[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <87ilr92yrv.fsf@meer.lwn.net>
Date: Sat, 16 Apr 2022 02:55:16 -0600
From: Jonathan Corbet <corbet@....net>
To: Jui-Tse Huang <juitse.huang@...il.com>,
Peter Zijlstra <peterz@...radead.org>,
Valentin Schneider <valentin.schneider@....com>,
Mauro Carvalho Chehab <mchehab+huawei@...nel.org>,
Huaixin Chang <changhuaixin@...ux.alibaba.com>,
Beata Michalska <beata.michalska@....com>,
Chun-Hung Tseng <henrybear327@...il.com>,
linux-doc@...r.kernel.org, linux-kernel@...r.kernel.org
Cc: Jui-Tse Huang <juitse.huang@...il.com>,
Ching-Chun Huang <jserv@...s.ncku.edu.tw>
Subject: Re: [PATCH] docs/scheduler: fix unit error
Jui-Tse Huang <juitse.huang@...il.com> writes:
> The unit mentioned in the documentation of scheduler statistics is
> outdated which may mislead the readers.
>
> The unit of statistics that is reported by /proc/schedstat is modified
> to nanosecond, and the unit of statistics that is reported by
> /proc/PID/schedstat is provided as well to make the context consistent.
>
> The rq_cpu_time and the rq_sched_info.run_delay of a run queue, and the
> sched_info.run_delay of a task are all updated based on the clock of the
> run queue, while the se.sum_exec_runtime of a task is updated based on
> the clock_task of the run queue of the task. Both the clock and
> clock_task are relied on the return value of the function sched_clock()
> which is in the unit of nanosecond.
>
> Signed-off-by: Jui-Tse Huang <juitse.huang@...il.com>
> ---
> Documentation/scheduler/sched-stats.rst | 8 ++++----
> 1 file changed, 4 insertions(+), 4 deletions(-)
Part of this had already been fixed by a previous patch, but git was
able to figure it out...this one's applied as well, thanks.
jon
Powered by blists - more mailing lists