| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | # --- Availability --- |
| 4 | |
| 5 | template: am_load_balancers_vip_availability |
| 6 | on: azure_monitor.load_balancers.vip_availability |
| 7 | class: Availability |
| 8 | type: Other |
| 9 | component: Azure Load Balancer |
| 10 | lookup: average -5m unaligned of average |
| 11 | units: percentage |
| 12 | every: 1m |
| 13 | warn: $this < (($status >= $WARNING) ? (99.9) : (99)) |
| 14 | crit: $this < (($status == $CRITICAL) ? (99) : (90)) |
| 15 | delay: down 5m multiplier 1.5 max 1h |
| 16 | summary: LB data path availability on ${label:resource_name} |
| 17 | info: Data path availability of Azure Load Balancer ${label:resource_name} \ |
| 18 | in ${label:resource_group} (${label:region}). \ |
| 19 | Low values indicate the load balancer is unable to forward traffic |
| 20 | to: sysadmin |
| 21 | |
| 22 | template: am_load_balancers_dip_availability |
| 23 | on: azure_monitor.load_balancers.dip_availability |
| 24 | class: Availability |
| 25 | type: Other |
| 26 | component: Azure Load Balancer |
| 27 | lookup: average -5m unaligned of average |
| 28 | units: percentage |
| 29 | every: 1m |
| 30 | warn: $this < (($status >= $WARNING) ? (99.9) : (99)) |
| 31 | crit: $this < (($status == $CRITICAL) ? (99) : (90)) |
| 32 | delay: down 5m multiplier 1.5 max 1h |
| 33 | summary: LB health probe status on ${label:resource_name} |
| 34 | info: Health probe availability of Azure Load Balancer ${label:resource_name} \ |
| 35 | in ${label:resource_group} (${label:region}). \ |
| 36 | Low values indicate backend instances are failing health probes |
| 37 | to: sysadmin |
| 38 | |
| 39 | template: am_load_balancers_global_backend_availability |
| 40 | on: azure_monitor.load_balancers.global_backend_availability |
| 41 | class: Availability |
| 42 | type: Other |
| 43 | component: Azure Load Balancer |
| 44 | lookup: average -5m unaligned of average |
| 45 | units: percentage |
| 46 | every: 1m |
| 47 | warn: $this != nan AND $this < (($status >= $WARNING) ? (99.9) : (99)) |
| 48 | crit: $this != nan AND $this < (($status == $CRITICAL) ? (99) : (90)) |
| 49 | delay: down 5m multiplier 1.5 max 1h |
| 50 | summary: LB global backend availability on ${label:resource_name} |
| 51 | info: Global backend availability of Azure Load Balancer ${label:resource_name} \ |
| 52 | in ${label:resource_group} (${label:region}). \ |
| 53 | Applies to cross-region load balancers only |
| 54 | to: sysadmin |
| 55 | |
| 56 | # --- SNAT Port Exhaustion --- |
| 57 | |
| 58 | template: am_load_balancers_snat_port_utilization |
| 59 | on: azure_monitor.load_balancers.snat_ports |
| 60 | class: Utilization |
| 61 | type: Other |
| 62 | component: Azure Load Balancer |
| 63 | calc: ($allocated > 0) ? ($used * 100 / $allocated) : (0) |
| 64 | units: % |
| 65 | every: 1m |
| 66 | warn: $this > (($status >= $WARNING) ? (70) : (80)) |
| 67 | crit: $this > (($status == $CRITICAL) ? (85) : (95)) |
| 68 | delay: down 5m multiplier 1.5 max 1h |
| 69 | summary: LB SNAT port utilization on ${label:resource_name} |
| 70 | info: Percentage of allocated SNAT ports in use on Azure Load Balancer ${label:resource_name} \ |
| 71 | in ${label:resource_group} (${label:region}). \ |
| 72 | SNAT port exhaustion causes outbound connection failures |
| 73 | to: sysadmin |