| 1 | plugin_name: go.d.plugin |
| 2 | modules: |
| 3 | - meta: |
| 4 | plugin_name: go.d.plugin |
| 5 | module_name: ceph |
| 6 | monitored_instance: |
| 7 | name: Ceph |
| 8 | link: "https://ceph.io/" |
| 9 | categories: |
| 10 | - data-collection.storage |
| 11 | icon_filename: "ceph.svg" |
| 12 | related_resources: |
| 13 | integrations: |
| 14 | list: [] |
| 15 | info_provided_to_referring_integrations: |
| 16 | description: "" |
| 17 | keywords: |
| 18 | - ceph |
| 19 | - storage |
| 20 | overview: |
| 21 | data_collection: |
| 22 | metrics_description: | |
| 23 | This collector monitors the overall health status and performance of your Ceph clusters. |
| 24 | It gathers key metrics for the entire cluster, individual Pools, and OSDs. |
| 25 | method_description: | |
| 26 | It collects metrics by periodically issuing HTTP GET requests to the Ceph Manager [REST API](https://docs.ceph.com/en/reef/mgr/ceph_api/#): |
| 27 | |
| 28 | - [/api/monitor](https://docs.ceph.com/en/reef/mgr/ceph_api/#get--api-monitor) (only once to get the Ceph cluster id (fsid)) |
| 29 | - [/api/health/minimal](https://docs.ceph.com/en/reef/mgr/ceph_api/#get--api-health-minimal) |
| 30 | - [/api/osd](https://docs.ceph.com/en/reef/mgr/ceph_api/#get--api-osd) |
| 31 | - [/api/pool?stats=true](https://docs.ceph.com/en/reef/mgr/ceph_api/#get--api-pool) |
| 32 | supported_platforms: |
| 33 | include: [Linux] |
| 34 | exclude: [] |
| 35 | multi_instance: true |
| 36 | additional_permissions: |
| 37 | description: "" |
| 38 | default_behavior: |
| 39 | auto_detection: |
| 40 | description: | |
| 41 | The collector can automatically detect Ceph Manager instances running on: |
| 42 | |
| 43 | - localhost that are listening on port 8443 |
| 44 | - within Docker containers |
| 45 | |
| 46 | > **Note that the Ceph REST API requires a username and password**. |
| 47 | > While Netdata can automatically detect Ceph Manager instances and create data collection jobs, these jobs will fail unless you provide the necessary credentials. |
| 48 | limits: |
| 49 | description: "" |
| 50 | performance_impact: |
| 51 | description: "" |
| 52 | setup: |
| 53 | prerequisites: |
| 54 | list: [] |
| 55 | configuration: |
| 56 | file: |
| 57 | name: go.d/ceph.conf |
| 58 | options: |
| 59 | description: | |
| 60 | The following options can be defined globally: update_every. |
| 61 | folding: |
| 62 | title: Config options |
| 63 | enabled: true |
| 64 | list: |
| 65 | - name: update_every |
| 66 | description: Data collection interval (seconds). |
| 67 | default_value: 1 |
| 68 | required: false |
| 69 | group: Collection |
| 70 | - name: autodetection_retry |
| 71 | description: Autodetection retry interval (seconds). Set 0 to disable. |
| 72 | default_value: 0 |
| 73 | required: false |
| 74 | group: Collection |
| 75 | |
| 76 | - name: url |
| 77 | description: The URL of the [Ceph Manager API](https://docs.ceph.com/en/reef/mgr/ceph_api/). |
| 78 | default_value: https://127.0.0.1:8443 |
| 79 | required: true |
| 80 | group: Target |
| 81 | - name: timeout |
| 82 | description: HTTP request timeout (seconds). |
| 83 | default_value: 2 |
| 84 | required: false |
| 85 | group: Target |
| 86 | |
| 87 | - name: username |
| 88 | description: Username for Basic HTTP authentication. |
| 89 | default_value: "" |
| 90 | required: true |
| 91 | group: HTTP Auth |
| 92 | - name: password |
| 93 | description: Password for Basic HTTP authentication. |
| 94 | default_value: "" |
| 95 | required: true |
