Skip to content

oke-troubleshooter.md

Latest commit

 

History

History
41 lines (27 loc) · 1.33 KB

oke-troubleshooter.md

File metadata and controls

41 lines (27 loc) · 1.33 KB
Raw

OKE Troubleshooter Transcript

This is a shortened successful troubleshooting run with redacted identifiers.

Prompt

/oke-agent-plugin:oke-troubleshooter "pods stuck Pending in prod namespace"

Transcript

User: Pods are stuck Pending in the prod namespace.

Agent: I mapped the symptom to Pod scheduling, Node health, Cluster Autoscaler, and OCI limits. I will collect read-only evidence with kubectl and OCI CLI.

Agent: Evidence collected:

  • kubectl -n prod get pods --field-selector=status.phase=Pending -o wide
  • kubectl -n prod get events --field-selector reason=FailedScheduling
  • kubectl -n kube-system logs deployment/cluster-autoscaler --tail=200
  • oci ce node-pool list --compartment-id <compartment_ocid> --cluster-id <cluster_ocid>

Agent: Findings:

Hypothesis Score Evidence
Node pool max size reached 9 FailedScheduling reports insufficient CPU; autoscaler logs show max node group size reached
OCI compute capacity or quota limit 5 No direct quota error found, but scale-out was blocked

Agent: Next steps:

kubectl -n prod describe pod <pending-pod>
oci ce node-pool update --node-pool-id <node_pool_ocid> --size <larger_size>

What This Produces

See sample troubleshooting report.