arosen@hen.ulowell.edu (MFHorn) (04/28/89)
In article <67727@pyramid.pyramid.com> csg@pyramid.pyramid.com (Carl S. Gutekunst) writes: In article <2470@helios.ee.lbl.gov> Jef Poskanzer <jef@helios.ee.lbl.gov> writes: >(I haven't tried it on a heavily loaded system yet because I >haven't managed to get the load average above 1.6...) There's a reason for that. Dynix divides the load average by the number of CPUs you have. If uptime(1) displays 1.6, and you have four CPUs, then the load average is really 6.4. If uptime(1) says "1.6" on a 4-CPU system, the load would really be 6.4 *on a single processor system* If Dynix says the load is 1.6, it really is 1.6 . The load average is very relative to the machine you're working on, though. System Memory # users 'load average' Delay in response time 20-CPU Balance 21K 22 Meg 50+ 0.8 none VAX 11/750 8 Meg 28 37.69 minutes per keystroke MV/15000 (~12 Mips) 16 Meg 1 15+ none Load averages can be very misleading, and should be looked at with respect to the load average _on the same system_ under varying conditions. It is "the average number of jobs in the run queue over the last 1, 5 and 15 minutes", nothing more.
hanst@maestro.htsa.aha.nl (Hans Trompert) (05/08/89)
In article <67727@pyramid.pyramid.com> csg@pyramid.pyramid.com (Carl S. Gutekunst) writes: >In article <2470@helios.ee.lbl.gov> Jef Poskanzer <jef@helios.ee.lbl.gov> writes: >>(I haven't tried it on a heavily loaded system yet because I >>haven't managed to get the load average above 1.6...) >There's a reason for that. Dynix divides the load average by the number of >CPUs you have. If uptime(1) displays 1.6, and you have four CPUs, then the >load average is really 6.4. If you want a GOOD load average, try a parallel make with 50 source files (the nethack sources will do fine), that will do the trick !! On our Sequent (Balance 8000 with 8 CPU's) it results in a load average above 10.0. The only problem is the size of your swap space, you run quickly out of memory. Try it and have fun ?!!
dhawk@well.UUCP (David Hawkins) (05/09/89)
In the referenced article, hanst@htsa.UUCP (Hans Trompert) wrote: >If you want a GOOD load average, try a parallel make with 50 source files >(the nethack sources will do fine), that will do the trick !! >On our Sequent (Balance 8000 with 8 CPU's) it results in a load average above >10.0. The only problem is the size of your swap space, you run quickly out >of memory. Try it and have fun ?!! Hmm, odd. We compiled nethack on the B8 and the load average only went up to 1.60 -- and there were 10 users or so online who didn't even notice. (That was with a parallel make, by the way.) We did get a 2.30 load average yesterday doing a parallel make of gcc and had about 23 users online. (We do have 16 megs of memory and 6 CPU's.) later, david -- David Hawkins {apple,pacbell,hplabs,ucbvax}!well!dhawk It is better to encounter one's existence in disgust than never to encounter it at all. - William Barrett