foxhunt/monitoring/grafana/api_gateway_dashboard.json

{
  "dashboard": {
    "title": "API Gateway - Authentication & Performance",
    "tags": ["api-gateway", "authentication", "hft"],
    "timezone": "browser",
    "schemaVersion": 16,
    "version": 1,
    "refresh": "5s",
    "panels": [
      {
        "id": 1,
        "title": "Authentication Overview",
        "type": "row",
        "gridPos": { "x": 0, "y": 0, "w": 24, "h": 1 }
      },
      {
        "id": 2,
        "title": "Auth Requests (Total vs Success vs Failure)",
        "type": "graph",
        "gridPos": { "x": 0, "y": 1, "w": 12, "h": 8 },
        "targets": [
          {
            "expr": "rate(api_gateway_auth_requests_total[1m])",
            "legendFormat": "Total Requests/s",
            "refId": "A"
          },
          {
            "expr": "rate(api_gateway_auth_requests_success[1m])",
            "legendFormat": "Success/s",
            "refId": "B"
          },
          {
            "expr": "rate(api_gateway_auth_requests_failure[1m])",
            "legendFormat": "Failures/s",
            "refId": "C"
          }
        ],
        "yaxes": [
          { "format": "reqps", "label": "Requests/s" },
          { "format": "short" }
        ]
      },
      {
        "id": 3,
        "title": "Auth Success Rate (%)",
        "type": "singlestat",
        "gridPos": { "x": 12, "y": 1, "w": 6, "h": 4 },
        "targets": [
          {
            "expr": "100 * rate(api_gateway_auth_requests_success[5m]) / rate(api_gateway_auth_requests_total[5m])",
            "refId": "A"
          }
        ],
        "format": "percent",
        "thresholds": "90,95",
        "colors": ["#d44a3a", "#e0b400", "#299c46"]
      },
      {
        "id": 4,
        "title": "Auth SLA Compliance (<10μs)",
        "type": "singlestat",
        "gridPos": { "x": 18, "y": 1, "w": 6, "h": 4 },
        "targets": [
          {
            "expr": "100 * rate(api_gateway_auth_sla_met[5m]) / (rate(api_gateway_auth_sla_met[5m]) + rate(api_gateway_auth_sla_exceeded[5m]))",
            "refId": "A"
          }
        ],
        "format": "percent",
        "thresholds": "95,99",
        "colors": ["#d44a3a", "#e0b400", "#299c46"]
      },
      {
        "id": 5,
        "title": "Authentication Layer Latencies (μs)",
        "type": "graph",
        "gridPos": { "x": 0, "y": 9, "w": 24, "h": 8 },
        "targets": [
          {
            "expr": "histogram_quantile(0.99, rate(api_gateway_jwt_extraction_duration_microseconds_bucket[1m]))",
            "legendFormat": "JWT Extraction p99",
            "refId": "A"
          },
          {
            "expr": "histogram_quantile(0.99, rate(api_gateway_jwt_validation_duration_microseconds_bucket[1m]))",
            "legendFormat": "JWT Validation p99",
            "refId": "B"
          },
          {
            "expr": "histogram_quantile(0.99, rate(api_gateway_revocation_check_duration_microseconds_bucket[1m]))",
            "legendFormat": "Revocation Check p99",
            "refId": "C"
          },
          {
            "expr": "histogram_quantile(0.99, rate(api_gateway_rbac_check_duration_microseconds_bucket[1m]))",
            "legendFormat": "RBAC Check p99",
            "refId": "D"
          },
          {
            "expr": "histogram_quantile(0.99, rate(api_gateway_rate_limit_check_duration_microseconds_bucket[1m]))",
            "legendFormat": "Rate Limit Check p99",
            "refId": "E"
          },
          {
            "expr": "histogram_quantile(0.99, rate(api_gateway_auth_total_duration_microseconds_bucket[1m]))",
            "legendFormat": "Total Auth p99",
            "refId": "F"
          }
        ],
        "yaxes": [
          { "format": "µs", "label": "Latency (μs)" },
          { "format": "short" }
        ],
        "alert": {
          "name": "Auth Latency SLA Violation",
          "conditions": [
            {
              "evaluator": { "params": [10], "type": "gt" },
              "query": { "params": ["F", "5m", "now"] },
              "type": "query"
            }
          ],
          "message": "Authentication latency exceeded 10μs SLA"
        }
      },
      {
        "id": 6,
        "title": "Authentication Errors by Type",
        "type": "graph",
        "gridPos": { "x": 0, "y": 17, "w": 12, "h": 8 },
        "targets": [
          {
            "expr": "rate(api_gateway_auth_errors_missing_jwt[1m])",
