-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathalerts.yml
More file actions
58 lines (54 loc) · 1.96 KB
/
Copy pathalerts.yml
File metadata and controls
58 lines (54 loc) · 1.96 KB
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
groups:
- name: proseqgo_simple_alerts
interval: 30s
rules:
- alert: ProSeqGOServiceMetricsTargetDown
expr: up{job=~"prometheus|embedding_api_metrics|embedding_worker_metrics|go_prediction_api_metrics|trainer_api_metrics|redis_exporter"} == 0
for: 2m
labels:
severity: critical
annotations:
summary: "Service scrape target down: {{ $labels.job }}"
description: "{{ $labels.instance }} is down for >2m"
- alert: ProSeqGOHighHttp5xxRatio
expr: |
(
sum by (service) (rate(http_requests_total{status_code=~"5.."}[5m]))
/
clamp_min(sum by (service) (rate(http_requests_total[5m])), 0.001)
) > 0.05
and
sum by (service) (rate(http_requests_total[5m])) > 0.1
for: 10m
labels:
severity: warning
annotations:
summary: "High 5xx ratio on {{ $labels.service }}"
description: "5xx ratio >5% for 10m with enough traffic"
- alert: ProSeqGOEmbeddingQueueBacklogHigh
expr: embedding_queue_jobs{status="queued"} > 20
for: 10m
labels:
severity: warning
annotations:
summary: "Embedding queue backlog high"
description: "Queued embedding jobs >20 for 10m"
- alert: ProSeqGOEmbeddingWorkerDownWithBacklog
expr: |
up{job="embedding_worker_metrics"} == 0
and
rq_queue_length{queue="embedding-jobs"} > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Embedding RQ worker down while queue has jobs"
description: "embedding-worker scrape is down and Redis queue embedding-jobs is non-empty"
- alert: ProSeqGORedisDown
expr: redis_up == 0
for: 2m
labels:
severity: critical
annotations:
summary: "Redis is down"
description: "redis_exporter reports redis_up == 0"