| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | # --- CPU --- |
| 4 | |
| 5 | template: am_vm_cpu |
| 6 | on: azure_monitor.virtual_machines.cpu |
| 7 | class: Utilization |
| 8 | type: System |
| 9 | component: Azure VM |
| 10 | lookup: average -5m unaligned of average |
| 11 | units: percentage |
| 12 | every: 1m |
| 13 | warn: $this > (($status >= $WARNING) ? (85) : (90)) |
| 14 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 15 | delay: down 5m multiplier 1.5 max 1h |
| 16 | summary: VM CPU on ${label:resource_name} |
| 17 | info: Average CPU utilization on Azure VM ${label:resource_name} \ |
| 18 | in ${label:resource_group} (${label:region}) |
| 19 | to: sysadmin |
| 20 | |
| 21 | # CPU credits are only available on burstable B-series VMs. |
| 22 | # NaN guard: remaining is NaN on non-burstable VM sizes. |
| 23 | |
| 24 | template: am_vm_cpu_credits_remaining |
| 25 | on: azure_monitor.virtual_machines.cpu_credits |
| 26 | class: Utilization |
| 27 | type: System |
| 28 | component: Azure VM |
| 29 | lookup: average -5m unaligned of remaining |
| 30 | units: credits |
| 31 | every: 1m |
| 32 | warn: $this != nan AND $this < (($status >= $WARNING) ? (30) : (20)) |
| 33 | crit: $this != nan AND $this < (($status == $CRITICAL) ? (20) : (10)) |
| 34 | delay: down 5m multiplier 1.5 max 1h |
| 35 | summary: VM CPU credits low on ${label:resource_name} |
| 36 | info: CPU credits remaining on burstable Azure VM ${label:resource_name} \ |
| 37 | in ${label:resource_group} (${label:region}). \ |
| 38 | When credits are exhausted, CPU performance is capped. |
| 39 | to: sysadmin |
| 40 | |
| 41 | # --- Memory --- |
| 42 | # Available Memory Percentage: low is bad. |
| 43 | |
| 44 | template: am_vm_memory_available |
| 45 | on: azure_monitor.virtual_machines.memory_percentage |
| 46 | class: Utilization |
| 47 | type: System |
| 48 | component: Azure VM |
| 49 | lookup: average -5m unaligned of available |
| 50 | units: percentage |
| 51 | every: 1m |
| 52 | warn: $this < (($status >= $WARNING) ? (15) : (10)) |
| 53 | crit: $this < (($status == $CRITICAL) ? (10) : (5)) |
| 54 | delay: down 5m multiplier 1.5 max 1h |
| 55 | summary: VM available memory on ${label:resource_name} |
| 56 | info: Available memory percentage on Azure VM ${label:resource_name} \ |
| 57 | in ${label:resource_group} (${label:region}) |
| 58 | to: sysadmin |
| 59 | |
| 60 | # --- Availability --- |
| 61 | # VmAvailabilityMetric: 1 = available, < 1 = degraded/unavailable. |
| 62 | |
| 63 | template: am_vm_availability |
| 64 | on: azure_monitor.virtual_machines.availability |
| 65 | class: Availability |
| 66 | type: System |
| 67 | component: Azure VM |
| 68 | lookup: average -5m unaligned of average |
| 69 | units: state |
| 70 | every: 1m |
| 71 | crit: $this < 1 |
| 72 | delay: down 5m multiplier 1.5 max 1h |
| 73 | summary: VM unavailable ${label:resource_name} |
| 74 | info: Azure VM ${label:resource_name} in ${label:resource_group} (${label:region}) \ |
| 75 | is reporting degraded or unavailable state |
| 76 | to: sysadmin |
| 77 | |
| 78 | # --- OS Disk Latency --- |
| 79 | |
| 80 | template: am_vm_os_disk_latency |
| 81 | on: azure_monitor.virtual_machines.os_disk_latency |
| 82 | class: Latency |
| 83 | type: System |
| 84 | component: Azure VM |
| 85 | lookup: average -5m unaligned of average |
| 86 | units: milliseconds |
| 87 | every: 1m |
| 88 | warn: $this > (($status >= $WARNING) ? (30) : (50)) |
| 89 | crit: $this > (($status == $CRITICAL) ? (50) : (100)) |
| 90 | delay: down 5m multiplier 1.5 max 1h |
| 91 | summary: VM OS disk latency on ${label:resource_name} |
| 92 | info: Average OS disk latency on Azure VM ${label:resource_name} \ |
| 93 | in ${label:resource_group} (${label:region}). \ |
| 94 | High latency indicates disk I/O bottleneck. |
| 95 | to: sysadmin |
| 96 | |
| 97 | # --- OS Disk Queue Depth --- |
| 98 | |
| 99 | template: am_vm_os_disk_queue_depth |
| 100 | on: azure_monitor.virtual_machines.os_disk_queue_depth |
