Worker threads blocked on decode
An image-processing pipeline (a pool of 64 worker threads pulling jobs off a queue) grinds to a halt: the queue backlog grows by tens of thousands, but completed-jobs-per-minute drops to near zero. Dashboards: all 64 workers show 'busy' but throughput is ~0; CPU is low. A thread sample shows most workers stuck inside the same library call decoding a particular video container with no timeout. A user started uploading a batch of malformed/huge files an hour ago. Triage and stabilize the pipeline.
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 30 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.