From 6c757e9f55f02fbc226823f8d441cd03cc282109 Mon Sep 17 00:00:00 2001 From: Jui-Tse Huang Date: Fri, 15 Apr 2022 11:36:18 +0800 Subject: [PATCH] docs/scheduler: fix unit error The unit mentioned in the documentation of scheduler statistics is outdated which may mislead the readers.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 Signed-off-by: Jonathan Corbet --- Documentation/scheduler/sched-stats.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/scheduler/sched-stats.rst b/Documentation/scheduler/sched-stats.rst index 9078a27a4137..03c062915998 100644 --- a/Documentation/scheduler/sched-stats.rst +++ b/Documentation/scheduler/sched-stats.rst @@ -155,8 +155,8 @@ schedstats also adds a new /proc//schedstat file to include some of the same information on a per-process level. There are three fields in this file correlating for that process to: - 1) time spent on the cpu - 2) time spent waiting on a runqueue + 1) time spent on the cpu (in nanoseconds) + 2) time spent waiting on a runqueue (in nanoseconds) 3) # of timeslices run on this cpu A program could be easily written to make use of these extra fields to