Date: Tue, 22 Nov 2011 13:35:49 +0700 From: Eugene Grosbein <eugen@grosbein.pp.ru> To: Luigi Rizzo <rizzo@iet.unipi.it> Cc: hackers@freebsd.org Subject: Re: dummynet(4) kernel process CPU usage monitoring Message-ID: <4ECB42C5.6050108@grosbein.pp.ru> In-Reply-To: <20111121083003.GA54883@onelab2.iet.unipi.it> References: <4EC39367.4030109@rdtc.ru> <4EC9EE5A.2070204@grosbein.pp.ru> <20111121083003.GA54883@onelab2.iet.unipi.it>
next in thread | previous in thread | raw e-mail | index | archive | help
21.11.2011 15:30, Luigi Rizzo пишет: > On Mon, Nov 21, 2011 at 01:23:22PM +0700, Eugene Grosbein wrote: >> Hi! >> >> I need to draw graph of dummynet's CPU usage. >> "procstat -t 0" shows me TID (thread id) of dummynet kernel thread. >> "ps -Hxo time,lwp" shows me total CPU time consumed by this thread. >> >> Now I see this time has 9 seconds increase during 60 seconds of real time. >> This should be 9/60=15% CPU usage, but "top -SHP" shows me 0.00% meantime. > > apart from the scaling on number of cores (e.g. if you have 8 cores > the 15% becomes a bare 2%) I have 4 cores (no hyperthreading) and it seems that "top -SHP" does not scale anything in this mode. > remember that percentages are computed > with some kind of filtering (EWMA ?) so if the load of dummynet threads > is bursty, the filter might eat most of it. I do not understand what this filter is. Btw, dummynet load is steady here. > not completely sure this explains a steady 0.00%, if that's is > what you are seeing Yes, I see 0.00% except of hours of most load where top shows about 10% and ps shows about 30%. Eugene Grosbein
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4ECB42C5.6050108>