Add backup testing scripts

This commit is contained in:
Ruben Hensen
2025-03-04 03:23:44 +01:00
parent 36ce0e0009
commit 0522748a2b
5 changed files with 203 additions and 123 deletions
@@ -39,6 +39,15 @@ This script will look for credentials in `~/.velero/credentials-velero` or promp
Execute the test script with appropriate parameters:
```bash
./test-velero-backup.sh \
--s3-access-key <ACCESS_KEY> \
--s3-secret-key <SECRET_KEY> \
--backup-name <BACKUP_NAME> \
--original-namespace mbgwp \
--test-namespace mbgwp
```
```bash
./test-velero-backup.sh \
--s3-access-key YOUR_ACCESS_KEY \
+23
View File
@@ -0,0 +1,23 @@
apiVersion: v1
kind: ConfigMap
metadata:
# any name can be used; Velero uses the labels (below)
# to identify it rather than the name
name: change-storage-class-config
# must be in the velero namespace
namespace: velero
# the below labels should be used verbatim in your
# ConfigMap.
labels:
# this value-less label identifies the ConfigMap as
# config for a plugin (i.e. the built-in change storage
# class restore item action plugin)
velero.io/plugin-config: ""
# this label identifies the name and kind of plugin
# that this ConfigMap is for.
velero.io/change-storage-class: RestoreItemAction
data:
# add 1+ key-value pairs here, where the key is the old
# storage class name and the value is the new storage
# class name.
longhorn: local-path
-39
View File
@@ -1,39 +0,0 @@
#!/bin/bash
# setup-credentials.sh - Script to help setup credentials for Velero testing
# Directory where Velero credentials are stored on the production system
# This would be your production system's credentials for accessing MinIO
VELERO_CREDS_PATH="${HOME}/.velero/credentials-velero"
if [ -f "${VELERO_CREDS_PATH}" ]; then
echo "Found Velero credentials at ${VELERO_CREDS_PATH}"
# Extract AWS credentials from the file
AWS_ACCESS_KEY_ID=$(grep aws_access_key_id ${VELERO_CREDS_PATH} | cut -d= -f2 | tr -d '[:space:]')
AWS_SECRET_ACCESS_KEY=$(grep aws_secret_access_key ${VELERO_CREDS_PATH} | cut -d= -f2 | tr -d '[:space:]')
if [ -n "${AWS_ACCESS_KEY_ID}" ] && [ -n "${AWS_SECRET_ACCESS_KEY}" ]; then
echo "Credentials found and will be used for backup testing"
# Store them temporarily for the test script to use
cat > /tmp/velero-test-credentials <<EOF
[default]
aws_access_key_id=${AWS_ACCESS_KEY_ID}
aws_secret_access_key=${AWS_SECRET_ACCESS_KEY}
EOF
echo "Credentials saved to /tmp/velero-test-credentials"
echo ""
echo "Run your test script with:"
echo "./test-velero-backup.sh --s3-access-key ${AWS_ACCESS_KEY_ID} --s3-secret-key ${AWS_SECRET_ACCESS_KEY} [other options]"
else
echo "Error: Could not extract credentials from ${VELERO_CREDS_PATH}"
exit 1
fi
else
echo "Error: Velero credentials file not found at ${VELERO_CREDS_PATH}"
echo "Please create this file with the following format:"
echo "[default]"
echo "aws_access_key_id=YOUR_MINIO_ACCESS_KEY"
echo "aws_secret_access_key=YOUR_MINIO_SECRET_KEY"
exit 1
fi
+94 -84
View File
@@ -76,7 +76,7 @@ while [[ $# -gt 0 ]]; do
done
# Verify required variables
if [[ -z "$S3_BUCKET" || -z "$S3_REGION" || -z "$S3_ACCESS_KEY" || -z "$S3_SECRET_KEY" ]]; then
if [[ -z "$S3_BUCKET" || -z "$S3_REGION" || -z "$S3_ACCESS_KEY" || -z "$S3_SECRET_KEY" || -z "$ORIGINAL_NAMESPACE" || -z "$TEST_NAMESPACE" ]]; then
echo "Error: S3 configuration is incomplete"
exit 1
fi
@@ -106,29 +106,34 @@ k3d cluster create backup-test \
--api-port 6443 \
--port "80:80@loadbalancer" \
--port "443:443@loadbalancer" \
--agents 2 \
--agents 0 \
--k3s-arg "--disable=traefik@server:0" \
--wait
# -v /mnt/longhorn:/var/lib/longhorn:shared@all \
# -i hebury/k3s:v1.32.2-k3s1 \
# --wait
# Verify cluster is running
kubectl config use-context k3d-backup-test
kubectl get nodes
# 2. Install Longhorn
echo "Installing Longhorn..."
