| 1 | plugin_name: cgroups.plugin |
| 2 | modules: |
| 3 | - &module |
| 4 | meta: &meta |
| 5 | plugin_name: cgroups.plugin |
| 6 | module_name: /sys/fs/cgroup |
| 7 | monitored_instance: |
| 8 | name: Containers |
| 9 | link: "" |
| 10 | categories: |
| 11 | - data-collection.containers-and-vms |
| 12 | icon_filename: container.svg |
| 13 | related_resources: |
| 14 | integrations: |
| 15 | list: [] |
| 16 | info_provided_to_referring_integrations: |
| 17 | description: "" |
| 18 | keywords: |
| 19 | - containers |
| 20 | - docker |
| 21 | - podman |
| 22 | - containerd |
| 23 | - cri-o |
| 24 | - lxc |
| 25 | - lxd |
| 26 | - incus |
| 27 | - nomad |
| 28 | - ecs |
| 29 | - systemd-nspawn |
| 30 | - nspawn |
| 31 | - cgroups |
| 32 | - linux containers |
| 33 | overview: &overview |
| 34 | data_collection: &data_collection |
| 35 | metrics_description: "Monitor containers and virtual machines resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 36 | method_description: "" |
| 37 | supported_platforms: |
| 38 | include: |
| 39 | - Linux |
| 40 | exclude: [] |
| 41 | multi_instance: true |
| 42 | additional_permissions: |
| 43 | description: "" |
| 44 | default_behavior: |
| 45 | auto_detection: |
| 46 | description: "" |
| 47 | limits: |
| 48 | description: "" |
| 49 | performance_impact: |
| 50 | description: "" |
| 51 | setup: |
| 52 | prerequisites: |
| 53 | list: [] |
| 54 | configuration: |
| 55 | file: |
| 56 | name: "" |
| 57 | description: "" |
| 58 | options: |
| 59 | description: "" |
| 60 | folding: |
| 61 | title: "" |
| 62 | enabled: true |
| 63 | list: [] |
| 64 | examples: |
| 65 | folding: |
| 66 | enabled: true |
| 67 | title: "" |
| 68 | list: [] |
| 69 | troubleshooting: |
| 70 | problems: |
| 71 | list: [] |
| 72 | alerts: |
| 73 | - name: cgroup_10min_cpu_usage |
| 74 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf |
| 75 | metric: cgroup.cpu_limit |
| 76 | info: average cgroup CPU utilization over the last 10 minutes |
| 77 | - name: cgroup_ram_in_use |
| 78 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf |
| 79 | metric: cgroup.mem_usage |
| 80 | info: cgroup memory utilization |
| 81 | - name: cgroup_1m_received_packets_rate |
| 82 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf |
| 83 | metric: cgroup.net_packets |
| 84 | info: average number of packets received by the network interface ${label:device} over the last minute |
| 85 | - name: cgroup_10s_received_packets_storm |
| 86 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf |
| 87 | metric: cgroup.net_packets |
| 88 | info: |
| 89 | ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over |
| 90 | the last minute |
| 91 | metrics: |
| 92 | folding: |
| 93 | title: Metrics |
| 94 | enabled: false |
| 95 | description: "" |
| 96 | availability: [] |
| 97 | scopes: |
| 98 | - name: cgroup |
| 99 | description: "" |
| 100 | labels: |
| 101 | - name: container_name |
| 102 | description: The container name or group path if name resolution fails. |
| 103 | - name: image |
| 104 | description: Docker/Podman container image name. |
| 105 | metrics: |
| 106 | - name: cgroup.cpu_limit |
| 107 | description: CPU Usage within the limits |
| 108 | unit: "percentage" |
| 109 | chart_type: line |
| 110 | dimensions: |
| 111 | - name: used |
| 112 | - name: cgroup.cpu |
| 113 | description: CPU Usage (100% = 1 core) |
| 114 | unit: "percentage" |
| 115 | chart_type: stacked |
| 116 | dimensions: |
| 117 | - name: user |
| 118 | - name: system |
| 119 | - name: cgroup.cpu_per_core |
| 120 | description: CPU Usage (100% = 1 core) Per Core |
| 121 | unit: "percentage" |
| 122 | chart_type: line |
| 123 | dimensions: |
| 124 | - name: a dimension per core |
| 125 | - name: cgroup.throttled |
| 126 | description: CPU Throttled Runnable Periods |
| 127 | unit: "percentage" |
| 128 | chart_type: line |
| 129 | dimensions: |
| 130 | - name: throttled |
| 131 | - name: cgroup.throttled_duration |
| 132 | description: CPU Throttled Time Duration |
| 133 | unit: "ms" |
| 134 | chart_type: line |
| 135 | dimensions: |
| 136 | - name: duration |
| 137 | - name: cgroup.cpu_shares |
| 138 | description: CPU Time Relative Share |
| 139 | unit: "shares" |
| 140 | chart_type: line |
| 141 | dimensions: |
| 142 | - name: shares |
| 143 | - name: cgroup.mem |
| 144 | description: Memory Usage |
| 145 | unit: "MiB" |
| 146 | chart_type: stacked |
| 147 | dimensions: |
| 148 | - name: cache |
| 149 | - name: rss |
| 150 | - name: swap |
| 151 | - name: rss_huge |
| 152 | - name: mapped_file |
| 153 | - name: cgroup.writeback |
| 154 | description: Writeback Memory |
| 155 | unit: "MiB" |
| 156 | chart_type: area |
| 157 | dimensions: |
| 158 | - name: dirty |
| 159 | - name: writeback |
| 160 | - name: cgroup.mem_activity |
| 161 | description: Memory Activity |
| 162 | unit: "MiB/s" |
| 163 | chart_type: line |
| 164 | dimensions: |
| 165 | - name: in |
| 166 | - name: out |
| 167 | - name: cgroup.pgfaults |
| 168 | description: Memory Page Faults |
| 169 | unit: "MiB/s" |
| 170 | chart_type: line |
| 171 | dimensions: |
