From: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
To: Salvatore Dipietro <dipiets@amazon.it>, linux-kernel@vger.kernel.org
Cc: dipiets@amazon.it, alisaidi@amazon.com, blakgeof@amazon.com,
abuehaze@amazon.de, dipietro.salvatore@gmail.com,
willy@infradead.org, stable@vger.kernel.org,
Christian Brauner <brauner@kernel.org>,
"Darrick J. Wong" <djwong@kernel.org>,
linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-mm@kvack.org
Subject: Re: [PATCH 1/1] iomap: avoid compaction for costly folio order allocation
Date: Sat, 04 Apr 2026 06:43:06 +0530 [thread overview]
Message-ID: <bjfzmst9.ritesh.list@gmail.com> (raw)
In-Reply-To: <20260403193535.9970-2-dipiets@amazon.it>
Let's cc: linux-mm too.
Salvatore Dipietro <dipiets@amazon.it> writes:
> Commit 5d8edfb900d5 ("iomap: Copy larger chunks from userspace")
> introduced high-order folio allocations in the buffered write
> path. When memory is fragmented, each failed allocation triggers
Isn't it the right thing to do i.e. run compaction, when memory is
fragmented?
> compaction and drain_all_pages() via __alloc_pages_slowpath(),
> causing a 0.75x throughput drop on pgbench (simple-update) with
> 1024 clients on a 96-vCPU arm64 system.
>
I think removing the __GFP_DIRECT_RECLAIM flag unconditionally at the
caller may cause -ENOMEM. Note that it is the __filemap_get_folio()
which retries with smaller order allocations, so instead of changing the
callers, shouldn't this be fixed in __filemap_get_folio() instead?
Maybe in there too, we should keep the reclaim flag (if passed by
caller) at least for <= PAGE_ALLOC_COSTLY_ORDER + 1
Thoughts?
-ritesh
next prev parent reply other threads:[~2026-04-04 1:43 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-03 19:35 [PATCH 0/1] iomap: avoid compaction for costly folio order allocation Salvatore Dipietro
2026-04-03 19:35 ` [PATCH 1/1] " Salvatore Dipietro
2026-04-04 1:13 ` Ritesh Harjani [this message]
2026-04-04 4:15 ` Matthew Wilcox
2026-04-04 16:47 ` Ritesh Harjani
2026-04-04 20:46 ` Matthew Wilcox
2026-04-05 22:43 ` Dave Chinner
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=bjfzmst9.ritesh.list@gmail.com \
--to=ritesh.list@gmail.com \
--cc=abuehaze@amazon.de \
--cc=alisaidi@amazon.com \
--cc=blakgeof@amazon.com \
--cc=brauner@kernel.org \
--cc=dipietro.salvatore@gmail.com \
--cc=dipiets@amazon.it \
--cc=djwong@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=stable@vger.kernel.org \
--cc=willy@infradead.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