diff --git a/k8s/deployment-backfill.yaml b/k8s/deployment-backfill.yaml index 21364dbf..6e218212 100644 --- a/k8s/deployment-backfill.yaml +++ b/k8s/deployment-backfill.yaml @@ -73,20 +73,25 @@ spec: - secretRef: name: prop-secrets # No HTTP probes (no web server). Use exec probe against the - # running BEAM to confirm the VM is responsive. + # running BEAM to confirm the VM is responsive. timeoutSeconds + # is generous because `rpc ':ok'` has to spawn a release CLI + # and round-trip through distributed Erlang; during an IEM + # 429 retry storm (WeatherFetchWorker sleeping 1-16 s between + # attempts) the scheduler is responsive but slow, and a 5 s + # probe timeout was tripping failureThreshold every ~10 min. startupProbe: exec: command: ["/bin/sh", "-c", "/app/bin/microwaveprop rpc ':ok'"] initialDelaySeconds: 10 periodSeconds: 5 failureThreshold: 24 - timeoutSeconds: 5 + timeoutSeconds: 15 livenessProbe: exec: command: ["/bin/sh", "-c", "/app/bin/microwaveprop rpc ':ok'"] periodSeconds: 30 failureThreshold: 3 - timeoutSeconds: 5 + timeoutSeconds: 15 resources: # 8GB T620 box — leave ~3GB for kubelet/containerd/OS. requests: