loadavg 1.0 on idle system

Hello!

I am running RedHat Enterprise Linux WS4 update 2 (64 bit) (fully updated) on a SunFire X4200 with one 248 CPU (single core), 1GB of memory.

My problem is that the server seems to have a loadavg around 1.0 for a couple of hours and then the loadavg goes down to 0.0. After some hours it does it again.

The strange thing is that I am quite convenced that me system is quite idle.

Top shows the following statistics:
-----
top - 15:36:12 up 4:13, 2 users, load average: 0.96, 0.98, 0.79
Tasks: 62 total, 2 running, 60 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.0% us, 0.7% sy, 0.0% ni, 99.0% id, 0.3% wa, 0.0% hi, 0.0% si
-----

Is'nt it strange that the system is 99% idle but the load is almost 1.0. I know that a high loadavg can be produced if the host waits on IO but how can I see if that is the problem and how can I see what process is causing the problem.

Could this be a kernel problem?

Best regards,
- Morten Green Hermansen
.

Relevant Pages

  • Re: "Load Balancing": How Busy are the servers?
    ... For instance, I've always been taugth that 'loadavg' is not an indication of how busy a server is, since a high loadavg on a single CPU server might be an overloaded server, but moderately loaded on a dual CPU server ... ...
    (freebsd-questions)
  • loadavg 1.0 on idle system
    ... My problem is that the server seems to have a loadavg around 1.0 for a couple of hours and then the loadavg goes down to 0.0. ... I know that a high loadavg can be produced if the host waits on IO but how can I see if that is the problem and how can I see what process is causing the problem. ... Best regards, ...
    (alt.os.linux.redhat)
  • anormal loadavg
    ... on a DELL server bi-Xéon 3,2Ghz, i've got a loadavg of 55.37 all days longs but all work fine on the ... To UNSUBSCRIBE, email to debian-user-REQUEST@xxxxxxxxxxxxxxxx ...
    (Debian-User)