Files
felhom.eu/documentation/audits/dooplex-survival-2026-10-09/partB/bf_test.yml
T

56 lines
2.0 KiB
YAML

rule_files:
- bf.yml
evaluation_interval: 1m
tests:
- interval: 5m
input_series:
- series: felhom_dooplex_offsite_last_success_timestamp_seconds{instance="dooplex"}
values: 0+0x400
- series: felhom_dooplex_offsite_restore_test_last_success_timestamp_seconds{instance="dooplex"}
values: 0+0x400
alert_rule_test:
- eval_time: 26h
alertname: DooplexGiteaOffsiteStale
exp_alerts: []
- eval_time: 26h40m
alertname: DooplexGiteaOffsiteStale
exp_alerts:
- exp_labels:
severity: critical
component: backup
instance: dooplex
exp_annotations: &id001
summary: Gitea and DooPlex's secrets have not reached ep0 for 26 h (R-232)
description: No successful off-site push of Gitea (repositories, database dump, config) and the secrets export for >26h (daily at 00:20). Check `journalctl -u felhom-dooplex-offsite.service` and the tunnel `systemctl status felhom-ep0-pbs-tunnel`.
- interval: 1h
input_series:
- series: felhom_dooplex_offsite_last_success_timestamp_seconds{instance="dooplex"}
values: 0x23 86400x23 172800x3
- series: felhom_dooplex_offsite_restore_test_last_success_timestamp_seconds{instance="dooplex"}
values: 0+0x50
alert_rule_test:
- eval_time: 50h
alertname: DooplexGiteaOffsiteStale
exp_alerts: []
- interval: 5m
input_series:
- series: up{job="node"}
values: 1+0x30
alert_rule_test:
- eval_time: 40m
alertname: DooplexGiteaOffsiteStale
exp_alerts:
- exp_labels:
severity: critical
component: backup
exp_annotations: *id001
- eval_time: 2h
alertname: DooplexGiteaRestoreTestStale
exp_alerts:
- exp_labels:
severity: warning
component: backup
exp_annotations:
summary: The Gitea copy on ep0 has not passed a restore test for 8 days (R-232)
description: The weekly restore test (Sun 05:30) has not succeeded for >8 days. Check `journalctl -u felhom-dooplex-offsite-restore-test.service`.