[GE users] Calculation of load average accurately

John Coldrick jc at axyzfx.com
Tue Aug 10 22:06:05 BST 2004


    [ The following text is in the "iso-8859-1" character set. ]
    [ Your display is set for the "ISO-8859-10" character set.  ]
    [ Some special characters may be displayed incorrectly. ]

On Tuesday 10 August 2004 16:50, Anand S Bisen wrote:
> What should be the correct way to define the load average in the sun grid
> engine 5.3ee. Currently on my cluster that consists of 64 node all with
> dual Pentium 4 3.2 GHz processors we are using np_load_average as the
> method for load formula and the threshold that is set as of now is 1.75.

	I've been curious about this too.  My understanding is that SGE returns 
load_avg in the same way that the command "uptime" does - using the same call 
to the system.  The second number after "load average" from uptime is this 
value.   I also know that sometimes certain activities such as fairly heavy 
nfs activity on a given system can artificially increase load activity on a 
system, even though it's not really impacting cpu all that much.   This has 
improved in SGE6, I've found...less misleading.   Tracking system load in 
Linux is a bugger.  :)

	Cheers,

	J.C.

-- 
John Coldrick                  www.axyzfx.com        Axyz Animation
Houdini/Renderman/Discreet                           425 Adelaide St W
416-504-0425                                         Toronto, ON Canada
jc at axyzfx.com                                        M5V 1S4
-----------------------------------------------------------------------
"The way to make a small fortune in the commodities market is to start
with a large fortune."

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list