diff --git a/group_vars/metricspi/alerts.yml b/group_vars/metricspi/alerts.yml index a1fc6bf..fdac376 100644 --- a/group_vars/metricspi/alerts.yml +++ b/group_vars/metricspi/alerts.yml @@ -47,8 +47,27 @@ vmalert_rules: - alert: mdraid failed disk expr: collectd_md_md_disks{type="failed"} != 0 - - name: BURP RAID + - name: BURP rules: + - alert: no recent backups + expr: absent(burp_client_last_backup_timestamp) + for: 8h + annotations: + summary: No clients have been backed up recently + description: >- + This alert indicates that NO clients have been backed up within the + last day. There is likely a problem with the BURP server. + - alert: missed client backup + expr: + time() - (burp_client_last_backup_timestamp > now() - 86400 * 90) > 86400 * 2 + for: 3h + annotations: + summary: A client has not backed up today + description: >- + A client has not been backed up for more than a day. This may be + because the client is offline, or because the backup process has + failed. Clients that have not been backed up for more than 90 days + will not trigger this alert. - alert: disks need swapped expr: time() - tlast_change_over_time(