| 172 | - name: pgfault |
| 173 | - name: swap |
| 174 | - name: cgroup.mem_usage |
| 175 | description: Used Memory |
| 176 | unit: "MiB" |
| 177 | chart_type: stacked |
| 178 | dimensions: |
| 179 | - name: ram |
| 180 | - name: swap |
| 181 | - name: cgroup.mem_usage_limit |
| 182 | description: Used RAM within the limits |
| 183 | unit: "MiB" |
| 184 | chart_type: stacked |
| 185 | dimensions: |
| 186 | - name: available |
| 187 | - name: used |
| 188 | - name: cgroup.mem_utilization |
| 189 | description: Memory Utilization |
| 190 | unit: "percentage" |
| 191 | chart_type: line |
| 192 | dimensions: |
| 193 | - name: utilization |
| 194 | - name: cgroup.mem_failcnt |
| 195 | description: Memory Limit Failures |
| 196 | unit: "count" |
| 197 | chart_type: line |
| 198 | dimensions: |
| 199 | - name: failures |
| 200 | - name: cgroup.io |
| 201 | description: I/O Bandwidth (all disks) |
| 202 | unit: "KiB/s" |
| 203 | chart_type: area |
| 204 | dimensions: |
| 205 | - name: read |
| 206 | - name: write |
| 207 | - name: cgroup.serviced_ops |
| 208 | description: Serviced I/O Operations (all disks) |
| 209 | unit: "operations/s" |
| 210 | chart_type: line |
| 211 | dimensions: |
| 212 | - name: read |
| 213 | - name: write |
| 214 | - name: cgroup.throttle_io |
| 215 | description: Throttle I/O Bandwidth (all disks) |
| 216 | unit: "KiB/s" |
| 217 | chart_type: area |
| 218 | dimensions: |
| 219 | - name: read |
| 220 | - name: write |
| 221 | - name: cgroup.throttle_serviced_ops |
| 222 | description: Throttle Serviced I/O Operations (all disks) |
| 223 | unit: "operations/s" |
| 224 | chart_type: line |
| 225 | dimensions: |
| 226 | - name: read |
| 227 | - name: write |
| 228 | - name: cgroup.queued_ops |
| 229 | description: Queued I/O Operations (all disks) |
| 230 | unit: "operations" |
| 231 | chart_type: line |
| 232 | dimensions: |
| 233 | - name: read |
| 234 | - name: write |
| 235 | - name: cgroup.merged_ops |
| 236 | description: Merged I/O Operations (all disks) |
| 237 | unit: "operations/s" |
| 238 | chart_type: line |
| 239 | dimensions: |
| 240 | - name: read |
| 241 | - name: write |
| 242 | - name: cgroup.cpu_some_pressure |
| 243 | description: CPU some pressure |
| 244 | unit: "percentage" |
| 245 | chart_type: line |
| 246 | dimensions: |
| 247 | - name: some10 |
| 248 | - name: some60 |
| 249 | - name: some300 |
| 250 | - name: cgroup.cpu_some_pressure_stall_time |
| 251 | description: CPU some pressure stall time |
| 252 | unit: "ms" |
| 253 | chart_type: line |
| 254 | dimensions: |
| 255 | - name: time |
| 256 | - name: cgroup.cpu_full_pressure |
| 257 | description: CPU full pressure |
| 258 | unit: "percentage" |
| 259 | chart_type: line |
| 260 | dimensions: |
| 261 | - name: some10 |
| 262 | - name: some60 |
| 263 | - name: some300 |
| 264 | - name: cgroup.cpu_full_pressure_stall_time |
| 265 | description: CPU full pressure stall time |
| 266 | unit: "ms" |
| 267 | chart_type: line |
| 268 | dimensions: |
| 269 | - name: time |
| 270 | - name: cgroup.memory_some_pressure |
| 271 | description: Memory some pressure |
| 272 | unit: "percentage" |
| 273 | chart_type: line |
| 274 | dimensions: |
| 275 | - name: some10 |
| 276 | - name: some60 |
| 277 | - name: some300 |
| 278 | - name: cgroup.memory_some_pressure_stall_time |
| 279 | description: Memory some pressure stall time |
| 280 | unit: "ms" |
| 281 | chart_type: line |
| 282 | dimensions: |
| 283 | - name: time |
| 284 | - name: cgroup.memory_full_pressure |
| 285 | description: Memory full pressure |
| 286 | unit: "percentage" |
| 287 | chart_type: line |
| 288 | dimensions: |
| 289 | - name: some10 |
| 290 | - name: some60 |
| 291 | - name: some300 |
| 292 | - name: cgroup.memory_full_pressure_stall_time |
| 293 | description: Memory full pressure stall time |
| 294 | unit: "ms" |
| 295 | chart_type: line |
| 296 | dimensions: |
| 297 | - name: time |
| 298 | - name: cgroup.io_some_pressure |
| 299 | description: I/O some pressure |
| 300 | unit: "percentage" |
| 301 | chart_type: line |
| 302 | dimensions: |
| 303 | - name: some10 |
| 304 | - name: some60 |
| 305 | - name: some300 |
| 306 | - name: cgroup.io_some_pressure_stall_time |
| 307 | description: I/O some pressure stall time |
| 308 | unit: "ms" |
| 309 | chart_type: line |
| 310 | dimensions: |
| 311 | - name: time |
| 312 | - name: cgroup.io_full_pressure |
| 313 | description: I/O some pressure |
| 314 | unit: "percentage" |
| 315 | chart_type: line |
| 316 | dimensions: |
| 317 | - name: some10 |
| 318 | - name: some60 |
| 319 | - name: some300 |
| 320 | - name: cgroup.io_full_pressure_stall_time |
| 321 | description: I/O some pressure stall time |
| 322 | unit: "ms" |
| 323 | chart_type: line |
| 324 | dimensions: |
| 325 | - name: time |
| 326 | - name: cgroup.pids_current |
| 327 | description: Number of processes |
| 328 | unit: "pids" |
| 329 | chart_type: line |
| 330 | dimensions: |
| 331 | - name: pids |
| 332 | - name: cgroup network device |
| 333 | description: "" |
| 334 | labels: |
| 335 | - name: container_name |
