| 1 | |
| 2 | template: mdstat_disks |
| 3 | on: md.disks |
| 4 | class: Errors |
| 5 | type: System |
| 6 | component: RAID |
| 7 | units: failed devices |
| 8 | every: 10s |
| 9 | calc: $down |
| 10 | warn: $this > 0 |
| 11 | summary: MD array device ${label:device} down |
| 12 | info: Number of devices in the down state for the ${label:device} ${label:raid_level} array. \ |
| 13 | Any number > 0 indicates that the array is degraded. |
| 14 | to: sysadmin |
| 15 | |
| 16 | template: mdstat_mismatch_cnt |
| 17 | on: md.mismatch_cnt |
| 18 | class: Errors |
| 19 | type: System |
| 20 | component: RAID |
| 21 | chart labels: raid_level=!raid1 !raid10 * |
| 22 | units: unsynchronized blocks |
| 23 | calc: $count |
| 24 | every: 60s |
| 25 | warn: $this > 1024 |
| 26 | delay: up 30m |
| 27 | summary: MD array device ${label:device} unsynchronized blocks |
| 28 | info: Number of unsynchronized blocks for the ${label:device} ${label:raid_level} array |
| 29 | to: silent |
| 30 | |
| 31 | template: mdstat_nonredundant_last_collected |
| 32 | on: md.nonredundant |
| 33 | class: Latency |
| 34 | type: System |
| 35 | component: RAID |
| 36 | calc: $now - $last_collected_t |
| 37 | units: seconds ago |
| 38 | every: 10s |
| 39 | warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every)) |
| 40 | crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every)) |
| 41 | summary: MD array last collected |
| 42 | info: Number of seconds since the last successful data collection |
| 43 | to: sysadmin |