How to fix DeadlineExceeded in Kubernetes

# Describe the job to see status and events
kubectl describe job <job-name> -n <namespace>

# View the job YAML specification
kubectl get job <job-name> -n <namespace> -o yaml

# Check recent events
kubectl get events -n <namespace> --sort-by='.lastTimestamp'

# Get logs from the terminated pod
kubectl logs <pod-name> -n <namespace> --tail=100

# Check pod start and end times
kubectl get pod <pod-name> -n <namespace> -o jsonpath='{.status.containerStatuses[0].state}'

apiVersion: batch/v1
kind: Job
metadata:
  name: long-running-backup
spec:
  backoffLimit: 3
  activeDeadlineSeconds: 3600  # Increased from 600 to 3600 (1 hour)
  template:
    spec:
      containers:
      - name: backup-container
        image: myregistry/backup:latest
        command: ["./backup-script.sh"]
      restartPolicy: Never

# Check node capacity and allocation
kubectl top nodes
kubectl describe nodes

# View resource requests/limits in your job
kubectl get job <job-name> -n <namespace> -o yaml | grep -A 5 'resources:'

#!/bin/bash
# Wrap your command with GNU timeout
timeout 1800 ./my-long-running-process.sh
exit_code=$?

if [ $exit_code -eq 124 ]; then
  echo "Process timed out after 1800 seconds"
  exit 1
fi
exit $exit_code

# Correct: activeDeadlineSeconds at Job spec level
kubectl get job <job-name> -n <namespace> -o jsonpath='{.spec.activeDeadlineSeconds}'

# Check if Pod spec also has activeDeadlineSeconds (applies per-pod)
kubectl get job <job-name> -n <namespace> -o jsonpath='{.spec.template.spec.activeDeadlineSeconds}'

spec:
  activeDeadlineSeconds: 3600  # Job-level only
  template:
    spec:
      # Do NOT set activeDeadlineSeconds here unless you need per-Pod control
      containers: ...