christianbiere@gmx.de (Christian Biere) writes:

>I think someone else wrote it but I can confirm it as well that the behaviour
>on -current is the same. This might not be the case for everyone of course.
>However, it seems you can't sleep less than about 15 ms.

We are waiting on the HZ clock, the minimum wait time is 1 tick.
Since the first measurement synchronizes us to 1 tick we get
"almost" 2 ticks delay for the subsequent calls. Pretty simple.

-- 
-- 
                                Michael van Elst
Internet: mlelstv@serpens.de
                                "A potential Snark may lurk in every tree."