The divider core is the core plugin used by default by the vJoule service. It divides the consumptions of the watched cgroups using their consumption. It can monitor three different kind of sensor plugins cpu, gpu and ram.

A result directory is created for every watched cgroup. Each of them will contain three files cpu, ram and gpu containing the consumption of the cgroup in joule since its creation (i.e. since the moment vjoule started monitoring them).

A default configuration and explanation of the divider plugin can be acquired by running the command vjoule_service --ph divider.

Here an example of configuration that can be used by the divider core :

[sensor]
freq = 1 # frequency of update in hertz (the higher the faster)
log-lvl = "info" # debug < success < info < warn < error < none
log-path = "/etc/vjoule/service.log" # log file (empty means stdout)

# the name of the core plugin to use for the sensor
core = "divider" 

# the directory in which result will be written
output-dir = "/etc/vjoule/results" 

# delete cgroup result directories when the cgroup no longer exists
delete-res = true

# if true mount the result directory in tmpfs (less i/o generated by vjoule)
mount-tmpfs = true

# following configuration is optional
# It activates some part of the divider

[cpu] # configuration to enable CPU energy reading
name = "rapl" # rapl plugin for compatible intel or amd cpus

[ram] # configuration to enable RAM energy reading
name = "rapl" # rapl plugin for compatible intel or amd cpus

[gpu:0] # configuration to enable GPU energy reading
name = "nvidia" # nvidia plugin for nvidia GPUs

# A machine can have different GPU from different constructors
# For example a integrated GPU, and an nvidia GPU card
[gpu:1] # configuration to enable GPU energy 
name = "rapl" # rapl plugin form compatible intel of amd cpus

The flag delete-res can sometime comes in handy when monitoring cgroups that are appearing and disappearing during the lifetime of an experiment. It will forbid the service to remove the result directories when the cgroup disappear. By default result directories are deleted when cgroups disappear to avoid using two much memory or disk space.

On the other hand the flag mount-tmpfs will make the divider plugin mount the result directory in tmpfs, to avoid making I/O access when writting the result.

The divider core plugin uses another configuration file, in /etc/vjoule/cgroups, to filter the cgroups that are watched by the sensor, and ignore unwanted cgroups. This configuration file is a list of rules, every rules must start with a slice (a cgroup that contains other cgroups). For example my.slice/*., will make the sensor watch all the cgroups in the slice my.slice, and system.slice/docker* will watch all the cgroups in system.slice that starts with docker. Basically, it lists all the cgroups that would be found if the command ls my_rule was run in the cgroup mount directory. The following presents an example of configuration for cgroup listing that has to be placed in /etc/vjoule/cgroups.

vjoule.slice/*
system.slice/docker*
my_custom.slice/my_custom_cgroup