From: John Stultz <jstultz@google.com>
To: jaewon31.kim@samsung.com
Cc: "sumit.semwal@linaro.org" <sumit.semwal@linaro.org>,
"daniel.vetter@ffwll.ch" <daniel.vetter@ffwll.ch>,
"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
"hannes@cmpxchg.org" <hannes@cmpxchg.org>,
"mhocko@kernel.org" <mhocko@kernel.org>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"jaewon31.kim@gmail.com" <jaewon31.kim@gmail.com>,
"T.J. Mercier" <tjmercier@google.com>
Subject: Re: [PATCH] dma-buf: system_heap: avoid reclaim for order 4
Date: Tue, 17 Jan 2023 22:54:22 -0800 [thread overview]
Message-ID: <CANDhNCpKY5Af059ok8ZcgJ=wt7NaorZxqQXaTS848CwY0LNFiw@mail.gmail.com> (raw)
In-Reply-To: <20230117083103epcms1p63382eee1cce1077248a4b634681b0aca@epcms1p6>
On Tue, Jan 17, 2023 at 12:31 AM Jaewon Kim <jaewon31.kim@samsung.com> wrote:
> > Using order 4 pages would be helpful for many IOMMUs, but it could spend
> > quite much time in page allocation perspective.
> >
> > The order 4 allocation with __GFP_RECLAIM may spend much time in
> > reclaim and compation logic. __GFP_NORETRY also may affect. These cause
> > unpredictable delay.
> >
> > To get reasonable allocation speed from dma-buf system heap, use
> > HIGH_ORDER_GFP for order 4 to avoid reclaim.
Thanks for sharing this!
The case where the allocation gets stuck behind reclaim under pressure
does sound undesirable, but I'd be a bit hesitant to tweak numbers
that have been used for a long while (going back to ion) without a bit
more data.
It might be good to also better understand the tradeoff of potential
on-going impact to performance from using low order pages when the
buffer is used. Do you have any details like or tests that you could
share to help ensure this won't impact other users?
TJ: Do you have any additional thoughts on this?
thanks
-john
next prev parent reply other threads:[~2023-01-18 7:37 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20230117082521epcas1p22a709521a9e6d2346d06ac220786560d@epcas1p2.samsung.com>
2023-01-17 8:25 ` [PATCH] dma-buf: system_heap: avoid reclaim for order 4 Jaewon Kim
[not found] ` <CGME20230117082521epcas1p22a709521a9e6d2346d06ac220786560d@epcms1p6>
2023-01-17 8:31 ` Jaewon Kim
2023-01-18 6:54 ` John Stultz [this message]
2023-01-18 19:55 ` T.J. Mercier
[not found] ` <CGME20230117082521epcas1p22a709521a9e6d2346d06ac220786560d@epcms1p2>
2023-01-25 9:56 ` Jaewon Kim
2023-01-25 10:19 ` Jaewon Kim
2023-01-25 20:32 ` John Stultz
[not found] ` <CGME20230117082521epcas1p22a709521a9e6d2346d06ac220786560d@epcms1p3>
2023-01-26 4:42 ` 김재원
2023-01-26 5:04 ` (2) " John Stultz
[not found] ` <CGME20230117082521epcas1p22a709521a9e6d2346d06ac220786560d@epcms1p8>
2023-01-18 7:30 ` Jaewon Kim
2023-02-04 15:02 ` Jaewon Kim
2023-02-07 4:37 ` (2) " John Stultz
[not found] ` <CGME20230117082521epcas1p22a709521a9e6d2346d06ac220786560d@epcms1p1>
2023-02-07 7:33 ` Jaewon Kim
2023-02-07 16:56 ` John Stultz
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='CANDhNCpKY5Af059ok8ZcgJ=wt7NaorZxqQXaTS848CwY0LNFiw@mail.gmail.com' \
--to=jstultz@google.com \
--cc=akpm@linux-foundation.org \
--cc=daniel.vetter@ffwll.ch \
--cc=hannes@cmpxchg.org \
--cc=jaewon31.kim@gmail.com \
--cc=jaewon31.kim@samsung.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=sumit.semwal@linaro.org \
--cc=tjmercier@google.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;
as well as URLs for NNTP newsgroup(s).