diff options
Diffstat (limited to 'roles/monitoring/prometheus/server/defaults/main')
-rw-r--r-- | roles/monitoring/prometheus/server/defaults/main/main.yml | 1 | ||||
-rw-r--r-- | roles/monitoring/prometheus/server/defaults/main/rules_chrony.yml | 14 |
2 files changed, 15 insertions, 0 deletions
diff --git a/roles/monitoring/prometheus/server/defaults/main/main.yml b/roles/monitoring/prometheus/server/defaults/main/main.yml index d778bad8..1e0dcf32 100644 --- a/roles/monitoring/prometheus/server/defaults/main/main.yml +++ b/roles/monitoring/prometheus/server/defaults/main/main.yml @@ -22,6 +22,7 @@ prometheus_server_rules: prometheus: "{{ prometheus_server_rules_prometheus + ((prometheus_server_alertmanager is defined) | ternary(prometheus_server_rules_prometheus_alertmanager, [])) + prometheus_server_rules_prometheus_extra }}" node: "{{ prometheus_server_rules_node + prometheus_server_rules_node_extra }}" openwrt: "{{ prometheus_server_rules_openwrt + prometheus_server_rules_openwrt_extra }}" + chrony: "{{ prometheus_server_rules_chrony + prometheus_server_rules_chrony_extra }}" nut: "{{ prometheus_server_rules_nut + prometheus_server_rules_nut_extra }}" nut/ups: "{{ prometheus_server_rules_nut__ups + prometheus_server_rules_nut__ups_extra }}" blackbox: "{{ prometheus_server_rules_blackbox + prometheus_server_rules_blackbox_extra }}" diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_chrony.yml b/roles/monitoring/prometheus/server/defaults/main/rules_chrony.yml new file mode 100644 index 00000000..e845a60b --- /dev/null +++ b/roles/monitoring/prometheus/server/defaults/main/rules_chrony.yml @@ -0,0 +1,14 @@ +--- +prometheus_server_rules_chrony_extra: [] +prometheus_server_rules_chrony: + - record: instance:chrony_clock_error_seconds:abs + expr: abs(chrony_tracking_last_offset_seconds) + chrony_tracking_root_dispersion_seconds + (0.5 * chrony_tracking_root_delay_seconds) + + - alert: ChronyUnreachable + expr: chrony_up == 0 + for: 0m + labels: + severity: critical + annotations: + summary: Unable to scrape chrony metrics (instance {{ '{{' }} $labels.instance {{ '}}' }}) + description: "The chrony process might have crashed.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" |