[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <jv5aqz342nsq5s2ducloqcwt55naxl3iafdaz33ynp3yzea2pc@kycn6jegsf2w>
Date: Sun, 7 Sep 2025 19:18:01 -0400
From: Aaron Tomlin <atomlin@...mlin.com>
To: Mel Gorman <mgorman@...hsingularity.net>,
Peter Zijlstra <peterz@...radead.org>
Cc: tglx@...utronix.de, mingo@...hat.com, bp@...en8.de,
dave.hansen@...ux.intel.com, x86@...nel.org, juri.lelli@...hat.com,
vincent.guittot@...aro.org, hpa@...or.com, oleg@...hat.com, dietmar.eggemann@....com,
rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de, vschneid@...hat.com,
linux-kernel@...r.kernel.org, atomlin@...mlin.com
Subject: [RFC] sched: idle: Proposal to remove idle=poll
On Sun, Aug 31, 2025 at 06:29:18PM -0400, Aaron Tomlin wrote:
> Yes, I can confirm the PM QoS subsystem allows one to set constraints on a
> per-CPU basis or for the entire system. One can specify a maximum allowed
> latency constraint. As per function pm_qos_resume_latency_us_store() a
> value of "n/a" will prevent the specified CPU from entering the shallowest
> CPU idle-state (namely "C1") given its exit latency constraint.
> Indeed using "idle=poll" to prevent a CPU from entering idle C-states is
> problematic given its crude, all-or-nothing approach.
>
> Thank you for the suggestion.
Mel, Peter,
I wanted to ask given the availability of the PM QoS subsystem on a Linux
kernel that has Kconfig option CONFIG_PM enabled, does this feature make
'idle=poll' redundant? Furthermore, if I understand correctly, for
platforms that require a generic idle polling mechanism
(CONFIG_GENERIC_IDLE_POLL_SETUP) boot-time parameter 'nohlt' can still be
used, no?
I was thinking about submitting a RFC patch to remove idle=poll.
Kind regards,
--
Aaron Tomlin
Powered by blists - more mailing lists