Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:4 as permitted sender) client-ip=2620:137:e000::3:4;
From:   Stefan Roesch <shr@devkernel.io>
To:     kernel-team@fb.com
Cc:     shr@devkernel.io, akpm@linux-foundation.org, david@redhat.com,
        hannes@cmpxchg.org, riel@surriel.com, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org
Subject: [PATCH v2 0/4] Smart scanning mode for KSM
Date:   Mon, 18 Sep 2023 11:58:12 -0700
Message-Id: <20230918185816.1518366-1-shr@devkernel.io>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

This patch series adds "smart scanning" for KSM.

What is smart scanning?
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
KSM evaluates all the candidate pages for each scan. It does not use hist=
oric
information from previous scans. This has the effect that candidate pages=
 that
couldn't be used for KSM de-duplication continue to be evaluated for each=
 scan.

The idea of "smart scanning" is to keep historic information. With the hi=
storic
information we can temporarily skip the candidate page for one or several=
 scans.

Details:
=3D=3D=3D=3D=3D=3D=3D=3D
"Smart scanning" is to keep two small counters to store if the page has b=
een
used for KSM. One counter stores how often we already tried to use the pa=
ge for
KSM and the other counter stores when a page will be used as a candidate =
page
again.

How often we skip the candidate page depends how often a page failed KSM
de-duplication. The code skips a maximum of 8 times. During testing this =
has
shown to be a good compromise for different workloads.

New sysfs knob:
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
Smart scanning is not enabled by default. With /sys/kernel/mm/ksm/smart_s=
can
smart scanning can be enabled.

Monitoring:
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
To monitor how effective smart scanning is a new sysfs knob has been intr=
oduced.
/sys/kernel/mm/pages_skipped report how many pages have been skipped by s=
mart
scanning.

Results:
=3D=3D=3D=3D=3D=3D=3D=3D
- Various workloads have shown a 20% - 25% reduction in page scans
  For the instagram workload for instance, the number of pages scanned ha=
s been
  reduced from over 20M pages per scan to less than 15M pages.
- Less pages scans also resulted in an overall higher de-duplication rate=
 as
  some shorter lived pages could be de-duplicated additionally
- Less pages scanned allows to reduce the pages_to_scan parameter
  and this resulted in  a 25% reduction in terms of CPU.
- The improvements have been observed for workloads that enable KSM with
  madvise as well as prctl


Changes:
  - V2:
    - Renamed function inc_skip_age() to skip_age()
    - Added comment to skip_age() function
    - Renamed function skip_rmap_item() to should_skip_rmap_item()
    - Added more comments to should_skip_rmap_item function
    - Added explicit modification of age with overflow check


Stefan Roesch (4):
  mm/ksm: add "smart" page scanning mode
  mm/ksm: add pages_skipped metric
  mm/ksm: document smart scan mode
  mm/ksm: document pages_skipped sysfs knob

 Documentation/admin-guide/mm/ksm.rst |  11 +++
 mm/ksm.c                             | 120 +++++++++++++++++++++++++++
 2 files changed, 131 insertions(+)


base-commit: 15bcc9730fcd7526a3b92eff105d6701767a53bb
--=20
2.39.3