| 1 | |
| 2 | # Socket errors |
| 3 | |
| 4 | template: vernemq_socket_errors |
| 5 | on: vernemq.node_socket_errors |
| 6 | class: Errors |
| 7 | type: Messaging |
| 8 | component: VerneMQ |
| 9 | lookup: sum -1m unaligned |
| 10 | units: errors |
| 11 | every: 1m |
| 12 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 13 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 14 | summary: Node ${label:node} socket errors |
| 15 | info: Node ${label:node} socket errors in the last minute |
| 16 | to: sysadmin |
| 17 | |
| 18 | # Queues dropped/expired/unhandled PUBLISH messages |
| 19 | |
| 20 | template: vernemq_queue_message_drop |
| 21 | on: vernemq.node_queue_undelivered_messages |
| 22 | class: Errors |
| 23 | type: Messaging |
| 24 | component: VerneMQ |
| 25 | lookup: average -1m unaligned absolute of dropped |
| 26 | units: dropped messages |
| 27 | every: 1m |
| 28 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 29 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 30 | summary: Node ${label:node} dropped messages |
| 31 | info: Node ${label:node} dropped messages due to full queues in the last minute |
| 32 | to: sysadmin |
| 33 | |
| 34 | template: vernemq_queue_message_expired |
| 35 | on: vernemq.node_queue_undelivered_messages |
| 36 | class: Latency |
| 37 | type: Messaging |
| 38 | component: VerneMQ |
| 39 | lookup: average -1m unaligned absolute of expired |
| 40 | units: expired messages |
| 41 | every: 1m |
| 42 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 43 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 44 | summary: Node ${label:node} expired messages |
| 45 | info: Node ${label:node} expired before delivery messages in the last minute |
| 46 | to: sysadmin |
| 47 | |
| 48 | template: vernemq_queue_message_unhandled |
| 49 | on: vernemq.node_queue_undelivered_messages |
| 50 | class: Latency |
| 51 | type: Messaging |
| 52 | component: VerneMQ |
| 53 | lookup: average -1m unaligned absolute of unhandled |
| 54 | units: unhandled messages |
| 55 | every: 1m |
| 56 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 57 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 58 | summary: Node ${label:node} unhandled messages |
| 59 | info: Node ${label:node} unhandled messages in the last minute |
| 60 | to: sysadmin |
| 61 | |
| 62 | # Erlang VM |
| 63 | |
| 64 | template: vernemq_average_scheduler_utilization |
| 65 | on: vernemq.node_average_scheduler_utilization |
| 66 | class: Utilization |
| 67 | type: Messaging |
| 68 | component: VerneMQ |
| 69 | lookup: average -10m unaligned |
| 70 | units: % |
| 71 | every: 1m |
| 72 | warn: $this > (($status >= $WARNING) ? (75) : (85)) |
| 73 | crit: $this > (($status == $CRITICAL) ? (85) : (95)) |
| 74 | delay: down 15m multiplier 1.5 max 1h |
| 75 | summary: Node ${label:node} scheduler utilization |
| 76 | info: Node ${label:node} scheduler utilization over the last 10 minutes |
| 77 | to: sysadmin |
| 78 | |
| 79 | # Cluster communication and netsplits |
| 80 | |
| 81 | template: vernemq_cluster_dropped |
| 82 | on: vernemq.node_cluster_dropped |
| 83 | class: Errors |
| 84 | type: Messaging |
| 85 | component: VerneMQ |
| 86 | lookup: sum -1m unaligned |
| 87 | units: KiB |
| 88 | every: 1m |
| 89 | warn: $this > 0 |
| 90 | delay: up 5m down 5m multiplier 1.5 max 1h |
| 91 | summary: Node ${label:node} dropped cluster traffic |
| 92 | info: Node ${label:node} traffic dropped during communication with the cluster nodes in the last minute |
| 93 | to: sysadmin |
| 94 | |
| 95 | template: vernemq_netsplits |
| 96 | on: vernemq.node_netsplits |
| 97 | class: Workload |
| 98 | type: Messaging |
| 99 | component: VerneMQ |
| 100 | lookup: sum -1m unaligned absolute of detected |
| 101 | units: netsplits |
| 102 | every: 10s |
| 103 | warn: $this > 0 |
| 104 | delay: down 5m multiplier 1.5 max 2h |
| 105 | summary: Node ${label:node} detected netsplits |
| 106 | info: Node ${label:node} detected netsplits (split brain) in the last minute |
| 107 | to: sysadmin |
| 108 | |
| 109 | # Unsuccessful CONNACK |
| 110 | |
| 111 | template: vernemq_mqtt_connack_sent_reason_unsuccessful |
