Connection limit metastable collapse
At 12:00 your gRPC service's goodput (successful RPS) collapses to near zero and stays there even after you scale it 3x. Dashboards: incoming connection count is pinned at the limit; clients have a 1s timeout and immediately reconnect+retry on failure; the server spends most of its time on TLS handshakes and request setup for connections whose deadline expires before the work finishes; CPU is 100% but useful completions ~0. A brief upstream slowdown at 11:58 kicked it off and has since cleared. How do you triage and mitigate?
What a strong answer looks like
Stop the bleeding first (mitigate), then form hypotheses from real signals. Separate root cause from symptom, communicate status as you go, and close with what prevents a repeat.
0:00 of about 45 min
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.