Blocking call starves event loop
A reactive (Project Reactor / Netty) Java service that normally handles 50k RPS on a handful of event-loop threads suddenly drops to handling almost nothing — latency goes to seconds, throughput collapses, but CPU is near idle (15%). Thread dumps show all of the small number of event-loop threads BLOCKED, parked inside a synchronous JDBC call and a `.block()` added in last night's deploy to 'quickly reuse' a legacy DAO. No upstream/downstream change. 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 35 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.