Status and monitoring

At the Carlos I Institute of Theoretical and Computational Physics we have several tools that help to know the status of PROTEUS and its workload. It is useful to know this information when planning the submission of new work. They also allow us to know more detailed data about the execution of the programmes.

_

Ganglia

General monitoring

Displays the overall status of the cluster, such as total number of nodes and CPUs, their workload, RAM usage, network traffic, temperature, etc. It is broken down into node families.
Ganglia. Monitorización de PROTEUS
Ganglia. Monitorización de PROTEUS
Xdmod. Monitorización y estadísticas PROTEUS
Xdmod. Monitorización y estadísticas PROTEUS
_

Xdmod

PROTEUS Usage statistics

Includes number of jobs, CPU hours, users, etc. Due to the sensitivity of the data, it requires connection from the UGR-Network. It also allows identified access to have a more detailed view of the resources consumed by the user’s jobs.
_

Do you need more info?

_