Re: [Ganglia-general] Weide hosts reports

2010-12-14 Thread Bernard Li 
Hi Jonathan:

How many hosts did you add at a time and did you do anything to your
gmond collector while these hosts were coming up?

Cheers,

Bernard

On Sat, Dec 11, 2010 at 12:59 PM, Jonathan Weiss j...@innerewut.de wrote:
 Cheers,


 We maintain several cluster on EC2 for customers that we monitor with
 Ganglia. We automatically boot and configure instances on EC2 and let
 them report to a Ganglia cluster per customer.

 We often see hosts come up and report in Ganglia with weired stats, see

 https://skitch.com/jweiss/rrt18/cluster
 https://skitch.com/jweiss/rrt1w/load
 https://skitch.com/jweiss/rrt1a/cpu

 On the host view we only see static values and on the cluster overview
 the number of cores/processes alternates. When I manually restart
 gmond on the instance, the stats are fixed again. No changes in the
 configuration, just a restart of the local gmond. You can see the
 effect of the restart at the end in the screenshots.

 We use Ganglia on Ubuntu 9.10:
 ubu...@mimas:~$ dpkg -l | grep ganglia
 ii  ganglia-monitor                   3.1.2-2
  cluster system monitoring daemon
 ii  libganglia1                       3.1.2-2
  ganglia cluster system monitor toolkit (shar

 Any idea what is going on?

 Thanks,
 Jonathan

 --
 Jonathan Weiss
 http://blog.innerewut.de
 http://twitter.com/jweiss

 --
 Oracle to DB2 Conversion Guide: Learn learn about native support for PL/SQL,
 new data types, scalar functions, improved concurrency, built-in packages,
 OCI, SQL*Plus, data movement tools, best practices and more.
 http://p.sf.net/sfu/oracle-sfdev2dev
 ___
 Ganglia-general mailing list
 Ganglia-general@lists.sourceforge.net
 https://lists.sourceforge.net/lists/listinfo/ganglia-general


--
Lotusphere 2011
Register now for Lotusphere 2011 and learn how
to connect the dots, take your collaborative environment
to the next level, and enter the era of Social Business.
http://p.sf.net/sfu/lotusphere-d2d
___
Ganglia-general mailing list
Ganglia-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-general

Re: [Ganglia-general] Weide hosts reports

2010-12-14 Thread Jonathan Weiss 
Hi Bernard,

 How many hosts did you add at a time and did you do anything to your
 gmond collector while these hosts were coming up?

On some clusters just one or two instances are starting at one time,
on others up to four instances are added.
While all of this is going on, we don't touch the collecting gmond.
Sometimes we restart gmetad if a completely new role (like
Caching-Server) is added. But we this the weird behavior mostly in
cluster were we just start  stop instances within an existing ole.
E.g. increasing the number of web servers when the load increases.

Jonathan

-- 
Jonathan Weiss
http://blog.innerewut.de
http://twitter.com/jweiss

--
Lotusphere 2011
Register now for Lotusphere 2011 and learn how
to connect the dots, take your collaborative environment
to the next level, and enter the era of Social Business.
http://p.sf.net/sfu/lotusphere-d2d
___
Ganglia-general mailing list
Ganglia-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/ganglia-general