| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | # Warn on any compute errors encountered. |
| 4 | template: boinc_compute_errors |
| 5 | on: boinc.tasks_per_state |
| 6 | class: Errors |
| 7 | type: Computing |
| 8 | component: BOINC |
| 9 | lookup: average -10m unaligned of compute_error |
| 10 | units: tasks |
| 11 | every: 1m |
| 12 | warn: $this > 0 |
| 13 | delay: up 1m down 5m multiplier 1.5 max 1h |
| 14 | summary: BOINC compute errors |
| 15 | info: Average number of compute errors over the last 10 minutes |
| 16 | to: sysadmin |
| 17 | |
| 18 | # Warn on lots of upload errors |
| 19 | template: boinc_upload_errors |
| 20 | on: boinc.tasks_per_state |
| 21 | class: Errors |
| 22 | type: Computing |
| 23 | component: BOINC |
| 24 | lookup: average -10m unaligned of upload_failed |
| 25 | units: tasks |
| 26 | every: 1m |
| 27 | warn: $this > 0 |
| 28 | delay: up 1m down 5m multiplier 1.5 max 1h |
| 29 | summary: BOINC failed uploads |
| 30 | info: Average number of failed uploads over the last 10 minutes |
| 31 | to: sysadmin |
| 32 | |
| 33 | # Warn on the task queue being empty |
| 34 | template: boinc_total_tasks |
| 35 | on: boinc.tasks |
| 36 | class: Utilization |
| 37 | type: Computing |
| 38 | component: BOINC |
| 39 | lookup: average -10m unaligned of total |
| 40 | units: tasks |
| 41 | every: 1m |
| 42 | warn: $this < 1 |
| 43 | delay: up 5m down 10m multiplier 1.5 max 1h |
| 44 | summary: BOINC total tasks |
| 45 | info: Average number of total tasks over the last 10 minutes |
| 46 | to: sysadmin |
| 47 | |
| 48 | # Warn on no active tasks with a non-empty queue |
| 49 | template: boinc_active_tasks |
| 50 | on: boinc.tasks |
| 51 | class: Utilization |
| 52 | type: Computing |
| 53 | component: BOINC |
| 54 | lookup: average -10m unaligned of active |
| 55 | calc: ($boinc_total_tasks >= 1) ? ($this) : (inf) |
| 56 | units: tasks |
| 57 | every: 1m |
| 58 | warn: $this < 1 |
| 59 | delay: up 5m down 10m multiplier 1.5 max 1h |
| 60 | summary: BOINC active tasks |
| 61 | info: Average number of active tasks over the last 10 minutes |
| 62 | to: sysadmin |