Hi Richard,

On Wednesday 07 February 2007 16:11, [EMAIL PROTECTED] wrote:
> a swiss consultancy has implemented a native windows gmond
[...]

Thanks for the announcement.

Most HEP people run Linux clusters, but I know people that like Ganglia and 
run Windows machines; I'll forward the link.

[...]
> The final point is that as the extra metrics are binary coded, it should
> be deployed in an all or nothing way per cluster.

This is a shame.  So one cannot simply run the nice gmond.exe on a WIndows 
machine and start monitoring it within an existing *nix-based ganglia 
framework.

If I've understood this correctly, this reflects (what I feel is) one of the 
weaknesses of Ganglia at the moment: non-core data (e.g. gmetric) is treated 
as if it were second-class information.  If other gmond-like daemons are to 
send other interesting metrics, then ganglia should move away from 
hard-coding the core metrics into the binary encoding (protocol.x).

Instead, ganglia's encoding of data could be metric neutral;  a UDP packet 
would contain multiple metrics,  all, some or none of which could be "core".  
What are currently core metrics, as provided by gmond, could be identified by 
their names (i.e. have "well known" names).

Is this in keeping with any current plans?

Cheers,

Paul.

Attachment: pgpCGKDrw6ngc.pgp
Description: PGP signature

Reply via email to