Another question I had on Friday was on loadaverage.

I knew that it was an average of some sort sampling on CPU load, but I
didn't know what exactly it was sampling

For what it's worth, here is a quite good explanation

http://subwiki.honeypot.net/cgi-bin/view/Computing/LoadAverage

And a non-technical explanation:

"Imagine that there are several lines (queues, for the British) to
stand in, and the processes are the ones standing in line. There's a
CPU line, an InputOutput? line, a FileSystem? line, and so on. The
LoadAverage is the average number of processes standing in the CPU
line. Imagine the lines are like checkout lines, and there are
"people" to serve the processes waiting at the end of the line. A
SingleProcessor? machine has only one person to serve everyone in
line. A DualProcessor? machine has two, and so on. So, a LoadAverage
of 2 means that there's no contention for the CPU in a DualProcessor?
machine."

You gotta love the loadaverage -> effect chart

LoadAverage      Effect
0       New processes start and run quickly. The system is very responsive.
If this is a server, then you spent too much money on it, since it's
mostly sitting idle
0.5     WindowsNineX? machines begin to feel unresponsive.
1.0     The machine is processing incoming events quickly and
efficiently. Many machines running CPU-intensive background tasks sit
at this level for months at a time.
2.0     The machine is beginning to earn its keep. It is still running
efficiently, but some interactive tasks begin to feel "jittery."
4.0     Interactive tasks are noticeably jumpy.
6.0     The system may be beginning to thrash.
10.0    A FreeBSD server begins to wake up and wonder what the ruckus is about.
15.0    Some older Unix systems begin to cry.
30.0    FreeBSD begins to cry, but keeps working.
40.0    That $300,000 Sun Enterprise Server begins to seem pretty reasonable.

Reply via email to