| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | # --- Capacity / Utilization --- |
| 4 | |
| 5 | template: am_api_management_capacity |
| 6 | on: azure_monitor.api_management.capacity |
| 7 | class: Utilization |
| 8 | type: Web Server |
| 9 | component: API Management |
| 10 | lookup: average -5m unaligned of capacity |
| 11 | units: percentage |
| 12 | every: 1m |
| 13 | warn: $this > (($status >= $WARNING) ? (70) : (80)) |
| 14 | crit: $this > (($status == $CRITICAL) ? (80) : (90)) |
| 15 | delay: down 5m multiplier 1.5 max 1h |
| 16 | summary: APIM capacity on ${label:resource_name} |
| 17 | info: Average capacity utilization of API Management service ${label:resource_name} \ |
| 18 | in ${label:resource_group} (${label:region}). \ |
| 19 | High capacity indicates the service is approaching its scaling limits |
| 20 | to: sysadmin |
| 21 | |
| 22 | template: am_api_management_gateway_cpu |
| 23 | on: azure_monitor.api_management.gateway_cpu |
| 24 | class: Utilization |
| 25 | type: Web Server |
| 26 | component: API Management |
| 27 | lookup: average -5m unaligned of cpu |
| 28 | units: percentage |
| 29 | every: 1m |
| 30 | warn: $this != nan AND $this > (($status >= $WARNING) ? (70) : (80)) |
| 31 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (85) : (95)) |
| 32 | delay: down 5m multiplier 1.5 max 1h |
| 33 | summary: APIM gateway CPU on ${label:resource_name} |
| 34 | info: Average gateway CPU utilization of API Management service ${label:resource_name} \ |
| 35 | in ${label:resource_group} (${label:region}) |
| 36 | to: sysadmin |
| 37 | |
| 38 | template: am_api_management_gateway_memory |
| 39 | on: azure_monitor.api_management.gateway_memory |
| 40 | class: Utilization |
| 41 | type: Web Server |
| 42 | component: API Management |
| 43 | lookup: average -5m unaligned of memory |
| 44 | units: percentage |
| 45 | every: 1m |
| 46 | warn: $this != nan AND $this > (($status >= $WARNING) ? (70) : (80)) |
| 47 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (85) : (95)) |
| 48 | delay: down 5m multiplier 1.5 max 1h |
| 49 | summary: APIM gateway memory on ${label:resource_name} |
| 50 | info: Average gateway memory utilization of API Management service ${label:resource_name} \ |
| 51 | in ${label:resource_group} (${label:region}) |
| 52 | to: sysadmin |
| 53 | |
| 54 | # --- Request Latency --- |
| 55 | |
| 56 | template: am_api_management_request_duration |
| 57 | on: azure_monitor.api_management.request_duration |
| 58 | class: Latency |
| 59 | type: Web Server |
| 60 | component: API Management |
| 61 | lookup: average -5m unaligned of overall |
| 62 | units: milliseconds |
| 63 | every: 1m |
| 64 | warn: $this > (($status >= $WARNING) ? (3000) : (5000)) |
| 65 | crit: $this > (($status == $CRITICAL) ? (5000) : (10000)) |
| 66 | delay: down 5m multiplier 1.5 max 1h |
| 67 | summary: APIM request duration on ${label:resource_name} |
| 68 | info: Average overall request duration of API Management service ${label:resource_name} \ |
| 69 | in ${label:resource_group} (${label:region}) |
| 70 | to: sysadmin |
| 71 | |
| 72 | template: am_api_management_backend_duration |
| 73 | on: azure_monitor.api_management.request_duration |
| 74 | class: Latency |
| 75 | type: Web Server |
| 76 | component: API Management |
| 77 | lookup: average -5m unaligned of backend |
| 78 | units: milliseconds |
| 79 | every: 1m |
| 80 | warn: $this > (($status >= $WARNING) ? (3000) : (5000)) |
| 81 | crit: $this > (($status == $CRITICAL) ? (5000) : (10000)) |
| 82 | delay: down 5m multiplier 1.5 max 1h |
| 83 | summary: APIM backend duration on ${label:resource_name} |
| 84 | info: Average backend request duration of API Management service ${label:resource_name} \ |
| 85 | in ${label:resource_group} (${label:region}) |
| 86 | to: sysadmin |
| 87 | |
| 88 | # --- Network Connectivity --- |
| 89 | |
| 90 | template: am_api_management_network_connectivity |
| 91 | on: azure_monitor.api_management.network_connectivity |
| 92 | class: Availability |
| 93 | type: Web Server |
| 94 | component: API Management |
