summaryrefslogtreecommitdiff
path: root/roles/monitoring/prometheus/server
diff options
context:
space:
mode:
authorChristian Pointner <equinox@spreadspace.org>2023-09-21 18:37:34 +0200
committerChristian Pointner <equinox@spreadspace.org>2023-09-21 18:37:34 +0200
commit67dbf646f686dac08419cad521a178a793be2c22 (patch)
tree8bacf331cb0fe01656427a3428f0ed3f148d3562 /roles/monitoring/prometheus/server
parentuacme: eab hmac key is most likely already encoded and doesn't need additiona... (diff)
fix smartctl text collector and add some alerts for nvme metrics
Diffstat (limited to 'roles/monitoring/prometheus/server')
-rw-r--r--roles/monitoring/prometheus/server/defaults/main/rules_node.yml18
1 files changed, 18 insertions, 0 deletions
diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
index 5493da57..fe6e781b 100644
--- a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
+++ b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml
@@ -393,6 +393,24 @@ prometheus_server_rules_node:
summary: Host disk S.M.A.R.T. reports offline uncorrectable errors (instance {{ '{{' }} $labels.instance {{ '}}' }})
description: "S.M.A.R.T. reports offline uncorrectable errors for disk {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be failing.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
+ - alert: SmartmonNVMEMediaErrors
+ expr: delta(smartmon_media_errors_total[72h]) > 0
+ for: 0m
+ labels:
+ severity: warning
+ annotations:
+ summary: Host disk S.M.A.R.T. reports NVMe media errors. (instance {{ '{{' }} $labels.instance {{ '}}' }})
+ description: "S.M.A.R.T. reports NVMe media errors for disk {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be failing.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
+
+ - alert: SmartmonNVMEPercentageUsed
+ expr: smartmon_percentage_used_ratio > 80
+ for: 0m
+ labels:
+ severity: warning
+ annotations:
+ summary: Host disk S.M.A.R.T. reports worn out disk. (instance {{ '{{' }} $labels.instance {{ '}}' }})
+ description: "S.M.A.R.T. reports NVMe high usage of device {{ '{{' }} $labels.device {{ '}}' }} on host {{ '{{' }} $labels.instance {{ '}}' }}, the drive might be completely worn out soon.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}"
+
## syncoid-pull scripts
- alert: SyncoidPullJobTooLongAgo
expr: time() - syncoid_pull_run > (24 * 3600)