[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-Id: <171155695404.507853.16905998627647073688.b4-ty@kernel.dk>
Date: Wed, 27 Mar 2024 10:29:14 -0600
From: Jens Axboe <axboe@...nel.dk>
To: linux-block@...r.kernel.org, Ming Lei <ming.lei@...hat.com>
Cc: linux-kernel@...r.kernel.org, Tim Chen <tim.c.chen@...ux.intel.com>,
Juri Lelli <juri.lelli@...hat.com>, Andrew Theurer <atheurer@...hat.com>,
Joe Mario <jmario@...hat.com>, Sebastian Jug <sejug@...hat.com>,
Frederic Weisbecker <frederic@...nel.org>,
Bart Van Assche <bvanassche@....org>, Tejun Heo <tj@...nel.org>
Subject: Re: [PATCH V5] blk-mq: don't schedule block kworker on isolated
CPUs
On Fri, 22 Mar 2024 10:12:44 +0800, Ming Lei wrote:
> Kernel parameter of `isolcpus=` or 'nohz_full=' are used to isolate CPUs
> for specific task, and it isn't expected to let block IO disturb these CPUs.
> blk-mq kworker shouldn't be scheduled on isolated CPUs. Also if isolated
> CPUs is run for blk-mq kworker, long block IO latency can be caused.
>
> Kernel workqueue only respects CPU isolation for WQ_UNBOUND, for bound
> WQ, the responsibility is on user because CPU is specified as WQ API
> parameter, such as mod_delayed_work_on(cpu), queue_delayed_work_on(cpu)
> and queue_work_on(cpu).
>
> [...]
Applied, thanks!
[1/1] blk-mq: don't schedule block kworker on isolated CPUs
commit: 5f27f3d892743312fce237958a4194859ef93d69
Best regards,
--
Jens Axboe
Powered by blists - more mailing lists