Headroom reduction

Headroom reduction deploys new nodes much faster than other autoscalers with large-scale node hibernation and re-activation reducing the need for buffer.

The following video shows how Headroom reduction reduces the need for an overallocated node buffer:

The magic behind the scenes

When you activate Headroom reduction on a workload, the following automatic (and manual) steps ensure protection:

1. Hibernated nodes begin warming up. Kompass listens to the unscheduled Pods pool.

2. After you verify that the protection is active, for best cost savings, manually reduce replicas to the recommended minimum.

3. When Kompass determines that there are unscheduled Pods in the pool, Kompass deploys pre-baked, hibernated nodes to respond to spikes.

   At the same time, Karpenter launches new nodes.

4. When the Karpenter nodes are ready to serve requests* and there are no more unscheduled Pods in the pool, the Kompass nodes are drained and returned to hibernation.