diff options
Diffstat (limited to 'rules/smartctl.yml')
| -rw-r--r-- | rules/smartctl.yml | 40 |
1 files changed, 39 insertions, 1 deletions
diff --git a/rules/smartctl.yml b/rules/smartctl.yml index 3982e06..60a2caa 100644 --- a/rules/smartctl.yml +++ b/rules/smartctl.yml @@ -59,6 +59,36 @@ groups: + sum by (host, device) (smartctl_write_total_uncorrected_errors) or (count by (host, device) (smartctl_device_smart_status) * 0) + # --- NVMe ----------------------------------------------------------------- + # NVMe has neither an ATA attribute table nor SCSI error counters. Its health is + # in the SMART/Health Information log, which smartctl_exporter emits only when the + # interface is nvme. + # + # Each arm is reduced to {host, device} *before* the `or`, so the union + # deduplicates per drive rather than emitting one series per metric name -- the + # count is then "did anything fire", which is all smartctl:health_code asks. + - record: smartctl:nvme_failing:count + expr: | + ( + count by (host, device) (smartctl_device_critical_warning > 0) + or + count by (host, device) (smartctl_device_media_errors > 0) + or + count by (host, device) ( + smartctl_device_available_spare + < on(host, device) smartctl_device_available_spare_threshold + ) + ) + or (count by (host, device) (smartctl_device_smart_status) * 0) + + # percentage_used is the controller's own estimate of consumed write endurance, + # where 100 means the drive has reached its rated lifetime. Drives routinely run + # well past it, so this is a warning and not a failure. + - record: smartctl:nvme_caution:count + expr: | + count by (host, device) (smartctl_device_percentage_used >= 90) + or (count by (host, device) (smartctl_device_smart_status) * 0) + # --- Verdict -------------------------------------------------------------- # 0 good, 1 caution, 2 bad. The inner clamp_max on each group keeps two # simultaneous caution signals from adding up to a false "bad". @@ -69,22 +99,30 @@ groups: (max by (host, device) (smartctl_device_smart_status) == bool 0) + (smartctl:attr_failing:count > bool 0) + (smartctl:scsi_uncorrected:count > bool 0) + + (smartctl:nvme_failing:count > bool 0) , 1) + clamp_max( (smartctl:attr_caution:count > bool 0) + (smartctl:scsi_defects:count > bool 0) + + (smartctl:nvme_caution:count > bool 0) , 1) , 2) # --- Row labels ----------------------------------------------------------- # Which section of the SMART dashboard a drive belongs in. Keyed on metric # presence rather than the `protocol` label: only ATA drives report an attribute - # table, and only SCSI drives report a grown defect list. + # table, only SCSI drives report a grown defect list, and smartctl_exporter emits + # percentage_used only for nvme. The three are disjoint by construction, so the + # order of the `or` arms does not matter -- but a drive matching none of them gets + # no bus, drops out of the smartctl:row join, and silently loses its dashboard + # section, which is what NVMe used to do. - record: smartctl:bus expr: | label_replace(count by (host, device) (smartctl_device_attribute), "bus", "ata", "", "") or label_replace(count by (host, device) (smartctl_scsi_grown_defect_list), "bus", "sas", "", "") + or + label_replace(count by (host, device) (smartctl_device_percentage_used), "bus", "nvme", "", "") # The identity string from collectors/smart-selftest.py, made total so a drive # still gets a row if that collector has not written its file yet. `unless` (not |