| 1 | # IBM AS/400 (IBM i) health alerts |
| 2 | |
| 3 | # CPU utilization |
| 4 | # High sustained CPU usage across the entire system usually warrants action. |
| 5 | template: as400_cpu_utilization |
| 6 | on: as400.cpu_utilization |
| 7 | class: Utilization |
| 8 | type: Database |
| 9 | component: AS/400 |
| 10 | lookup: average -5m unaligned of utilization |
| 11 | units: % |
| 12 | every: 30s |
| 13 | warn: $this > 85 |
| 14 | crit: $this > 92 |
| 15 | delay: down 15m multiplier 1.5 max 1h |
| 16 | summary: AS/400 CPU utilization |
| 17 | info: CPU utilization is ${value}% on the AS/400 system |
| 18 | to: dba |
| 19 | |
| 20 | # System ASP (disk) usage |
| 21 | # Alert when the primary storage pool approaches capacity. |
| 22 | template: as400_system_asp_usage |
| 23 | on: as400.system_asp_usage |
| 24 | class: Utilization |
| 25 | type: Database |
| 26 | component: AS/400 |
| 27 | lookup: average -5m unaligned of used |
| 28 | units: % |
| 29 | every: 1m |
| 30 | warn: $this > 85 |
| 31 | crit: $this > 92 |
| 32 | delay: down 30m multiplier 1.5 max 2h |
| 33 | summary: AS/400 system ASP usage |
| 34 | info: System ASP usage is ${value}% on the AS/400 system |
| 35 | to: dba |
| 36 | |
| 37 | # Average disk busy percentage |
| 38 | # Sustained high disk activity often correlates with system slowdowns. |
| 39 | template: as400_disk_busy_average |
| 40 | on: as400.disk_busy_average |
| 41 | class: Utilization |
| 42 | type: Database |
| 43 | component: AS/400 |
| 44 | lookup: average -5m unaligned of busy |
| 45 | units: % |
| 46 | every: 1m |
| 47 | warn: $this > 80 |
| 48 | crit: $this > 90 |
| 49 | delay: down 30m multiplier 1.5 max 2h |
| 50 | summary: AS/400 average disk busy |
| 51 | info: Average disk busy percentage is ${value}% on the AS/400 system |
| 52 | to: dba |
| 53 | |
| 54 | # Waiting jobs in the main job queue |
| 55 | # Trigger only when a large backlog of waiting jobs accumulates. |
| 56 | template: as400_job_queue_waiting |
| 57 | on: as400.job_queue_length |
| 58 | class: Workload |
| 59 | type: Database |
| 60 | component: AS/400 |
| 61 | lookup: max -5m unaligned of waiting |
| 62 | units: jobs |
| 63 | every: 1m |
| 64 | warn: $this > 200 |
| 65 | crit: $this > 500 |
| 66 | delay: down 15m multiplier 1.5 max 2h |
| 67 | summary: AS/400 waiting jobs in main job queue |
| 68 | info: ${value} jobs are waiting in the system job queue on the AS/400 system |
| 69 | to: dba |