Currently, the CPU/GPU data in the requests being sent to the database are being pulled straight from the .yaml config file. So if the resources are not being used fully, it won't show.
Need to implement more precise tracking of these two metrics during a job, and then populate the redis futures file with that data.
Currently in ventis/controllers/utils/sqlalchemy.py, on around line 62 the GPU/CPU is being pulled from the config file as the variable res.
Currently, the CPU/GPU data in the requests being sent to the database are being pulled straight from the .yaml config file. So if the resources are not being used fully, it won't show.
Need to implement more precise tracking of these two metrics during a job, and then populate the redis futures file with that data.
Currently in ventis/controllers/utils/sqlalchemy.py, on around line 62 the GPU/CPU is being pulled from the config file as the variable res.