feat: close preprod observability loop
This commit is contained in:
@@ -11,6 +11,16 @@ groups:
|
||||
summary: Socialize API telemetry is missing
|
||||
description: No API request telemetry has been received for 5 minutes. The API or telemetry pipeline may be down.
|
||||
|
||||
- alert: SocializePreprodEndpointDown
|
||||
expr: probe_success{job="preprod-uptime"} == 0
|
||||
for: 2m
|
||||
labels:
|
||||
severity: critical
|
||||
service: socialize-preprod
|
||||
annotations:
|
||||
summary: Preprod endpoint is down
|
||||
description: '{{ $labels.instance }} has failed blackbox checks for 2 minutes.'
|
||||
|
||||
- alert: SocializeApiHighErrorRate
|
||||
expr: |
|
||||
(
|
||||
@@ -56,6 +66,26 @@ groups:
|
||||
summary: Socialize core usage is quiet
|
||||
description: No content, comment, approval, or feedback activity has been observed over the last 12 hours.
|
||||
|
||||
- alert: SocializeContentStaleInApproval
|
||||
expr: socialize_workflow_stale_in_approval > 0
|
||||
for: 30m
|
||||
labels:
|
||||
severity: warning
|
||||
service: socialize-api
|
||||
annotations:
|
||||
summary: Content is stale in approval
|
||||
description: One or more content items have been in approval longer than the configured threshold.
|
||||
|
||||
- alert: SocializeNoActiveWorkspaces
|
||||
expr: socialize_workflow_active_workspaces{window="24h"} < 1
|
||||
for: 1h
|
||||
labels:
|
||||
severity: info
|
||||
service: socialize-api
|
||||
annotations:
|
||||
summary: No active workspaces in the last 24 hours
|
||||
description: No workspace has content workflow activity in the last 24 hours.
|
||||
|
||||
- alert: SocializeFeedbackBugSubmitted
|
||||
expr: sum(increase(socialize_feedback_submitted_total{feedback_type="Bug"}[15m])) > 0
|
||||
for: 0m
|
||||
|
||||
Reference in New Issue
Block a user