| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | # --- D2C Telemetry Throttling --- |
| 4 | |
| 5 | template: am_iot_hub_d2c_telemetry_throttle |
| 6 | on: azure_monitor.iot_hub.d2c_telemetry_throttle |
| 7 | class: Errors |
| 8 | type: Messaging |
| 9 | component: IoT Hub |
| 10 | lookup: average -5m unaligned of throttled |
| 11 | units: errors/s |
| 12 | every: 1m |
| 13 | warn: $this > (($status >= $WARNING) ? (1) : (5)) |
| 14 | crit: $this > (($status == $CRITICAL) ? (10) : (50)) |
| 15 | delay: down 5m multiplier 1.5 max 1h |
| 16 | summary: IoT Hub telemetry throttling on ${label:resource_name} |
| 17 | info: Device-to-cloud telemetry throttling errors on IoT Hub ${label:resource_name} \ |
| 18 | in ${label:resource_group} (${label:region}). \ |
| 19 | Throttling indicates the hub is exceeding its message rate limits |
| 20 | to: sysadmin |
| 21 | |
| 22 | # --- C2D Messages Expired --- |
| 23 | |
| 24 | template: am_iot_hub_c2d_messages_expired |
| 25 | on: azure_monitor.iot_hub.c2d_messages_expired |
| 26 | class: Errors |
| 27 | type: Messaging |
| 28 | component: IoT Hub |
| 29 | lookup: average -5m unaligned of expired |
| 30 | units: messages/s |
| 31 | every: 1m |
| 32 | warn: $this > (($status >= $WARNING) ? (0) : (1)) |
| 33 | crit: $this > (($status == $CRITICAL) ? (5) : (10)) |
| 34 | delay: down 5m multiplier 1.5 max 1h |
| 35 | summary: IoT Hub C2D messages expiring on ${label:resource_name} |
| 36 | info: Cloud-to-device messages expiring before delivery on IoT Hub ${label:resource_name} \ |
| 37 | in ${label:resource_group} (${label:region}). \ |
| 38 | Expired messages indicate devices are not receiving commands in time |
| 39 | to: sysadmin |
| 40 | |
| 41 | # --- C2D Direct Method Failures --- |
| 42 | |
| 43 | template: am_iot_hub_c2d_methods_failed |
| 44 | on: azure_monitor.iot_hub.c2d_methods |
| 45 | class: Errors |
| 46 | type: Messaging |
| 47 | component: IoT Hub |
| 48 | lookup: average -5m unaligned of failed |
| 49 | units: invocations/s |
| 50 | every: 1m |
| 51 | warn: $this > (($status >= $WARNING) ? (1) : (5)) |
| 52 | crit: $this > (($status == $CRITICAL) ? (10) : (50)) |
| 53 | delay: down 5m multiplier 1.5 max 1h |
| 54 | summary: IoT Hub direct method failures on ${label:resource_name} |
| 55 | info: Failed cloud-to-device direct method invocations on IoT Hub ${label:resource_name} \ |
| 56 | in ${label:resource_group} (${label:region}) |
| 57 | to: sysadmin |
| 58 | |
| 59 | # --- C2D Twin Read Failures --- |
| 60 | |
| 61 | template: am_iot_hub_c2d_twin_read_failures |
| 62 | on: azure_monitor.iot_hub.c2d_twin_reads |
| 63 | class: Errors |
| 64 | type: Messaging |
| 65 | component: IoT Hub |
| 66 | lookup: average -5m unaligned of failed |
| 67 | units: operations/s |
| 68 | every: 1m |
| 69 | warn: $this > (($status >= $WARNING) ? (1) : (5)) |
| 70 | crit: $this > (($status == $CRITICAL) ? (10) : (50)) |
| 71 | delay: down 5m multiplier 1.5 max 1h |
| 72 | summary: IoT Hub backend twin read failures on ${label:resource_name} |
| 73 | info: Failed backend twin read operations on IoT Hub ${label:resource_name} \ |
| 74 | in ${label:resource_group} (${label:region}) |
| 75 | to: sysadmin |
| 76 | |
| 77 | # --- C2D Twin Update Failures --- |
| 78 | |
| 79 | template: am_iot_hub_c2d_twin_update_failures |
| 80 | on: azure_monitor.iot_hub.c2d_twin_updates |
| 81 | class: Errors |
