| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | # --- Pipeline Runs --- |
| 4 | |
| 5 | template: am_data_factory_pipeline_failed_runs |
| 6 | on: azure_monitor.data_factory.pipeline_runs |
| 7 | class: Errors |
| 8 | type: Other |
| 9 | component: Azure Data Factory |
| 10 | lookup: sum -5m unaligned of failed |
| 11 | units: runs |
| 12 | every: 1m |
| 13 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 14 | delay: down 5m multiplier 1.5 max 1h |
| 15 | summary: Data Factory pipeline failures on ${label:resource_name} |
| 16 | info: Failed pipeline runs on Data Factory ${label:resource_name} \ |
| 17 | in ${label:resource_group} (${label:region}) over the last 5 minutes |
| 18 | to: sysadmin |
| 19 | |
| 20 | template: am_data_factory_pipeline_cancelled_runs |
| 21 | on: azure_monitor.data_factory.pipeline_runs |
| 22 | class: Errors |
| 23 | type: Other |
| 24 | component: Azure Data Factory |
| 25 | lookup: sum -10m unaligned of cancelled |
| 26 | units: runs |
| 27 | every: 1m |
| 28 | warn: $this > (($status >= $WARNING) ? (5) : (10)) |
| 29 | delay: down 5m multiplier 1.5 max 1h |
| 30 | summary: Data Factory pipeline cancellations on ${label:resource_name} |
| 31 | info: Cancelled pipeline runs on Data Factory ${label:resource_name} \ |
| 32 | in ${label:resource_group} (${label:region}) over the last 10 minutes. \ |
| 33 | Frequent cancellations may indicate configuration or dependency issues |
| 34 | to: sysadmin |
| 35 | |
| 36 | # --- Activity Runs --- |
| 37 | |
| 38 | template: am_data_factory_activity_failed_runs |
| 39 | on: azure_monitor.data_factory.activity_runs |
| 40 | class: Errors |
| 41 | type: Other |
| 42 | component: Azure Data Factory |
| 43 | lookup: sum -5m unaligned of failed |
| 44 | units: runs |
| 45 | every: 1m |
| 46 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 47 | delay: down 5m multiplier 1.5 max 1h |
| 48 | summary: Data Factory activity failures on ${label:resource_name} |
| 49 | info: Failed activity runs on Data Factory ${label:resource_name} \ |
| 50 | in ${label:resource_group} (${label:region}) over the last 5 minutes |
| 51 | to: sysadmin |
| 52 | |
| 53 | # --- Trigger Runs --- |
| 54 | |
| 55 | template: am_data_factory_trigger_failed_runs |
| 56 | on: azure_monitor.data_factory.trigger_runs |
| 57 | class: Errors |
| 58 | type: Other |
| 59 | component: Azure Data Factory |
| 60 | lookup: sum -5m unaligned of failed |
| 61 | units: runs |
| 62 | every: 1m |
| 63 | warn: $this > (($status >= $WARNING) ? (0) : (5)) |
| 64 | delay: down 5m multiplier 1.5 max 1h |
| 65 | summary: Data Factory trigger failures on ${label:resource_name} |
| 66 | info: Failed trigger runs on Data Factory ${label:resource_name} \ |
| 67 | in ${label:resource_group} (${label:region}) over the last 5 minutes |
| 68 | to: sysadmin |
| 69 | |
| 70 | # --- SSIS Integration Runtime --- |
| 71 | |
| 72 | template: am_data_factory_ssis_ir_start_failures |
| 73 | on: azure_monitor.data_factory.ssis_ir_starts |
| 74 | class: Errors |
| 75 | type: Other |
| 76 | component: Azure Data Factory |
| 77 | lookup: sum -5m unaligned of failed |
| 78 | units: runs |
| 79 | every: 1m |
| 80 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (1)) |
| 81 | delay: down 5m multiplier 1.5 max 1h |
| 82 | summary: Data Factory SSIS IR start failures on ${label:resource_name} |
| 83 | info: Failed SSIS Integration Runtime start operations on Data Factory \ |
| 84 | ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 85 | to: sysadmin |
| 86 | |
| 87 | template: am_data_factory_ssis_ir_stop_stuck |
| 88 | on: azure_monitor.data_factory.ssis_ir_stops |
| 89 | class: Errors |
| 90 | type: Other |
| 91 | component: Azure Data Factory |
| 92 | lookup: sum -5m unaligned of stuck |
| 93 | units: runs |
| 94 | every: 1m |
| 95 | warn: $this != nan AND $this > 0 |
| 96 | delay: down 5m multiplier 1.5 max 1h |
| 97 | summary: Data Factory SSIS IR stuck stops on ${label:resource_name} |
