Hi Martin,
Thanks. ;)
I'm afraid I don't have LSF support available _yet_. I haven't found a
proper Python interface to the LSF library (and not parsing binary output).
However, there is a lot of interest and misc. others have asked me the
same and I am planning on integrating LSF support in some future release
asap. It's high on my TODO list.
I just have to find the time somewhere to work it out. ;)
Kind regards,
- Ramon.
[EMAIL PROTECTED] wrote:
Hi Ramon,
Your addon is great! Do you have this Integration for Lava/LSF available?
Regards,
Martin
-----Ursprüngliche Nachricht-----
Von: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Im Auftrag von Ramon Bastiaans
Gesendet: Mittwoch, 3. Mai 2006 12:29
An: Babu Sundaram
Cc: [EMAIL PROTECTED]; [email protected]
Betreff: Re: [Ganglia-general] HPC Metrics via Ganglia
Babu,
I don't know which specific metrics you would like to see?
I have written an addon to Ganglia that allready reports a great amount
of job/HPC/batch information in Ganglia. Currently it supports all
PBS/Torque based batch systems.
An example is viewable here: http://ganglia.sara.nl/ (view the "LISA
Cluster" overview for the best view)
You can get it here:
ftp://ftp.sara.nl/pub/outgoing/ganglia_jobmonarch-latest.tar.gz
Average CPU Load over past timeperiods is allready displayed in
Ganglia's own graphs I think? Average job queue lengths and assorted
could be easily added/implemented/integrated with my addon.
It might be a little unnecessary to develop another HPC addon, while the
functionality/features you'd like to see are easily integrated into Job
Monarch. Is this the case?
I'm open to any suggestions for extra functionality or patches you might
have.
Kind regards,
- Ramon.
Babu Sundaram wrote:
Hello All :
I am planning to propose a Ganglia-related project to the OSCAR
toolkit as part of Google Summer of Code and hope I can get some input
from this list. One of the possible enhancements to the OSCAR-Ganglia
package is to derive and show some useful HPC metrics to the user from
the output of Ganglia, for example, average CPU load over the past n
timeperiods, average job queue lengths over past n timeperiods and
such. Are there any other meaningful metrics that users often like to
see and get implemented? Please let me know if you have any
suggestions. Thank you.
Regards,
Babu
http://www.cs.uh.edu/~babu
-------------------------------------------------------
Using Tomcat but need to do more? Need to support web services,
security? Get stuff done quickly with pre-integrated technology to
make your job easier Download IBM WebSphere Application Server v.1.0.1
based on Apache Geronimo
http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642
_______________________________________________
Ganglia-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/ganglia-general
--
ing. R. Bastiaans HPC - Systems Programmer
SARA - Computing and Networking Services
Kruislaan 415 PO Box 194613
1098 SJ Amsterdam 1090 GP Amsterdam
Tel. +31 (0) 20 592 3000 Fax. +31 (0) 20 668 3167
---
There are really only three types of people:
Those who make things happen, those who watch things happen
and those who say, "What happened?"
