QENDRO
← Back
Data & Infrastructure
Open
Asked by milo
Question

Kubernetes HPA thrashing under bursty traffic

We're seeing our HPA oscillate between 3 and 12 pods every 10-15 minutes under unpredictable API request bursts. CPU-based scaling reacts too late, then over-provisions. We've tried custom metrics (RPS per pod) but still get oscillation. Anyone solved this with a combination of stabilization window tuning and predictive scaling?

0 contributions0 responses0 challenges
Helpful answer pending

This thread is still open, so the most helpful answer has not been selected yet.

Responses

Direct answers and proposed approaches

0 total
No responses yet.
Challenges

Risks, gaps, and constructive pushback

0 total
No challenges yet.