| 101 | class: Utilization |
| 102 | type: System |
| 103 | component: Azure VM |
| 104 | lookup: average -5m unaligned of average |
| 105 | units: operations |
| 106 | every: 1m |
| 107 | warn: $this > (($status >= $WARNING) ? (16) : (32)) |
| 108 | crit: $this > (($status == $CRITICAL) ? (32) : (64)) |
| 109 | delay: down 5m multiplier 1.5 max 1h |
| 110 | summary: VM OS disk queue depth on ${label:resource_name} |
| 111 | info: Average OS disk queue depth on Azure VM ${label:resource_name} \ |
| 112 | in ${label:resource_group} (${label:region}). \ |
| 113 | High queue depth indicates I/O saturation. |
| 114 | to: sysadmin |
| 115 | |
| 116 | # --- OS Disk Throttling --- |
| 117 | # Bandwidth and IOPS consumed percentage. High values mean the disk |
| 118 | # is approaching its provisioned performance limit and may be throttled. |
| 119 | |
| 120 | template: am_vm_os_disk_bandwidth_throttling |
| 121 | on: azure_monitor.virtual_machines.os_disk_throttling |
| 122 | class: Utilization |
| 123 | type: System |
| 124 | component: Azure VM |
| 125 | lookup: average -5m unaligned of bandwidth |
| 126 | units: percentage |
| 127 | every: 1m |
| 128 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 129 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 130 | delay: down 5m multiplier 1.5 max 1h |
| 131 | summary: VM OS disk bandwidth throttling on ${label:resource_name} |
| 132 | info: OS disk bandwidth consumed percentage on Azure VM ${label:resource_name} \ |
| 133 | in ${label:resource_group} (${label:region}). \ |
| 134 | Approaching the provisioned bandwidth limit causes throttling. |
| 135 | to: sysadmin |
| 136 | |
| 137 | template: am_vm_os_disk_iops_throttling |
| 138 | on: azure_monitor.virtual_machines.os_disk_throttling |
| 139 | class: Utilization |
| 140 | type: System |
| 141 | component: Azure VM |
| 142 | lookup: average -5m unaligned of iops |
| 143 | units: percentage |
| 144 | every: 1m |
| 145 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 146 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 147 | delay: down 5m multiplier 1.5 max 1h |
| 148 | summary: VM OS disk IOPS throttling on ${label:resource_name} |
| 149 | info: OS disk IOPS consumed percentage on Azure VM ${label:resource_name} \ |
| 150 | in ${label:resource_group} (${label:region}). \ |
| 151 | Approaching the provisioned IOPS limit causes throttling. |
| 152 | to: sysadmin |
| 153 | |
| 154 | # --- OS Disk Burst Credits --- |
| 155 | # Burst credit usage: high means credits are being depleted. |
| 156 | # NaN guard: burst credits are only available on eligible disk tiers. |
| 157 | |
| 158 | template: am_vm_os_disk_burst_bps_credits |
| 159 | on: azure_monitor.virtual_machines.os_disk_burst_credits |
| 160 | class: Utilization |
| 161 | type: System |
| 162 | component: Azure VM |
| 163 | lookup: average -5m unaligned of bandwidth |
| 164 | units: percentage |
| 165 | every: 1m |
| 166 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 167 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 168 | delay: down 5m multiplier 1.5 max 1h |
| 169 | summary: VM OS disk burst bandwidth credits on ${label:resource_name} |
| 170 | info: OS disk burst bandwidth credits consumed on Azure VM ${label:resource_name} \ |
| 171 | in ${label:resource_group} (${label:region}). \ |
| 172 | When credits are exhausted, disk throughput drops to baseline. |
| 173 | to: sysadmin |
| 174 | |
| 175 | template: am_vm_os_disk_burst_io_credits |
| 176 | on: azure_monitor.virtual_machines.os_disk_burst_credits |
| 177 | class: Utilization |
| 178 | type: System |
| 179 | component: Azure VM |
| 180 | lookup: average -5m unaligned of io |
| 181 | units: percentage |
| 182 | every: 1m |
| 183 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 184 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 185 | delay: down 5m multiplier 1.5 max 1h |
| 186 | summary: VM OS disk burst IO credits on ${label:resource_name} |