            "legendFormat": "Missing JWT",
            "refId": "A"
          },
          {
            "expr": "rate(api_gateway_auth_errors_invalid_jwt[1m])",
            "legendFormat": "Invalid JWT",
            "refId": "B"
          },
          {
            "expr": "rate(api_gateway_auth_errors_expired_jwt[1m])",
            "legendFormat": "Expired JWT",
            "refId": "C"
          },
          {
            "expr": "rate(api_gateway_auth_errors_revoked_jwt[1m])",
            "legendFormat": "Revoked JWT",
            "refId": "D"
          },
          {
            "expr": "rate(api_gateway_auth_errors_permission_denied[1m])",
            "legendFormat": "Permission Denied",
            "refId": "E"
          },
          {
            "expr": "rate(api_gateway_auth_errors_rate_limited[1m])",
            "legendFormat": "Rate Limited",
            "refId": "F"
          }
        ],
        "yaxes": [
          { "format": "reqps", "label": "Errors/s" },
          { "format": "short" }
        ]
      },
      {
        "id": 7,
        "title": "Cache Performance",
        "type": "graph",
        "gridPos": { "x": 12, "y": 17, "w": 12, "h": 8 },
        "targets": [
          {
            "expr": "100 * rate(api_gateway_jwt_cache_hits[1m]) / (rate(api_gateway_jwt_cache_hits[1m]) + rate(api_gateway_jwt_cache_misses[1m]))",
            "legendFormat": "JWT Cache Hit Rate %",
            "refId": "A"
          },
          {
            "expr": "100 * rate(api_gateway_rbac_cache_hits[1m]) / (rate(api_gateway_rbac_cache_hits[1m]) + rate(api_gateway_rbac_cache_misses[1m]))",
            "legendFormat": "RBAC Cache Hit Rate %",
            "refId": "B"
          }
        ],
        "yaxes": [
          { "format": "percent", "label": "Hit Rate %", "min": 0, "max": 100 },
          { "format": "short" }
        ]
      },
      {
        "id": 8,
        "title": "Backend Services",
        "type": "row",
        "gridPos": { "x": 0, "y": 25, "w": 24, "h": 1 }
      },
      {
        "id": 9,
        "title": "Backend Request Latency by Service (p99)",
        "type": "graph",
        "gridPos": { "x": 0, "y": 26, "w": 12, "h": 8 },
        "targets": [
          {
            "expr": "histogram_quantile(0.99, rate(api_gateway_backend_request_duration_milliseconds_bucket{service=\"trading\"}[1m]))",
            "legendFormat": "Trading Service p99",
            "refId": "A"
          },
          {
            "expr": "histogram_quantile(0.99, rate(api_gateway_backend_request_duration_milliseconds_bucket{service=\"backtesting\"}[1m]))",
            "legendFormat": "Backtesting Service p99",
            "refId": "B"
          },
          {
            "expr": "histogram_quantile(0.99, rate(api_gateway_backend_request_duration_milliseconds_bucket{service=\"ml_training\"}[1m]))",
            "legendFormat": "ML Training Service p99",
            "refId": "C"
          }
        ],
        "yaxes": [
          { "format": "ms", "label": "Latency (ms)" },
          { "format": "short" }
        ]
      },
      {
        "id": 10,
        "title": "Circuit Breaker States",
        "type": "graph",
        "gridPos": { "x": 12, "y": 26, "w": 12, "h": 8 },
        "targets": [
          {
            "expr": "api_gateway_circuit_breaker_state{service=\"trading\"}",
            "legendFormat": "Trading (0=closed, 2=open)",
            "refId": "A"
          },
          {
            "expr": "api_gateway_circuit_breaker_state{service=\"backtesting\"}",
            "legendFormat": "Backtesting",
            "refId": "B"
          },
          {
            "expr": "api_gateway_circuit_breaker_state{service=\"ml_training\"}",
            "legendFormat": "ML Training",
            "refId": "C"
          }
        ],
        "yaxes": [
          { "format": "short", "label": "State", "min": 0, "max": 2 },
          { "format": "short" }
        ],
        "alert": {
          "name": "Circuit Breaker Open",
          "conditions": [
            {
              "evaluator": { "params": [1.5], "type": "gt" },
              "query": { "params": ["A", "1m", "now"] },
              "type": "query"
            }
          ],
          "message": "Circuit breaker opened for backend service"
        }
      },
      {
        "id": 11,
        "title": "Backend Health Status",
        "type": "table",
        "gridPos": { "x": 0, "y": 34, "w": 12, "h": 6 },
        "targets": [
          {
