The ganglia build has a weird problem with it's includes that can break
the build when a previous version is installed. The build it set up
such that $(prefix)/include is before the local ganglia directories
which means that incompatible versions of ganglia headers are picked up
before the system
On Nov 11, 2003, at 8:36 AM, John M Hicks wrote:
Above metrics derived from /proc file system (kvm, kstat). Are
Cluster and
grid metrics simply averaged over total number of nodes? Can someone
tell me
which /proc entry is used for each metric?
They are generally aggregated (sum). Howeve
I feel compelled to respond since I was probably the last person to
attempt to document metrics...
Someone has just won themselves the grand prize, a self-guided tour of
the gmond/machines/$platform_name.c file!
In this file you'll find out exactly where and how your version of
Ganglia compu
All,
I need to answer some questions about the standard metrics that ganglia
collects. For example:
Here is the current list of metrics:
- Number of CPUs and Clock speed
- %CPU (user, nice, system, idle)
- Load (1,5,15 minute average)
- Memory (free, shared , buffered, cached, total)
- Pr