| 98 | info: SSIS Integration Runtime stop operations stuck on Data Factory \ |
| 99 | ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 100 | to: sysadmin |
| 101 | |
| 102 | template: am_data_factory_ssis_package_failures |
| 103 | on: azure_monitor.data_factory.ssis_package_executions |
| 104 | class: Errors |
| 105 | type: Other |
| 106 | component: Azure Data Factory |
| 107 | lookup: sum -5m unaligned of failed |
| 108 | units: executions |
| 109 | every: 1m |
| 110 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (1)) |
| 111 | delay: down 5m multiplier 1.5 max 1h |
| 112 | summary: Data Factory SSIS package failures on ${label:resource_name} |
| 113 | info: Failed SSIS package executions on Data Factory ${label:resource_name} \ |
| 114 | in ${label:resource_group} (${label:region}) |
| 115 | to: sysadmin |
| 116 | |
| 117 | # --- Integration Runtime Resources --- |
| 118 | |
| 119 | template: am_data_factory_ir_cpu |
| 120 | on: azure_monitor.data_factory.ir_cpu |
| 121 | class: Utilization |
| 122 | type: Other |
| 123 | component: Azure Data Factory |
| 124 | lookup: average -5m unaligned of average |
| 125 | units: percentage |
| 126 | every: 1m |
| 127 | warn: $this > (($status >= $WARNING) ? (75) : (85)) |
| 128 | crit: $this > (($status == $CRITICAL) ? (85) : (95)) |
| 129 | delay: down 5m multiplier 1.5 max 1h |
| 130 | summary: Data Factory IR CPU on ${label:resource_name} |
| 131 | info: Integration Runtime CPU utilization on Data Factory ${label:resource_name} \ |
| 132 | in ${label:resource_group} (${label:region}) |
| 133 | to: sysadmin |
| 134 | |
| 135 | template: am_data_factory_ir_queue_length |
| 136 | on: azure_monitor.data_factory.ir_queue |
| 137 | class: Workload |
| 138 | type: Other |
| 139 | component: Azure Data Factory |
| 140 | lookup: average -5m unaligned of queue_length |
| 141 | units: tasks |
| 142 | every: 1m |
| 143 | warn: $this > (($status >= $WARNING) ? (10) : (20)) |
| 144 | crit: $this > (($status == $CRITICAL) ? (20) : (50)) |
| 145 | delay: down 5m multiplier 1.5 max 1h |
| 146 | summary: Data Factory IR queue depth on ${label:resource_name} |
| 147 | info: Integration Runtime queue length on Data Factory ${label:resource_name} \ |
| 148 | in ${label:resource_group} (${label:region}). \ |
| 149 | Growing queues indicate the runtime cannot keep up with submitted work |
| 150 | to: sysadmin |
| 151 | |
| 152 | template: am_data_factory_ir_task_pickup_delay |
| 153 | on: azure_monitor.data_factory.ir_task_pickup_delay |
| 154 | class: Latency |
| 155 | type: Other |
| 156 | component: Azure Data Factory |
| 157 | lookup: average -5m unaligned of average |
| 158 | units: seconds |
| 159 | every: 1m |
| 160 | warn: $this > (($status >= $WARNING) ? (30) : (60)) |
| 161 | crit: $this > (($status == $CRITICAL) ? (60) : (120)) |
| 162 | delay: down 5m multiplier 1.5 max 1h |
| 163 | summary: Data Factory IR task pickup delay on ${label:resource_name} |
| 164 | info: Average task pickup delay for Integration Runtime on Data Factory \ |
| 165 | ${label:resource_name} in ${label:resource_group} (${label:region}). \ |
| 166 | High delay indicates insufficient runtime capacity |
| 167 | to: sysadmin |
| 168 | |
| 169 | # --- Factory Capacity --- |
| 170 | |
| 171 | template: am_data_factory_size_utilization |
| 172 | on: azure_monitor.data_factory.factory_size |
| 173 | class: Utilization |
| 174 | type: Other |
| 175 | component: Azure Data Factory |
| 176 | calc: ($max_allowed > 0) ? ($current * 100 / $max_allowed) : (0) |
| 177 | units: % |
| 178 | every: 5m |
| 179 | warn: $this > (($status >= $WARNING) ? (70) : (80)) |
| 180 | crit: $this > (($status == $CRITICAL) ? (80) : (90)) |
| 181 | delay: down 5m multiplier 1.5 max 1h |
| 182 | summary: Data Factory size utilization on ${label:resource_name} |
| 183 | info: Factory size as percentage of maximum allowed on Data Factory \ |
| 184 | ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 185 | to: sysadmin |
