diff options
Diffstat (limited to 'kubernetes')
| -rw-r--r-- | kubernetes/namespaces/monitoring/alerts/alerts.d/mail.yaml | 22 |
1 files changed, 22 insertions, 0 deletions
diff --git a/kubernetes/namespaces/monitoring/alerts/alerts.d/mail.yaml b/kubernetes/namespaces/monitoring/alerts/alerts.d/mail.yaml new file mode 100644 index 0000000..39f6a3e --- /dev/null +++ b/kubernetes/namespaces/monitoring/alerts/alerts.d/mail.yaml @@ -0,0 +1,22 @@ +groups: + - name: postfix + rules: + - alert: postfix/down + expr: postfix_up != 1 + for: 5m + labels: + severity: warning + annotations: + summary: Postfix is down (instance {{ $labels.instance }}) + - alert: postfix/smtp-temporary-errors + expr: rate(postfix_smtpd_messages_rejected_total{code=~"^4.*"}[15m]) > 0 + for: 0m + labels: + severity: warning + annotations: + summary: Postfix is rejecting messages due to errors (instance {{ $labels.instance }}) + description: Postfix has seen code {{ $labels.code }} errors recently + and temporarily rejected emails. + https://en.wikipedia.org/wiki/List_of_SMTP_server_return_codes and + `sudo journalctl -xeu postfix@-` may provide more information on + the current issue. |