在 2022/8/16 20:19, Lukasz Luba 写道:
Add missing update for the documentation bit of some scheduler knob.
The knobs have been moved to /debug/sched/ location (with adjusted names).
Signed-off-by: Lukasz Luba <lukasz.luba@xxxxxxx>
Tested-by: Yanteng Si <siyanteng@xxxxxxxxxxx>
CC Yizhou
Thanks,
Yanteng
---
Documentation/scheduler/sched-design-CFS.rst | 2 +-
Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/Documentation/scheduler/sched-design-CFS.rst b/Documentation/scheduler/sched-design-CFS.rst
index 59b2d1fb4dc4..03db55504515 100644
--- a/Documentation/scheduler/sched-design-CFS.rst
+++ b/Documentation/scheduler/sched-design-CFS.rst
@@ -94,7 +94,7 @@ other HZ detail. Thus the CFS scheduler has no notion of "timeslices" in the
way the previous scheduler had, and has no heuristics whatsoever. There is
only one central tunable (you have to switch on CONFIG_SCHED_DEBUG):
- /proc/sys/kernel/sched_min_granularity_ns
+ /sys/kernel/debug/sched/min_granularity_ns
which can be used to tune the scheduler from "desktop" (i.e., low latencies) to
"server" (i.e., good batching) workloads. It defaults to a setting suitable
diff --git a/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst b/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst
index 26b0f36f793d..3076402406c4 100644
--- a/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst
+++ b/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst
@@ -80,7 +80,7 @@ p->se.vruntime。一旦p->se.vruntime变得足够大,其它的任务将成为
CFS使用纳秒粒度的计时,不依赖于任何jiffies或HZ的细节。因此CFS并不像之前的调度器那样
有“时间片”的概念,也没有任何启发式的设计。唯一可调的参数(你需要打开CONFIG_SCHED_DEBUG)是:
- /proc/sys/kernel/sched_min_granularity_ns
+ /sys/kernel/debug/sched/min_granularity_ns
它可以用来将调度器从“桌面”模式(也就是低时延)调节为“服务器”(也就是高批处理)模式。
它的默认设置是适合桌面的工作负载。SCHED_BATCH也被CFS调度器模块处理。