From: Yu Zhao <yuzhao@google.com>
To: Charan Teja Kalla <quic_charante@quicinc.com>
Cc: Jaroslav Pulchart <jaroslav.pulchart@gooddata.com>,
Daniel Secik <daniel.secik@gooddata.com>,
Igor Raits <igor.raits@gooddata.com>,
Kalesh Singh <kaleshsingh@google.com>,
akpm@linux-foundation.org, linux-mm@kvack.org
Subject: Re: high kswapd CPU usage with symmetrical swap in/out pattern with multi-gen LRU
Date: Thu, 7 Dec 2023 11:23:41 -0700 [thread overview]
Message-ID: <CAOUHufZXWSocBeYNsON9CA7orJOWARCAkvb++RZnHphpza7FKg@mail.gmail.com> (raw)
In-Reply-To: <7df7e478-bd93-03df-5b10-19308f416e95@quicinc.com>
On Thu, Dec 7, 2023 at 1:47 AM Charan Teja Kalla
<quic_charante@quicinc.com> wrote:
>
> Hi yu,
>
> On 12/2/2023 5:22 AM, Yu Zhao wrote:
> > Charan, does the fix previously attached seem acceptable to you? Any
> > additional feedback? Thanks.
>
> First, thanks for taking this patch to upstream.
>
> A comment in code snippet is checking just 'high wmark' pages might
> succeed here but can fail in the immediate kswapd sleep, see
> prepare_kswapd_sleep(). This can show up into the increased
> KSWAPD_HIGH_WMARK_HIT_QUICKLY, thus unnecessary kswapd run time.
> @Jaroslav: Have you observed something like above?
>
> So, in downstream, we have something like for zone_watermark_ok():
> unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH << 2;
>
> Hard to convince of this 'MIN_LRU_BATCH << 2' empirical value, may be we
> should atleast use the 'MIN_LRU_BATCH' with the mentioned reasoning, is
> what all I can say for this patch.
Yeah, we can add MIN_LRU_BATCH on top of the high watermark.
next prev parent reply other threads:[~2023-12-07 18:24 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-08 14:35 Jaroslav Pulchart
2023-11-08 18:47 ` Yu Zhao
2023-11-08 20:04 ` Jaroslav Pulchart
2023-11-08 22:09 ` Yu Zhao
2023-11-09 6:39 ` Jaroslav Pulchart
2023-11-09 6:48 ` Yu Zhao
2023-11-09 10:58 ` Jaroslav Pulchart
2023-11-10 1:31 ` Yu Zhao
[not found] ` <CAK8fFZ5xUe=JMOxUWgQ-0aqWMXuZYF2EtPOoZQqr89sjrL+zTw@mail.gmail.com>
2023-11-13 20:09 ` Yu Zhao
2023-11-14 7:29 ` Jaroslav Pulchart
2023-11-14 7:47 ` Yu Zhao
2023-11-20 8:41 ` Jaroslav Pulchart
2023-11-22 6:13 ` Yu Zhao
2023-11-22 7:12 ` Jaroslav Pulchart
2023-11-22 7:30 ` Jaroslav Pulchart
2023-11-22 14:18 ` Yu Zhao
2023-11-29 13:54 ` Jaroslav Pulchart
2023-12-01 23:52 ` Yu Zhao
2023-12-07 8:46 ` Charan Teja Kalla
2023-12-07 18:23 ` Yu Zhao [this message]
2023-12-08 8:03 ` Jaroslav Pulchart
2024-01-03 21:30 ` Jaroslav Pulchart
2024-01-04 3:03 ` Yu Zhao
2024-01-04 9:46 ` Jaroslav Pulchart
2024-01-04 14:34 ` Jaroslav Pulchart
2024-01-04 23:51 ` Igor Raits
2024-01-05 17:35 ` Ertman, David M
2024-01-08 17:53 ` Jaroslav Pulchart
2024-01-16 4:58 ` Yu Zhao
2024-01-16 17:34 ` Jaroslav Pulchart
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=CAOUHufZXWSocBeYNsON9CA7orJOWARCAkvb++RZnHphpza7FKg@mail.gmail.com \
--to=yuzhao@google.com \
--cc=akpm@linux-foundation.org \
--cc=daniel.secik@gooddata.com \
--cc=igor.raits@gooddata.com \
--cc=jaroslav.pulchart@gooddata.com \
--cc=kaleshsingh@google.com \
--cc=linux-mm@kvack.org \
--cc=quic_charante@quicinc.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