| 1 | # you can disable an alarm notification by setting the 'to' line to: silent |
| 2 | |
| 3 | # --- CPU --- |
| 4 | |
| 5 | template: am_vmss_cpu |
| 6 | on: azure_monitor.vmss.cpu |
| 7 | class: Utilization |
| 8 | type: System |
| 9 | component: Azure VMSS |
| 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: VMSS CPU utilization on ${label:resource_name} |
| 17 | info: Average CPU utilization of VMSS ${label:resource_name} \ |
| 18 | in ${label:resource_group} (${label:region}) |
| 19 | to: sysadmin |
| 20 | |
| 21 | template: am_vmss_cpu_credits_remaining |
| 22 | on: azure_monitor.vmss.cpu_credits |
| 23 | class: Utilization |
| 24 | type: System |
| 25 | component: Azure VMSS |
| 26 | lookup: average -5m unaligned of remaining |
| 27 | units: credits |
| 28 | every: 1m |
| 29 | warn: $this != nan AND $this < (($status >= $WARNING) ? (30) : (20)) |
| 30 | crit: $this != nan AND $this < (($status == $CRITICAL) ? (20) : (10)) |
| 31 | delay: down 5m multiplier 1.5 max 1h |
| 32 | summary: VMSS CPU credits low on ${label:resource_name} |
| 33 | info: Remaining CPU credits on burstable VMSS ${label:resource_name} \ |
| 34 | in ${label:resource_group} (${label:region}). \ |
| 35 | Running out of credits will cap performance to baseline. |
| 36 | to: sysadmin |
| 37 | |
| 38 | # --- Memory --- |
| 39 | |
| 40 | template: am_vmss_memory_available |
| 41 | on: azure_monitor.vmss.memory_percentage |
| 42 | class: Utilization |
| 43 | type: System |
| 44 | component: Azure VMSS |
| 45 | lookup: average -5m unaligned of available |
| 46 | units: percentage |
| 47 | every: 1m |
| 48 | warn: $this < (($status >= $WARNING) ? (15) : (10)) |
| 49 | crit: $this < (($status == $CRITICAL) ? (10) : (5)) |
| 50 | delay: down 5m multiplier 1.5 max 1h |
| 51 | summary: VMSS available memory low on ${label:resource_name} |
| 52 | info: Average available memory percentage on VMSS ${label:resource_name} \ |
| 53 | in ${label:resource_group} (${label:region}) |
| 54 | to: sysadmin |
| 55 | |
| 56 | # --- Availability --- |
| 57 | |
| 58 | template: am_vmss_availability |
| 59 | on: azure_monitor.vmss.availability |
| 60 | class: Availability |
| 61 | type: System |
| 62 | component: Azure VMSS |
| 63 | lookup: average -5m unaligned of average |
| 64 | units: state |
| 65 | every: 1m |
| 66 | crit: $this < 1 |
| 67 | delay: down 5m multiplier 1.5 max 1h |
| 68 | summary: VMSS availability degraded on ${label:resource_name} |
| 69 | info: VM availability state on VMSS ${label:resource_name} \ |
| 70 | in ${label:resource_group} (${label:region}). \ |
| 71 | Values below 1 indicate instances are unavailable. |
| 72 | to: sysadmin |
| 73 | |
| 74 | # --- OS Disk --- |
| 75 | |
| 76 | template: am_vmss_os_disk_latency |
| 77 | on: azure_monitor.vmss.os_disk_latency |
| 78 | class: Latency |
| 79 | type: System |
| 80 | component: Azure VMSS |
| 81 | lookup: average -5m unaligned of average |
| 82 | units: milliseconds |
| 83 | every: 1m |
| 84 | warn: $this > (($status >= $WARNING) ? (30) : (50)) |
| 85 | crit: $this > (($status == $CRITICAL) ? (50) : (100)) |
| 86 | delay: down 5m multiplier 1.5 max 1h |
| 87 | summary: VMSS OS disk latency on ${label:resource_name} |
| 88 | info: Average OS disk latency on VMSS ${label:resource_name} \ |
| 89 | in ${label:resource_group} (${label:region}) |
| 90 | to: sysadmin |
| 91 | |
| 92 | template: am_vmss_os_disk_queue_depth |
| 93 | on: azure_monitor.vmss.os_disk_queue_depth |
| 94 | class: Utilization |
| 95 | type: System |
| 96 | component: Azure VMSS |
| 97 | lookup: average -5m unaligned of average |
| 98 | units: operations |
| 99 | every: 1m |
| 100 | warn: $this > (($status >= $WARNING) ? (16) : (32)) |
| 101 | crit: $this > (($status == $CRITICAL) ? (32) : (64)) |
| 102 | delay: down 5m multiplier 1.5 max 1h |
| 103 | summary: VMSS OS disk queue depth on ${label:resource_name} |
| 104 | info: Average OS disk queue depth on VMSS ${label:resource_name} \ |