| 336 | description: The container name or group path if name resolution fails. |
| 337 | - name: image |
| 338 | description: Docker/Podman container image name. |
| 339 | - name: device |
| 340 | description: "The name of the host network interface linked to the container's network interface." |
| 341 | - name: container_device |
| 342 | description: Container network interface name. |
| 343 | - name: interface_type |
| 344 | description: 'Network interface type. Always "virtual" for the containers.' |
| 345 | metrics: |
| 346 | - name: cgroup.net_net |
| 347 | description: Bandwidth |
| 348 | unit: "kilobits/s" |
| 349 | chart_type: area |
| 350 | dimensions: |
| 351 | - name: received |
| 352 | - name: sent |
| 353 | - name: cgroup.net_packets |
| 354 | description: Packets |
| 355 | unit: "pps" |
| 356 | chart_type: line |
| 357 | dimensions: |
| 358 | - name: received |
| 359 | - name: sent |
| 360 | - name: multicast |
| 361 | - name: cgroup.net_errors |
| 362 | description: Interface Errors |
| 363 | unit: "errors/s" |
| 364 | chart_type: line |
| 365 | dimensions: |
| 366 | - name: inbound |
| 367 | - name: outbound |
| 368 | - name: cgroup.net_drops |
| 369 | description: Interface Drops |
| 370 | unit: "errors/s" |
| 371 | chart_type: line |
| 372 | dimensions: |
| 373 | - name: inbound |
| 374 | - name: outbound |
| 375 | - name: cgroup.net_fifo |
| 376 | description: Interface FIFO Buffer Errors |
| 377 | unit: "errors/s" |
| 378 | chart_type: line |
| 379 | dimensions: |
| 380 | - name: receive |
| 381 | - name: transmit |
| 382 | - name: cgroup.net_compressed |
| 383 | description: Interface FIFO Buffer Errors |
| 384 | unit: "pps" |
| 385 | chart_type: line |
| 386 | dimensions: |
| 387 | - name: receive |
| 388 | - name: sent |
| 389 | - name: cgroup.net_events |
| 390 | description: Network Interface Events |
| 391 | unit: "events/s" |
| 392 | chart_type: line |
| 393 | dimensions: |
| 394 | - name: frames |
| 395 | - name: collisions |
| 396 | - name: carrier |
| 397 | - name: cgroup.net_operstate |
| 398 | description: Interface Operational State |
| 399 | unit: "state" |
| 400 | chart_type: line |
| 401 | dimensions: |
| 402 | - name: up |
| 403 | - name: down |
| 404 | - name: notpresent |
| 405 | - name: lowerlayerdown |
| 406 | - name: testing |
| 407 | - name: dormant |
| 408 | - name: unknown |
| 409 | - name: cgroup.net_carrier |
| 410 | description: Interface Physical Link State |
| 411 | unit: "state" |
| 412 | chart_type: line |
| 413 | dimensions: |
| 414 | - name: up |
| 415 | - name: down |
| 416 | - name: cgroup.net_mtu |
| 417 | description: Interface MTU |
| 418 | unit: "octets" |
| 419 | chart_type: line |
| 420 | dimensions: |
| 421 | - name: mtu |
| 422 | - <<: *module |
| 423 | meta: |
| 424 | <<: *meta |
| 425 | monitored_instance: |
| 426 | name: Kubernetes Containers |
| 427 | link: https://kubernetes.io/ |
| 428 | icon_filename: kubernetes.svg |
| 429 | categories: |
| 430 | #- data-collection.containers-and-vms |
| 431 | - data-collection.containers-and-vms |
| 432 | keywords: |
| 433 | - k8s |
| 434 | - kubernetes |
| 435 | - pods |
| 436 | - containers |
| 437 | - openshift |
| 438 | - rancher |
| 439 | - rke |
| 440 | - rke2 |
| 441 | - k3s |
| 442 | - microk8s |
| 443 | - eks |
| 444 | - gke |
| 445 | - aks |
| 446 | - tanzu |
| 447 | - minikube |
| 448 | - kind |
| 449 | - containerd |
| 450 | - cri-o |
| 451 | - kubelet |
| 452 | - kubepods |
| 453 | related_resources: |
| 454 | integrations: |
| 455 | list: |
| 456 | - plugin_name: go.d.plugin |
| 457 | module_name: k8s_state |
| 458 | - plugin_name: go.d.plugin |
| 459 | module_name: k8s_apiserver |
| 460 | - plugin_name: go.d.plugin |
| 461 | module_name: k8s_kubelet |
| 462 | - plugin_name: go.d.plugin |
| 463 | module_name: k8s_kubeproxy |
| 464 | - plugin_name: go.d.plugin |
| 465 | module_name: coredns |
| 466 | overview: |
| 467 | <<: *overview |
| 468 | data-collection: |
| 469 | <<: *data_collection |
| 470 | metrics_description: Monitor Kubernetes pod and container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups. |
| 471 | alerts: &k8s_alerts |
| 472 | - name: k8s_cgroup_10min_cpu_usage |
| 473 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf |
| 474 | metric: k8s.cgroup.cpu_limit |
| 475 | info: average cgroup CPU utilization over the last 10 minutes |
| 476 | - name: k8s_cgroup_ram_in_use |
| 477 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf |
| 478 | metric: k8s.cgroup.mem_usage |
| 479 | info: cgroup memory utilization |
| 480 | - name: k8s_cgroup_1m_received_packets_rate |
| 481 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf |
| 482 | metric: k8s.cgroup.net_packets |
| 483 | info: average number of packets received by the network interface ${label:device} over the last minute |
| 484 | - name: k8s_cgroup_10s_received_packets_storm |
| 485 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cgroups.conf |
| 486 | metric: k8s.cgroup.net_packets |
| 487 | info: |
| 488 | ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over |
| 489 | the last minute |
| 490 | metrics: &k8s_metrics |
