|
|
|
@ -299,3 +299,36 @@ groups:
|
|
|
|
identifier: '{{ '{{' }} $labels.instance {{ '}}' }}'
|
|
|
|
identifier: '{{ '{{' }} $labels.instance {{ '}}' }}'
|
|
|
|
summary: "ssh root login on Instance <{{ '{{' }} $labels.instance {{ '}}' }}> detected. plz check"
|
|
|
|
summary: "ssh root login on Instance <{{ '{{' }} $labels.instance {{ '}}' }}> detected. plz check"
|
|
|
|
description: "unexpected ssh root login detected."
|
|
|
|
description: "unexpected ssh root login detected."
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
- alert: offsite backup pending
|
|
|
|
|
|
|
|
expr: |
|
|
|
|
|
|
|
|
(time() - offsite_backup_archive_started_seconds) > 25 * 3600 or
|
|
|
|
|
|
|
|
(time() - offsite_backup_archive_ended_seconds) > 25 * 3600 or
|
|
|
|
|
|
|
|
(time() - offsite_backup_transfer_started_seconds) > 25 * 3600 or
|
|
|
|
|
|
|
|
(time() - offsite_backup_transfer_ended_seconds) > 25 * 3600 or
|
|
|
|
|
|
|
|
(time() - offsite_backup_forget_started_seconds) > 25 * 3600 or
|
|
|
|
|
|
|
|
(time() - offsite_backup_forget_ended_seconds) > 25 * 3600
|
|
|
|
|
|
|
|
for: 1m
|
|
|
|
|
|
|
|
labels:
|
|
|
|
|
|
|
|
severity: critical
|
|
|
|
|
|
|
|
annotations:
|
|
|
|
|
|
|
|
identifier: '{{ '{{' }} $labels.instance {{ '}}' }}'
|
|
|
|
|
|
|
|
summary: "one or more offsite backup metric timestamps for Instance <{{ '{{' }} $labels.instance {{ '}}' }}> older then 25h"
|
|
|
|
|
|
|
|
description: "offsite backups older then 25h."
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
- alert: offsite backup metrics unavailable
|
|
|
|
|
|
|
|
expr: |
|
|
|
|
|
|
|
|
absent(offsite_backup_archive_started_seconds) or
|
|
|
|
|
|
|
|
absent(offsite_backup_archive_ended_seconds) or
|
|
|
|
|
|
|
|
absent(offsite_backup_transfer_started_seconds) or
|
|
|
|
|
|
|
|
absent(offsite_backup_transfer_ended_seconds) or
|
|
|
|
|
|
|
|
absent(offsite_backup_forget_started_seconds) or
|
|
|
|
|
|
|
|
absent(offsite_backup_forget_ended_seconds)
|
|
|
|
|
|
|
|
for: 5m
|
|
|
|
|
|
|
|
labels:
|
|
|
|
|
|
|
|
severity: critical
|
|
|
|
|
|
|
|
annotations:
|
|
|
|
|
|
|
|
identifier: '{{ '{{' }} $labels.instance {{ '}}' }}'
|
|
|
|
|
|
|
|
summary: "one or more offsite backup metric unavailable for Instance <{{ '{{' }} $labels.instance {{ '}}' }}>"
|
|
|
|
|
|
|
|
description: "offsite metrics unavailable."
|
|
|
|
|
|
|
|
|
|
|
|
|