| 95 | lookup: average -5m unaligned of connectivity |
| 96 | units: status |
| 97 | every: 1m |
| 98 | crit: $this < (($status == $CRITICAL) ? (1) : (0.5)) |
| 99 | delay: down 5m multiplier 1.5 max 1h |
| 100 | summary: APIM network connectivity on ${label:resource_name} |
| 101 | info: Network connectivity status of API Management service ${label:resource_name} \ |
| 102 | in ${label:resource_group} (${label:region}). \ |
| 103 | Values below 1 indicate connectivity problems to backend dependencies |
| 104 | to: sysadmin |
| 105 | |
| 106 | # --- EventHub Errors --- |
| 107 | |
| 108 | template: am_api_management_eventhub_failed_events |
| 109 | on: azure_monitor.api_management.eventhub_events |
| 110 | class: Errors |
| 111 | type: Web Server |
| 112 | component: API Management |
| 113 | lookup: average -5m unaligned of failed |
| 114 | units: events/s |
| 115 | every: 1m |
| 116 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (5)) |
| 117 | delay: down 5m multiplier 1.5 max 1h |
| 118 | summary: APIM EventHub failed events on ${label:resource_name} |
| 119 | info: Rate of failed EventHub events for API Management service ${label:resource_name} \ |
| 120 | in ${label:resource_group} (${label:region}) |
| 121 | to: sysadmin |
| 122 | |
| 123 | template: am_api_management_eventhub_dropped_events |
| 124 | on: azure_monitor.api_management.eventhub_events |
| 125 | class: Errors |
| 126 | type: Web Server |
| 127 | component: API Management |
| 128 | lookup: average -5m unaligned of dropped |
| 129 | units: events/s |
| 130 | every: 1m |
| 131 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (5)) |
| 132 | delay: down 5m multiplier 1.5 max 1h |
| 133 | summary: APIM EventHub dropped events on ${label:resource_name} |
| 134 | info: Rate of dropped EventHub events for API Management service ${label:resource_name} \ |
| 135 | in ${label:resource_group} (${label:region}) |
| 136 | to: sysadmin |
| 137 | |
| 138 | template: am_api_management_eventhub_rejected_events |
| 139 | on: azure_monitor.api_management.eventhub_events |
| 140 | class: Errors |
| 141 | type: Web Server |
| 142 | component: API Management |
| 143 | lookup: average -5m unaligned of rejected |
| 144 | units: events/s |
| 145 | every: 1m |
| 146 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (5)) |
| 147 | delay: down 5m multiplier 1.5 max 1h |
| 148 | summary: APIM EventHub rejected events on ${label:resource_name} |
| 149 | info: Rate of rejected EventHub events for API Management service ${label:resource_name} \ |
| 150 | in ${label:resource_group} (${label:region}) |
| 151 | to: sysadmin |
| 152 | |
| 153 | template: am_api_management_eventhub_throttled_events |
| 154 | on: azure_monitor.api_management.eventhub_events |
| 155 | class: Errors |
| 156 | type: Web Server |
| 157 | component: API Management |
| 158 | lookup: average -5m unaligned of throttled |
| 159 | units: events/s |
| 160 | every: 1m |
| 161 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (10)) |
| 162 | delay: down 5m multiplier 1.5 max 1h |
| 163 | summary: APIM EventHub throttled events on ${label:resource_name} |
| 164 | info: Rate of throttled EventHub events for API Management service ${label:resource_name} \ |
| 165 | in ${label:resource_group} (${label:region}). \ |
| 166 | Throttling indicates EventHub throughput limits are being reached |
| 167 | to: sysadmin |
| 168 | |
| 169 | template: am_api_management_eventhub_timedout_events |
| 170 | on: azure_monitor.api_management.eventhub_events |
| 171 | class: Errors |
| 172 | type: Web Server |
| 173 | component: API Management |
| 174 | lookup: average -5m unaligned of timed_out |
| 175 | units: events/s |
| 176 | every: 1m |
| 177 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (5)) |
| 178 | delay: down 5m multiplier 1.5 max 1h |
| 179 | summary: APIM EventHub timed out events on ${label:resource_name} |
| 180 | info: Rate of timed out EventHub events for API Management service ${label:resource_name} \ |
| 181 | in ${label:resource_group} (${label:region}) |
| 182 | to: sysadmin |