| 491 | folding: |
| 492 | title: Metrics |
| 493 | enabled: false |
| 494 | description: "" |
| 495 | availability: [] |
| 496 | scopes: |
| 497 | - name: k8s cgroup |
| 498 | description: These metrics refer to the Pod container. |
| 499 | labels: |
| 500 | - name: k8s_node_name |
| 501 | description: 'Node name. The value of _pod.spec.nodeName_.' |
| 502 | - name: k8s_namespace |
| 503 | description: 'Namespace name. The value of _pod.metadata.namespace_.' |
| 504 | - name: k8s_controller_kind |
| 505 | description: 'Controller kind (ReplicaSet, DaemonSet, StatefulSet, Job, etc.). The value of _pod.OwnerReferences.Controller.Kind_.' |
| 506 | - name: k8s_controller_name |
| 507 | description: 'Controller name.The value of _pod.OwnerReferences.Controller.Name_.' |
| 508 | - name: k8s_pod_name |
| 509 | description: 'Pod name. The value of _pod.metadata.name_.' |
| 510 | - name: k8s_container_name |
| 511 | description: 'Container name. The value of _pod.spec.containers.name_.' |
| 512 | - name: k8s_kind |
| 513 | description: 'Instance kind: "pod" or "container".' |
| 514 | - name: k8s_qos_class |
| 515 | description: 'QoS class (guaranteed, burstable, besteffort).' |
| 516 | - name: k8s_cluster_id |
| 517 | description: 'Cluster ID. The value of kube-system namespace _namespace.metadata.uid_.' |
| 518 | metrics: |
| 519 | - name: k8s.cgroup.cpu_limit |
| 520 | description: CPU Usage within the limits |
| 521 | unit: "percentage" |
| 522 | chart_type: line |
| 523 | dimensions: |
| 524 | - name: used |
| 525 | - name: k8s.cgroup.cpu |
| 526 | description: CPU Usage (100% = 1000 mCPU) |
| 527 | unit: "percentage" |
| 528 | chart_type: stacked |
| 529 | dimensions: |
| 530 | - name: user |
| 531 | - name: system |
| 532 | - name: k8s.cgroup.cpu_per_core |
| 533 | description: CPU Usage (100% = 1000 mCPU) Per Core |
| 534 | unit: "percentage" |
| 535 | chart_type: line |
| 536 | dimensions: |
| 537 | - name: a dimension per core |
| 538 | - name: k8s.cgroup.throttled |
| 539 | description: CPU Throttled Runnable Periods |
| 540 | unit: "percentage" |
| 541 | chart_type: line |
| 542 | dimensions: |
| 543 | - name: throttled |
| 544 | - name: k8s.cgroup.throttled_duration |
| 545 | description: CPU Throttled Time Duration |
| 546 | unit: "ms" |
| 547 | chart_type: line |
| 548 | dimensions: |
| 549 | - name: duration |
| 550 | - name: k8s.cgroup.cpu_shares |
| 551 | description: CPU Time Relative Share |
| 552 | unit: "shares" |
| 553 | chart_type: line |
| 554 | dimensions: |
| 555 | - name: shares |
| 556 | - name: k8s.cgroup.mem |
| 557 | description: Memory Usage |
| 558 | unit: "MiB" |
| 559 | chart_type: stacked |
| 560 | dimensions: |
| 561 | - name: cache |
| 562 | - name: rss |
| 563 | - name: swap |
| 564 | - name: rss_huge |
| 565 | - name: mapped_file |
| 566 | - name: k8s.cgroup.writeback |
| 567 | description: Writeback Memory |
| 568 | unit: "MiB" |
| 569 | chart_type: area |
| 570 | dimensions: |
| 571 | - name: dirty |
| 572 | - name: writeback |
| 573 | - name: k8s.cgroup.mem_activity |
| 574 | description: Memory Activity |
| 575 | unit: "MiB/s" |
| 576 | chart_type: line |
| 577 | dimensions: |
| 578 | - name: in |
| 579 | - name: out |
| 580 | - name: k8s.cgroup.pgfaults |
| 581 | description: Memory Page Faults |
| 582 | unit: "MiB/s" |
| 583 | chart_type: line |
| 584 | dimensions: |
| 585 | - name: pgfault |
| 586 | - name: swap |
| 587 | - name: k8s.cgroup.mem_usage |
| 588 | description: Used Memory |
| 589 | unit: "MiB" |
| 590 | chart_type: stacked |
| 591 | dimensions: |
| 592 | - name: ram |
| 593 | - name: swap |
| 594 | - name: k8s.cgroup.mem_usage_limit |
| 595 | description: Used RAM within the limits |
| 596 | unit: "MiB" |
| 597 | chart_type: stacked |
| 598 | dimensions: |
| 599 | - name: available |
| 600 | - name: used |
| 601 | - name: k8s.cgroup.mem_utilization |
| 602 | description: Memory Utilization |
| 603 | unit: "percentage" |
| 604 | chart_type: line |
| 605 | dimensions: |
| 606 | - name: utilization |
| 607 | - name: k8s.cgroup.mem_failcnt |
| 608 | description: Memory Limit Failures |
| 609 | unit: "count" |
| 610 | chart_type: line |
| 611 | dimensions: |
| 612 | - name: failures |
| 613 | - name: k8s.cgroup.io |
| 614 | description: I/O Bandwidth (all disks) |
| 615 | unit: "KiB/s" |
| 616 | chart_type: area |
| 617 | dimensions: |
| 618 | - name: read |
| 619 | - name: write |
| 620 | - name: k8s.cgroup.serviced_ops |
| 621 | description: Serviced I/O Operations (all disks) |
| 622 | unit: "operations/s" |
| 623 | chart_type: line |
| 624 | dimensions: |
| 625 | - name: read |
| 626 | - name: write |
| 627 | - name: k8s.cgroup.throttle_io |
| 628 | description: Throttle I/O Bandwidth (all disks) |
| 629 | unit: "KiB/s" |
| 630 | chart_type: area |
| 631 | dimensions: |
| 632 | - name: read |
| 633 | - name: write |
| 634 | - name: k8s.cgroup.throttle_serviced_ops |
| 635 | description: Throttle Serviced I/O Operations (all disks) |
| 636 | unit: "operations/s" |
| 637 | chart_type: line |
| 638 | dimensions: |
| 639 | - name: read |
| 640 | - name: write |
| 641 | - name: k8s.cgroup.queued_ops |
| 642 | description: Queued I/O Operations (all disks) |
| 643 | unit: "operations" |
| 644 | chart_type: line |
| 645 | dimensions: |
| 646 | - name: read |
| 647 | - name: write |
| 648 | - name: k8s.cgroup.merged_ops |
| 649 | description: Merged I/O Operations (all disks) |
| 650 | unit: "operations/s" |
| 651 | chart_type: line |
| 652 | dimensions: |
| 653 | - name: read |
| 654 | - name: write |
| 655 | - name: k8s.cgroup.cpu_some_pressure |
| 656 | description: CPU some pressure |
| 657 | unit: "percentage" |
| 658 | chart_type: line |
| 659 | dimensions: |
| 660 | - name: some10 |
| 661 | - name: some60 |
| 662 | - name: some300 |
| 663 | - name: k8s.cgroup.cpu_some_pressure_stall_time |
| 664 | description: CPU some pressure stall time |
| 665 | unit: "ms" |
| 666 | chart_type: line |
| 667 | dimensions: |
| 668 | - name: time |
| 669 | - name: k8s.cgroup.cpu_full_pressure |
| 670 | description: CPU full pressure |
| 671 | unit: "percentage" |
| 672 | chart_type: line |
| 673 | dimensions: |
| 674 | - name: some10 |
| 675 | - name: some60 |
| 676 | - name: some300 |
| 677 | - name: k8s.cgroup.cpu_full_pressure_stall_time |
| 678 | description: CPU full pressure stall time |
| 679 | unit: "ms" |
| 680 | chart_type: line |
| 681 | dimensions: |
| 682 | - name: time |
| 683 | - name: k8s.cgroup.memory_some_pressure |
| 684 | description: Memory some pressure |
| 685 | unit: "percentage" |
| 686 | chart_type: line |
| 687 | dimensions: |
| 688 | - name: some10 |
| 689 | - name: some60 |
| 690 | - name: some300 |
| 691 | - name: k8s.cgroup.memory_some_pressure_stall_time |
| 692 | description: Memory some pressure stall time |
| 693 | unit: "ms" |
| 694 | chart_type: line |
| 695 | dimensions: |
| 696 | - name: time |
| 697 | - name: k8s.cgroup.memory_full_pressure |
| 698 | description: Memory full pressure |
| 699 | unit: "percentage" |
| 700 | chart_type: line |
| 701 | dimensions: |
| 702 | - name: some10 |
| 703 | - name: some60 |
| 704 | - name: some300 |
| 705 | - name: k8s.cgroup.memory_full_pressure_stall_time |
| 706 | description: Memory full pressure stall time |
| 707 | unit: "ms" |
| 708 | chart_type: line |
| 709 | dimensions: |
| 710 | - name: time |
| 711 | - name: k8s.cgroup.io_some_pressure |
| 712 | description: I/O some pressure |
| 713 | unit: "percentage" |
| 714 | chart_type: line |
| 715 | dimensions: |
| 716 | - name: some10 |
| 717 | - name: some60 |
| 718 | - name: some300 |
| 719 | - name: k8s.cgroup.io_some_pressure_stall_time |
| 720 | description: I/O some pressure stall time |
| 721 | unit: "ms" |
| 722 | chart_type: line |
| 723 | dimensions: |
| 724 | - name: time |
| 725 | - name: k8s.cgroup.io_full_pressure |
| 726 | description: I/O some pressure |
| 727 | unit: "percentage" |
| 728 | chart_type: line |
| 729 | dimensions: |
| 730 | - name: some10 |
| 731 | - name: some60 |
| 732 | - name: some300 |
| 733 | - name: k8s.cgroup.io_full_pressure_stall_time |
| 734 | description: I/O some pressure stall time |
| 735 | unit: "ms" |
| 736 | chart_type: line |
| 737 | dimensions: |
| 738 | - name: time |
| 739 | - name: k8s.cgroup.pids_current |
| 740 | description: Number of processes |
| 741 | unit: "pids" |
| 742 | chart_type: line |
| 743 | dimensions: |
| 744 | - name: pids |
| 745 | - name: k8s cgroup network device |
| 746 | description: These metrics refer to the Pod container network interface. |
| 747 | labels: |
| 748 | - name: device |
| 749 | description: "The name of the host network interface linked to the container's network interface." |
| 750 | - name: container_device |
| 751 | description: Container network interface name. |
| 752 | - name: interface_type |
| 753 | description: 'Network interface type. Always "virtual" for the containers.' |
| 754 | - name: k8s_node_name |
| 755 | description: 'Node name. The value of _pod.spec.nodeName_.' |
| 756 | - name: k8s_namespace |
| 757 | description: 'Namespace name. The value of _pod.metadata.namespace_.' |
| 758 | - name: k8s_controller_kind |
| 759 | description: 'Controller kind (ReplicaSet, DaemonSet, StatefulSet, Job, etc.). The value of _pod.OwnerReferences.Controller.Kind_.' |
| 760 | - name: k8s_controller_name |
| 761 | description: 'Controller name.The value of _pod.OwnerReferences.Controller.Name_.' |
| 762 | - name: k8s_pod_name |
| 763 | description: 'Pod name. The value of _pod.metadata.name_.' |
| 764 | - name: k8s_container_name |
| 765 | description: 'Container name. The value of _pod.spec.containers.name_.' |
| 766 | - name: k8s_kind |
| 767 | description: 'Instance kind: "pod" or "container".' |
| 768 | - name: k8s_qos_class |
| 769 | description: 'QoS class (guaranteed, burstable, besteffort).' |
| 770 | - name: k8s_cluster_id |
| 771 | description: 'Cluster ID. The value of kube-system namespace _namespace.metadata.uid_.' |
| 772 | metrics: |
| 773 | - name: k8s.cgroup.net_net |
| 774 | description: Bandwidth |
| 775 | unit: "kilobits/s" |
| 776 | chart_type: area |
| 777 | dimensions: |
| 778 | - name: received |
