Date: Tue, 25 Jan 2011 06:20:02 -0700 From: Dmitri Brengauz <dmitri@momus.net> To: FreeBSD Questions <freebsd-questions@freebsd.org> Subject: Re: more CPU being used than I have (?) Message-ID: <AANLkTi=wX%2BEVyjnH=8m0-%2B3qzi4KF1YeZZngUe_EQ2sw@mail.gmail.com> In-Reply-To: <20110125030725.GA62670@guilt.hydra> References: <20110124235740.GA62134@guilt.hydra> <1295917366.59721.2.camel@main> <20110125030725.GA62670@guilt.hydra>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Jan 24, 2011 at 8:07 PM, Chad Perrin <perrin@apotheon.com> wrote: > On Tue, Jan 25, 2011 at 01:02:46AM +0000, Craig Butler wrote: > > On Mon, 2011-01-24 at 16:57 -0700, Chad Perrin wrote: > > > I'm running a two-core laptop that, once in a great while, shows > > > approximately 250% CPU usage by a single process in top. How exactly > > > does that work? > > > > > > Note: It's not entirely surprising that this particular process is > > > consuming a lot of resources. It's just surprising to me that it's > > > consuming more than CPUs * 100%. > > > > Hi Chad > > > > Its to do with top using weighted CPU percentage... for some reason this > > show peaks as more usage than 100% -- maybe something to do with the top > > averaging out over a specific time. > > I find that raw CPU mode gives a more accurate representation. > > > > raw mode is toggled by passing the -C argument to top. > > Do you have a reference to a relatively simple explanation of how that > weighting works (and why)? > > -- > Chad Perrin [ original content licensed OWL: http://owl.apotheon.org ] > man 1 ps: %cpu The CPU utilization of the process; this is a decaying average over up to a minute of previous (real) time. Since the time base over which this is computed varies (since processes may be very young) it is possible for the sum of all %cpu fields to exceed 100%.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTi=wX%2BEVyjnH=8m0-%2B3qzi4KF1YeZZngUe_EQ2sw>