| 82 | type: Messaging |
| 83 | component: IoT Hub |
| 84 | lookup: average -5m unaligned of failed |
| 85 | units: operations/s |
| 86 | every: 1m |
| 87 | warn: $this > (($status >= $WARNING) ? (1) : (5)) |
| 88 | crit: $this > (($status == $CRITICAL) ? (10) : (50)) |
| 89 | delay: down 5m multiplier 1.5 max 1h |
| 90 | summary: IoT Hub backend twin update failures on ${label:resource_name} |
| 91 | info: Failed backend twin update operations on IoT Hub ${label:resource_name} \ |
| 92 | in ${label:resource_group} (${label:region}) |
| 93 | to: sysadmin |
| 94 | |
| 95 | # --- D2C Twin Read Failures --- |
| 96 | |
| 97 | template: am_iot_hub_d2c_twin_read_failures |
| 98 | on: azure_monitor.iot_hub.d2c_twin_reads |
| 99 | class: Errors |
| 100 | type: Messaging |
| 101 | component: IoT Hub |
| 102 | lookup: average -5m unaligned of failed |
| 103 | units: operations/s |
| 104 | every: 1m |
| 105 | warn: $this > (($status >= $WARNING) ? (1) : (5)) |
| 106 | crit: $this > (($status == $CRITICAL) ? (10) : (50)) |
| 107 | delay: down 5m multiplier 1.5 max 1h |
| 108 | summary: IoT Hub device twin read failures on ${label:resource_name} |
| 109 | info: Failed device-initiated twin read operations on IoT Hub ${label:resource_name} \ |
| 110 | in ${label:resource_group} (${label:region}) |
| 111 | to: sysadmin |
| 112 | |
| 113 | # --- D2C Twin Update Failures --- |
| 114 | |
| 115 | template: am_iot_hub_d2c_twin_update_failures |
| 116 | on: azure_monitor.iot_hub.d2c_twin_updates |
| 117 | class: Errors |
| 118 | type: Messaging |
| 119 | component: IoT Hub |
| 120 | lookup: average -5m unaligned of failed |
| 121 | units: operations/s |
| 122 | every: 1m |
| 123 | warn: $this > (($status >= $WARNING) ? (1) : (5)) |
| 124 | crit: $this > (($status == $CRITICAL) ? (10) : (50)) |
| 125 | delay: down 5m multiplier 1.5 max 1h |
| 126 | summary: IoT Hub device twin update failures on ${label:resource_name} |
| 127 | info: Failed device-initiated twin update operations on IoT Hub ${label:resource_name} \ |
| 128 | in ${label:resource_group} (${label:region}) |
| 129 | to: sysadmin |
| 130 | |
| 131 | # --- Routing Dropped Messages --- |
| 132 | |
| 133 | template: am_iot_hub_routing_dropped |
| 134 | on: azure_monitor.iot_hub.routing_deliveries |
| 135 | class: Errors |
| 136 | type: Messaging |
| 137 | component: IoT Hub |
| 138 | lookup: average -5m unaligned of dropped |
| 139 | units: messages/s |
| 140 | every: 1m |
| 141 | warn: $this > (($status >= $WARNING) ? (0) : (1)) |
| 142 | crit: $this > (($status == $CRITICAL) ? (5) : (10)) |
| 143 | delay: down 5m multiplier 1.5 max 1h |
| 144 | summary: IoT Hub routing dropped messages on ${label:resource_name} |
| 145 | info: Messages dropped by the routing engine on IoT Hub ${label:resource_name} \ |
| 146 | in ${label:resource_group} (${label:region}). \ |
| 147 | Dropped messages indicate dead endpoints or misconfigured routes |
| 148 | to: sysadmin |
| 149 | |
| 150 | # --- Routing Orphaned Messages --- |
| 151 | |
| 152 | template: am_iot_hub_routing_orphaned |
| 153 | on: azure_monitor.iot_hub.routing_deliveries |
| 154 | class: Errors |
| 155 | type: Messaging |
| 156 | component: IoT Hub |
| 157 | lookup: average -5m unaligned of orphaned |
| 158 | units: messages/s |
| 159 | every: 1m |
| 160 | warn: $this > (($status >= $WARNING) ? (0) : (1)) |