| 779 | - name: sent |
| 780 | - name: k8s.cgroup.net_packets |
| 781 | description: Packets |
| 782 | unit: "pps" |
| 783 | chart_type: line |
| 784 | dimensions: |
| 785 | - name: received |
| 786 | - name: sent |
| 787 | - name: multicast |
| 788 | - name: k8s.cgroup.net_errors |
| 789 | description: Interface Errors |
| 790 | unit: "errors/s" |
| 791 | chart_type: line |
| 792 | dimensions: |
| 793 | - name: inbound |
| 794 | - name: outbound |
| 795 | - name: k8s.cgroup.net_drops |
| 796 | description: Interface Drops |
| 797 | unit: "errors/s" |
| 798 | chart_type: line |
| 799 | dimensions: |
| 800 | - name: inbound |
| 801 | - name: outbound |
| 802 | - name: k8s.cgroup.net_fifo |
| 803 | description: Interface FIFO Buffer Errors |
| 804 | unit: "errors/s" |
| 805 | chart_type: line |
| 806 | dimensions: |
| 807 | - name: receive |
| 808 | - name: transmit |
| 809 | - name: k8s.cgroup.net_compressed |
| 810 | description: Interface FIFO Buffer Errors |
| 811 | unit: "pps" |
| 812 | chart_type: line |
| 813 | dimensions: |
| 814 | - name: receive |
| 815 | - name: sent |
| 816 | - name: k8s.cgroup.net_events |
| 817 | description: Network Interface Events |
| 818 | unit: "events/s" |
| 819 | chart_type: line |
| 820 | dimensions: |
| 821 | - name: frames |
| 822 | - name: collisions |
| 823 | - name: carrier |
| 824 | - name: k8s.cgroup.net_operstate |
| 825 | description: Interface Operational State |
| 826 | unit: "state" |
| 827 | chart_type: line |
| 828 | dimensions: |
| 829 | - name: up |
| 830 | - name: down |
| 831 | - name: notpresent |
| 832 | - name: lowerlayerdown |
| 833 | - name: testing |
| 834 | - name: dormant |
| 835 | - name: unknown |
| 836 | - name: k8s.cgroup.net_carrier |
| 837 | description: Interface Physical Link State |
| 838 | unit: "state" |
| 839 | chart_type: line |
| 840 | dimensions: |
| 841 | - name: up |
| 842 | - name: down |
| 843 | - name: k8s.cgroup.net_mtu |
| 844 | description: Interface MTU |
| 845 | unit: "octets" |
| 846 | chart_type: line |
| 847 | dimensions: |
| 848 | - name: mtu |
| 849 | - <<: *module |
| 850 | meta: |
| 851 | <<: *meta |
| 852 | monitored_instance: |
| 853 | name: Systemd Services |
| 854 | link: "" |
| 855 | icon_filename: systemd.svg |
| 856 | categories: |
| 857 | - data-collection.operating-systems |
| 858 | keywords: |
| 859 | - systemd |
| 860 | - services |
| 861 | - units |
| 862 | - daemons |
| 863 | - systemctl |
| 864 | - cgroups |
| 865 | overview: |
| 866 | <<: *overview |
| 867 | data-collection: |
| 868 | <<: *data_collection |
| 869 | metrics_description: "Monitor Systemd service resource utilization — CPU, memory, and disk I/O — via Linux cgroups." |
| 870 | alerts: [] |
| 871 | metrics: |
| 872 | folding: |
| 873 | title: Metrics |
| 874 | enabled: false |
| 875 | description: "" |
| 876 | availability: [] |
| 877 | scopes: |
| 878 | - name: systemd service |
| 879 | description: "" |
| 880 | labels: |
| 881 | - name: service_name |
| 882 | description: Service name |
| 883 | metrics: |
| 884 | - name: systemd.service.cpu.utilization |
| 885 | description: Systemd Services CPU utilization (100% = 1 core) |
| 886 | unit: percentage |
| 887 | chart_type: stacked |
| 888 | dimensions: |
| 889 | - name: user |
| 890 | - name: system |
| 891 | - name: systemd.service.memory.usage |
| 892 | description: Systemd Services Used Memory |
| 893 | unit: MiB |
| 894 | chart_type: stacked |
| 895 | dimensions: |
| 896 | - name: ram |
| 897 | - name: swap |
| 898 | - name: systemd.service.memory.failcnt |
| 899 | description: Systemd Services Memory Limit Failures |
| 900 | unit: failures/s |
| 901 | chart_type: line |
| 902 | dimensions: |
| 903 | - name: fail |
| 904 | - name: systemd.service.memory.ram.usage |
| 905 | description: Systemd Services Memory |
| 906 | unit: MiB |
| 907 | chart_type: stacked |
| 908 | dimensions: |
| 909 | - name: rss |
| 910 | - name: cache |
| 911 | - name: mapped_file |
| 912 | - name: rss_huge |
| 913 | - name: systemd.service.memory.writeback |
| 914 | description: Systemd Services Writeback Memory |
| 915 | unit: MiB |
| 916 | chart_type: stacked |
| 917 | dimensions: |
| 918 | - name: writeback |
| 919 | - name: dirty |
| 920 | - name: systemd.service.memory.paging.faults |
| 921 | description: Systemd Services Memory Minor and Major Page Faults |
| 922 | unit: MiB/s |
| 923 | chart_type: area |
| 924 | dimensions: |
| 925 | - name: minor |
| 926 | - name: major |
| 927 | - name: systemd.service.memory.paging.io |
| 928 | description: Systemd Services Memory Paging IO |
| 929 | unit: MiB/s |
| 930 | chart_type: area |
| 931 | dimensions: |
| 932 | - name: in |
| 933 | - name: out |
| 934 | - name: systemd.service.disk.io |
| 935 | description: Systemd Services Disk Read/Write Bandwidth |
| 936 | unit: KiB/s |
| 937 | chart_type: area |
| 938 | dimensions: |
| 939 | - name: read |
| 940 | - name: write |
| 941 | - name: systemd.service.disk.iops |
| 942 | description: Systemd Services Disk Read/Write Operations |
| 943 | unit: operations/s |
| 944 | chart_type: line |
| 945 | dimensions: |
| 946 | - name: read |
| 947 | - name: write |
| 948 | - name: systemd.service.disk.throttle.io |
| 949 | description: Systemd Services Throttle Disk Read/Write Bandwidth |
| 950 | unit: KiB/s |
| 951 | chart_type: area |
| 952 | dimensions: |
| 953 | - name: read |
| 954 | - name: write |
| 955 | - name: systemd.service.disk.throttle.iops |
| 956 | description: Systemd Services Throttle Disk Read/Write Operations |
| 957 | unit: operations/s |
| 958 | chart_type: line |
| 959 | dimensions: |
| 960 | - name: read |
| 961 | - name: write |
| 962 | - name: systemd.service.disk.queued_iops |
| 963 | description: Systemd Services Queued Disk Read/Write Operations |
| 964 | unit: operations/s |
| 965 | chart_type: line |
| 966 | dimensions: |
| 967 | - name: read |
| 968 | - name: write |
| 969 | - name: systemd.service.disk.merged_iops |
| 970 | description: Systemd Services Merged Disk Read/Write Operations |
| 971 | unit: operations/s |
| 972 | chart_type: line |
| 973 | dimensions: |
| 974 | - name: read |
| 975 | - name: write |
| 976 | - name: systemd.service.pids.current |
| 977 | description: Systemd Services Number of Processes |
| 978 | unit: pids |
| 979 | chart_type: line |
| 980 | dimensions: |
| 981 | - name: pids |
| 982 | - <<: *module |
| 983 | meta: |
| 984 | <<: *meta |
| 985 | monitored_instance: |
| 986 | name: Virtual Machines |
| 987 | link: "" |
| 988 | icon_filename: container.svg |
| 989 | categories: |
| 990 | - data-collection.containers-and-vms |
| 991 | keywords: |
| 992 | - vms |
| 993 | - virtual machines |
| 994 | - virtualization |
| 995 | - hypervisor |
| 996 | - kvm |
| 997 | - qemu |
| 998 | - libvirt |
| 999 | - proxmox |
| 1000 | - proxmox ve |
| 1001 | - ovirt |
| 1002 | - openstack |
| 1003 | - openstack nova |
| 1004 | - cgroups |
| 1005 | overview: |
| 1006 | <<: *overview |
| 1007 | data_collection: |
| 1008 | <<: *data_collection |
| 1009 | metrics_description: "Monitor virtual machine resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1010 | - <<: *module |
| 1011 | meta: |
| 1012 | <<: *meta |
| 1013 | monitored_instance: |
| 1014 | name: LXC Containers |
| 1015 | link: "" |
| 1016 | icon_filename: lxc.png |
| 1017 | categories: |
| 1018 | - data-collection.containers-and-vms |
| 1019 | keywords: |
| 1020 | - lxc |
| 1021 | - lxd |
| 1022 | - incus |
| 1023 | - linux containers |
| 1024 | - system containers |
| 1025 | - container |
| 1026 | overview: |
| 1027 | <<: *overview |
| 1028 | data_collection: |
| 1029 | <<: *data_collection |
| 1030 | metrics_description: "Monitor LXC/LXD/Incus container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1031 | - <<: *module |
| 1032 | meta: |
| 1033 | <<: *meta |
| 1034 | monitored_instance: |
| 1035 | name: Libvirt VMs and Containers |
| 1036 | link: "" |
| 1037 | icon_filename: libvirt.png |
| 1038 | categories: |
| 1039 | - data-collection.containers-and-vms |
| 1040 | keywords: |
| 1041 | - libvirt |
| 1042 | - kvm |
| 1043 | - qemu |
| 1044 | - virsh |
| 1045 | - virt-manager |
| 1046 | - virtual machine |
| 1047 | - vm |
| 1048 | - container |
| 1049 | overview: |
| 1050 | <<: *overview |
| 1051 | data_collection: |
| 1052 | <<: *data_collection |
| 1053 | metrics_description: "Monitor libvirt-managed VM and container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1054 | - <<: *module |
| 1055 | meta: |
| 1056 | <<: *meta |
| 1057 | monitored_instance: |
| 1058 | name: oVirt VMs |
| 1059 | link: "" |
| 1060 | icon_filename: ovirt.svg |
| 1061 | categories: |
| 1062 | - data-collection.containers-and-vms |
| 1063 | keywords: |
| 1064 | - ovirt |
| 1065 | - rhev |
| 1066 | - red hat virtualization |
| 1067 | - red hat enterprise virtualization |
| 1068 | - kvm |
| 1069 | - qemu |
| 1070 | - libvirt |
| 1071 | - virtual machine |
| 1072 | - vm |
| 1073 | overview: |
| 1074 | <<: *overview |
| 1075 | data_collection: |
| 1076 | <<: *data_collection |
| 1077 | metrics_description: "Monitor oVirt/RHEV virtual machine resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1078 | - <<: *module |
| 1079 | meta: |
| 1080 | <<: *meta |
| 1081 | monitored_instance: |
| 1082 | name: Proxmox VMs and Containers |
| 1083 | link: "" |
| 1084 | icon_filename: proxmox.png |
| 1085 | categories: |
| 1086 | - data-collection.containers-and-vms |
| 1087 | keywords: |
| 1088 | - proxmox |
| 1089 | - proxmox ve |
| 1090 | - pve |
| 1091 | - kvm |
| 1092 | - qemu |
| 1093 | - lxc |
| 1094 | - libvirt |
| 1095 | - virtual machine |
| 1096 | - vm |
| 1097 | - container |
| 1098 | overview: |
| 1099 | <<: *overview |
| 1100 | data_collection: |
| 1101 | <<: *data_collection |
| 1102 | metrics_description: "Monitor Proxmox VE virtual machine and container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1103 | - <<: *module |
| 1104 | meta: |
| 1105 | <<: *meta |
| 1106 | monitored_instance: |
| 1107 | name: Docker Containers |
| 1108 | link: https://www.docker.com/ |
| 1109 | icon_filename: docker.svg |
| 1110 | categories: |
| 1111 | - data-collection.containers-and-vms |
| 1112 | keywords: |
| 1113 | - docker |
| 1114 | - containers |
| 1115 | - docker compose |
| 1116 | - docker swarm |
| 1117 | - moby |
| 1118 | - containerd |
| 1119 | - runc |
| 1120 | overview: |
| 1121 | <<: *overview |
| 1122 | data_collection: |
| 1123 | <<: *data_collection |
| 1124 | metrics_description: "Monitor Docker container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1125 | - <<: *module |
| 1126 | meta: |
| 1127 | <<: *meta |
| 1128 | monitored_instance: |
| 1129 | name: Podman Containers |
| 1130 | link: https://podman.io/ |
| 1131 | icon_filename: podman.png |
| 1132 | categories: |
| 1133 | - data-collection.containers-and-vms |
| 1134 | keywords: |
| 1135 | - podman |
| 1136 | - containers |
| 1137 | - pods |
| 1138 | - oci |
| 1139 | - crun |
| 1140 | - runc |
| 1141 | overview: |
| 1142 | <<: *overview |
| 1143 | data_collection: |
| 1144 | <<: *data_collection |
| 1145 | metrics_description: "Monitor Podman container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1146 | - <<: *module |
| 1147 | meta: |
| 1148 | <<: *meta |
| 1149 | monitored_instance: |
| 1150 | name: AWS ECS Containers |
| 1151 | link: https://aws.amazon.com/ecs/ |
| 1152 | icon_filename: aws.svg |
| 1153 | categories: |
| 1154 | - data-collection.containers-and-vms |
| 1155 | keywords: |
| 1156 | - aws |
| 1157 | - ecs |
| 1158 | - elastic container service |
| 1159 | - amazon |
| 1160 | - containers |
| 1161 | overview: |
| 1162 | <<: *overview |
| 1163 | data_collection: |
| 1164 | <<: *data_collection |
| 1165 | metrics_description: "Monitor AWS ECS container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1166 | - <<: *module |
| 1167 | meta: |
| 1168 | <<: *meta |
| 1169 | monitored_instance: |
| 1170 | name: Nomad Containers |
| 1171 | link: https://www.nomadproject.io/ |
| 1172 | icon_filename: nomad.png |
| 1173 | categories: |
| 1174 | - data-collection.containers-and-vms |
| 1175 | keywords: |
| 1176 | - nomad |
| 1177 | - hashicorp |
| 1178 | - containers |
| 1179 | - orchestrator |
| 1180 | overview: |
| 1181 | <<: *overview |
| 1182 | data_collection: |
| 1183 | <<: *data_collection |
| 1184 | metrics_description: "Monitor HashiCorp Nomad container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1185 | - <<: *module |
| 1186 | meta: |
| 1187 | <<: *meta |
| 1188 | monitored_instance: |
| 1189 | name: containerd Containers |
| 1190 | link: https://containerd.io/ |
| 1191 | icon_filename: containerd.png |
| 1192 | categories: |
| 1193 | - data-collection.containers-and-vms |
| 1194 | keywords: |
| 1195 | - containerd |
| 1196 | - containers |
| 1197 | - cri |
| 1198 | - container runtime |
| 1199 | - nerdctl |
| 1200 | overview: |
| 1201 | <<: *overview |
| 1202 | data_collection: |
| 1203 | <<: *data_collection |
| 1204 | metrics_description: "Monitor containerd container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1205 | - <<: *module |
| 1206 | meta: |
| 1207 | <<: *meta |
| 1208 | monitored_instance: |
| 1209 | name: systemd-nspawn Containers |
| 1210 | link: https://www.freedesktop.org/software/systemd/man/systemd-nspawn.html |
| 1211 | icon_filename: systemd.svg |
| 1212 | categories: |
| 1213 | - data-collection.containers-and-vms |
| 1214 | keywords: |
| 1215 | - systemd-nspawn |
| 1216 | - nspawn |
| 1217 | - machinectl |
| 1218 | - systemd |
| 1219 | - containers |
| 1220 | overview: |
| 1221 | <<: *overview |
| 1222 | data_collection: |
| 1223 | <<: *data_collection |
| 1224 | metrics_description: "Monitor systemd-nspawn container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1225 | - <<: *module |
| 1226 | meta: |
| 1227 | <<: *meta |
| 1228 | monitored_instance: |
| 1229 | name: OpenShift Containers |
| 1230 | link: https://www.redhat.com/en/technologies/cloud-computing/openshift |
| 1231 | icon_filename: openshift.png |
| 1232 | categories: |
| 1233 | - data-collection.containers-and-vms |
| 1234 | keywords: |
| 1235 | - openshift |
| 1236 | - red hat openshift |
| 1237 | - okd |
| 1238 | - kubernetes |
| 1239 | - k8s |
| 1240 | - containers |
| 1241 | - pods |
| 1242 | overview: |
| 1243 | <<: *overview |
| 1244 | data_collection: |
| 1245 | <<: *data_collection |
| 1246 | metrics_description: "Monitor Red Hat OpenShift container resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |
| 1247 | alerts: *k8s_alerts |
| 1248 | metrics: *k8s_metrics |
| 1249 | - <<: *module |
| 1250 | meta: |
| 1251 | <<: *meta |
| 1252 | monitored_instance: |
| 1253 | name: OpenStack VMs |
| 1254 | link: https://www.openstack.org/ |
| 1255 | icon_filename: openstack.svg |
| 1256 | categories: |
| 1257 | - data-collection.containers-and-vms |
| 1258 | keywords: |
| 1259 | - openstack |
| 1260 | - openstack nova |
| 1261 | - openstack compute |
| 1262 | - kvm |
| 1263 | - qemu |
| 1264 | - libvirt |
| 1265 | - virtual machine |
| 1266 | - vm |
| 1267 | - cloud |
| 1268 | overview: |
| 1269 | <<: *overview |
| 1270 | data_collection: |
| 1271 | <<: *data_collection |
| 1272 | metrics_description: "Monitor OpenStack Nova virtual machine resource utilization — CPU, memory, disk I/O, and network — via Linux cgroups." |