| 186 | |
| 187 | template: am_data_factory_entity_utilization |
| 188 | on: azure_monitor.data_factory.entity_count |
| 189 | class: Utilization |
| 190 | type: Other |
| 191 | component: Azure Data Factory |
| 192 | calc: ($max_allowed > 0) ? ($current * 100 / $max_allowed) : (0) |
| 193 | units: % |
| 194 | every: 5m |
| 195 | warn: $this > (($status >= $WARNING) ? (70) : (80)) |
| 196 | crit: $this > (($status == $CRITICAL) ? (80) : (90)) |
| 197 | delay: down 5m multiplier 1.5 max 1h |
| 198 | summary: Data Factory entity count on ${label:resource_name} |
| 199 | info: Entity count (pipelines, datasets, etc.) as percentage of maximum allowed \ |
| 200 | on Data Factory ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 201 | to: sysadmin |
| 202 | |
| 203 | # --- MVNet IR Capacity --- |
| 204 | |
| 205 | template: am_data_factory_mvnet_ir_copy_utilization |
| 206 | on: azure_monitor.data_factory.mvnet_ir_copy_capacity |
| 207 | class: Utilization |
| 208 | type: Other |
| 209 | component: Azure Data Factory |
| 210 | lookup: average -5m unaligned of utilization |
| 211 | units: percentage |
| 212 | every: 1m |
| 213 | warn: $this != nan AND $this > (($status >= $WARNING) ? (70) : (80)) |
| 214 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (80) : (90)) |
| 215 | delay: down 5m multiplier 1.5 max 1h |
| 216 | summary: Data Factory MVNet IR copy utilization on ${label:resource_name} |
| 217 | info: Managed VNet Integration Runtime copy capacity utilization on Data Factory \ |
| 218 | ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 219 | to: sysadmin |
| 220 | |
| 221 | template: am_data_factory_mvnet_ir_external_utilization |
| 222 | on: azure_monitor.data_factory.mvnet_ir_external_capacity |
| 223 | class: Utilization |
| 224 | type: Other |
| 225 | component: Azure Data Factory |
| 226 | lookup: average -5m unaligned of utilization |
| 227 | units: percentage |
| 228 | every: 1m |
| 229 | warn: $this != nan AND $this > (($status >= $WARNING) ? (70) : (80)) |
| 230 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (80) : (90)) |
| 231 | delay: down 5m multiplier 1.5 max 1h |
| 232 | summary: Data Factory MVNet IR external utilization on ${label:resource_name} |
| 233 | info: Managed VNet Integration Runtime external activity capacity utilization \ |
| 234 | on Data Factory ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 235 | to: sysadmin |
| 236 | |
| 237 | template: am_data_factory_mvnet_ir_pipeline_utilization |
| 238 | on: azure_monitor.data_factory.mvnet_ir_pipeline_capacity |
| 239 | class: Utilization |
| 240 | type: Other |
| 241 | component: Azure Data Factory |
| 242 | lookup: average -5m unaligned of utilization |
| 243 | units: percentage |
| 244 | every: 1m |
| 245 | warn: $this != nan AND $this > (($status >= $WARNING) ? (70) : (80)) |
| 246 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (80) : (90)) |
| 247 | delay: down 5m multiplier 1.5 max 1h |
| 248 | summary: Data Factory MVNet IR pipeline utilization on ${label:resource_name} |
| 249 | info: Managed VNet Integration Runtime pipeline capacity utilization \ |
| 250 | on Data Factory ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 251 | to: sysadmin |
| 252 | |
| 253 | # --- Airflow IR Resources --- |
| 254 | |
| 255 | template: am_data_factory_airflow_ir_cpu |
| 256 | on: azure_monitor.data_factory.airflow_ir_cpu |
| 257 | class: Utilization |
| 258 | type: Other |
| 259 | component: Azure Data Factory |
| 260 | lookup: average -5m unaligned of percentage |
| 261 | units: percentage |
| 262 | every: 1m |
| 263 | warn: $this != nan AND $this > (($status >= $WARNING) ? (75) : (85)) |
| 264 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (85) : (95)) |
| 265 | delay: down 5m multiplier 1.5 max 1h |
| 266 | summary: Data Factory Airflow IR CPU on ${label:resource_name} |
| 267 | info: Airflow Integration Runtime CPU utilization on Data Factory \ |
