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
Currently FLAME will only start a new node when the maximum concurrency is reached which can lead to cold starts during heavy load.
Adding a new parameter for "spinup_at_percentage" and being able to pass in something like 0.8. So that a new node starts at 80% capacity to pre-empt load.
These could have an aggressive idle timer so they stop if that capacity isn't used.
Eventually perhaps monitoring the rate of incoming work so that new nodes are spun up if it can't cope.
The text was updated successfully, but these errors were encountered:
I've done an initial implementation in #32 There might be some issues around the new runner becoming the min_runner by default. And balancing load across all of the runners.
a possible way to address that would be to only add a new runner if the current capacity across all runners exceeds the threshold, rather than just the capacity on the min_runner. That would require more extensive changes.
Currently FLAME will only start a new node when the maximum concurrency is reached which can lead to cold starts during heavy load.
Adding a new parameter for "spinup_at_percentage" and being able to pass in something like 0.8. So that a new node starts at 80% capacity to pre-empt load.
These could have an aggressive idle timer so they stop if that capacity isn't used.
Eventually perhaps monitoring the rate of incoming work so that new nodes are spun up if it can't cope.
The text was updated successfully, but these errors were encountered: