I'm trying to get this nvidia module working on CentOS 7:
https://github.com/ganglia/gmond_python_modules/tree/master/gpu/nvidia
I did the following:
* Installed CUDA on node but NOT on the Ganglia server
* Installed nvidia-ml-py-7.352.0.tar.gz on both node and server
* put nvidia.py into
Do you know if the metrics are actually being collected?
An easy way to test is to use netcat or telnet to connect to the
compute node with the nVidia card:
nc node123 8649
That should dump a bunch of XML, and you can search that for the
metrics generated by the plugin. If you find them
Hi!
We changed our ganglia server to use rrdcache and at the source site is
everything ok.
But when you switch to a node site there is only a "1" between the header and
footer.
ganglia 3.7.2
ganglia web 3.7.1
rrdtool 1.4.7
dwoo1.1.1
3 matches
Mail list logo