| 105 | in ${label:resource_group} (${label:region}). \ |
| 106 | High queue depth indicates disk I/O saturation. |
| 107 | to: sysadmin |
| 108 | |
| 109 | template: am_vmss_os_disk_bandwidth_throttling |
| 110 | on: azure_monitor.vmss.os_disk_throttling |
| 111 | class: Utilization |
| 112 | type: System |
| 113 | component: Azure VMSS |
| 114 | lookup: average -5m unaligned of bandwidth |
| 115 | units: percentage |
| 116 | every: 1m |
| 117 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 118 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 119 | delay: down 5m multiplier 1.5 max 1h |
| 120 | summary: VMSS OS disk bandwidth consumed on ${label:resource_name} |
| 121 | info: OS disk bandwidth consumed percentage on VMSS ${label:resource_name} \ |
| 122 | in ${label:resource_group} (${label:region}). \ |
| 123 | Approaching 100% means disk throughput is being throttled. |
| 124 | to: sysadmin |
| 125 | |
| 126 | template: am_vmss_os_disk_iops_throttling |
| 127 | on: azure_monitor.vmss.os_disk_throttling |
| 128 | class: Utilization |
| 129 | type: System |
| 130 | component: Azure VMSS |
| 131 | lookup: average -5m unaligned of iops |
| 132 | units: percentage |
| 133 | every: 1m |
| 134 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 135 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 136 | delay: down 5m multiplier 1.5 max 1h |
| 137 | summary: VMSS OS disk IOPS consumed on ${label:resource_name} |
| 138 | info: OS disk IOPS consumed percentage on VMSS ${label:resource_name} \ |
| 139 | in ${label:resource_group} (${label:region}). \ |
| 140 | Approaching 100% means disk IOPS is being throttled. |
| 141 | to: sysadmin |
| 142 | |
| 143 | template: am_vmss_os_disk_burst_bps_credits |
| 144 | on: azure_monitor.vmss.os_disk_burst_credits |
| 145 | class: Utilization |
| 146 | type: System |
| 147 | component: Azure VMSS |
| 148 | lookup: average -5m unaligned of bandwidth |
| 149 | units: percentage |
| 150 | every: 1m |
| 151 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 152 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 153 | delay: down 5m multiplier 1.5 max 1h |
| 154 | summary: VMSS OS disk burst BPS credits depleting on ${label:resource_name} |
| 155 | info: OS disk burst bandwidth credits consumed on VMSS ${label:resource_name} \ |
| 156 | in ${label:resource_group} (${label:region}). \ |
| 157 | Exhausting burst credits will throttle disk throughput to baseline. |
| 158 | to: sysadmin |
| 159 | |
| 160 | template: am_vmss_os_disk_burst_io_credits |
| 161 | on: azure_monitor.vmss.os_disk_burst_credits |
| 162 | class: Utilization |
| 163 | type: System |
| 164 | component: Azure VMSS |
| 165 | lookup: average -5m unaligned of io |
| 166 | units: percentage |
| 167 | every: 1m |
| 168 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 169 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 170 | delay: down 5m multiplier 1.5 max 1h |
| 171 | summary: VMSS OS disk burst IO credits depleting on ${label:resource_name} |
| 172 | info: OS disk burst IO credits consumed on VMSS ${label:resource_name} \ |
| 173 | in ${label:resource_group} (${label:region}). \ |
| 174 | Exhausting burst credits will throttle disk IOPS to baseline. |
| 175 | to: sysadmin |
| 176 | |
| 177 | # --- Data Disk --- |
| 178 | |
| 179 | template: am_vmss_data_disk_latency |
| 180 | on: azure_monitor.vmss.data_disk_latency |
| 181 | class: Latency |
| 182 | type: System |
| 183 | component: Azure VMSS |
| 184 | lookup: average -5m unaligned of average |
| 185 | units: milliseconds |
| 186 | every: 1m |
| 187 | warn: $this > (($status >= $WARNING) ? (30) : (50)) |
| 188 | crit: $this > (($status == $CRITICAL) ? (50) : (100)) |
| 189 | delay: down 5m multiplier 1.5 max 1h |
| 190 | summary: VMSS data disk latency on ${label:resource_name} |
| 191 | info: Average data disk latency on VMSS ${label:resource_name} \ |
| 192 | in ${label:resource_group} (${label:region}) |
| 193 | to: sysadmin |
| 194 | |
