You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Frigate pod deployed to Node A, with GPU and Coral applied as nodeselectors / resource limits.
Plex pod is deployed as well, I want to make sure frigate is never preempted by the Plex pod (as it also looks for GPU for hardware transcoding).
Since Frigate is "stuck" on a node due to hardware requirements from the Coral USB TPU, it doesn't have the luxury of just moving to another node. priorityClassName would mean that it doesn't have to, and it can actually boot other pods out as needed.
Hello,
As far as I know, this Helm Chart doesn't offer this ability to set the
priorityClassName
to Frigate pods.This might be useful as some pods in the cluster might need to have lower/higher priorities than Frigate.
If you are willing to implement this, I can make the PR.
The text was updated successfully, but these errors were encountered: