Date: Thu, 14 Sep 2006 14:13:55 -0400 From: Gary Corcoran <gcorcoran@rcn.com> To: Mike Meyer <mwm@mired.org> Cc: freebsd-hackers@freebsd.org Subject: Re: numbers don't lie ... Message-ID: <45099BE3.6080902@rcn.com> In-Reply-To: <17673.37830.1883.272019@bhuda.mired.org> References: <E1GNOLq-000DC2-1Q@cs1.cs.huji.ac.il> <863bauk3gp.fsf@dwp.des.no> <45099123.4000500@rcn.com> <17673.37830.1883.272019@bhuda.mired.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Mike Meyer wrote: > In <45099123.4000500@rcn.com>, Gary Corcoran <gcorcoran@rcn.com> typed: >> The confusing thing is that I thought 'real' time should be >= 'user' + 'sys'. >> But here 'user' is much greater than 'real' for both machines! The sense I >> got from the other messages in this thread is that 'user' time is somewhat >> meaningless (i.e. unreliable as a measure) in a multi-CPU and/or hyperthreading >> environment. Can you clarify? > > 'real' is wall clock time. 'user' and 'sys' are cpu time. If your > process gets all of some cpu, then user + sys will be the same as real > time. It's not possible to get more than all of a cpu, so that's a > maximum *per cpu*. If you have multiple cpus, the formula you want is > 'real' * ncpu >= 'user' + 'sys'. Thanks to all of you for the responses. The thing that was not clear is that despite the printed messages, user (and sys) time are *not* measures of time. IMO it would be much easier to understand if the message said that they were so-many cpu-seconds, rather than just seconds. Then it would be fairly obvious that in a multiprocessor environment that the real time could be less than the sum of user + sys. I know, once you understand the true meaning of user/sys time it's "obvious", but not to the first-time multiprocessor observer... :-) > I made the comment about freebsd's measure of user time being skewed > by hyperthreading. That's a bit vague. The problem is that waiting > caused by hyperthreading will count against the instruction that's > doing the waiting, which skews them. But as Kris pointed out, there > are other things that have that property, so this is just one more > complication when it comes to figuring the performance of modern CPUs. ;-) Thanks, Gary
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?45099BE3.6080902>