feat(deploy): add WebRTC Prometheus alert rules
This commit is contained in:
parent
4b8d9f0e8c
commit
e8f39daa75
1 changed files with 45 additions and 0 deletions
45
deploy/truenas/core/prom/rules/webrtc-alerts.yml
Normal file
45
deploy/truenas/core/prom/rules/webrtc-alerts.yml
Normal file
|
|
@ -0,0 +1,45 @@
|
|||
groups:
|
||||
- name: dragonfork-webrtc
|
||||
rules:
|
||||
- alert: WebRTCWHEPErrorRateHigh
|
||||
expr: |
|
||||
sum by (stream_id) (
|
||||
rate(dragonfork_webrtc_whep_requests_total{code=~"4..|5.."}[5m])
|
||||
) > 0.5
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "WHEP error rate high on stream {{ $labels.stream_id }}"
|
||||
description: "Sustained 4xx/5xx rate >0.5/sec for 5m."
|
||||
|
||||
- alert: WebRTCICEEstablishmentSlow
|
||||
expr: |
|
||||
histogram_quantile(0.95,
|
||||
sum by (le, stream_id) (
|
||||
rate(dragonfork_webrtc_ice_establishment_duration_seconds_bucket[10m])
|
||||
)
|
||||
) > 3
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "ICE establishment p95 >3s on {{ $labels.stream_id }}"
|
||||
|
||||
- alert: WebRTCICEFailureRateHigh
|
||||
expr: |
|
||||
sum by (stream_id) (rate(dragonfork_webrtc_ice_failures_total[5m])) > 0.2
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "ICE failures sustained on {{ $labels.stream_id }}"
|
||||
|
||||
- alert: WebRTCFFmpegLegFailure
|
||||
expr: |
|
||||
increase(dragonfork_webrtc_ffmpeg_leg_failures_total[5m]) > 0
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "FFmpeg RTP leg failed on {{ $labels.stream_id }} ({{ $labels.leg }})"
|
||||
description: "Process stopped while peers were active. Check FFmpeg logs."
|
||||
Loading…
Reference in a new issue