linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Yuanchu Xie <yuanchu@google.com>
To: Gregory Price <gourry@gourry.net>
Cc: SeongJae Park <sj@kernel.org>,
	lsf-pc@lists.linux-foundation.org, damon@lists.linux.dev,
	 linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	kernel-team@meta.com,  Raghavendra K T <raghavendra.kt@amd.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	 Kaiyang Zhao <kaiyang2@cs.cmu.edu>,
	Jiaming Yan <jiamingy@amazon.com>,
	 Honggyu Kim <honggyu.kim@sk.com>
Subject: Re: [LSF/MM/BPF TOPIC] DAMON Requirements for Access-aware MM of Future
Date: Wed, 29 Jan 2025 18:15:08 -0800	[thread overview]
Message-ID: <CAJj2-QF1y1XNRYy9sT5c5=pi20+67Duf9B2Amatnu01HLmw06Q@mail.gmail.com> (raw)
In-Reply-To: <Z4XUoWlU-UgRik18@gourry-fedora-PF4VCD3F>

On Mon, Jan 13, 2025 at 7:06 PM Gregory Price <gourry@gourry.net> wrote:
> 5) Scarce resources
>
>    We need to be careful not to consume excessive amounts of resources
>    in an attempt to track all these identifying mechanisms.  Even 1 byte
>    per folio is 256MB on a 1TB machine.  This gets out of hand quick.
>
>    With task-work, I was able to add no additional resource consumption,
>    but deferring to a fully async scenario and needing to track things
>    like last-accessing CPU, timestamps, and etc.
>
>    We'll need to examine this closely if we decide to aggregate either
>    of these mechanisms.
My concern with physical address space monitoring is fragmentation. I
ran some numbers on a few prod machines. Grouping by regions with the
same memcg and ignoring any unmapped memory to be generous, machines
with higher utilization can have a region/total pages ratio of ~40%,
and even those with lower utilization (<50%) can also reach 20%.
Accurately tracking these regions would require quite the region
metadata, on the order of GBs.


  parent reply	other threads:[~2025-01-30  2:15 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-01-01 22:20 SeongJae Park
2025-01-02  4:09 ` Matthew Wilcox
2025-01-02 15:22   ` Gregory Price
2025-01-02 18:00     ` SeongJae Park
2025-01-02 18:04       ` SeongJae Park
2025-01-14  3:06 ` Gregory Price
2025-01-24  2:11   ` SeongJae Park
2025-01-24 17:21     ` Gregory Price
2025-01-25  1:17       ` SeongJae Park
2025-01-30  2:15   ` Yuanchu Xie [this message]
2025-01-30  3:47     ` SeongJae Park
2025-01-31 10:05       ` Jonathan Cameron
2025-01-20 18:46 ` Jonathan Cameron
2025-03-25 21:01 ` 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='CAJj2-QF1y1XNRYy9sT5c5=pi20+67Duf9B2Amatnu01HLmw06Q@mail.gmail.com' \
    --to=yuanchu@google.com \
    --cc=Jonathan.Cameron@huawei.com \
    --cc=damon@lists.linux.dev \
    --cc=gourry@gourry.net \
    --cc=honggyu.kim@sk.com \
    --cc=jiamingy@amazon.com \
    --cc=kaiyang2@cs.cmu.edu \
    --cc=kernel-team@meta.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lsf-pc@lists.linux-foundation.org \
    --cc=raghavendra.kt@amd.com \
    --cc=sj@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