From: Andrew Morton <akpm@linux-foundation.org>
To: Hongchen Zhang <zhanghongchen@loongson.cn>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] mm/vmscan: don't scan adjust too much if current is not kswapd
Date: Wed, 14 Sep 2022 15:51:42 -0700 [thread overview]
Message-ID: <20220914155142.bf388515a39fb45bae987231@linux-foundation.org> (raw)
In-Reply-To: <20220914023318.549118-1-zhanghongchen@loongson.cn>
On Wed, 14 Sep 2022 10:33:18 +0800 Hongchen Zhang <zhanghongchen@loongson.cn> wrote:
> when a process falls into page fault and there is not enough free
> memory,it will do direct reclaim. At the same time,it is holding
> mmap_lock.So in case of multi-thread,it should exit from page fault
> ASAP.
> When reclaim memory,we do scan adjust between anon and file lru which
> may cost too much time and trigger hung task for other thread.So for a
> process which is not kswapd,it should just do a little scan adjust.
Well, that's a pretty nasty bug. Before diving into a possible fix,
can you please tell us more about how this happens? What sort of
machine, what sort of workload. Can you suggest why others are not
experiencing this?
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -3042,11 +3042,17 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
> nr[lru] = targets[lru] * (100 - percentage) / 100;
> nr[lru] -= min(nr[lru], nr_scanned);
>
> + if (!current_is_kswapd())
> + nr[lru] = min(nr[lru], nr_to_reclaim);
> +
> lru += LRU_ACTIVE;
> nr_scanned = targets[lru] - nr[lru];
> nr[lru] = targets[lru] * (100 - percentage) / 100;
> nr[lru] -= min(nr[lru], nr_scanned);
>
> + if (!current_is_kswapd())
> + nr[lru] = min(nr[lru], nr_to_reclaim);
> +
> scan_adjusted = true;
> }
> blk_finish_plug(&plug);
It would be better if these additions had code comments explaining why
they're there. But let's more fully understand the problem before
altering your patch.
next prev parent reply other threads:[~2022-09-14 22:51 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-14 2:33 [PATCH] mm/vmscan: don't scan adjust too much if current is not kswapd Hongchen Zhang
2022-09-14 22:51 ` Andrew Morton [this message]
2022-09-14 23:02 ` Matthew Wilcox
2022-09-15 1:19 ` Hongchen Zhang
2022-09-15 7:28 ` Matthew Wilcox
2022-09-15 8:02 ` Hongchen Zhang
2022-09-15 9:00 ` Matthew Wilcox
2022-09-15 9:30 ` Hongchen Zhang
2022-09-16 0:57 ` Hongchen Zhang
2022-09-16 8:40 ` Matthew Wilcox
2022-09-16 10:19 ` Hongchen Zhang
2022-09-19 23:32 ` Yosry Ahmed
2022-09-20 5:53 ` Hongchen Zhang
2022-09-20 2:23 ` Hongchen Zhang
2022-09-21 9:13 ` Mel Gorman
2022-09-21 10:14 ` Hongchen Zhang
2022-09-15 13:38 ` Feng Tang
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=20220914155142.bf388515a39fb45bae987231@linux-foundation.org \
--to=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=zhanghongchen@loongson.cn \
/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).