kubectl create namespace longhorn-system
# echo "Installing Longhorn..."
# kubectl create namespace longhorn-system
helm repo add longhorn https://charts.longhorn.io
helm repo update
# helm repo add longhorn https://charts.longhorn.io
# helm repo update
helm install longhorn longhorn/longhorn \
--namespace longhorn-system \
--set persistence.defaultClassReplicaCount=1 \
--set defaultSettings.backupTarget="" \
--set defaultSettings.defaultReplicaCount=1
# helm install longhorn longhorn/longhorn \
# --namespace longhorn-system \
# --set persistence.defaultClassReplicaCount=1 \
# --set defaultSettings.backupTarget="" \
# --set defaultSettings.defaultReplicaCount=1
echo "Waiting for Longhorn to be ready..."
kubectl -n longhorn-system rollout status deployment/longhorn-ui
# echo "Waiting for Longhorn to be ready..."
# kubectl -n longhorn-system rollout status deployment/longhorn-ui
# kubectl -n longhorn-system rollout status deployment/longhorn-driver-deployer
# kubectl -n longhorn-system rollout status daemonset/longhorn-manager
# 3. Install Velero with S3 provider
echo "Installing Velero..."
@@ -174,6 +179,9 @@ rm velero-credentials
echo "Waiting for Velero to be fully ready..."
kubectl -n velero rollout status deployment/velero --timeout=120s
echo "Install change-storage-class.yaml"
kubectl apply -f change-storage-class.yaml
# Check if velero CLI is installed and functioning
if ! command -v velero &> /dev/null; then
echo "Error: Velero CLI is not installed or not in PATH"
@@ -262,6 +270,8 @@ else
velero restore create --from-backup $BACKUP_NAME \
--namespace-mappings $ORIGINAL_NAMESPACE:$TEST_NAMESPACE \
--include-namespaces $ORIGINAL_NAMESPACE \
--exclude-namespaces kube-system,kube-public,kube-node-lease,velero \
--exclude-resources certificates.cert-manager.io \
--wait
fi
@@ -274,89 +284,89 @@ echo "Waiting for pods to be ready..."
kubectl wait --for=condition=ready pod --all -n $TEST_NAMESPACE --timeout=300s || true
# 8. Run validation script (create it first if it doesn't exist)
if [[ ! -f ./validate-restore.sh ]]; then
echo "Creating validation script..."
cat > validate-restore.sh <<'EOF'
#!/bin/bash
# validate-restore.sh - Script to validate Velero backup restoration
# if [[ ! -f ./validate-restore.sh ]]; then
# echo "Creating validation script..."
# cat > validate-restore.sh <<'EOF'
# #!/bin/bash
# # validate-restore.sh - Script to validate Velero backup restoration
set -e
echo "Starting validation of restored resources..."
# set -e
# echo "Starting validation of restored resources..."
# Get namespace from command line or use default
NAMESPACE="${1:-default}"
# # Get namespace from command line or use default
# NAMESPACE="${1:-default}"
# Check all deployments
echo "Checking deployments..."
deployments=$(kubectl get deployment -n $NAMESPACE -o name)
if [[ -z "$deployments" ]]; then
echo "❌ No deployments found in namespace $NAMESPACE"
else
echo "Found deployments: $deployments"
# # Check all deployments
# echo "Checking deployments..."
# deployments=$(kubectl get deployment -n $NAMESPACE -o name)
# if [[ -z "$deployments" ]]; then
# echo "❌ No deployments found in namespace $NAMESPACE"
# else
# echo "Found deployments: $deployments"
# Check if pods are running for each deployment
for deployment in $deployments; do
name=$(echo $deployment | cut -d'/' -f2)
echo -n "Checking deployment $name: "
# # Check if pods are running for each deployment
# for deployment in $deployments; do
# name=$(echo $deployment | cut -d'/' -f2)
# echo -n "Checking deployment $name: "
# Check if pods are running
ready_replicas=$(kubectl get deployment -n $NAMESPACE $name -o jsonpath='{.status.readyReplicas}')
if [[ -n "$ready_replicas" && "$ready_replicas" != "0" ]]; then
echo "✅ $ready_replicas pods ready"
else
echo "❌ No pods running"
fi
done
fi
# # Check if pods are running
# ready_replicas=$(kubectl get deployment -n $NAMESPACE $name -o jsonpath='{.status.readyReplicas}')
# if [[ -n "$ready_replicas" && "$ready_replicas" != "0" ]]; then
# echo "✅ $ready_replicas pods ready"
# else
# echo "❌ No pods running"
# fi
# done
# fi
# Check all services
echo "Checking services..."
services=$(kubectl get service -n $NAMESPACE -o name | grep -v "kubernetes")
if [[ -z "$services" ]]; then
echo "❌ No services found in namespace $NAMESPACE"
else
echo "Found services: $services"
# # Check all services
# echo "Checking services..."
# services=$(kubectl get service -n $NAMESPACE -o name | grep -v "kubernetes")
# if [[ -z "$services" ]]; then
# echo "❌ No services found in namespace $NAMESPACE"
# else
# echo "Found services: $services"
# Check if services have endpoints
for service in $services; do
name=$(echo $service | cut -d'/' -f2)
echo -n "Checking service $name: "
# # Check if services have endpoints
# for service in $services; do
# name=$(echo $service | cut -d'/' -f2)
# echo -n "Checking service $name: "
# Check if service has endpoints
endpoints=$(kubectl get endpoints -n $NAMESPACE $name -o jsonpath='{.subsets[*].addresses[*].ip}')
if [ -n "$endpoints" ]; then
echo "✅ Has endpoints"
else
echo "❌ No endpoints"
fi
done
fi
# # Check if service has endpoints
# endpoints=$(kubectl get endpoints -n $NAMESPACE $name -o jsonpath='{.subsets[*].addresses[*].ip}')
# if [ -n "$endpoints" ]; then
# echo "✅ Has endpoints"
# else
# echo "❌ No endpoints"
# fi
# done
# fi
# Check PVCs
echo "Checking PVCs..."