| 268 | ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 269 | to: sysadmin |
| 270 | |
| 271 | template: am_data_factory_airflow_ir_memory |
| 272 | on: azure_monitor.data_factory.airflow_ir_memory |
| 273 | class: Utilization |
| 274 | type: Other |
| 275 | component: Azure Data Factory |
| 276 | lookup: average -5m unaligned of percentage |
| 277 | units: percentage |
| 278 | every: 1m |
| 279 | warn: $this != nan AND $this > (($status >= $WARNING) ? (75) : (85)) |
| 280 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (85) : (95)) |
| 281 | delay: down 5m multiplier 1.5 max 1h |
| 282 | summary: Data Factory Airflow IR memory on ${label:resource_name} |
| 283 | info: Airflow Integration Runtime memory utilization on Data Factory \ |
| 284 | ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 285 | to: sysadmin |
| 286 | |
| 287 | # --- Airflow IR DAG Errors --- |
| 288 | |
| 289 | template: am_data_factory_airflow_ir_dag_errors |
| 290 | on: azure_monitor.data_factory.airflow_ir_dag_errors |
| 291 | class: Errors |
| 292 | type: Other |
| 293 | component: Azure Data Factory |
| 294 | lookup: sum -5m unaligned of callback_exceptions,file_refresh,import |
| 295 | units: errors |
| 296 | every: 1m |
| 297 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (5)) |
| 298 | delay: down 5m multiplier 1.5 max 1h |
| 299 | summary: Data Factory Airflow DAG errors on ${label:resource_name} |
| 300 | info: DAG processing errors (callback exceptions, file refresh errors, import errors) \ |
| 301 | on Airflow IR of Data Factory ${label:resource_name} \ |
| 302 | in ${label:resource_group} (${label:region}) |
| 303 | to: sysadmin |
| 304 | |
| 305 | # --- Airflow IR Operators --- |
| 306 | |
| 307 | template: am_data_factory_airflow_ir_operator_failures |
| 308 | on: azure_monitor.data_factory.airflow_ir_operators |
| 309 | class: Errors |
| 310 | type: Other |
| 311 | component: Azure Data Factory |
| 312 | lookup: sum -5m unaligned of failures |
| 313 | units: operations |
| 314 | every: 1m |
| 315 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (5)) |
| 316 | delay: down 5m multiplier 1.5 max 1h |
| 317 | summary: Data Factory Airflow operator failures on ${label:resource_name} |
| 318 | info: Failed Airflow operator executions on Data Factory ${label:resource_name} \ |
| 319 | in ${label:resource_group} (${label:region}) |
| 320 | to: sysadmin |
| 321 | |
| 322 | # --- Airflow IR Jobs --- |
| 323 | |
| 324 | template: am_data_factory_airflow_ir_job_heartbeat_failures |
| 325 | on: azure_monitor.data_factory.airflow_ir_jobs |
| 326 | class: Errors |
| 327 | type: Other |
| 328 | component: Azure Data Factory |
| 329 | lookup: sum -5m unaligned of heartbeat_failures |
| 330 | units: failures |
| 331 | every: 1m |
| 332 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (1)) |
| 333 | delay: down 5m multiplier 1.5 max 1h |
| 334 | summary: Data Factory Airflow job heartbeat failures on ${label:resource_name} |
| 335 | info: Airflow job heartbeat failures on Data Factory ${label:resource_name} \ |
| 336 | in ${label:resource_group} (${label:region}). \ |
| 337 | Heartbeat failures indicate scheduler or worker health issues |
| 338 | to: sysadmin |
| 339 | |
| 340 | # --- Airflow IR Pool Starvation --- |
| 341 | |
| 342 | template: am_data_factory_airflow_ir_pool_starving |
| 343 | on: azure_monitor.data_factory.airflow_ir_pool_starving |
| 344 | class: Workload |
| 345 | type: Other |
| 346 | component: Azure Data Factory |
| 347 | lookup: sum -5m unaligned of starving |
| 348 | units: tasks |
| 349 | every: 1m |
| 350 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (5)) |
| 351 | delay: down 5m multiplier 1.5 max 1h |
| 352 | summary: Data Factory Airflow pool starvation on ${label:resource_name} |
| 353 | info: Starving tasks in Airflow pool on Data Factory ${label:resource_name} \ |
| 354 | in ${label:resource_group} (${label:region}). \ |
| 355 | Tasks are waiting for pool slots, consider increasing pool size |