| 112 | on: vernemq.node_mqtt_connack_sent_by_reason_code |
| 113 | class: Errors |
| 114 | type: Messaging |
| 115 | component: VerneMQ |
| 116 | lookup: average -1m unaligned absolute of !success,* |
| 117 | units: packets |
| 118 | every: 1m |
| 119 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 120 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 121 | summary: Node ${label:node} unsuccessful sent CONNACK |
| 122 | info: Node ${label:node} unsuccessful sent v5 CONNACK packets in the last minute |
| 123 | to: sysadmin |
| 124 | |
| 125 | # Not normal DISCONNECT |
| 126 | |
| 127 | template: vernemq_mqtt_disconnect_received_reason_not_normal |
| 128 | on: vernemq.node_mqtt_disconnect_received_by_reason_code |
| 129 | class: Workload |
| 130 | type: Messaging |
| 131 | component: VerneMQ |
| 132 | lookup: average -1m unaligned absolute of !normal_disconnect,* |
| 133 | units: packets |
| 134 | every: 1m |
| 135 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 136 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 137 | summary: Node ${label:node} received not normal DISCONNECT |
| 138 | info: Node ${label:node} received not normal v5 DISCONNECT packets in the last minute |
| 139 | to: sysadmin |
| 140 | |
| 141 | template: vernemq_mqtt_disconnect_sent_reason_not_normal |
| 142 | on: vernemq.node_mqtt_disconnect_sent_by_reason_code |
| 143 | class: Errors |
| 144 | type: Messaging |
| 145 | component: VerneMQ |
| 146 | lookup: average -1m unaligned absolute of !normal_disconnect,* |
| 147 | units: packets |
| 148 | every: 1m |
| 149 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 150 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 151 | summary: Node ${label:node} sent not normal DISCONNECT |
| 152 | info: Node ${label:node} sent not normal v5 DISCONNECT packets in the last minute |
| 153 | to: sysadmin |
| 154 | |
| 155 | # SUBSCRIBE errors and unauthorized attempts |
| 156 | |
| 157 | template: vernemq_mqtt_subscribe_error |
| 158 | on: vernemq.node_mqtt_subscribe_error |
| 159 | class: Errors |
| 160 | type: Messaging |
| 161 | component: VerneMQ |
| 162 | lookup: average -1m unaligned absolute |
| 163 | units: failed ops |
| 164 | every: 1m |
| 165 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 166 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 167 | summary: Node ${label:node} mqtt v${label:mqtt_version} failed SUBSCRIBE |
| 168 | info: Node ${label:node} mqtt v${label:mqtt_version} failed SUBSCRIBE operations in the last minute |
| 169 | to: sysadmin |
| 170 | |
| 171 | template: vernemq_mqtt_subscribe_auth_error |
| 172 | on: vernemq.node_mqtt_subscribe_auth_error |
| 173 | class: Workload |
| 174 | type: Messaging |
| 175 | component: VerneMQ |
| 176 | lookup: average -1m unaligned absolute |
| 177 | units: attempts |
| 178 | every: 1m |
| 179 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 180 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 181 | summary: Node ${label:node} mqtt v${label:mqtt_version} unauthorized SUBSCRIBE |
| 182 | info: Node ${label:node} mqtt v${label:mqtt_version} unauthorized SUBSCRIBE attempts in the last minute |
| 183 | to: sysadmin |
| 184 | |
| 185 | # UNSUBSCRIBE errors |
| 186 | |
| 187 | template: vernemq_mqtt_unsubscribe_error |
| 188 | on: vernemq.node_mqtt_unsubscribe_error |
| 189 | class: Errors |
| 190 | type: Messaging |
| 191 | component: VerneMQ |
| 192 | lookup: average -1m unaligned absolute |
| 193 | units: failed ops |
| 194 | every: 1m |
| 195 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 196 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 197 | summary: Node ${label:node} mqtt v${label:mqtt_version} failed UNSUBSCRIBE |
| 198 | info: Node ${label:node} mqtt v${label:mqtt_version} failed UNSUBSCRIBE operations in the last minute |
| 199 | to: sysadmin |
| 200 | |
| 201 | # PUBLISH errors and unauthorized attempts |
| 202 | |
| 203 | template: vernemq_mqtt_publish_errors |
| 204 | on: vernemq.node_mqtt_publish_errors |
| 205 | class: Errors |
| 206 | type: Messaging |
| 207 | component: VerneMQ |
