The tug-wait hosts show high CPU while invoke counts still look modest, because each call does heavy featurization. Scaling on invoke count alone never adds capacity in time. Which auto scaling metric fits?
Select an answer to reveal the explanation.
Short Explanation
Tug-wait hosts show high CPU while invoke counts look modest, because each call does heavy featurization. Scale on CPU utilization. InvocationsPerInstance misses the wall, and scheduled scaling is a clock policy, not a CPU signal.
Full Explanation
Scale on CPU utilization when the bottleneck is host CPU, not raw invoke count. InvocationsPerInstance misses heavy per-call featurization. Fraud Detector is not that metric, and scheduled scaling is a clock policy, not a CPU signal.