| 96 | group: HTTP Auth |
| 97 | - name: bearer_token_file |
| 98 | description: "Path to a file containing a bearer token (used for `Authorization: Bearer`)." |
| 99 | default_value: "" |
| 100 | required: false |
| 101 | group: HTTP Auth |
| 102 | |
| 103 | - name: tls_skip_verify |
| 104 | description: Skip TLS certificate and hostname verification (insecure). |
| 105 | default_value: yes |
| 106 | required: false |
| 107 | group: TLS |
| 108 | - name: tls_ca |
| 109 | description: Path to CA bundle used to validate the server certificate. |
| 110 | default_value: "" |
| 111 | required: false |
| 112 | group: TLS |
| 113 | - name: tls_cert |
| 114 | description: Path to client TLS certificate (for mTLS). |
| 115 | default_value: "" |
| 116 | required: false |
| 117 | group: TLS |
| 118 | - name: tls_key |
| 119 | description: Path to client TLS private key (for mTLS). |
| 120 | default_value: "" |
| 121 | required: false |
| 122 | group: TLS |
| 123 | |
| 124 | - name: proxy_url |
| 125 | description: HTTP proxy URL. |
| 126 | default_value: "" |
| 127 | required: false |
| 128 | group: Proxy |
| 129 | - name: proxy_username |
| 130 | description: Username for proxy Basic HTTP authentication. |
| 131 | default_value: "" |
| 132 | required: false |
| 133 | group: Proxy |
| 134 | - name: proxy_password |
| 135 | description: Password for proxy Basic HTTP authentication. |
| 136 | default_value: "" |
| 137 | required: false |
| 138 | group: Proxy |
| 139 | |
| 140 | - name: method |
| 141 | description: HTTP method to use. |
| 142 | default_value: GET |
| 143 | required: false |
| 144 | group: Request |
| 145 | - name: body |
| 146 | description: Request body (e.g., for POST/PUT). |
| 147 | default_value: "" |
| 148 | required: false |
| 149 | group: Request |
| 150 | - name: headers |
| 151 | description: "Additional HTTP headers (one per line as key: value)." |
| 152 | default_value: "" |
| 153 | required: false |
| 154 | group: Request |
| 155 | - name: not_follow_redirects |
| 156 | description: Do not follow HTTP redirects. |
| 157 | default_value: no |
| 158 | required: false |
| 159 | group: Request |
| 160 | - name: force_http2 |
| 161 | description: Force HTTP/2 (including h2c over TCP). |
| 162 | default_value: no |
| 163 | required: false |
| 164 | group: Request |
| 165 | |
| 166 | - name: vnode |
| 167 | description: Associates this data collection job with a [Virtual Node](https://learn.netdata.cloud/docs/netdata-agent/configuration/organize-systems-metrics-and-alerts#virtual-nodes). |
| 168 | default_value: "" |
| 169 | required: false |
| 170 | group: Virtual Node |
| 171 | examples: |
| 172 | folding: |
| 173 | title: "" |
| 174 | enabled: false |
| 175 | list: |
| 176 | - name: Basic |
| 177 | description: A basic example configuration. |
| 178 | folding: |
| 179 | enabled: false |
| 180 | config: | |
| 181 | jobs: |
| 182 | - name: local |
| 183 | url: https://127.0.0.1:8443 |
| 184 | username: user |
| 185 | password: pass |
| 186 | - name: Multi-instance |
| 187 | description: | |
| 188 | > **Note**: When you define multiple jobs, their names must be unique. |
| 189 | |
| 190 | Collecting metrics from local and remote instances. |
| 191 | config: | |
| 192 | jobs: |
| 193 | - name: local |
| 194 | url: https://127.0.0.1:8443 |
| 195 | username: user |
| 196 | password: pass |
| 197 | |
| 198 | - name: remote |
| 199 | url: https://192.0.2.1:8443 |
| 200 | username: user |
| 201 | password: pass |
| 202 | troubleshooting: |
| 203 | problems: |