| 187 | info: OS disk burst IO credits consumed on Azure VM ${label:resource_name} \ |
| 188 | in ${label:resource_group} (${label:region}). \ |
| 189 | When credits are exhausted, disk IOPS drops to baseline. |
| 190 | to: sysadmin |
| 191 | |
| 192 | # --- Data Disk Latency --- |
| 193 | |
| 194 | template: am_vm_data_disk_latency |
| 195 | on: azure_monitor.virtual_machines.data_disk_latency |
| 196 | class: Latency |
| 197 | type: System |
| 198 | component: Azure VM |
| 199 | lookup: average -5m unaligned of average |
| 200 | units: milliseconds |
| 201 | every: 1m |
| 202 | warn: $this > (($status >= $WARNING) ? (30) : (50)) |
| 203 | crit: $this > (($status == $CRITICAL) ? (50) : (100)) |
| 204 | delay: down 5m multiplier 1.5 max 1h |
| 205 | summary: VM data disk latency on ${label:resource_name} |
| 206 | info: Average data disk latency on Azure VM ${label:resource_name} \ |
| 207 | in ${label:resource_group} (${label:region}). \ |
| 208 | High latency indicates disk I/O bottleneck. |
| 209 | to: sysadmin |
| 210 | |
| 211 | # --- Data Disk Queue Depth --- |
| 212 | |
| 213 | template: am_vm_data_disk_queue_depth |
| 214 | on: azure_monitor.virtual_machines.data_disk_queue_depth |
| 215 | class: Utilization |
| 216 | type: System |
| 217 | component: Azure VM |
| 218 | lookup: average -5m unaligned of average |
| 219 | units: operations |
| 220 | every: 1m |
| 221 | warn: $this > (($status >= $WARNING) ? (16) : (32)) |
| 222 | crit: $this > (($status == $CRITICAL) ? (32) : (64)) |
| 223 | delay: down 5m multiplier 1.5 max 1h |
| 224 | summary: VM data disk queue depth on ${label:resource_name} |
| 225 | info: Average data disk queue depth on Azure VM ${label:resource_name} \ |
| 226 | in ${label:resource_group} (${label:region}). \ |
| 227 | High queue depth indicates I/O saturation. |
| 228 | to: sysadmin |
| 229 | |
| 230 | # --- Data Disk Throttling --- |
| 231 | |
| 232 | template: am_vm_data_disk_bandwidth_throttling |
| 233 | on: azure_monitor.virtual_machines.data_disk_throttling |
| 234 | class: Utilization |
| 235 | type: System |
| 236 | component: Azure VM |
| 237 | lookup: average -5m unaligned of bandwidth |
| 238 | units: percentage |
| 239 | every: 1m |
| 240 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 241 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 242 | delay: down 5m multiplier 1.5 max 1h |
| 243 | summary: VM data disk bandwidth throttling on ${label:resource_name} |
| 244 | info: Data disk bandwidth consumed percentage on Azure VM ${label:resource_name} \ |
| 245 | in ${label:resource_group} (${label:region}). \ |
| 246 | Approaching the provisioned bandwidth limit causes throttling. |
| 247 | to: sysadmin |
| 248 | |
| 249 | template: am_vm_data_disk_iops_throttling |
| 250 | on: azure_monitor.virtual_machines.data_disk_throttling |
| 251 | class: Utilization |
| 252 | type: System |
| 253 | component: Azure VM |
| 254 | lookup: average -5m unaligned of iops |
| 255 | units: percentage |
| 256 | every: 1m |
| 257 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 258 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 259 | delay: down 5m multiplier 1.5 max 1h |
| 260 | summary: VM data disk IOPS throttling on ${label:resource_name} |
| 261 | info: Data disk IOPS consumed percentage on Azure VM ${label:resource_name} \ |
| 262 | in ${label:resource_group} (${label:region}). \ |
| 263 | Approaching the provisioned IOPS limit causes throttling. |
| 264 | to: sysadmin |
| 265 | |
| 266 | # --- Data Disk Burst Credits --- |
| 267 | # NaN guard: burst credits are only available on eligible disk tiers. |
| 268 | |
| 269 | template: am_vm_data_disk_burst_bps_credits |
| 270 | on: azure_monitor.virtual_machines.data_disk_burst_credits |
| 271 | class: Utilization |
| 272 | type: System |
| 273 | component: Azure VM |
| 274 | lookup: average -5m unaligned of bandwidth |
| 275 | units: percentage |
| 276 | every: 1m |
