design: document threads type sample filter SeongJae Park
2025-12-08  6:29 ` [RFC PATCH v3 32/37] Docs/admin-guide/mm/damon/usage: document tids_arr file SeongJae Park
2025-12-08  6:29 ` [RFC PATCH v3 37/37] Docs/mm/damon/design: document write access sample filter type 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=20251208062943.68824-25-sj@kernel.org \
    --to=sj@kernel.org \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=corbet@lwn.net \
    --cc=damon@lists.linux.dev \
    --cc=david@kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=mhocko@suse.com \
    --cc=rppt@kernel.org \
    --cc=surenb@google.com \
    --cc=vbabka@suse.cz \
    /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).