Re: [RFC PATCH] tick/sched: update full_nohz status after SCHED dep is cleared
From: Frederic Weisbecker <frederic@kernel.org>
Date: 2020-06-29 21:35:17
Also in:
lkml
On Mon, Jun 29, 2020 at 02:36:51PM +0200, Juri Lelli wrote:
Hi, On 16/06/20 22:46, Frederic Weisbecker wrote:quoted
On Tue, Jun 16, 2020 at 08:57:57AM +0200, Juri Lelli wrote:quoted
Sure. Let me know if you find anything.I managed to reproduce. With "threadirqs" and without "tsc=reliable". I see tons of spurious TIMER softirqs. Investigation begins! I'll let you know.Gentle ping. Any new findings about this issue?
Yep, I'm working on a series to reduce timer softirqs. I'm almost done, should post it soon. I believe you guessed right: * Timer tick raises timer softirq * Ksoftirqd wakes up, restarts the tick * Timer tick raises timer softirq * ... Thanks.