| 161 | crit: $this > (($status == $CRITICAL) ? (5) : (10)) |
| 162 | delay: down 5m multiplier 1.5 max 1h |
| 163 | summary: IoT Hub routing orphaned messages on ${label:resource_name} |
| 164 | info: Orphaned messages with no matching routing rule on IoT Hub ${label:resource_name} \ |
| 165 | in ${label:resource_group} (${label:region}). \ |
| 166 | Orphaned messages indicate missing or incomplete routing configuration |
| 167 | to: sysadmin |
| 168 | |
| 169 | # --- Routing Invalid Messages --- |
| 170 | |
| 171 | template: am_iot_hub_routing_invalid |
| 172 | on: azure_monitor.iot_hub.routing_deliveries |
| 173 | class: Errors |
| 174 | type: Messaging |
| 175 | component: IoT Hub |
| 176 | lookup: average -5m unaligned of invalid |
| 177 | units: messages/s |
| 178 | every: 1m |
| 179 | warn: $this > (($status >= $WARNING) ? (0) : (1)) |
| 180 | crit: $this > (($status == $CRITICAL) ? (5) : (10)) |
| 181 | delay: down 5m multiplier 1.5 max 1h |
| 182 | summary: IoT Hub routing invalid messages on ${label:resource_name} |
| 183 | info: Invalid messages rejected by the routing engine on IoT Hub ${label:resource_name} \ |
| 184 | in ${label:resource_group} (${label:region}) |
| 185 | to: sysadmin |
| 186 | |
| 187 | # --- Routing Latency --- |
| 188 | |
| 189 | template: am_iot_hub_routing_latency |
| 190 | on: azure_monitor.iot_hub.routing_latency |
| 191 | class: Latency |
| 192 | type: Messaging |
| 193 | component: IoT Hub |
| 194 | lookup: max -5m unaligned |
| 195 | units: milliseconds |
| 196 | every: 1m |
| 197 | warn: $this != nan AND $this > (($status >= $WARNING) ? (3000) : (5000)) |
| 198 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (5000) : (10000)) |
| 199 | delay: down 5m multiplier 1.5 max 1h |
| 200 | summary: IoT Hub routing latency on ${label:resource_name} |
| 201 | info: Maximum message routing latency across all endpoints on IoT Hub ${label:resource_name} \ |
| 202 | in ${label:resource_group} (${label:region}) |
| 203 | to: sysadmin |
| 204 | |
| 205 | # --- Event Grid Latency --- |
| 206 | |
| 207 | template: am_iot_hub_event_grid_latency |
| 208 | on: azure_monitor.iot_hub.event_grid_latency |
| 209 | class: Latency |
| 210 | type: Messaging |
| 211 | component: IoT Hub |
| 212 | lookup: average -5m unaligned of average |
| 213 | units: milliseconds |
| 214 | every: 1m |
| 215 | warn: $this != nan AND $this > (($status >= $WARNING) ? (3000) : (5000)) |
| 216 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (5000) : (10000)) |
| 217 | delay: down 5m multiplier 1.5 max 1h |
| 218 | summary: IoT Hub Event Grid latency on ${label:resource_name} |
| 219 | info: Average Event Grid delivery latency on IoT Hub ${label:resource_name} \ |
| 220 | in ${label:resource_group} (${label:region}) |
| 221 | to: sysadmin |
| 222 | |
| 223 | # --- Job Failures --- |
| 224 | |
| 225 | template: am_iot_hub_jobs_failed |
| 226 | on: azure_monitor.iot_hub.jobs_status |
| 227 | class: Errors |
| 228 | type: Messaging |
| 229 | component: IoT Hub |
| 230 | lookup: average -5m unaligned of failed |
| 231 | units: operations/s |
| 232 | every: 1m |
| 233 | warn: $this > (($status >= $WARNING) ? (0) : (1)) |
| 234 | crit: $this > (($status == $CRITICAL) ? (5) : (10)) |
| 235 | delay: down 5m multiplier 1.5 max 1h |
| 236 | summary: IoT Hub job failures on ${label:resource_name} |
| 237 | info: Failed jobs on IoT Hub ${label:resource_name} \ |
