Comparison
Capacity planningvsSaturation
Capacity planning
you work out from load tests how much traffic one instance handles, and how many you need for Black Friday.
Determining the resources required to meet demand at a target latency, with headroom for failure and spikes. It requires a measured per-instance capacity, not an assumed one. Plan for the loss of a zone or a region as well as the peak, or your headroom disappears exactly when you need it.
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 →