| 356 | to: sysadmin |
| 357 | |
| 358 | # --- Airflow IR Scheduler Tasks --- |
| 359 | |
| 360 | template: am_data_factory_airflow_ir_tasks_killed_externally |
| 361 | on: azure_monitor.data_factory.airflow_ir_scheduler_tasks |
| 362 | class: Errors |
| 363 | type: Other |
| 364 | component: Azure Data Factory |
| 365 | lookup: sum -5m unaligned of killed_externally |
| 366 | units: tasks |
| 367 | every: 1m |
| 368 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (3)) |
| 369 | delay: down 5m multiplier 1.5 max 1h |
| 370 | summary: Data Factory Airflow tasks killed externally on ${label:resource_name} |
| 371 | info: Tasks killed externally by the Airflow scheduler on Data Factory \ |
| 372 | ${label:resource_name} in ${label:resource_group} (${label:region}). \ |
| 373 | May indicate OOM kills or infrastructure issues |
| 374 | to: sysadmin |
| 375 | |
| 376 | template: am_data_factory_airflow_ir_tasks_starving |
| 377 | on: azure_monitor.data_factory.airflow_ir_scheduler_tasks |
| 378 | class: Workload |
| 379 | type: Other |
| 380 | component: Azure Data Factory |
| 381 | lookup: sum -5m unaligned of starving |
| 382 | units: tasks |
| 383 | every: 1m |
| 384 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (10)) |
| 385 | delay: down 5m multiplier 1.5 max 1h |
| 386 | summary: Data Factory Airflow scheduler starving tasks on ${label:resource_name} |
| 387 | info: Starving tasks reported by Airflow scheduler on Data Factory \ |
| 388 | ${label:resource_name} in ${label:resource_group} (${label:region}). \ |
| 389 | Tasks cannot be scheduled due to resource constraints |
| 390 | to: sysadmin |
| 391 | |
| 392 | # --- Airflow IR Task Instances --- |
| 393 | |
| 394 | template: am_data_factory_airflow_ir_task_instance_failures |
| 395 | on: azure_monitor.data_factory.airflow_ir_task_instances |
| 396 | class: Errors |
| 397 | type: Other |
| 398 | component: Azure Data Factory |
| 399 | lookup: sum -5m unaligned of failed |
| 400 | units: instances |
| 401 | every: 1m |
| 402 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (5)) |
| 403 | delay: down 5m multiplier 1.5 max 1h |
| 404 | summary: Data Factory Airflow task failures on ${label:resource_name} |
| 405 | info: Failed Airflow task instances on Data Factory ${label:resource_name} \ |
| 406 | in ${label:resource_group} (${label:region}) |
| 407 | to: sysadmin |
| 408 | |
| 409 | # --- Airflow IR Trigger Issues --- |
| 410 | |
| 411 | template: am_data_factory_airflow_ir_trigger_issues |
| 412 | on: azure_monitor.data_factory.airflow_ir_trigger_issues |
| 413 | class: Errors |
| 414 | type: Other |
| 415 | component: Azure Data Factory |
| 416 | lookup: sum -5m unaligned of blocked_main_thread,celery_timeout_errors |
| 417 | units: events |
| 418 | every: 1m |
| 419 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (3)) |
| 420 | delay: down 5m multiplier 1.5 max 1h |
| 421 | summary: Data Factory Airflow trigger issues on ${label:resource_name} |
| 422 | info: Trigger issues (blocked main thread, Celery timeouts) on Airflow IR \ |
| 423 | of Data Factory ${label:resource_name} in ${label:resource_group} (${label:region}) |
| 424 | to: sysadmin |
| 425 | |
| 426 | # --- Airflow IR Zombies --- |
| 427 | |
| 428 | template: am_data_factory_airflow_ir_zombies |
| 429 | on: azure_monitor.data_factory.airflow_ir_zombies |
| 430 | class: Errors |
| 431 | type: Other |
| 432 | component: Azure Data Factory |
| 433 | lookup: sum -5m unaligned of killed |
| 434 | units: tasks |
| 435 | every: 1m |
| 436 | warn: $this != nan AND $this > (($status >= $WARNING) ? (0) : (3)) |
| 437 | delay: down 5m multiplier 1.5 max 1h |
| 438 | summary: Data Factory Airflow zombie tasks on ${label:resource_name} |
| 439 | info: Zombie tasks killed by Airflow on Data Factory ${label:resource_name} \ |
| 440 | in ${label:resource_group} (${label:region}). \ |
| 441 | Zombies occur when tasks are marked running but no process is executing them |
| 442 | to: sysadmin |