Cloud Costs Are Rising in 2026: The Complete FinOps Survival Guide for DevOps Teams

# AWS CLI — find instances with <10% avg CPU over 14 days
aws cloudwatch get-metric-statistics \
  --namespace AWS/EC2 \
  --metric-name CPUUtilization \
  --period 86400 \
  --statistics Average \
  --start-time $(date -d '14 days ago' -u +%Y-%m-%dT%H:%M:%S) \
  --end-time $(date -u +%Y-%m-%dT%H:%M:%S) \
  --dimensions Name=InstanceId,Value=i-1234567890abcdef0

# Enable Compute Optimizer
aws compute-optimizer update-enrollment-status --status Active
 
# Get recommendations
aws compute-optimizer get-ec2-instance-recommendations \
  --filters name=Finding,values=OVER_PROVISIONED

# Install VPA in recommendation-only mode
kubectl apply -f vpa-recommendation.yaml
 
# After 24 hours, check recommendations
kubectl get vpa -A -o jsonpath='{range .items[*]}{.metadata.name}: target={.status.recommendation.containerRecommendations[0].target}{"\n"}{end}'

# eksctl config for spot node group
apiVersion: eksctl.io/v1alpha5
kind: ClusterConfig
metadata:
  name: my-cluster
  region: us-east-1
 
managedNodeGroups:
  - name: spot-workers
    instanceTypes: ["m5.xlarge", "m5a.xlarge", "m5d.xlarge", "m6i.xlarge"]
    spot: true
    minSize: 2
    maxSize: 20
    desiredCapacity: 5
    labels:
      lifecycle: spot
    taints:
      - key: spot
        value: "true"
        effect: NoSchedule

# Get Savings Plans recommendations
aws ce get-savings-plans-purchase-recommendation \
  --savings-plans-type COMPUTE_SP \
  --term-in-years ONE_YEAR \
  --payment-option NO_UPFRONT \
  --lookback-period-in-days SIXTY_DAYS

aws ec2 create-vpc-endpoint \
  --vpc-id vpc-123abc \
  --service-name com.amazonaws.us-east-1.s3 \
  --route-table-ids rtb-123abc

# NGINX config
gzip on;
gzip_types application/json text/plain application/xml;
gzip_min_length 1000;

# CloudFront egress: $0.085/GB (first 10TB)
# Direct EC2 egress: $0.09/GB
# But cached responses = $0 origin egress

{
  "Rules": [
    {
      "ID": "OptimizeStorage",
      "Status": "Enabled",
      "Filter": {"Prefix": ""},
      "Transitions": [
        {"Days": 30, "StorageClass": "STANDARD_IA"},
        {"Days": 90, "StorageClass": "GLACIER_IR"},
        {"Days": 365, "StorageClass": "DEEP_ARCHIVE"}
      ],
      "Expiration": {"Days": 730}
    }
  ]
}

# Find unattached EBS volumes (you're paying for these!)
aws ec2 describe-volumes \
  --filters Name=status,Values=available \
  --query 'Volumes[*].{ID:VolumeId,Size:Size,Created:CreateTime}' \
  --output table
 
# Find old snapshots (>90 days)
aws ec2 describe-snapshots --owner-ids self \
  --query 'Snapshots[?StartTime<`2025-12-01`].{ID:SnapshotId,Size:VolumeSize,Date:StartTime}' \
  --output table
 
# Find unused Elastic IPs ($3.60/month each)
aws ec2 describe-addresses \
  --query 'Addresses[?AssociationId==null].{IP:PublicIp,AllocId:AllocationId}' \
  --output table

apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: web-app
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: web-app
  minReplicas: 2
  maxReplicas: 50
  behavior:
    scaleUp:
      stabilizationWindowSeconds: 60
      policies:
      - type: Percent
        value: 50
        periodSeconds: 60
    scaleDown:
      stabilizationWindowSeconds: 300  # wait 5 min before scaling down
      policies:
      - type: Percent
        value: 25
        periodSeconds: 120
  metrics:
  - type: Resource
    resource:
      name: cpu
      target:
        type: Utilization
        averageUtilization: 65

# Scale up at 8 AM EST, down at 8 PM
aws autoscaling put-scheduled-update-group-action \
  --auto-scaling-group-name my-asg \
  --scheduled-action-name scale-up-morning \
  --recurrence "0 13 * * MON-FRI" \
  --min-size 10 --max-size 50 --desired-capacity 15
 
aws autoscaling put-scheduled-update-group-action \
  --auto-scaling-group-name my-asg \
  --scheduled-action-name scale-down-evening \
  --recurrence "0 1 * * *" \
  --min-size 2 --max-size 10 --desired-capacity 2