Date: Mon, 26 Jan 2015 12:11:49 -0800 From: Adrian Chadd <adrian@freebsd.org> To: freebsd-current <freebsd-current@freebsd.org> Subject: Re: Is anyone using the schedgraph.d script? Message-ID: <CAJ-VmokZ7b1Wz0CsMdbjiVBwTQW_s78ePC2USE%2ByArzrMrbXbw@mail.gmail.com> In-Reply-To: <CAJ-VmonoZ0bz2HRNi2s5yA7vNSeUAGjwnt80L8MBY9OOEz_9-w@mail.gmail.com> References: <CAJ-VmonoZ0bz2HRNi2s5yA7vNSeUAGjwnt80L8MBY9OOEz_9-w@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
... ignore it for now; I ran some other profiling and then when I tried schedgraph.d again, it started spitting out events for that CPU. I'll file a PR if I see it happen more often. :( -a On 26 January 2015 at 12:05, Adrian Chadd <adrian@freebsd.org> wrote: > Hi, > > I'm having problems with Ryan's schedgraph.d script > (people.freebsd.org/~rstone/dtrace/) > > It runs fine, but if a CPU core is 100% busy, I get zero scheduler > events logged from it. Said core is doing around 30,000 syscalls a > second, around 250,000 context switches and 125,000 interrupt sa > second - but whilst it's doing this, I get zero events from dtrace for > said CPU. > > Has anyone hit this kind of situation before? > > > > -a
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAJ-VmokZ7b1Wz0CsMdbjiVBwTQW_s78ePC2USE%2ByArzrMrbXbw>