[PATCH 11/32] nohz/cpuset: Don't turn off the tick if rcu needs it
rostedt at goodmis.org
Wed Mar 28 01:06:45 UTC 2012
On Tue, 2012-03-27 at 19:42 -0500, Christoph Lameter wrote:
> On Tue, 27 Mar 2012, Steven Rostedt wrote:
> > On Tue, 2012-03-27 at 11:13 -0500, Christoph Lameter wrote:
> > > Please do not use "realtime" since I am not sure what you mean by that.
> > > Its for a low latency applications that cannot use "realtime" because that
> > > implies high latencies.
> > This statement totally confuses me, as the whole point of the -rt
> > (realtime) patch, is for lower latencies. Where do you get "realtime"
> > implies high latencies from?
> Obviously compiling a kernel with preemptiong introduces additional
> overhead to guarantee more deterministic behavior. Additional overhead
> increases latencies generated by the OS in general. Compile a kernel
> without preemption and it will run faster and thus have lower latencies.
I call that "lower overhead".
> Realtime avoids high latency spikes but in general increases average OS
Now to me the definition of a latency is the difference in time
something was suppose to happen and the time it actually does. A
I see you are calling the time spent in the kernel a latency. The time
added to complete a task is called "overhead". Yes, realtime adds
overhead to keep reaction time latency to a minimum.
According to wikipedia, the first thing it says about latency is:
"Latency is a measure of time delay experienced in a system, the precise
definition of which depends on the system and the time being measured.
Latencies may have different meaning in different contexts."
That last sentence is key. So lets avoid the term "latency" as it
obviously has a different meaning to the both of us.
Instead, lets use "determinism" (what we call latency in the realtime
world) and "overhead" (what you seem to see as latency caused by the
More information about the linaro-sched-sig