From: Philipp Stanner <phasta@mailbox.org>
To: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>,
amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: kernel-dev@igalia.com,
"Christian König" <christian.koenig@amd.com>,
"Danilo Krummrich" <dakr@kernel.org>,
"Matthew Brost" <matthew.brost@intel.com>,
"Philipp Stanner" <phasta@kernel.org>,
"Pierre-Eric Pelloux-Prayer" <pierre-eric.pelloux-prayer@amd.com>,
"Alex Deucher" <alexander.deucher@amd.com>
Subject: Re: [PATCH 12/28] drm/sched: Switch default policy to fair
Date: Fri, 10 Oct 2025 14:56:56 +0200 [thread overview]
Message-ID: <e4c766549e0e627cfc81cf44914a157d2a881112.camel@mailbox.org> (raw)
In-Reply-To: <20251008085359.52404-13-tvrtko.ursulin@igalia.com>
s/fair/FAIR
On Wed, 2025-10-08 at 09:53 +0100, Tvrtko Ursulin wrote:
> Fair policy works better than FIFO for all known use cases and either
s/Fair/FAIR
> matches or gets close to RR. Lets make it a default to improve the user
> experience especially with interactive workloads competing with heavy
> clients.
>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
> Cc: Christian König <christian.koenig@amd.com>
> Cc: Danilo Krummrich <dakr@kernel.org>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Philipp Stanner <phasta@kernel.org>
> Cc: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
I hope that we'll see an a-b or two here from some of the driver folks
to see that they're aware of this coming.
@Christian, @Alex (+Cc)
Your driver is the main benefactor from this series, so your blessing
for FAIR would be neat.
P.
> ---
> drivers/gpu/drm/scheduler/sched_main.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index 204d99c6699f..858fc28e91e4 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -84,7 +84,7 @@
> #define CREATE_TRACE_POINTS
> #include "gpu_scheduler_trace.h"
>
> -int drm_sched_policy = DRM_SCHED_POLICY_FIFO;
> +int drm_sched_policy = DRM_SCHED_POLICY_FAIR;
>
> /**
> * DOC: sched_policy (int)
next prev parent reply other threads:[~2025-10-10 12:57 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-08 8:53 [PATCH 00/28] Fair DRM scheduler Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 01/28] drm/sched: Reverse drm_sched_rq_init arguments Tvrtko Ursulin
2025-10-10 8:55 ` Philipp Stanner
2025-10-10 9:46 ` Tvrtko Ursulin
2025-10-10 10:36 ` Philipp Stanner
2025-10-11 13:21 ` Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 02/28] drm/sched: Add some scheduling quality unit tests Tvrtko Ursulin
2025-10-10 9:38 ` Philipp Stanner
2025-10-11 13:09 ` Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 03/28] drm/sched: Add some more " Tvrtko Ursulin
2025-10-10 9:48 ` Philipp Stanner
2025-10-11 13:21 ` Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 04/28] drm/sched: Implement RR via FIFO Tvrtko Ursulin
2025-10-10 10:18 ` Philipp Stanner
2025-10-11 13:30 ` Tvrtko Ursulin
2025-10-14 6:40 ` Philipp Stanner
2025-10-08 8:53 ` [PATCH 05/28] drm/sched: Consolidate entity run queue management Tvrtko Ursulin
2025-10-10 10:49 ` Philipp Stanner
2025-10-11 14:19 ` Tvrtko Ursulin
2025-10-14 6:53 ` Philipp Stanner
2025-10-14 7:26 ` Tvrtko Ursulin
2025-10-14 8:52 ` Philipp Stanner
2025-10-14 10:04 ` Tvrtko Ursulin
2025-10-14 11:23 ` Philipp Stanner
2025-10-08 8:53 ` [PATCH 06/28] drm/sched: Move run queue related code into a separate file Tvrtko Ursulin