| 277 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 278 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 279 | delay: down 5m multiplier 1.5 max 1h |
| 280 | summary: VM data disk burst bandwidth credits on ${label:resource_name} |
| 281 | info: Data disk burst bandwidth credits consumed on Azure VM ${label:resource_name} \ |
| 282 | in ${label:resource_group} (${label:region}). \ |
| 283 | When credits are exhausted, disk throughput drops to baseline. |
| 284 | to: sysadmin |
| 285 | |
| 286 | template: am_vm_data_disk_burst_io_credits |
| 287 | on: azure_monitor.virtual_machines.data_disk_burst_credits |
| 288 | class: Utilization |
| 289 | type: System |
| 290 | component: Azure VM |
| 291 | lookup: average -5m unaligned of io |
| 292 | units: percentage |
| 293 | every: 1m |
| 294 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 295 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 296 | delay: down 5m multiplier 1.5 max 1h |
| 297 | summary: VM data disk burst IO credits on ${label:resource_name} |
| 298 | info: Data disk burst IO credits consumed on Azure VM ${label:resource_name} \ |
| 299 | in ${label:resource_group} (${label:region}). \ |
| 300 | When credits are exhausted, disk IOPS drops to baseline. |
| 301 | to: sysadmin |
| 302 | |
| 303 | # --- VM-Level Cached IO Throttling --- |
| 304 | # VM-level limits are separate from individual disk limits. |
| 305 | # The VM can be throttled even when individual disks are not. |
| 306 | |
| 307 | template: am_vm_cached_bandwidth_throttling |
| 308 | on: azure_monitor.virtual_machines.vm_cached_throttling |
| 309 | class: Utilization |
| 310 | type: System |
| 311 | component: Azure VM |
| 312 | lookup: average -5m unaligned of bandwidth |
| 313 | units: percentage |
| 314 | every: 1m |
| 315 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 316 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 317 | delay: down 5m multiplier 1.5 max 1h |
| 318 | summary: VM cached bandwidth throttling on ${label:resource_name} |
| 319 | info: VM-level cached bandwidth consumed percentage on Azure VM ${label:resource_name} \ |
| 320 | in ${label:resource_group} (${label:region}). \ |
| 321 | VM-level throttling affects all disks on the VM. |
| 322 | to: sysadmin |
| 323 | |
| 324 | template: am_vm_cached_iops_throttling |
| 325 | on: azure_monitor.virtual_machines.vm_cached_throttling |
| 326 | class: Utilization |
| 327 | type: System |
| 328 | component: Azure VM |
| 329 | lookup: average -5m unaligned of iops |
| 330 | units: percentage |
| 331 | every: 1m |
| 332 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 333 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 334 | delay: down 5m multiplier 1.5 max 1h |
| 335 | summary: VM cached IOPS throttling on ${label:resource_name} |
| 336 | info: VM-level cached IOPS consumed percentage on Azure VM ${label:resource_name} \ |
| 337 | in ${label:resource_group} (${label:region}). \ |
| 338 | VM-level throttling affects all disks on the VM. |
| 339 | to: sysadmin |
| 340 | |
| 341 | # --- VM-Level Uncached IO Throttling --- |
| 342 | |
| 343 | template: am_vm_uncached_bandwidth_throttling |
| 344 | on: azure_monitor.virtual_machines.vm_uncached_throttling |
| 345 | class: Utilization |
| 346 | type: System |
| 347 | component: Azure VM |
| 348 | lookup: average -5m unaligned of bandwidth |
| 349 | units: percentage |
| 350 | every: 1m |
| 351 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 352 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 353 | delay: down 5m multiplier 1.5 max 1h |
| 354 | summary: VM uncached bandwidth throttling on ${label:resource_name} |
| 355 | info: VM-level uncached bandwidth consumed percentage on Azure VM ${label:resource_name} \ |
| 356 | in ${label:resource_group} (${label:region}). \ |
| 357 | VM-level throttling affects all disks on the VM. |
| 358 | to: sysadmin |
| 359 | |
| 360 | template: am_vm_uncached_iops_throttling |
| 361 | on: azure_monitor.virtual_machines.vm_uncached_throttling |
| 362 | class: Utilization |
