* Re: [PATCH 07/15] watchdog: Allow runtime toggle of lockup detector affinity
[not found] <20260325140324.GD3738786@noisy.programming.kicks-ass.net>
@ 2026-03-30 11:45 ` Qiliang Yuan
0 siblings, 0 replies; only message in thread
From: Qiliang Yuan @ 2026-03-30 11:45 UTC (permalink / raw)
To: peterz
Cc: longman, cgroups, akpm, anna-maria, boqun.feng, bsegall,
dietmar.eggemann, frederic, hannes, jackmanb, jiangshanlai,
joelagnelf, josh, juri.lelli, linux-kernel, linux-kselftest,
linux-mm, mathieu.desnoyers, mgorman, mhocko, mingo, mingo,
neeraj.upadhyay, paulmck, qiang.zhang, rcu, realwujing, rostedt,
shuah, surenb, tglx, tj, urezki, vbabka, vincent.guittot,
vschneid, ziy
On Wed, Mar 25, 2026 at 03:03:24PM +0100, Peter Zijlstra wrote:
> Why would we want to toggle the watchdog? It's linked to the
> TIMER housekeeping type anyway, right?
Yes, it is. The original patch had an independent toggle that felt
redundant to you, and I agree. The watchdog affinity follows the
timer housekeeping state.
I'll simplify this by removing the custom toggle and making it a
guaranteed side-effect of the global housekeeping state update.
This keeps the configuration simple while still achieving the goal
of keeping the isolated cores completely clean during dynamic changes.
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2026-03-30 11:46 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <20260325140324.GD3738786@noisy.programming.kicks-ass.net>
2026-03-30 11:45 ` [PATCH 07/15] watchdog: Allow runtime toggle of lockup detector affinity Qiliang Yuan
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox