Date: Mon, 07 Jul 2003 16:29:06 +0200 From: Marcin Dalecki <mdcki@gmx.net> To: Matthias Andree <matthias.andree@gmx.de> Cc: current@freebsd.org Subject: Re: /dev/shm Message-ID: <3F0983B2.5060500@gmx.net> In-Reply-To: <20030707135459.GH10021@merlin.emma.line.org> References: <3F08B199.3050409@comcast.net> <3F08B79B.2040805@gmx.net> <20030707001443.GA1530@invisible-island.net> <20030707002347.GC5141@aurema.com> <20030706203440.D89894@vhost101.his.com> <3F08C4FD.8010107@gmx.net> <m3el12lf91.fsf@merlin.emma.line.org> <3F09663D.9020200@gmx.net> <20030707123707.GA18750@saltmine.radix.net> <3F097719.8030301@gmx.net> <20030707135459.GH10021@merlin.emma.line.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Matthias Andree wrote: > On Mon, 07 Jul 2003, Marcin Dalecki wrote: > > >>The point is that this is one of the reasons why the top command in >>question takes a lot of relative CPU time under Linux. Some >>"faster" versions of procps utils try to cache data but the trade off >>is simply the fact that the results are not 100% accurate. > > > Top data is not accurate (I though that was obvious ;-). > > It's an obsolete snapshot the very moment it's printed to your console, Obsolete and never accurate are two different things. You know every information is obsolete the time it is recived. > and I bet it changes as you read with a lot of implementations because > no-one wants to beat the big kernel lock on the process list just > because some user happens to run top, might be a nice DoS otherwise, > fork-bombing top... > > If you want accurate data, use a kernel debugger with remote interface > and make sure the machine does nothing except servicing the debugger > interface. > > >>I tought this was obvious? > > > Why do I care? 0.58user 0.89system 1:00.91elapsed 2%CPU -- on a 266 MHz > Pentium-II, Linux 2.4, 5 years old, with 190 processes. The box idles > 73% of the time it's up, there's _ample_ CPU power left. > Well once in a former live I was administering some servers over sometimes slow lines. And if they where bogged down by actual *load* it was sometimes really really very inconvenient to have no real chance at getting a quick overview of the processes running there and causing the problem becouse top didn't even get a chance to show up due to the hefty IO load it was causing. If the box is idle I don't really care about the load as much as you don't care. :-). This is something that was never a problem on any *BSD or Solaris box I had to deal with thus far.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3F0983B2.5060500>