| 204 | list: [] |
| 205 | alerts: |
| 206 | - name: ceph_cluster_physical_capacity_utilization |
| 207 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/ceph.conf |
| 208 | metric: ceph.cluster_physical_capacity_utilization |
| 209 | info: 'Ceph cluster ${label:fsid} disk space utilization' |
| 210 | metrics: |
| 211 | folding: |
| 212 | title: Metrics |
| 213 | enabled: false |
| 214 | description: "" |
| 215 | availability: [] |
| 216 | scopes: |
| 217 | - name: cluster |
| 218 | description: "These metrics refer to the entire Ceph cluster." |
| 219 | labels: |
| 220 | - name: fsid |
| 221 | description: A unique identifier of the cluster. |
| 222 | metrics: |
| 223 | - name: ceph.cluster_status |
| 224 | description: Ceph Cluster Status |
| 225 | unit: status |
| 226 | chart_type: line |
| 227 | dimensions: |
| 228 | - name: ok |
| 229 | - name: err |
| 230 | - name: warn |
| 231 | - name: ceph.cluster_hosts_count |
| 232 | description: Ceph Cluster Hosts |
| 233 | unit: hosts |
| 234 | chart_type: line |
| 235 | dimensions: |
| 236 | - name: hosts |
| 237 | - name: ceph.cluster_monitors_count |
| 238 | description: Ceph Cluster Monitors |
| 239 | unit: monitors |
| 240 | chart_type: line |
| 241 | dimensions: |
| 242 | - name: monitors |
| 243 | - name: ceph.cluster_osds_count |
| 244 | description: Ceph Cluster OSDs |
| 245 | unit: osds |
| 246 | chart_type: line |
| 247 | dimensions: |
| 248 | - name: osds |
| 249 | - name: ceph.cluster_osds_by_status_count |
| 250 | description: Ceph Cluster OSDs by Status |
| 251 | unit: status |
| 252 | chart_type: line |
| 253 | dimensions: |
| 254 | - name: up |
| 255 | - name: down |
| 256 | - name: in |
| 257 | - name: out |
| 258 | - name: ceph.cluster_managers_count |
| 259 | description: Ceph Cluster Managers |
| 260 | unit: managers |
| 261 | chart_type: line |
| 262 | dimensions: |
| 263 | - name: active |
| 264 | - name: standby |
| 265 | - name: ceph.cluster_object_gateways_count |
| 266 | description: Ceph Cluster Object Gateways (RGW) |
| 267 | unit: gateways |
| 268 | chart_type: line |
| 269 | dimensions: |
| 270 | - name: object |
| 271 | - name: ceph.cluster_iscsi_gateways_count |
| 272 | description: Ceph Cluster iSCSI Gateways |
| 273 | unit: gateways |
| 274 | chart_type: line |
| 275 | dimensions: |
| 276 | - name: iscsi |
| 277 | - name: ceph.cluster_iscsi_gateways_by_status_count |
| 278 | description: Ceph Cluster iSCSI Gateways by Status |
| 279 | unit: gateways |
| 280 | chart_type: line |
| 281 | dimensions: |
| 282 | - name: up |
| 283 | - name: down |
| 284 | - name: ceph.cluster_physical_capacity_utilization |
| 285 | description: Ceph Cluster Physical Capacity Utilization |
| 286 | unit: percent |
| 287 | chart_type: area |
| 288 | dimensions: |
| 289 | - name: utilization |
| 290 | - name: ceph.cluster_physical_capacity_usage |
| 291 | description: Ceph Cluster Physical Capacity Usage |
| 292 | unit: bytes |
| 293 | chart_type: stacked |
| 294 | dimensions: |
| 295 | - name: avail |
| 296 | - name: used |
| 297 | - name: ceph.cluster_objects_count |
| 298 | description: Ceph Cluster Objects |
| 299 | unit: objects |
| 300 | chart_type: line |
| 301 | dimensions: |
| 302 | - name: objects |
| 303 | - name: ceph.cluster_objects_by_status_distribution |
| 304 | description: Ceph Cluster Objects by Status |
| 305 | unit: percent |
| 306 | chart_type: stacked |
| 307 | dimensions: |
| 308 | - name: healthy |
| 309 | - name: misplaced |
| 310 | - name: degraded |
| 311 | - name: unfound |
