On Thu, Nov 26, 2015 at 06:34:45PM +0000, Nuno Gonçalves wrote: > I'm still collecting data to be more sure. But it looks for now: > > 1 - nohz=off does not have any effect.
Can you confirm the rate at which the LOC counter in /proc/interrupts is increasing on an idle machine doesn't change with nohz=off? > 2 - With a kernel without Dynamic ticks enabled the latencies are > actually always greater, and they increase with system load! They > still decrease if I have a periodic thread waking very frequently. > > That is: Threads waking regularly and for short intervals decrease > latency. Threads waking infrequently but doing a log of work increase > latency. That's interesting. Is it possible that it affects only the PPS capture somehow? > I will share some annotated plots in a few days to make this very > clear. Anyway do you have any idea what can be happening here? Maybe > some cpuidle states are being entered despite being disabled? No idea. -- Miroslav Lichvar -- To unsubscribe email [email protected] with "unsubscribe" in the subject. For help email [email protected] with "help" in the subject. Trouble? Email [email protected].
