chaos-engineering

Chaos Engineering

Systematic resilience testing to discover weaknesses before they cause outages.

Steady State Hypothesis

# Define BEFORE injecting chaos - what "normal" looks like
steady_state_hypothesis:
  title: "API serves traffic within SLO"
  probes:
    - name: "API response time p95 < 500ms"
      type: http
      url: "https://api.example.com/health"
      threshold: 500

    - name: "Error rate < 1%"
      type: prometheus
      query: "rate(http_requests_total{status=~'5..'}[5m]) / rate(http_requests_total[5m])"
      threshold: 0.01

    - name: "Order processing queue depth < 100"
      type: cloudwatch
      metric: "ApproximateNumberOfMessagesVisible"
      threshold: 100

    - name: "Database connections < 80% capacity"
      type: prometheus
      query: "pg_stat_activity_count / pg_settings_max_connections"
      threshold: 0.8

Failure Injection Patterns

# Using Chaos Toolkit (chaostoolkit.org)
# experiment.json

{
  "title": "Database failover resilience",
  "description": "Verify app handles primary DB failover gracefully",

  "steady-state-hypothesis": {
    "title": "API responds normally",
    "probes": [
      {
        "name": "api-health",
        "type": "probe",
        "provider": {
          "type": "http",
          "url": "https://api.example.com/health",
          "timeout": 5
        },
        "tolerance": {"status": 200}
      }
    ]
  },

  "method": [
    {
      "name": "failover-primary-db",
      "type": "action",
      "provider": {
        "type": "python",
        "module": "chaosaws.rds.actions",
        "func": "failover_db_cluster",
        "arguments": {
          "db_cluster_identifier": "prod-cluster"
        }
      },
      "pauses": {"after": 60}
    }
  ],

  "rollbacks": [
    {
      "name": "verify-db-recovered",
      "type": "probe",
      "provider": {
        "type": "python",
        "module": "chaosaws.rds.probes",
        "func": "cluster_status",
        "arguments": {
          "db_cluster_identifier": "prod-cluster"
        }
      },
      "tolerance": "available"
    }
  ]
}