Chaos Tooling

apiVersion: litmuschaos.io/v1alpha1
kind: ChaosEngine
metadata:
  name: pod-delete-experiment
  namespace: production
spec:
  appinfo:
    appns: production
    applabel: app=user-api
    appkind: deployment
  chaosServiceAccount: litmus-admin
  experiments:
    - name: pod-delete
      spec:
        components:
          env:
            - name: TOTAL_CHAOS_DURATION
              value: "30"
            - name: CHAOS_INTERVAL
              value: "10"
            - name: FORCE
              value: "false"
        probe:
          - name: pod-health-check
            type: httpProbe
            httpProbe/inputs:
              url: http://user-api.production.svc:8080/healthz
              method:
                get:
                  criteria: ==
                  responseCode: "200"
            mode: Edge
            retryProperties:
              timeout: 60
              retry: 10
              delay: 5

---
apiVersion: litmuschaos.io/v1alpha1
kind: ChaosEngine
metadata:
  name: network-chaos-experiment
  namespace: production
spec:
  appinfo:
    appns: production
    applabel: app=user-api
    appkind: deployment
  chaosServiceAccount: litmus-admin
  experiments:
    - name: network-chaos
      spec:
        components:
          env:
            - name: TOTAL_CHAOS_DURATION
              value: "60"
            - name: NETWORK_INTERFACE
              value: "eth0"
            - name: NETWORK_LATENCY
              value: "200"
            - name: JITTER
              value: "100"

apiVersion: chaos-mesh.org/v1alpha1
kind: NetworkChaos
metadata:
  name: network-delay
  namespace: production
spec:
  action: delay
  mode: all
  selector:
    namespaces:
      - production
    labelSelectors:
      app: user-api
  delay:
    latency: "200ms"
    correlation: "100"
    jitter: "100ms"
  duration: "5m"

---
apiVersion: chaos-mesh.org/v1alpha1
kind: PodChaos
metadata:
  name: pod-kill
  namespace: production
spec:
  action: pod-kill
  mode: one
  selector:
    namespaces:
      - production
    labelSelectors:
      app: user-api
  scheduler:
    cron: "@every 5m"

---
apiVersion: chaos-mesh.org/v1alpha1
kind: IOChaos
metadata:
  name: io-delay
  namespace: production
spec:
  action: delay
  mode: all
  selector:
    namespaces:
      - production
    labelSelectors:
      app: user-api
  delay: "100ms"
  volumePath: /var/log
  duration: "5m"

---
apiVersion: chaos-mesh.org/v1alpha1
kind: StressChaos
metadata:
  name: cpu-stress
  namespace: production
spec:
  mode: one
  selector:
    namespaces:
      - production
    labelSelectors:
      app: user-api
  stressors:
    cpu:
      workers: 4
      load: 80
  duration: "5m"

fault_scenarios:
  pod_failures:
    description: "Kill or restart pods"
    tools: ["LitmusChaos", "Chaos Mesh", "kubectl delete pod"]
    risk: "Low — Kubernetes restarts pods automatically"
    validation: "Verify pod recovery and request success"

  network_faults:
    description: "Inject latency, packet loss, or DNS failures"
    tools: ["Chaos Mesh", "ToxiProxy", "iptables"]
    risk: "Medium — may cause cascading failures"
    validation: "Verify circuit breakers and retry logic"

  disk_faults:
    description: "Fill disk, corrupt files, or slow I/O"
    tools: ["LitmusChaos", "dd", "stress-ng"]
    risk: "Medium — may affect node stability"
    validation: "Verify disk cleanup and alerting"

  cpu_stress:
    description: "Consume CPU resources"
    tools: ["LitmusChaos", "stress-ng", "Chaos Mesh"]
    risk: "Low-Medium — may affect co-located pods"
    validation: "Verify autoscaling and resource limits"

  memory_stress:
    description: "Consume memory resources"
    tools: ["LitmusChaos", "stress-ng", "Chaos Mesh"]
    risk: "Medium — may trigger OOM kills"
    validation: "Verify OOM handling and recovery"

  time_skew:
    description: "Shift system clock"
    tools: ["Chaos Mesh", "faketime"]
    risk: "High — may break TLS, auth, and scheduling"
    validation: "Verify time-dependent systems handle skew"

kubernetes_failures:
  node_failure:
    description: "Simulate node going down"
    method: "Cordon and drain node, or use cloud API to stop instance"
    impact: "Pods rescheduled to other nodes"
    validation: "Verify pod scheduling and service availability"

  dns_failure:
    description: "Block DNS resolution"
    method: "Delete kube-dns pod or block DNS traffic"
    impact: "Service discovery fails"
    validation: "Verify DNS redundancy and fallback"

  etcd_failure:
    description: "Disrupt etcd cluster"
    method: "Stop etcd pod (single-node) or inject latency"
    impact: "Kubernetes control plane becomes unavailable"
    validation: "Verify etcd backup and recovery"

  storage_failure:
    description: "Simulate PVC or storage class failure"
    method: "Delete PVC or block storage access"
    impact: "Stateful services lose data access"
    validation: "Verify backup and restore procedures"

  rbac_failure:
    description: "Remove service account permissions"
    method: "Delete or modify RoleBinding"
    impact: "Service cannot access Kubernetes API"
    validation: "Verify RBAC least privilege"