| 312 | - name: ceph.cluster_pools_count |
| 313 | description: Ceph Cluster Pools |
| 314 | unit: pools |
| 315 | chart_type: line |
| 316 | dimensions: |
| 317 | - name: pools |
| 318 | - name: ceph.cluster_pgs_count |
| 319 | description: Ceph Cluster Placement Groups |
| 320 | unit: pgs |
| 321 | chart_type: line |
| 322 | dimensions: |
| 323 | - name: pgs |
| 324 | - name: ceph.cluster_pgs_by_status_count |
| 325 | description: Ceph Cluster Placement Groups by Status |
| 326 | unit: pgs |
| 327 | chart_type: stacked |
| 328 | dimensions: |
| 329 | - name: clean |
| 330 | - name: working |
| 331 | - name: warning |
| 332 | - name: unknown |
| 333 | - name: ceph.cluster_pgs_per_osd_count |
| 334 | description: Ceph Cluster Placement Groups per OSD |
| 335 | unit: pgs |
| 336 | chart_type: line |
| 337 | dimensions: |
| 338 | - name: per_osd |
| 339 | - name: osd |
| 340 | description: These metrics refer to the Object Storage Daemon (OSD). |
| 341 | labels: |
| 342 | - name: fsid |
| 343 | description: A unique identifier of the cluster. |
| 344 | - name: osd_uuid |
| 345 | description: OSD UUID. |
| 346 | - name: osd_name |
| 347 | description: OSD name. |
| 348 | - name: device_class |
| 349 | description: OSD device class. |
| 350 | metrics: |
| 351 | - name: ceph.osd_status |
| 352 | description: Ceph OSD Status |
| 353 | unit: status |
| 354 | chart_type: line |
| 355 | dimensions: |
| 356 | - name: up |
| 357 | - name: down |
| 358 | - name: in |
| 359 | - name: out |
| 360 | - name: ceph.osd_space_usage |
| 361 | description: Ceph OSD Space Usage |
| 362 | unit: bytes |
| 363 | chart_type: stacked |
| 364 | dimensions: |
| 365 | - name: avail |
| 366 | - name: used |
| 367 | - name: ceph.osd_io |
| 368 | description: Ceph OSD IO |
| 369 | unit: bytes/s |
| 370 | chart_type: area |
| 371 | dimensions: |
| 372 | - name: read |
| 373 | - name: written |
| 374 | - name: ceph.osd_iops |
| 375 | description: Ceph OSD IOPS |
| 376 | unit: ops/s |
| 377 | chart_type: area |
| 378 | dimensions: |
| 379 | - name: read |
| 380 | - name: write |
| 381 | - name: ceph.osd_latency |
| 382 | description: Ceph OSD Latency |
| 383 | unit: milliseconds |
| 384 | chart_type: line |
| 385 | dimensions: |
| 386 | - name: commit |
| 387 | - name: apply |
| 388 | - name: pool |
| 389 | description: These metrics refer to the Pool. |
| 390 | labels: |
| 391 | - name: fsid |
| 392 | description: A unique identifier of the cluster. |
| 393 | - name: pool_name |
| 394 | description: Pool name. |
| 395 | metrics: |
| 396 | - name: ceph.pool_space_utilization |
| 397 | description: Ceph Pool Space Utilization |
| 398 | unit: percent |
| 399 | chart_type: area |
| 400 | dimensions: |
| 401 | - name: utilization |
| 402 | - name: ceph.pool_space_usage |
| 403 | description: Ceph Pool Space Usage |
| 404 | unit: bytes |
| 405 | chart_type: stacked |
| 406 | dimensions: |
| 407 | - name: avail |
| 408 | - name: used |
| 409 | - name: ceph.pool_objects_count |
| 410 | description: Ceph Pool Objects |
| 411 | unit: objects |
| 412 | chart_type: line |
| 413 | dimensions: |
| 414 | - name: object |
| 415 | - name: ceph.pool_io |
| 416 | description: Ceph Pool IO |
| 417 | unit: bytes/s |
| 418 | chart_type: area |
| 419 | dimensions: |
| 420 | - name: read |
| 421 | - name: written |
| 422 | - name: ceph.pool_iops |
| 423 | description: Ceph Pool IOPS |
| 424 | unit: ops/s |
| 425 | chart_type: area |
| 426 | dimensions: |
| 427 | - name: read |
| 428 | - name: write |