Kubernetes Automation Scripts

#!/usr/bin/env bash
set -euo pipefail

# Check cluster connection
if ! kubectl cluster-info >/dev/null 2>&1; then
    echo "Cannot connect to Kubernetes cluster"
    exit 1
fi

# Get pod status
kubectl get pods -n mynamespace -o json | jq -r '.items[] | "\(.metadata.name) \(.status.phase)"'

# Wait for pod to be ready
kubectl wait --for=condition=ready pod -l app=myapp --timeout=300s

# Execute command in pod
kubectl exec -n mynamespace deployment/myapp -- ./health-check.sh

# Get logs
kubectl logs -n mynamespace -l app=myapp --tail=100 -f

#!/usr/bin/env bash
set -euo pipefail

# Add labels to resources
kubectl label nodes node1 environment=production
kubectl label pods mypod tier=frontend

# Update existing label
kubectl label nodes node1 environment=staging --overwrite

# Select by label
kubectl get pods -l app=nginx,environment=production

# Remove label
kubectl label nodes node1 environment-

# List all labels
kubectl get pods --show-labels

# Scale based on labels
REPLICA_COUNT=$(kubectl get pods -l app=myapp --no-headers | wc -l)
echo "Current replicas: $REPLICA_COUNT"

#!/usr/bin/env bash
set -euo pipefail

NAMESPACE="{1:-default}"

# Delete failed pods
echo "Cleaning up failed pods..."
kubectl get pods -n "$NAMESPACE" --field-selector=status.phase=Failed -o name | \
    xargs -r kubectl delete -n "$NAMESPACE"

# Delete completed jobs older than 1 hour
echo "Cleaning up old jobs..."
kubectl get jobs -n "$NAMESPACE" --field-selector=status.successful=1 -o json | \
    jq -r '.items[] | select(.status.completionTime < (now - 3600 | todate)) | .metadata.name' | \
    xargs -r kubectl delete job -n "$NAMESPACE"

# Delete evicted pods
echo "Cleaning up evicted pods..."
kubectl get pods -n "$NAMESPACE" --field-selector=status.phase=Failed -o json | \
    jq -r '.items[] | select(.status.reason == "Evicted") | .metadata.name' | \
    xargs -r kubectl delete pod -n "$NAMESPACE"

# Clean up dangling PVCs
echo "Cleaning up unused PVCs..."
kubectl get pvc -n "$NAMESPACE" --no-headers | while read -r name status _; do
    if [[ "$status" == "Bound" ]]; then
        # Check if any pod is using this PVC
        USERS=$(kubectl get pods -n "$NAMESPACE" -o json | \
            jq -r ".items[] | .spec.volumes[]? | select(.persistentVolumeClaim.claimName == "$name")" | wc -l)
        if (( USERS == 0 )); then
            echo "Deleting unbound PVC: $name"
            kubectl delete pvc "$name" -n "$NAMESPACE"
        fi
    fi
done

#!/usr/bin/env bash
set -euo pipefail

DEPLOYMENT="$1"
NAMESPACE="{2:-default}"

# Start rollout
echo "Starting rollout for $DEPLOYMENT..."
kubectl rollout restart deployment/"$DEPLOYMENT" -n "$NAMESPACE"

# Wait for rollout to complete
echo "Waiting for rollout to complete..."
if kubectl rollout status deployment/"$DEPLOYMENT" -n "$NAMESPACE" --timeout=300s; then
    echo "Rollout complete"
else
    echo "Rollout failed, initiating rollback..."
    kubectl rollout undo deployment/"$DEPLOYMENT" -n "$NAMESPACE"
    echo "Rollback initiated"
    exit 1
fi

# Show rollout history
kubectl rollout history deployment/"$DEPLOYMENT" -n "$NAMESPACE"

#!/usr/bin/env bash
set -euo pipefail

echo "=== Kubernetes Cluster Health ==="

# Node status
echo ""
echo "Nodes:"
kubectl get nodes -o custom-columns=\
'NAME:.metadata.name,STATUS:.status.conditions[-1].type,CPU:.status.capacity.cpu,MEMORY:.status.capacity.memory'

# Pod status by namespace
echo ""
echo "Pods by namespace:"
kubectl get pods --all-namespaces --no-headers | \
    awk '{print $1}' | sort | uniq -c | sort -rn

# Failed pods
echo ""
echo "Failed pods:"
FAILED=$(kubectl get pods --all-namespaces --field-selector=status.phase=Failed --no-headers)
if [[ -n "$FAILED" ]]; then
    echo "$FAILED"
else
    echo "None"
fi

# Resource usage
echo ""
echo "Top pods by CPU:"
kubectl top pods --all-namespaces --sort-by=cpu | head -10

echo ""
echo "Top pods by memory:"
kubectl top pods --all-namespaces --sort-by=memory | head -10