            "expr": "api_gateway_health_status",
            "format": "table",
            "instant": true,
            "refId": "A"
          }
        ],
        "styles": [
          {
            "pattern": "Value",
            "type": "string",
            "mappingType": 1,
            "valueMaps": [
              { "value": "0", "text": "Unhealthy" },
              { "value": "1", "text": "Healthy" }
            ]
          }
        ]
      },
      {
        "id": 12,
        "title": "Connection Pool Utilization",
        "type": "graph",
        "gridPos": { "x": 12, "y": 34, "w": 12, "h": 6 },
        "targets": [
          {
            "expr": "100 * api_gateway_connection_pool_active / api_gateway_connection_pool_max",
            "legendFormat": "{{service}} Pool Utilization %",
            "refId": "A"
          }
        ],
        "yaxes": [
          { "format": "percent", "label": "Pool Utilization %", "min": 0, "max": 100 },
          { "format": "short" }
        ]
      },
      {
        "id": 13,
        "title": "Configuration & Hot-Reload",
        "type": "row",
        "gridPos": { "x": 0, "y": 40, "w": 24, "h": 1 }
      },
      {
        "id": 14,
        "title": "Configuration Reload Events",
        "type": "graph",
        "gridPos": { "x": 0, "y": 41, "w": 12, "h": 6 },
        "targets": [
          {
            "expr": "rate(api_gateway_config_updates_auth[5m])",
            "legendFormat": "Auth Config Updates",
            "refId": "A"
          },
          {
            "expr": "rate(api_gateway_config_updates_routing[5m])",
            "legendFormat": "Routing Config Updates",
            "refId": "B"
          },
          {
            "expr": "rate(api_gateway_config_updates_rate_limit[5m])",
            "legendFormat": "Rate Limit Config Updates",
            "refId": "C"
          },
          {
            "expr": "rate(api_gateway_config_updates_backend[5m])",
            "legendFormat": "Backend Config Updates",
            "refId": "D"
          }
        ],
        "yaxes": [
          { "format": "ops", "label": "Updates/s" },
          { "format": "short" }
        ]
      },
      {
        "id": 15,
        "title": "Hot-Reload Latency (p95)",
        "type": "graph",
        "gridPos": { "x": 12, "y": 41, "w": 12, "h": 6 },
        "targets": [
          {
            "expr": "histogram_quantile(0.95, rate(api_gateway_config_reload_duration_milliseconds_bucket[1m]))",
            "legendFormat": "Config Reload p95",
            "refId": "A"
          },
          {
            "expr": "histogram_quantile(0.95, rate(api_gateway_config_fetch_duration_milliseconds_bucket[1m]))",
            "legendFormat": "Config Fetch p95",
            "refId": "B"
          }
        ],
        "yaxes": [
          { "format": "ms", "label": "Latency (ms)" },
          { "format": "short" }
        ]
      },
      {
        "id": 16,
        "title": "NOTIFY Listener Status",
        "type": "singlestat",
        "gridPos": { "x": 0, "y": 47, "w": 6, "h": 4 },
        "targets": [
          {
            "expr": "api_gateway_notify_listener_connected",
            "refId": "A"
          }
        ],
        "valueName": "current",
        "valueMaps": [
          { "value": "0", "text": "Disconnected" },
          { "value": "1", "text": "Connected" }
        ],
        "thresholds": "0.5,1",
        "colors": ["#d44a3a", "#e0b400", "#299c46"]
      },
      {
        "id": 17,
        "title": "Rate Limiting",
        "type": "row",
        "gridPos": { "x": 0, "y": 51, "w": 24, "h": 1 }
      },
      {
        "id": 18,
        "title": "Rate Limit Hits by User (Top 10)",
        "type": "graph",
        "gridPos": { "x": 0, "y": 52, "w": 12, "h": 8 },
        "targets": [
          {
            "expr": "topk(10, rate(api_gateway_rate_limits_by_user[1m]))",
            "legendFormat": "{{user_id}}",
            "refId": "A"
          }
        ],
        "yaxes": [
          { "format": "reqps", "label": "Rate Limit Hits/s" },
          { "format": "short" }
        ]
      },
      {
        "id": 19,
        "title": "Active Rate Limiter Entries",
        "type": "singlestat",
        "gridPos": { "x": 12, "y": 52, "w": 6, "h": 4 },
        "targets": [
          {
            "expr": "api_gateway_rate_limiter_entries",
            "refId": "A"
          }
        ],
        "format": "short",
        "valueName": "current"
      }
    ]
  }
}