| 208 | lookup: average -1m unaligned absolute |
| 209 | units: failed ops |
| 210 | every: 1m |
| 211 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 212 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 213 | summary: Node ${label:node} mqtt v${label:mqtt_version} failed PUBLISH |
| 214 | info: Node ${label:node} mqtt v${label:mqtt_version} failed PUBLISH operations in the last minute |
| 215 | to: sysadmin |
| 216 | |
| 217 | template: vernemq_mqtt_publish_auth_errors |
| 218 | on: vernemq.node_mqtt_publish_auth_errors |
| 219 | class: Workload |
| 220 | type: Messaging |
| 221 | component: VerneMQ |
| 222 | lookup: average -1m unaligned absolute |
| 223 | units: attempts |
| 224 | every: 1m |
| 225 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 226 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 227 | summary: Node ${label:node} mqtt v${label:mqtt_version} unauthorized PUBLISH |
| 228 | info: Node ${label:node} mqtt v${label:mqtt_version} unauthorized PUBLISH attempts in the last minute |
| 229 | to: sysadmin |
| 230 | |
| 231 | # Unsuccessful and unexpected PUBACK |
| 232 | |
| 233 | template: vernemq_mqtt_puback_received_reason_unsuccessful |
| 234 | on: vernemq.node_mqtt_puback_received_by_reason_code |
| 235 | class: Errors |
| 236 | type: Messaging |
| 237 | component: VerneMQ |
| 238 | lookup: average -1m unaligned absolute of !success,* |
| 239 | units: packets |
| 240 | every: 1m |
| 241 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 242 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 243 | summary: Node ${label:node} mqtt v5 received unsuccessful PUBACK |
| 244 | info: Node ${label:node} mqtt v5 received unsuccessful PUBACK packets in the last minute |
| 245 | to: sysadmin |
| 246 | |
| 247 | template: vernemq_mqtt_puback_sent_reason_unsuccessful |
| 248 | on: vernemq.node_mqtt_puback_sent_by_reason_code |
| 249 | class: Errors |
| 250 | type: Messaging |
| 251 | component: VerneMQ |
| 252 | lookup: average -1m unaligned absolute of !success,* |
| 253 | units: packets |
| 254 | every: 1m |
| 255 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 256 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 257 | summary: Node ${label:node} mqtt v5 unsuccessful sent PUBACK |
| 258 | info: Node ${label:node} mqtt v5 unsuccessful sent PUBACK packets in the last minute |
| 259 | to: sysadmin |
| 260 | |
| 261 | template: vernemq_mqtt_puback_unexpected |
| 262 | on: vernemq.node_mqtt_puback_invalid_error |
| 263 | class: Workload |
| 264 | type: Messaging |
| 265 | component: VerneMQ |
| 266 | lookup: average -1m unaligned absolute |
| 267 | units: messages |
| 268 | every: 1m |
| 269 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 270 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 271 | summary: Node ${label:node} mqtt v${label:mqtt_version} recieved unnexpected PUBACK |
| 272 | info: Node ${label:node} mqtt v${label:mqtt_version} received unexpected PUBACK messages in the last minute |
| 273 | to: sysadmin |
| 274 | |
| 275 | # Unsuccessful and unexpected PUBREC |
| 276 | |
| 277 | template: vernemq_mqtt_pubrec_received_reason_unsuccessful |
| 278 | on: vernemq.node_mqtt_pubrec_received_by_reason_code |
| 279 | class: Errors |
| 280 | type: Messaging |
| 281 | component: VerneMQ |
| 282 | lookup: average -1m unaligned absolute of !success,* |
| 283 | units: packets |
| 284 | every: 1m |
| 285 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 286 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 287 | summary: Node ${label:node} mqtt v5 received unsuccessful PUBREC |
| 288 | info: Node ${label:node} mqtt v5 received unsuccessful PUBREC packets in the last minute |
| 289 | to: sysadmin |
| 290 | |
| 291 | template: vernemq_mqtt_pubrec_sent_reason_unsuccessful |
| 292 | on: vernemq.node_mqtt_pubrec_sent_by_reason_code |
| 293 | class: Errors |
| 294 | type: Messaging |
| 295 | component: VerneMQ |
| 296 | lookup: average -1m unaligned absolute of !success,* |
| 297 | units: packets |
| 298 | every: 1m |
| 299 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 300 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 301 | summary: Node ${label:node} mqtt v5 unsuccessful sent PUBREC |