| 195 | template: am_vmss_data_disk_queue_depth |
| 196 | on: azure_monitor.vmss.data_disk_queue_depth |
| 197 | class: Utilization |
| 198 | type: System |
| 199 | component: Azure VMSS |
| 200 | lookup: average -5m unaligned of average |
| 201 | units: operations |
| 202 | every: 1m |
| 203 | warn: $this > (($status >= $WARNING) ? (16) : (32)) |
| 204 | crit: $this > (($status == $CRITICAL) ? (32) : (64)) |
| 205 | delay: down 5m multiplier 1.5 max 1h |
| 206 | summary: VMSS data disk queue depth on ${label:resource_name} |
| 207 | info: Average data disk queue depth on VMSS ${label:resource_name} \ |
| 208 | in ${label:resource_group} (${label:region}). \ |
| 209 | High queue depth indicates disk I/O saturation. |
| 210 | to: sysadmin |
| 211 | |
| 212 | template: am_vmss_data_disk_bandwidth_throttling |
| 213 | on: azure_monitor.vmss.data_disk_throttling |
| 214 | class: Utilization |
| 215 | type: System |
| 216 | component: Azure VMSS |
| 217 | lookup: average -5m unaligned of bandwidth |
| 218 | units: percentage |
| 219 | every: 1m |
| 220 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 221 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 222 | delay: down 5m multiplier 1.5 max 1h |
| 223 | summary: VMSS data disk bandwidth consumed on ${label:resource_name} |
| 224 | info: Data disk bandwidth consumed percentage on VMSS ${label:resource_name} \ |
| 225 | in ${label:resource_group} (${label:region}). \ |
| 226 | Approaching 100% means disk throughput is being throttled. |
| 227 | to: sysadmin |
| 228 | |
| 229 | template: am_vmss_data_disk_iops_throttling |
| 230 | on: azure_monitor.vmss.data_disk_throttling |
| 231 | class: Utilization |
| 232 | type: System |
| 233 | component: Azure VMSS |
| 234 | lookup: average -5m unaligned of iops |
| 235 | units: percentage |
| 236 | every: 1m |
| 237 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 238 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 239 | delay: down 5m multiplier 1.5 max 1h |
| 240 | summary: VMSS data disk IOPS consumed on ${label:resource_name} |
| 241 | info: Data disk IOPS consumed percentage on VMSS ${label:resource_name} \ |
| 242 | in ${label:resource_group} (${label:region}). \ |
| 243 | Approaching 100% means disk IOPS is being throttled. |
| 244 | to: sysadmin |
| 245 | |
| 246 | template: am_vmss_data_disk_burst_bps_credits |
| 247 | on: azure_monitor.vmss.data_disk_burst_credits |
| 248 | class: Utilization |
| 249 | type: System |
| 250 | component: Azure VMSS |
| 251 | lookup: average -5m unaligned of bandwidth |
| 252 | units: percentage |
| 253 | every: 1m |
| 254 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 255 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 256 | delay: down 5m multiplier 1.5 max 1h |
| 257 | summary: VMSS data disk burst BPS credits depleting on ${label:resource_name} |
| 258 | info: Data disk burst bandwidth credits consumed on VMSS ${label:resource_name} \ |
| 259 | in ${label:resource_group} (${label:region}). \ |
| 260 | Exhausting burst credits will throttle disk throughput to baseline. |
| 261 | to: sysadmin |
| 262 | |
| 263 | template: am_vmss_data_disk_burst_io_credits |
| 264 | on: azure_monitor.vmss.data_disk_burst_credits |
| 265 | class: Utilization |
| 266 | type: System |
| 267 | component: Azure VMSS |
| 268 | lookup: average -5m unaligned of io |
| 269 | units: percentage |
| 270 | every: 1m |
| 271 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 272 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 273 | delay: down 5m multiplier 1.5 max 1h |
| 274 | summary: VMSS data disk burst IO credits depleting on ${label:resource_name} |
| 275 | info: Data disk burst IO credits consumed on VMSS ${label:resource_name} \ |
| 276 | in ${label:resource_group} (${label:region}). \ |
| 277 | Exhausting burst credits will throttle disk IOPS to baseline. |
| 278 | to: sysadmin |
| 279 | |
| 280 | # --- Temp Disk --- |
| 281 | |
| 282 | template: am_vmss_temp_disk_latency |
