提交 ba49df47 编写于 作者: P Paul E. McKenney 提交者: Paul E. McKenney

rcu: Update RCU_FAST_NO_HZ help text

The RCU_FAST_NO_HZ help text included a warning about overhead on large
systems, but that issue has since been resolved.  The main remaining
issue with RCU_FAST_NO_HZ is increased real-time latency.  This commit
therefore updates the help text accordingly.
Signed-off-by: NPaul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
上级 4d9a5d43
...@@ -582,14 +582,13 @@ config RCU_FAST_NO_HZ ...@@ -582,14 +582,13 @@ config RCU_FAST_NO_HZ
depends on NO_HZ && SMP depends on NO_HZ && SMP
default n default n
help help
This option causes RCU to attempt to accelerate grace periods This option causes RCU to attempt to accelerate grace periods in
in order to allow CPUs to enter dynticks-idle state more order to allow CPUs to enter dynticks-idle state more quickly.
quickly. On the other hand, this option increases the overhead On the other hand, this option increases the overhead of the
of the dynticks-idle checking, particularly on systems with dynticks-idle checking, thus degrading scheduling latency.
large numbers of CPUs.
Say Y if energy efficiency is critically important, and you don't
Say Y if energy efficiency is critically important, particularly care about real-time response.
if you have relatively few CPUs.
Say N if you are unsure. Say N if you are unsure.
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册