| 302 | info: Node ${label:node} mqtt v5 unsuccessful sent PUBREC packets in the last minute |
| 303 | to: sysadmin |
| 304 | |
| 305 | template: vernemq_mqtt_pubrec_invalid_error |
| 306 | on: vernemq.node_mqtt_pubrec_invalid_error |
| 307 | class: Workload |
| 308 | type: Messaging |
| 309 | component: VerneMQ |
| 310 | lookup: average -1m unaligned absolute |
| 311 | units: messages |
| 312 | every: 1m |
| 313 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 314 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 315 | summary: Node ${label:node} mqtt v${label:mqtt_version} received invalid PUBREC |
| 316 | info: Node ${label:node} mqtt v${label:mqtt_version} received invalid PUBREC packets in the last minute |
| 317 | to: sysadmin |
| 318 | |
| 319 | # Unsuccessful PUBREL |
| 320 | |
| 321 | template: vernemq_mqtt_pubrel_received_reason_unsuccessful |
| 322 | on: vernemq.node_mqtt_pubrel_received_by_reason_code |
| 323 | class: Errors |
| 324 | type: Messaging |
| 325 | component: VerneMQ |
| 326 | lookup: average -1m unaligned absolute of !success,* |
| 327 | units: packets |
| 328 | every: 1m |
| 329 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 330 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 331 | summary: Node ${label:node} mqtt v5 received unsuccessful PUBREL |
| 332 | info: Node ${label:node} mqtt v5 received unsuccessful PUBREL packets in the last minute |
| 333 | to: sysadmin |
| 334 | |
| 335 | template: vernemq_mqtt_pubrel_sent_reason_unsuccessful |
| 336 | on: vernemq.node_mqtt_pubrel_sent_by_reason_code |
| 337 | class: Errors |
| 338 | type: Messaging |
| 339 | component: VerneMQ |
| 340 | lookup: average -1m unaligned absolute of !success,* |
| 341 | units: packets |
| 342 | every: 1m |
| 343 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 344 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 345 | summary: Node ${label:node} mqtt v5 unsuccessful sent PUBREL |
| 346 | info: Node ${label:node} mqtt v5 unsuccessful sent PUBREL packets in the last minute |
| 347 | to: sysadmin |
| 348 | |
| 349 | # Unsuccessful and unexpected PUBCOMP |
| 350 | |
| 351 | template: vernemq_mqtt_pubcomp_received_reason_unsuccessful |
| 352 | on: vernemq.node_mqtt_pubcomp_received_by_reason_code |
| 353 | class: Errors |
| 354 | type: Messaging |
| 355 | component: VerneMQ |
| 356 | lookup: average -1m unaligned absolute of !success,* |
| 357 | units: packets |
| 358 | every: 1m |
| 359 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 360 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 361 | summary: Node ${label:node} mqtt v5 received unsuccessful PUBCOMP |
| 362 | info: Node ${label:node} mqtt v5 received unsuccessful PUBCOMP packets in the last minute |
| 363 | to: sysadmin |
| 364 | |
| 365 | template: vernemq_mqtt_pubcomp_sent_reason_unsuccessful |
| 366 | on: vernemq.node_mqtt_pubcomp_sent_by_reason_code |
| 367 | class: Errors |
| 368 | type: Messaging |
| 369 | component: VerneMQ |
| 370 | lookup: average -1m unaligned absolute of !success,* |
| 371 | units: packets |
| 372 | every: 1m |
| 373 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 374 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 375 | summary: Node ${label:node} mqtt v5 unsuccessful sent PUBCOMP |
| 376 | info: Node ${label:node} mqtt v5 unsuccessful sent PUBCOMP packets in the last minute |
| 377 | to: sysadmin |
| 378 | |
| 379 | template: vernemq_mqtt_pubcomp_unexpected |
| 380 | on: vernemq.node_mqtt_pubcomp_invalid_error |
| 381 | class: Workload |
| 382 | type: Messaging |
| 383 | component: VerneMQ |
| 384 | lookup: average -1m unaligned absolute |
| 385 | units: messages |
| 386 | every: 1m |
| 387 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 388 | delay: up 2m down 5m multiplier 1.5 max 2h |
| 389 | summary: Node ${label:node} mqtt v${label:mqtt_version} received unexpected PUBCOMP |
| 390 | info: Node ${label:node} mqtt v${label:mqtt_version} received unexpected PUBCOMP packets in the last minute |
| 391 | to: sysadmin |