| 283 | on: azure_monitor.vmss.temp_disk_latency |
| 284 | class: Latency |
| 285 | type: System |
| 286 | component: Azure VMSS |
| 287 | lookup: average -5m unaligned of average |
| 288 | units: milliseconds |
| 289 | every: 1m |
| 290 | warn: $this > (($status >= $WARNING) ? (30) : (50)) |
| 291 | crit: $this > (($status == $CRITICAL) ? (50) : (100)) |
| 292 | delay: down 5m multiplier 1.5 max 1h |
| 293 | summary: VMSS temp disk latency on ${label:resource_name} |
| 294 | info: Average temp disk latency on VMSS ${label:resource_name} \ |
| 295 | in ${label:resource_group} (${label:region}) |
| 296 | to: sysadmin |
| 297 | |
| 298 | template: am_vmss_temp_disk_queue_depth |
| 299 | on: azure_monitor.vmss.temp_disk_queue_depth |
| 300 | class: Utilization |
| 301 | type: System |
| 302 | component: Azure VMSS |
| 303 | lookup: average -5m unaligned of average |
| 304 | units: operations |
| 305 | every: 1m |
| 306 | warn: $this > (($status >= $WARNING) ? (16) : (32)) |
| 307 | crit: $this > (($status == $CRITICAL) ? (32) : (64)) |
| 308 | delay: down 5m multiplier 1.5 max 1h |
| 309 | summary: VMSS temp disk queue depth on ${label:resource_name} |
| 310 | info: Average temp disk queue depth on VMSS ${label:resource_name} \ |
| 311 | in ${label:resource_group} (${label:region}). \ |
| 312 | High queue depth indicates disk I/O saturation. |
| 313 | to: sysadmin |
| 314 | |
| 315 | # --- VM-Level IO Throttling --- |
| 316 | |
| 317 | template: am_vmss_vm_cached_bandwidth_throttling |
| 318 | on: azure_monitor.vmss.vm_cached_throttling |
| 319 | class: Utilization |
| 320 | type: System |
| 321 | component: Azure VMSS |
| 322 | lookup: average -5m unaligned of bandwidth |
| 323 | units: percentage |
| 324 | every: 1m |
| 325 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 326 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 327 | delay: down 5m multiplier 1.5 max 1h |
| 328 | summary: VMSS cached bandwidth consumed on ${label:resource_name} |
| 329 | info: VM-level cached bandwidth consumed percentage on VMSS ${label:resource_name} \ |
| 330 | in ${label:resource_group} (${label:region}). \ |
| 331 | Approaching 100% means the VM is being throttled at the host level. |
| 332 | to: sysadmin |
| 333 | |
| 334 | template: am_vmss_vm_cached_iops_throttling |
| 335 | on: azure_monitor.vmss.vm_cached_throttling |
| 336 | class: Utilization |
| 337 | type: System |
| 338 | component: Azure VMSS |
| 339 | lookup: average -5m unaligned of iops |
| 340 | units: percentage |
| 341 | every: 1m |
| 342 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 343 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 344 | delay: down 5m multiplier 1.5 max 1h |
| 345 | summary: VMSS cached IOPS consumed on ${label:resource_name} |
| 346 | info: VM-level cached IOPS consumed percentage on VMSS ${label:resource_name} \ |
| 347 | in ${label:resource_group} (${label:region}). \ |
| 348 | Approaching 100% means the VM is being throttled at the host level. |
| 349 | to: sysadmin |
| 350 | |
| 351 | template: am_vmss_vm_uncached_bandwidth_throttling |
| 352 | on: azure_monitor.vmss.vm_uncached_throttling |
| 353 | class: Utilization |
| 354 | type: System |
| 355 | component: Azure VMSS |
| 356 | lookup: average -5m unaligned of bandwidth |
| 357 | units: percentage |
| 358 | every: 1m |
| 359 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 360 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 361 | delay: down 5m multiplier 1.5 max 1h |
| 362 | summary: VMSS uncached bandwidth consumed on ${label:resource_name} |
| 363 | info: VM-level uncached bandwidth consumed percentage on VMSS ${label:resource_name} \ |
| 364 | in ${label:resource_group} (${label:region}). \ |
| 365 | Approaching 100% means the VM is being throttled at the host level. |
| 366 | to: sysadmin |
| 367 | |
| 368 | template: am_vmss_vm_uncached_iops_throttling |
| 369 | on: azure_monitor.vmss.vm_uncached_throttling |
