|
On Tue, 25 Sep 2001, Peter Mueller wrote:
> > > I'm not disputing that your system is able to cope with the
> > > load you are
> > > putting on it. I'd to note that much of the CPU time that LVS
> > > uses is done
> > > within the kernel and as such it will not show up in a load
> > average or
> > > %CPU utilisation as shown by top and friends. This is because
> > > cycles used
> > > within the kernel more or less disappear from userspace,
> > > throwing the stats
> > > out.
>
> I believe I remember hearing a few times that you can use ucd-snmp and mrtg
> to get load. The best way I know of to keep track of these numbers in a
> meaningful fashion is to use mrtg. (you're using lvsgrp+mrtg for connection
> totals anyway in your LVS cluster, right?). I believe the UCD-load SNMP
> function gets total CPU as found in /proc/stat, which is probably what you
> are looking for (load of machine, who cares what uses what - right?).
>
> The disucssions in the past seem to indicate that /proc/stat is a good way
> of keeping track of actual load. Snipped from the archive ....
CPU time and load average are totally different things. On a director you
would have 0 load average while having important amounts of kernel-space CPU
time consumed.
On a real-server on the other hand, you may have a total of CPU time used less
than 80% (user + kernel) while having a load average of 2 , 3 or even more.
Load average is the vaerage number of processes in the "Running" state
computed over a certain amount of time. Just run 2 infinte loops concurrently
and you'll see that load goes to 2 while CPU time remains at 100% , regardless
of the number of such programs running.
Radu-Adrian Feurdean
mailto: raf @ chez.com
---------------------------------------------------------------------------
Computer science is merely the post-Turing decline in formal systems theory
|
