GistPin/infrastructure/monitoring/bandwidth-alerts.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
55
56
57
58
59
60
61
62
63
# Network Bandwidth Alerting Rules
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: bandwidth-alerts
  namespace: monitoring
  labels:
    prometheus: kube-prometheus
    role: alert-rules
spec:
  groups:
    - name: bandwidth.alerts
      rules:
        # Sustained high ingress on any single pod
        - alert: HighIngressBandwidth
          expr: |
            gistpin:network_ingress_bytes_per_second > 104857600
          for: 5m
          labels:
            severity: warning
            team: infrastructure
          annotations:
            summary: "High ingress bandwidth on {{ $labels.pod }}"
            description: "Pod {{ $labels.pod }} ingress exceeds 100 MiB/s for 5 minutes (current: {{ $value | humanizeBytes }}/s)."
            runbook_url: "https://github.com/PinSpace-Org/GistPin/blob/main/infrastructure/docs/RUNBOOKS.md#bandwidth"

        # Sustained high egress — cost concern
        - alert: HighEgressBandwidth
          expr: |
            gistpin:network_egress_bytes_per_second > 52428800
          for: 5m
          labels:
            severity: warning
            team: infrastructure
          annotations:
            summary: "High egress bandwidth on {{ $labels.pod }}"
            description: "Pod {{ $labels.pod }} egress exceeds 50 MiB/s for 5 minutes (current: {{ $value | humanizeBytes }}/s). Check for data exfil or misconfigured clients."
            runbook_url: "https://github.com/PinSpace-Org/GistPin/blob/main/infrastructure/docs/RUNBOOKS.md#bandwidth"

        # Anomalous spike — 3× normal baseline
        - alert: BandwidthAnomalyDetected
          expr: |
            gistpin:network_total_bytes_per_second
            > 3 * avg_over_time(gistpin:network_total_bytes_per_second[1h] offset 1h)
          for: 3m
          labels:
            severity: warning
            team: infrastructure
          annotations:
            summary: "Bandwidth anomaly on {{ $labels.pod }}"
            description: "Bandwidth is 3× the 1-hour baseline on pod {{ $labels.pod }}."

        # Daily egress cost exceeds budget threshold
        - alert: EgressCostExceedsBudget
          expr: |
            sum(gistpin:estimated_egress_cost_usd_daily) > 50
          for: 0m
          labels:
            severity: warning
            team: infrastructure
          annotations:
            summary: "Estimated daily egress cost exceeds $50"
            description: "Projected 24-hour egress cost is ${{ $value | printf \"%.2f\" }}. Review top consumers in the bandwidth dashboard."