oci-deal-accelerator/kb/well-architected/reliability-resilience.yaml

# OCI Well-Architected Framework — Pillar 2: Reliability and Resilience
# Source: https://docs.oracle.com/en/solutions/oci-best-practices/reliable-and-resilient-cloud-topology-practices1.html

pillar:
  name: "Reliability and Resilience"
  id: reliability_resilience
  wa_reference: "https://docs.oracle.com/en/solutions/oci-best-practices/reliable-and-resilient-cloud-topology-practices1.html"
  reference: "https://docs.oracle.com/en/solutions/oci-best-practices/reliable-and-resilient-cloud-topology-practices1.html"

categories:
  - name: "Scalability"
    id: scalability
    checks:
      - id: REL-SCL-001
        name: "Auto-scaling configured"
        description: "Auto-scaling configured for variable workloads"
        auto_detect:
          pass_if: "auto-scaling policies defined for compute or OKE"
          gap_if: "variable workloads without auto-scaling"
        severity: MEDIUM
        applies_when: "has_variable_workloads"

      - id: REL-SCL-002
        name: "Service limits reviewed"
        description: "Service limits reviewed and increased where needed"
        auto_detect:
          pass_if: "service limit review mentioned in deployment plan"
          gap_if: "no service limit review planned"
        severity: LOW
        applies_when: always

      - id: REL-SCL-003
        name: "Capacity reservations"
        description: "Capacity reservations for critical workloads"
        auto_detect:
          pass_if: "capacity reservations specified for critical compute"
          gap_if: "critical production workloads without capacity reservations"
        severity: MEDIUM
        applies_when: "has_critical_workloads"

  - name: "Fault-Tolerant Networking"
    id: fault_tolerant_networking
    checks:
      - id: REL-NET-001
        name: "Redundant FastConnect"
        description: "Redundant FastConnect circuits (2 virtual circuits, different physical paths)"
        auto_detect:
          pass_if: "dual FastConnect circuits on diverse paths"
          gap_if: "single FastConnect circuit without redundancy"
        severity: HIGH
        applies_when: "has_fastconnect"

      - id: REL-NET-002
        name: "VPN backup for FastConnect"
        description: "VPN as backup if FastConnect is primary"
        auto_detect:
          pass_if: "IPSec VPN configured as FastConnect backup"
          gap_if: "FastConnect without VPN backup"
        severity: MEDIUM
        applies_when: "has_fastconnect"

      - id: REL-NET-003
        name: "Redundant DRG tunnels"
        description: "DRG with redundant tunnels"
        auto_detect:
          pass_if: "DRG configured with redundant IPSec tunnels"
          gap_if: "DRG with single tunnel"
        severity: MEDIUM
        applies_when: "has_drg"

      - id: REL-NET-004
        name: "Load Balancer health checks"
        description: "Load Balancer health checks configured"
        auto_detect:
          pass_if: "health check policies defined on load balancers"
          gap_if: "load balancers without health checks"
        severity: HIGH
        applies_when: "has_load_balancers"

      - id: REL-NET-005
        name: "Multi-AD/FD compute placement"
        description: "Multiple ADs or FDs used for compute placement"
        auto_detect:
          pass_if: "compute instances distributed across ADs or FDs"
          gap_if: "all compute in single AD/FD"
        severity: HIGH
        applies_when: "has_production_compute"

  - name: "Data Backup"
    id: data_backup
    checks:
      - id: REL-BAK-001
        name: "Automated database backups"
        description: "Automated backups enabled for all databases"
        auto_detect:
          pass_if: "automated backup configured for all database services"
          gap_if: "any database without automated backup"
        severity: HIGH
        applies_when: "has_databases"

      - id: REL-BAK-002
        name: "Backup retention policy"
        description: "Backup retention policy defined and documented"
        auto_detect:
          pass_if: "backup retention periods specified"
          gap_if: "no backup retention policy defined"
        severity: MEDIUM
        applies_when: "has_databases"

      - id: REL-BAK-003
        name: "Block Volume backups"
        description: "Block Volume backups scheduled"
        auto_detect:
          pass_if: "block volume backup policies configured"
          gap_if: "block volumes without backup schedules"
        severity: MEDIUM
        applies_when: "has_block_volumes"

      - id: REL-BAK-004
        name: "Cross-region backup copy"
        description: "Cross-region backup copy for critical data"
        auto_detect:
          pass_if: "cross-region backup replication configured"
          gap_if: "critical data without cross-region backup"
        severity: MEDIUM
        applies_when: "has_critical_data"

      - id: REL-BAK-005
        name: "Boot volume backups"
        description: "Boot volume backups for compute instances"
        auto_detect:
          pass_if: "boot volume backup policies configured"
          gap_if: "compute instances without boot volume backups"
        severity: LOW
        applies_when: "has_compute_instances"

  - name: "Data Replication"
    id: data_replication
    checks:
      - id: REL-REP-001
        name: "Data Guard / ADG"
        description: "Data Guard (or ADG for ADB) configured for HA databases"
        auto_detect:
          pass_if: "Data Guard or Autonomous Data Guard configured"
          gap_if: "production databases without HA replication"
        severity: HIGH
        applies_when: "has_production_databases"

      - id: REL-REP-002
        name: "RPO/RTO documented"
        description: "RPO/RTO documented and validated with actual testing"
        auto_detect:
          pass_if: "RPO and RTO targets defined with validation plan"
          gap_if: "no RPO/RTO targets documented"
        severity: HIGH
        applies_when: "has_production_workloads"

      - id: REL-REP-003
        name: "Cross-region Object Storage replication"
        description: "Cross-region replication for Object Storage"
        auto_detect:
          pass_if: "Object Storage replication configured to DR region"
          gap_if: "critical object storage without cross-region replication"
        severity: MEDIUM
        applies_when: "has_critical_object_storage"

  - name: "Disaster Recovery"
    id: disaster_recovery
    checks:
      - id: REL-DR-001
        name: "DR region identified"
        description: "DR region identified and provisioned"
        auto_detect:
          pass_if: "DR region specified in architecture"
          gap_if: "no DR region identified"
        severity: HIGH
        applies_when: "requires_dr"

      - id: REL-DR-002
        name: "DR architecture documented"
        description: "DR architecture documented with switchover/failover procedures"
        auto_detect:
          pass_if: "DR runbook with switchover/failover procedures defined"
          gap_if: "no DR procedures documented"
        severity: HIGH
        applies_when: "requires_dr"

      - id: REL-DR-003
        name: "DR drill schedule"
        description: "DR drill schedule defined (quarterly minimum)"
        auto_detect:
          pass_if: "DR drill schedule defined"
          gap_if: "no DR drill schedule"
        severity: MEDIUM
        applies_when: "requires_dr"

      - id: REL-DR-004
        name: "DNS failover"
        description: "DNS failover or traffic management configured"
        auto_detect:
          pass_if: "OCI Traffic Management or DNS failover configured"
          gap_if: "no automated DNS failover for DR"
        severity: MEDIUM
        applies_when: "requires_dr"

      - id: REL-DR-005
        name: "Application tier DR"
        description: "Application tier DR strategy (pre-provisioned, Terraform-on-demand, or pilot light)"
        auto_detect:
          pass_if: "application DR strategy defined and documented"
          gap_if: "no application tier DR strategy"
        severity: HIGH
        applies_when: "requires_dr"