[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230412142616.GI628377@hirez.programming.kicks-ass.net>
Date: Wed, 12 Apr 2023 16:26:16 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Aaron Lu <aaron.lu@...el.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
linux-kernel@...r.kernel.org, Olivier Dion <odion@...icios.com>,
michael.christie@...cle.com
Subject: Re: [RFC PATCH v4] sched: Fix performance regression introduced by
mm_cid
On Wed, Apr 12, 2023 at 07:42:40PM +0800, Aaron Lu wrote:
> I *guess* you might be able to see some contention with hackbench on
> that HSW-EX system with v4.
Indeed! Notably it seems to be the wakeup from idle that trips it
hardest:
11.31% 0.03% swapper [kernel.vmlinux] [k] schedule_idle
|
--11.28%--schedule_idle
|
--11.27%--__schedule
|
|--8.61%--mm_cid_get
| |
| --5.78%--_raw_spin_lock
| |
| --5.56%--native_queued_spin_lock_slowpath
|
|--0.81%--finish_task_switch.isra.0
| |
| --0.69%--asm_sysvec_call_function_single
| |
| --0.58%--sysvec_call_function_single
|
--0.57%--switch_mm_irqs_off
Powered by blists - more mailing lists