pvcs=$(kubectl get pvc -n $NAMESPACE -o name)
if [[ -z "$pvcs" ]]; then
echo "No PVCs found in namespace $NAMESPACE"
else
pvc_count=$(echo "$pvcs" | wc -l)
echo "Found $pvc_count PVCs"
# # Check PVCs
# echo "Checking PVCs..."
# pvcs=$(kubectl get pvc -n $NAMESPACE -o name)
# if [[ -z "$pvcs" ]]; then
# echo "No PVCs found in namespace $NAMESPACE"
# else
# pvc_count=$(echo "$pvcs" | wc -l)
# echo "Found $pvc_count PVCs"
# Check if PVCs are bound
bound_count=$(kubectl get pvc -n $NAMESPACE -o jsonpath='{.items[?(@.status.phase=="Bound")].metadata.name}' | wc -w)
echo "$bound_count/$pvc_count PVCs are bound"
# # Check if PVCs are bound
# bound_count=$(kubectl get pvc -n $NAMESPACE -o jsonpath='{.items[?(@.status.phase=="Bound")].metadata.name}' | wc -w)
# echo "$bound_count/$pvc_count PVCs are bound"
if [ "$bound_count" -ne "$pvc_count" ]; then
echo "❌ Not all PVCs are bound"
else
echo "✅ All PVCs are bound"
fi
fi
# if [ "$bound_count" -ne "$pvc_count" ]; then
# echo "❌ Not all PVCs are bound"
# else
# echo "✅ All PVCs are bound"
# fi
# fi
echo "Validation complete!"
exit 0
EOF
chmod +x validate-restore.sh
fi
# echo "Validation complete!"
# exit 0
# EOF
# chmod +x validate-restore.sh
# fi
echo "Running validation tests..."
./validate-restore.sh $TEST_NAMESPACE
+77
View File
@@ -0,0 +1,77 @@
#!/bin/bash
# validate-restore.sh - Script to validate Velero backup restoration
set -e
echo "Starting validation of restored resources..."
# Get namespace from command line or use default
NAMESPACE="${1:-default}"
# Check all deployments
echo "Checking deployments..."
deployments=$(kubectl get deployment -n $NAMESPACE -o name)
if [[ -z "$deployments" ]]; then
echo "❌ No deployments found in namespace $NAMESPACE"
else
echo "Found deployments: $deployments"
# Check if pods are running for each deployment
for deployment in $deployments; do
name=$(echo $deployment | cut -d'/' -f2)
echo -n "Checking deployment $name: "
# Check if pods are running
ready_replicas=$(kubectl get deployment -n $NAMESPACE $name -o jsonpath='{.status.readyReplicas}')
if [[ -n "$ready_replicas" && "$ready_replicas" != "0" ]]; then
echo "$ready_replicas pods ready"
else
echo "❌ No pods running"
fi
done
fi
# Check all services
echo "Checking services..."
services=$(kubectl get service -n $NAMESPACE -o name | grep -v "kubernetes")
if [[ -z "$services" ]]; then
echo "❌ No services found in namespace $NAMESPACE"
else
echo "Found services: $services"
# Check if services have endpoints
for service in $services; do
name=$(echo $service | cut -d'/' -f2)
echo -n "Checking service $name: "
# Check if service has endpoints
endpoints=$(kubectl get endpoints -n $NAMESPACE $name -o jsonpath='{.subsets[*].addresses[*].ip}')
if [ -n "$endpoints" ]; then
echo "✅ Has endpoints"
else
echo "❌ No endpoints"
fi
done
fi
# Check PVCs
echo "Checking PVCs..."
pvcs=$(kubectl get pvc -n $NAMESPACE -o name)
if [[ -z "$pvcs" ]]; then
echo "No PVCs found in namespace $NAMESPACE"
else
pvc_count=$(echo "$pvcs" | wc -l)
echo "Found $pvc_count PVCs"
# Check if PVCs are bound
bound_count=$(kubectl get pvc -n $NAMESPACE -o jsonpath='{.items[?(@.status.phase=="Bound")].metadata.name}' | wc -w)
echo "$bound_count/$pvc_count PVCs are bound"
if [ "$bound_count" -ne "$pvc_count" ]; then
echo "❌ Not all PVCs are bound"
else
echo "✅ All PVCs are bound"
fi
fi
echo "Validation complete!"
exit 0