Model Control Plane (MCP) Server

prometheus
groups:
  - name: memory_alerts
    rules:
      - alert: LowMemoryUsage
        expr: (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 > 30
        for: 1m
        labels:
          severity: info
        annotations:
          summary: "Low memory usage on {{ $labels.instance }}"
          description: "Memory usage is above 30% on {{ $labels.instance }} for more than 1 minute."
      
      - alert: MediumMemoryUsage
        expr: (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 > 40
        for: 1m
        labels:
          severity: warning
        annotations:
          summary: "Medium memory usage on {{ $labels.instance }}"
          description: "Memory usage is above 40% on {{ $labels.instance }} for more than 1 minute."
      
      - alert: HighMemoryUsage
        expr: (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 > 50
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "High memory usage on {{ $labels.instance }}"
          description: "Memory usage is above 50% on {{ $labels.instance }} for more than 1 minute."
      
      # Container memory alerts (cAdvisor metrics)
      - alert: ContainerMemoryUsage
        expr: (container_memory_usage_bytes / container_spec_memory_limit_bytes) * 100 > 50
        for: 1m
        labels:
          severity: warning
        annotations:
          summary: "High container memory usage"
          description: "Container {{ $labels.name }} memory usage is above 50% for more than 1 minute." 