| 370 | class: Utilization |
| 371 | type: System |
| 372 | component: Azure VMSS |
| 373 | lookup: average -5m unaligned of iops |
| 374 | units: percentage |
| 375 | every: 1m |
| 376 | warn: $this > (($status >= $WARNING) ? (80) : (90)) |
| 377 | crit: $this > (($status == $CRITICAL) ? (90) : (95)) |
| 378 | delay: down 5m multiplier 1.5 max 1h |
| 379 | summary: VMSS uncached IOPS consumed on ${label:resource_name} |
| 380 | info: VM-level uncached IOPS consumed percentage on VMSS ${label:resource_name} \ |
| 381 | in ${label:resource_group} (${label:region}). \ |
| 382 | Approaching 100% means the VM is being throttled at the host level. |
| 383 | to: sysadmin |
| 384 | |
| 385 | # --- VM-Level Burst Credits --- |
| 386 | |
| 387 | template: am_vmss_vm_cached_burst_bps_credits |
| 388 | on: azure_monitor.vmss.vm_cached_burst_credits |
| 389 | class: Utilization |
| 390 | type: System |
| 391 | component: Azure VMSS |
| 392 | lookup: average -5m unaligned of bandwidth |
| 393 | units: percentage |
| 394 | every: 1m |
| 395 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 396 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 397 | delay: down 5m multiplier 1.5 max 1h |
| 398 | summary: VMSS cached burst BPS credits depleting on ${label:resource_name} |
| 399 | info: VM-level cached burst bandwidth credits consumed on VMSS ${label:resource_name} \ |
| 400 | in ${label:resource_group} (${label:region}). \ |
| 401 | Exhausting credits will throttle cached IO throughput to baseline. |
| 402 | to: sysadmin |
| 403 | |
| 404 | template: am_vmss_vm_cached_burst_io_credits |
| 405 | on: azure_monitor.vmss.vm_cached_burst_credits |
| 406 | class: Utilization |
| 407 | type: System |
| 408 | component: Azure VMSS |
| 409 | lookup: average -5m unaligned of io |
| 410 | units: percentage |
| 411 | every: 1m |
| 412 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 413 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 414 | delay: down 5m multiplier 1.5 max 1h |
| 415 | summary: VMSS cached burst IO credits depleting on ${label:resource_name} |
| 416 | info: VM-level cached burst IO credits consumed on VMSS ${label:resource_name} \ |
| 417 | in ${label:resource_group} (${label:region}). \ |
| 418 | Exhausting credits will throttle cached IOPS to baseline. |
| 419 | to: sysadmin |
| 420 | |
| 421 | template: am_vmss_vm_uncached_burst_bps_credits |
| 422 | on: azure_monitor.vmss.vm_uncached_burst_credits |
| 423 | class: Utilization |
| 424 | type: System |
| 425 | component: Azure VMSS |
| 426 | lookup: average -5m unaligned of bandwidth |
| 427 | units: percentage |
| 428 | every: 1m |
| 429 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 430 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 431 | delay: down 5m multiplier 1.5 max 1h |
| 432 | summary: VMSS uncached burst BPS credits depleting on ${label:resource_name} |
| 433 | info: VM-level uncached burst bandwidth credits consumed on VMSS ${label:resource_name} \ |
| 434 | in ${label:resource_group} (${label:region}). \ |
| 435 | Exhausting credits will throttle uncached IO throughput to baseline. |
| 436 | to: sysadmin |
| 437 | |
| 438 | template: am_vmss_vm_uncached_burst_io_credits |
| 439 | on: azure_monitor.vmss.vm_uncached_burst_credits |
| 440 | class: Utilization |
| 441 | type: System |
| 442 | component: Azure VMSS |
| 443 | lookup: average -5m unaligned of io |
| 444 | units: percentage |
| 445 | every: 1m |
| 446 | warn: $this != nan AND $this > (($status >= $WARNING) ? (80) : (90)) |
| 447 | crit: $this != nan AND $this > (($status == $CRITICAL) ? (90) : (95)) |
| 448 | delay: down 5m multiplier 1.5 max 1h |
| 449 | summary: VMSS uncached burst IO credits depleting on ${label:resource_name} |
| 450 | info: VM-level uncached burst IO credits consumed on VMSS ${label:resource_name} \ |
| 451 | in ${label:resource_group} (${label:region}). \ |
| 452 | Exhausting credits will throttle uncached IOPS to baseline. |
| 453 | to: sysadmin |