mirror of
https://github.com/makayabou/asg-server.git
synced 2026-05-02 17:43:36 +02:00
49 lines
2.3 KiB
YAML
49 lines
2.3 KiB
YAML
groups:
|
|
- name: sse-alerts
|
|
rules:
|
|
- alert: HighSSEErrorRate
|
|
expr: |
|
|
(sum(rate(sms_sse_connection_errors_total[5m])) / sum(rate(sms_sse_events_sent_total[5m]))) > 0.05
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "High SSE error rate ({{ $value | humanize }}%)"
|
|
description: "SSE error rate has exceeded 5% for 5 minutes. This may indicate client connectivity issues or server-side processing problems."
|
|
dashboard: "https://grafana.example.com/d/sse-dashboard"
|
|
runbook: "https://internal.dev-docs/server/sse-troubleshooting#high-error-rate"
|
|
|
|
- alert: SSEConnectionLoss
|
|
expr: sms_sse_active_connections == 0
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "All SSE connections lost"
|
|
description: "No active SSE connections detected for 5 minutes. This indicates complete service disruption for real-time updates."
|
|
dashboard: "https://grafana.example.com/d/sse-dashboard"
|
|
runbook: "https://internal.dev-docs/server/sse-troubleshooting#connection-loss"
|
|
|
|
- alert: HighSSELatency
|
|
expr: |
|
|
histogram_quantile(0.95, rate(sms_sse_event_delivery_latency_seconds_bucket[5m])) > 10
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "High SSE event latency (95th percentile > 10s)"
|
|
description: "95th percentile of event delivery latency has exceeded 10 seconds for 5 minutes. Clients may experience significant delays in receiving real-time updates."
|
|
dashboard: "https://grafana.example.com/d/sse-dashboard"
|
|
runbook: "https://internal.dev-docs/server/sse-troubleshooting#high-latency"
|
|
|
|
- alert: HighConnectionChurn
|
|
expr: rate(sms_sse_connections_opened_total[5m]) > 10
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "High SSE connection churn ({{ $value | humanize }} connections/sec)"
|
|
description: "SSE connection churn rate has exceeded 10 connections per second for 5 minutes. This may indicate unstable client connections or aggressive reconnection logic."
|
|
dashboard: "https://grafana.example.com/d/sse-dashboard"
|
|
runbook: "https://internal.dev-docs/server/sse-troubleshooting#connection-churn"
|