2025-10-08 22:49 ` Matthew Brost
2025-10-08 8:53 ` [PATCH 07/28] drm/sched: Free all finished jobs at once Tvrtko Ursulin
2025-10-08 22:48 ` Matthew Brost
2025-10-08 8:53 ` [PATCH 08/28] drm/sched: Account entity GPU time Tvrtko Ursulin
2025-10-10 12:22 ` Philipp Stanner
2025-10-11 14:56 ` Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 09/28] drm/sched: Remove idle entity from tree Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 10/28] drm/sched: Add fair scheduling policy Tvrtko Ursulin
2025-10-14 10:27 ` Philipp Stanner
2025-10-14 12:56 ` Tvrtko Ursulin
2025-10-14 14:02 ` Philipp Stanner
2025-10-14 14:32 ` Simona Vetter
2025-10-14 14:58 ` Tvrtko Ursulin
2025-10-16 7:06 ` Philipp Stanner
2025-10-16 8:42 ` Tvrtko Ursulin
2025-10-16 9:50 ` Danilo Krummrich
2025-10-16 10:54 ` Tvrtko Ursulin
2025-10-16 11:14 ` Danilo Krummrich
2025-10-08 8:53 ` [PATCH 11/28] drm/sched: Favour interactive clients slightly Tvrtko Ursulin
2025-10-14 10:53 ` Philipp Stanner
2025-10-14 12:20 ` Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 12/28] drm/sched: Switch default policy to fair Tvrtko Ursulin
2025-10-10 12:56 ` Philipp Stanner [this message]
2025-10-08 8:53 ` [PATCH 13/28] drm/sched: Remove FIFO and RR and simplify to a single run queue Tvrtko Ursulin
2025-10-14 11:16 ` Philipp Stanner
2025-10-14 13:16 ` Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 14/28] drm/sched: Embed run queue singleton into the scheduler Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 15/28] accel/amdxdna: Remove drm_sched_init_args->num_rqs usage Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 16/28] accel/rocket: " Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 17/28] drm/amdgpu: " Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 18/28] drm/etnaviv: " Tvrtko Ursulin
2025-10-08 10:31 ` Christian Gmeiner
2025-10-08 8:53 ` [PATCH 19/28] drm/imagination: " Tvrtko Ursulin
2025-10-10 14:29 ` Matt Coster
2025-10-08 8:53 ` [PATCH 20/28] drm/lima: " Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 21/28] drm/msm: " Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 22/28] drm/nouveau: " Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 23/28] drm/panfrost: " Tvrtko Ursulin
2025-10-08 14:55 ` Steven Price
2025-10-08 8:53 ` [PATCH 24/28] drm/panthor: " Tvrtko Ursulin
2025-10-08 14:55 ` Steven Price
2025-10-10 10:02 ` Liviu Dudau
2025-10-08 8:53 ` [PATCH 25/28] drm/sched: " Tvrtko Ursulin
2025-10-08 22:44 ` Matthew Brost
2025-10-08 8:53 ` [PATCH 26/28] drm/v3d: " Tvrtko Ursulin
2025-10-10 14:15 ` Melissa Wen
2025-10-08 8:53 ` [PATCH 27/28] drm/xe: " Tvrtko Ursulin
2025-10-08 8:53 ` [PATCH 28/28] drm/sched: Remove drm_sched_init_args->num_rqs Tvrtko Ursulin
2025-10-10 13:00 ` Philipp Stanner
2025-10-11 14:58 ` Tvrtko Ursulin
2025-10-10 8:59 ` [PATCH 00/28] Fair DRM scheduler Philipp Stanner
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=e4c766549e0e627cfc81cf44914a157d2a881112.camel@mailbox.org \
--to=phasta@mailbox.org \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
--cc=dakr@kernel.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=kernel-dev@igalia.com \
--cc=matthew.brost@intel.com \
--cc=phasta@kernel.org \
--cc=pierre-eric.pelloux-prayer@amd.com \
--cc=tvrtko.ursulin@igalia.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).