BeaverDeck logo
BeaverDeck

Home / BeaverDeck / Docs / Insights Guide / GPU Insights / GPU Pod Pending

GPU Pod Pending

BeaverDeck uses this check to identify a specific gpu condition that may need operator review.

Permissions: viewing checks requires insights: view. Opening a linked object or logs requires the corresponding resource permission, and the BeaverDeck ServiceAccount must be allowed to read the Kubernetes resources used by the check. Suppressing a finding requires insights: edit and affects all users.
Check typegpu-pod-pending
Insights sectionGPU Insights
Alert severityWarning

When It Reports A Finding

An active Pod requests GPUs and remains Pending for at least 5 minutes.

Why This Is A Problem

The workload is not running while demand for scarce accelerator capacity remains unsatisfied.

Recommended Response

  1. Review included events such as FailedScheduling, NotTriggerScaleUp, and FailedMount.
  2. Check available GPU capacity, node taints, tolerations, affinity, selectors, CPU/memory requests, storage, and autoscaler compatibility.
  3. Correct placement constraints or provide a node capable of satisfying the full request.

Scope And Limitations

The check starts after five minutes. It does not assume that GPU capacity is the only scheduling constraint.

After remediation: refresh GPU Insights and verify the underlying resource or metric. Suppress the finding only when the condition is intentional and its risk is accepted.