| 238 | in ${label:resource_group} (${label:region}) |
| 239 | to: sysadmin |
| 240 | |
| 241 | # --- Twin Query Failures --- |
| 242 | |
| 243 | template: am_iot_hub_twin_query_failures |
| 244 | on: azure_monitor.iot_hub.twin_queries |
| 245 | class: Errors |
| 246 | type: Messaging |
| 247 | component: IoT Hub |
| 248 | lookup: average -5m unaligned of failed |
| 249 | units: queries/s |
| 250 | every: 1m |
| 251 | warn: $this > (($status >= $WARNING) ? (1) : (5)) |
| 252 | crit: $this > (($status == $CRITICAL) ? (10) : (50)) |
| 253 | delay: down 5m multiplier 1.5 max 1h |
| 254 | summary: IoT Hub twin query failures on ${label:resource_name} |
| 255 | info: Failed twin queries on IoT Hub ${label:resource_name} \ |
| 256 | in ${label:resource_group} (${label:region}) |
| 257 | to: sysadmin |
| 258 | |
| 259 | # --- C2D Commands Abandoned --- |
| 260 | |
| 261 | template: am_iot_hub_c2d_commands_abandoned |
| 262 | on: azure_monitor.iot_hub.c2d_commands |
| 263 | class: Errors |
| 264 | type: Messaging |
| 265 | component: IoT Hub |
| 266 | lookup: average -5m unaligned of abandoned |
| 267 | units: messages/s |
| 268 | every: 1m |
| 269 | warn: $this > (($status >= $WARNING) ? (1) : (5)) |
| 270 | crit: $this > (($status == $CRITICAL) ? (10) : (50)) |
| 271 | delay: down 5m multiplier 1.5 max 1h |
| 272 | summary: IoT Hub C2D commands abandoned on ${label:resource_name} |
| 273 | info: Cloud-to-device commands abandoned by devices on IoT Hub ${label:resource_name} \ |
| 274 | in ${label:resource_group} (${label:region}). \ |
| 275 | Abandoned commands indicate devices are not properly handling received messages |
| 276 | to: sysadmin |
| 277 | |
| 278 | # --- C2D Commands Rejected --- |
| 279 | |
| 280 | template: am_iot_hub_c2d_commands_rejected |
| 281 | on: azure_monitor.iot_hub.c2d_commands |
| 282 | class: Errors |
| 283 | type: Messaging |
| 284 | component: IoT Hub |
| 285 | lookup: average -5m unaligned of rejected |
| 286 | units: messages/s |
| 287 | every: 1m |
| 288 | warn: $this > (($status >= $WARNING) ? (1) : (5)) |
| 289 | crit: $this > (($status == $CRITICAL) ? (10) : (50)) |
| 290 | delay: down 5m multiplier 1.5 max 1h |
| 291 | summary: IoT Hub C2D commands rejected on ${label:resource_name} |
| 292 | info: Cloud-to-device commands rejected by devices on IoT Hub ${label:resource_name} \ |
| 293 | in ${label:resource_group} (${label:region}). \ |
| 294 | Rejected commands indicate devices are explicitly refusing messages |
| 295 | to: sysadmin |
| 296 | |
| 297 | # --- Routing Delivery Latency (Preview) --- |
| 298 | |
| 299 | template: am_iot_hub_routing_delivery_latency_preview |
| 300 | on: azure_monitor.iot_hub.routing_delivery_latency_preview |
| 301 | class: Latency |
| 302 | type: Messaging |
| 303 | component: IoT Hub |
| 304 | lookup: average -5m unaligned of average |
| 305 | units: milliseconds |
| 306 | every: 1m |
| 307 | warn: $this != nan AND $this > (($status >= $WARNING) ? (3000) : (5000)) |
| 308 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (5000) : (10000)) |
| 309 | delay: down 5m multiplier 1.5 max 1h |
| 310 | summary: IoT Hub routing delivery latency on ${label:resource_name} |
| 311 | info: Average routing delivery latency (preview metric) on IoT Hub ${label:resource_name} \ |
| 312 | in ${label:resource_group} (${label:region}) |
| 313 | to: sysadmin |