GistPin/infrastructure/monitoring/cadvisor-config.yml at main · ghzhost/GistPin · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
# cAdvisor configuration for GistPin container resource monitoring
cadvisor:
  # Collection interval
  housekeeping_interval: 10s
  global_housekeeping_interval: 1m

  # Storage
  storage_duration: 2m

  # Metrics to collect
  enabled_metrics:
    - cpu
    - cpuLoad
    - disk
    - diskIO
    - memory
    - network
    - oom_event
    - process

  # Containers to monitor (empty = all)
  docker_only: true

  # HTTP endpoint
  http_auth_file: ""
  http_digest_file: ""
  port: 8080
  listen_ip: "0.0.0.0"

  # Prometheus metrics endpoint
  prometheus_endpoint: /metrics

  # Resource limits for cAdvisor itself
  resources:
    requests:
      cpu: 150m
      memory: 200Mi
    limits:
      cpu: 300m
      memory: 400Mi

  # Label filters — only track GistPin containers
  store_container_labels: true
  whitelisted_container_labels:
    - app
    - version
    - component

  # Anomaly detection thresholds
  anomaly_detection:
    cpu_spike_threshold: 90       # % — alert if CPU > 90%
    memory_spike_threshold: 85    # % — alert if memory > 85%
    network_spike_mbps: 100       # Mbps
    oom_kill_alert: true