Victor
08/28/2025, 6:08 PMMarvin
08/28/2025, 6:08 PMMarvin
08/28/2025, 6:13 PMprefect work-pool inspect "<your-pool>"
This helps confirm the worker is attached to the right pool and queues.
- For any recent flow run, view logs and look for lines indicating submission/pickup by a worker:
prefect flow-run logs <flow_run_id>
Look for lines like “Picked up flow run …” or “Submitted flow run …”; those usually include the worker name.
On the worker host(s)
- Start workers with a distinct name so you can identify them:
prefect worker start --pool "<your-pool>" --name "temp-worker-xyz" [--work-queue "<queue-name>"]
- Watch the worker’s stdout. You should see logs like “Polling for scheduled flow runs…”, and when it’s helping you’ll see messages about picking up/submitting flow runs.
If your temp worker appears idle
- Make sure it’s pointed at the same pool and the correct work queue(s). If your deployments target specific queues, the worker must include those queue names via --work-queue
.
- Ensure the pool isn’t paused, and there isn’t a pool or queue-level concurrency limit preventing additional runs.
- Confirm your deployments are assigned to this pool (and queues).
- Increase worker log verbosity temporarily to see polling and claim attempts:
PREFECT_LOGGING_LEVEL=DEBUG prefect worker start --pool "<your-pool>" --name "temp-worker-xyz"
Docs for reference:
- Workers (Prefect 3.x)
- Worker healthchecks
If you share:
- the pool name
- how you started the temp worker (the exact command)
- a short snippet of its logs
…I can quickly confirm whether it’s picking up runs and suggest any fixes.