| 363 | type: System |
| 364 | component: Azure VM |
| 365 | lookup: average -5m unaligned of iops |
| 366 | units: percentage |
| 367 | every: 1m |
| 368 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 369 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 370 | delay: down 5m multiplier 1.5 max 1h |
| 371 | summary: VM uncached IOPS throttling on ${label:resource_name} |
| 372 | info: VM-level uncached IOPS consumed percentage on Azure VM ${label:resource_name} \ |
| 373 | in ${label:resource_group} (${label:region}). \ |
| 374 | VM-level throttling affects all disks on the VM. |
| 375 | to: sysadmin |
| 376 | |
| 377 | # --- VM-Level Burst Credits --- |
| 378 | # NaN guard: burst credits are only available on burstable VM sizes. |
| 379 | |
| 380 | template: am_vm_cached_burst_bps_credits |
| 381 | on: azure_monitor.virtual_machines.vm_cached_burst_credits |
| 382 | class: Utilization |
| 383 | type: System |
| 384 | component: Azure VM |
| 385 | lookup: average -5m unaligned of bandwidth |
| 386 | units: percentage |
| 387 | every: 1m |
| 388 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 389 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 390 | delay: down 5m multiplier 1.5 max 1h |
| 391 | summary: VM cached burst bandwidth credits on ${label:resource_name} |
| 392 | info: VM-level cached burst bandwidth credits consumed on Azure VM ${label:resource_name} \ |
| 393 | in ${label:resource_group} (${label:region}). \ |
| 394 | When credits are exhausted, cached I/O throughput drops to baseline. |
| 395 | to: sysadmin |
| 396 | |
| 397 | template: am_vm_cached_burst_io_credits |
| 398 | on: azure_monitor.virtual_machines.vm_cached_burst_credits |
| 399 | class: Utilization |
| 400 | type: System |
| 401 | component: Azure VM |
| 402 | lookup: average -5m unaligned of io |
| 403 | units: percentage |
| 404 | every: 1m |
| 405 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 406 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 407 | delay: down 5m multiplier 1.5 max 1h |
| 408 | summary: VM cached burst IO credits on ${label:resource_name} |
| 409 | info: VM-level cached burst IO credits consumed on Azure VM ${label:resource_name} \ |
| 410 | in ${label:resource_group} (${label:region}). \ |
| 411 | When credits are exhausted, cached IOPS drops to baseline. |
| 412 | to: sysadmin |
| 413 | |
| 414 | template: am_vm_uncached_burst_bps_credits |
| 415 | on: azure_monitor.virtual_machines.vm_uncached_burst_credits |
| 416 | class: Utilization |
| 417 | type: System |
| 418 | component: Azure VM |
| 419 | lookup: average -5m unaligned of bandwidth |
| 420 | units: percentage |
| 421 | every: 1m |
| 422 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 423 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 424 | delay: down 5m multiplier 1.5 max 1h |
| 425 | summary: VM uncached burst bandwidth credits on ${label:resource_name} |
| 426 | info: VM-level uncached burst bandwidth credits consumed on Azure VM ${label:resource_name} \ |
| 427 | in ${label:resource_group} (${label:region}). \ |
| 428 | When credits are exhausted, uncached I/O throughput drops to baseline. |
| 429 | to: sysadmin |
| 430 | |
| 431 | template: am_vm_uncached_burst_io_credits |
| 432 | on: azure_monitor.virtual_machines.vm_uncached_burst_credits |
| 433 | class: Utilization |
| 434 | type: System |
| 435 | component: Azure VM |
| 436 | lookup: average -5m unaligned of io |
| 437 | units: percentage |
| 438 | every: 1m |
| 439 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 440 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 441 | delay: down 5m multiplier 1.5 max 1h |
| 442 | summary: VM uncached burst IO credits on ${label:resource_name} |
| 443 | info: VM-level uncached burst IO credits consumed on Azure VM ${label:resource_name} \ |
| 444 | in ${label:resource_group} (${label:region}). \ |
| 445 | When credits are exhausted, uncached IOPS drops to baseline. |
| 446 | to: sysadmin |