mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Xueyuan Chen <xueyuan.chen@vivo.com>
To: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Minchan Kim <minchan@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	xueyuan.chen21@gmail.com
Subject: Re: [RFC PATCH 0/2] mm: zsmalloc: make shrinker compaction budget-aware
Date: Fri, 7 Aug 2026 18:57:32 +0800	[thread overview]
Message-ID: <47ed45b5-de67-41aa-aa21-a3ba3479a7cc@vivo.com> (raw)
In-Reply-To: <anVWZVOt-xeD0dMH@google.com>

Hi Sergey,

Here is some additional data:

I used the following definitions:
   compactable ratio = freeable_pages / total_pages
   memory reclaimed  = pages_freed * PAGE_SIZE

freeable_pages is the estimate before compaction, based on the same
calculation as zs_shrinker_count(), while pages_freed is the actual
number of backing pages released.

There were 264 callbacks in the trace:
   callback elapsed time:
     median:    5.77 ms
     p95:      55.82 ms
     maximum: 271.36 ms

   compactable ratio before compaction:
     median:   0.32%
     p95:      2.86%
     maximum:  8.33%

   memory reclaimed per callback:
     median:    3.80 MiB
     p95:      30.45 MiB
     maximum:  92.73 MiB

The longest callback took 271.36 ms. Its compactable ratio was 3.25%,
and it released 7,650 pages, or about 29.88 MiB.

There was also a 241.91 ms callback (with 30 schedule-outs) with a
compactable ratio of 0.44%. It released 1,019 pages, or about
3.98 MiB.

Based on this data, it seems better to remove the shrinker.

Would you prefer that I change v2 to remove the zsmalloc shrinker
callbacks directly?

Thanks,
Xueyuan


On 8/7/2026 11:56 AM, Sergey Senozhatsky wrote:
> On (26/08/06 16:27), xueyuan.chen@vivo.com wrote:
>> On an Android device with 12 GB of RAM, observed zsmalloc compaction
>> durations had a p95 of 38.86 ms and a maximum of 269.68 ms, motivating a
>> per-scan reclaim goal.
> Would it be possible to give a little more data?  What was the
> fragmentation ratio, how much memory was saved during that
> auto-compaction, etc.  If possible.
>
> Somewhere in the back of my mind I was thinking about, maybe,
> disabling (removing) zsmalloc shrinker callbacks, in other words
> disabling auto-compaction.  We have a sysfs knob for pool compaction
> for system that still want to run compaction.  So I'm leaning towards
> removal of shrinker callbacks from zsmalloc.

  reply	other threads:[~2026-08-07 10:57 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <cover.1786003779.git.xueyuan.chen@vivo.com>
2026-08-07  3:56 ` Sergey Senozhatsky
2026-08-07 10:57   ` Xueyuan Chen [this message]
2026-08-07 12:12     ` Sergey Senozhatsky
2026-08-07 16:25       ` Nhat Pham
2026-08-11  9:03         ` Xueyuan Chen
2026-08-11 16:25           ` Nhat Pham
2026-08-14 16:50             ` Xueyuan Chen
2026-08-18 12:11             ` Xueyuan Chen
2026-10-29  1:43         ` Sergey Senozhatsky
2026-10-29  1:48           ` Sergey Senozhatsky
2026-11-02  2:58             ` Xueyuan Chen
2026-11-04 18:06             ` Nhat Pham
2026-10-30  2:05           ` Xueyuan Chen
2026-10-29  2:26         ` Sergey Senozhatsky
2026-11-01 23:47           ` Sergey Senozhatsky
2026-11-02 20:24             ` Chris Wiseman
2026-11-04 17:57               ` Nhat Pham
2026-11-04 18:46                 ` Chris Wiseman
2026-11-04 21:54                   ` Nhat Pham
2026-11-05  1:10                     ` Xueyuan Chen
2026-11-05  5:05                       ` Sergey Senozhatsky
2026-11-05 13:36                         ` Chris Wiseman
2026-11-05 15:08                           ` Nhat Pham
2026-11-05 15:32                             ` Xueyuan Chen
2026-11-05 15:38                             ` Yosry Ahmed
2026-11-05 15:39                               ` Yosry Ahmed
2026-11-05 16:53                                 ` Chris Wiseman
2026-11-05 16:56                                   ` Yosry Ahmed
2026-11-12  5:58                                   ` Sergey Senozhatsky
2026-11-05 15:24                         ` Xueyuan Chen
2026-11-05  5:01                     ` Sergey Senozhatsky

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=47ed45b5-de67-41aa-aa21-a3ba3479a7cc@vivo.com \
    --to=xueyuan.chen@vivo.com \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=minchan@kernel.org \
    --cc=senozhatsky@chromium.org \
    --cc=xueyuan.chen21@gmail.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

all inboxes | Powered by JetHome®