Comparison
OvercommitvsSaturation
Overcommit
the sum of every limit on the node is three times the node, and it works fine until the day everything is busy at once.
Allowing the total of workloads' limits to exceed a node's real capacity, on the assumption that they will not all peak together. It is the mechanism that makes shared infrastructure economical, and it is a bet rather than a configuration. The bet loses in exactly the situation you care about — a correlated traffic spike — which is when eviction and throttling arrive together and the platform looks like it caused the incident.
Full entry →Saturation
you push utilisation past eighty percent and latency stops rising gently and starts going vertical.
How close a resource is to its limit. The relationship with latency is non-linear: queueing delay climbs steeply as utilisation approaches one, so a system at 90 percent is not slightly worse than one at 70, it is on a cliff. This is why capacity plans target utilisation well below full.
Full entry →