And, if it's running under z/VM, an idle system (instance) uses all
of the CPU cycles it's given.
Which need not be all that many.
You have the same problems w/ vmstat and sar since you're measuring
from WITHIN the system.
It's almost like what happens to time and distance at relativistic
speeds...
(but the measurements should look all the same like this- except
that the clock is still running at outside time)
--------------------
John R. Campbell, Speaker to Machines (GNUrd) {813-356|697}-5322
Adsumo ergo raptus sum
IBM Certified: IBM AIX 4.3 System Administration, System Support
----- Forwarded by John Campbell/Tampa/IBM on 12/04/2002 11:00 AM -----
"Post, Mark K"
<[EMAIL PROTECTED] To: [EMAIL PROTECTED]
m> cc:
Sent by: Linux on Subject: Re: [LINUX-390] Linux 2.4.19
Kernel loadavg
390 Port
<[EMAIL PROTECTED]
IST.EDU>
12/04/2002 10:13
AM
Please respond to
Linux on 390 Port
Sergey,
Nothing is taking all the CPU. The system is idling. That's why it's a
bug. :)
Mark Post
-----Original Message-----
From: Sergey Korzhevsky [mailto:[EMAIL PROTECTED]]
Sent: Wednesday, December 04, 2002 9:10 AM
To: [EMAIL PROTECTED]
Subject: Re: Linux 2.4.19 Kernel loadavg
What is 'top' command saying? What is the process taking all CPU?
WBR, Sergey
"Post, Mark K" <[EMAIL PROTECTED]>
Sent by: Linux on 390 Port <[EMAIL PROTECTED]>
03.12.2002 22:13
Please respond to Linux on 390 Port
To: [EMAIL PROTECTED]
cc:
Subject: Linux 2.4.19 Kernel loadavg
Since I upgraded to the 2.4.19 kernel, I've noticed that my loadavg is
always 1.00 or higher, never lower, even when idling. I'm presuming this
is
a bug of some sort.
Has anyone else seen this? Any pointers to a patch to fix it?
Mark Post
