M22: implement operational observability
This commit is contained in:
@@ -0,0 +1,39 @@
|
||||
groups:
|
||||
- name: mobilityops
|
||||
rules:
|
||||
- alert: MobilityOpsApiDown
|
||||
expr: up{job="mobilityops-api"} == 0
|
||||
for: 2m
|
||||
labels: {severity: critical}
|
||||
annotations:
|
||||
summary: MobilityOps API metrics target is down
|
||||
- alert: MobilityOpsDatabaseNotReady
|
||||
expr: mobilityops_database_ready == 0
|
||||
for: 2m
|
||||
labels: {severity: critical}
|
||||
annotations:
|
||||
summary: MobilityOps database readiness is failing
|
||||
- alert: MobilityOpsHighErrorRate
|
||||
expr: sum(rate(mobilityops_http_requests_total{status=~"5.."}[5m])) / clamp_min(sum(rate(mobilityops_http_requests_total[5m])), 0.001) > 0.05
|
||||
for: 10m
|
||||
labels: {severity: warning}
|
||||
annotations:
|
||||
summary: More than 5% of MobilityOps requests return 5xx
|
||||
- alert: MobilityOpsHighLatency
|
||||
expr: histogram_quantile(0.95, sum by (le) (rate(mobilityops_http_request_duration_seconds_bucket[5m]))) > 2
|
||||
for: 10m
|
||||
labels: {severity: warning}
|
||||
annotations:
|
||||
summary: MobilityOps p95 API latency exceeds two seconds
|
||||
- alert: MobilityOpsOutboxBacklog
|
||||
expr: sum(mobilityops_outbox_events{status=~"pending|delivering",scenario="operational"}) > 10
|
||||
for: 10m
|
||||
labels: {severity: warning}
|
||||
annotations:
|
||||
summary: MobilityOps operational outbox backlog exceeds ten events
|
||||
- alert: MobilityOpsOutboxFailure
|
||||
expr: sum(mobilityops_outbox_events{status="failed",scenario="operational"}) > 0
|
||||
for: 2m
|
||||
labels: {severity: critical}
|
||||
annotations:
|
||||
summary: MobilityOps has a real failed outbox event
|
||||
Reference in New Issue
Block a user