| 1 | plugin_name: go.d.plugin |
| 2 | modules: |
| 3 | - meta: |
| 4 | id: collector-go.d.plugin-hfs |
| 5 | plugin_name: go.d.plugin |
| 6 | module_name: hfs |
| 7 | monitored_instance: |
| 8 | name: Hadoop Distributed File System (HDFS) |
| 9 | link: https://hadoop.apache.org/docs/r1.2.1/hdfs_design.html |
| 10 | icon_filename: hadoop.svg |
| 11 | categories: |
| 12 | - data-collection.storage |
| 13 | keywords: |
| 14 | - hdfs |
| 15 | - hadoop |
| 16 | related_resources: |
| 17 | integrations: |
| 18 | list: [] |
| 19 | info_provided_to_referring_integrations: |
| 20 | description: "" |
| 21 | overview: |
| 22 | data_collection: |
| 23 | metrics_description: | |
| 24 | This collector monitors HDFS nodes. |
| 25 | |
| 26 | Netdata accesses HDFS metrics over `Java Management Extensions` (JMX) through the web interface of an HDFS daemon. |
| 27 | method_description: "" |
| 28 | supported_platforms: |
| 29 | include: [] |
| 30 | exclude: [] |
| 31 | multi_instance: true |
| 32 | additional_permissions: |
| 33 | description: "" |
| 34 | default_behavior: |
| 35 | auto_detection: |
| 36 | description: "" |
| 37 | limits: |
| 38 | description: "" |
| 39 | performance_impact: |
| 40 | description: "" |
| 41 | setup: |
| 42 | prerequisites: |
| 43 | list: [] |
| 44 | configuration: |
| 45 | file: |
| 46 | name: go.d/hdfs.conf |
| 47 | options: |
| 48 | description: | |
| 49 | The following options can be defined globally: update_every, autodetection_retry. |
| 50 | folding: |
| 51 | title: Config options |
| 52 | enabled: true |
| 53 | list: |
| 54 | - name: update_every |
| 55 | description: Data collection interval (seconds). |
| 56 | default_value: 1 |
| 57 | required: false |
| 58 | group: Collection |
| 59 | - name: autodetection_retry |
| 60 | description: Autodetection retry interval (seconds). Set 0 to disable. |
| 61 | default_value: 0 |
| 62 | required: false |
| 63 | group: Collection |
| 64 | |
| 65 | - name: url |
| 66 | description: Target endpoint URL. |
| 67 | default_value: http://127.0.0.1:9870/jmx |
| 68 | required: true |
| 69 | group: Target |
| 70 | - name: timeout |
| 71 | description: HTTP request timeout (seconds). |
| 72 | default_value: 1 |
| 73 | required: false |
| 74 | group: Target |
| 75 | |
| 76 | - name: username |
| 77 | description: Username for Basic HTTP authentication. |
| 78 | default_value: "" |
| 79 | required: false |
| 80 | group: HTTP Auth |
| 81 | - name: password |
| 82 | description: Password for Basic HTTP authentication. |
| 83 | default_value: "" |
| 84 | required: false |
| 85 | group: HTTP Auth |
| 86 | - name: bearer_token_file |
| 87 | description: "Path to a file containing a bearer token (used for `Authorization: Bearer`)." |
| 88 | default_value: "" |
| 89 | required: false |
| 90 | group: HTTP Auth |
| 91 | |
| 92 | - name: tls_skip_verify |
| 93 | description: Skip TLS certificate and hostname verification (insecure). |
| 94 | default_value: no |
| 95 | required: false |
| 96 | group: TLS |
| 97 | - name: tls_ca |
| 98 | description: Path to CA bundle used to validate the server certificate. |
| 99 | default_value: "" |
| 100 | required: false |
| 101 | group: TLS |
| 102 | - name: tls_cert |
| 103 | description: Path to client TLS certificate (for mTLS). |
| 104 | default_value: "" |
| 105 | required: false |
| 106 | group: TLS |
| 107 | - name: tls_key |
| 108 | description: Path to client TLS private key (for mTLS). |
| 109 | default_value: "" |
| 110 | required: false |
| 111 | group: TLS |
| 112 | |
| 113 | - name: proxy_url |
| 114 | description: HTTP proxy URL. |
| 115 | default_value: "" |
| 116 | required: false |
| 117 | group: Proxy |
| 118 | - name: proxy_username |
| 119 | description: Username for proxy Basic HTTP authentication. |
| 120 | default_value: "" |
| 121 | required: false |
| 122 | group: Proxy |
| 123 | - name: proxy_password |
| 124 | description: Password for proxy Basic HTTP authentication. |
| 125 | default_value: "" |
| 126 | required: false |
| 127 | group: Proxy |
| 128 | |
| 129 | - name: method |
| 130 | description: HTTP method to use. |
| 131 | default_value: "GET" |
| 132 | required: false |
| 133 | group: Request |
| 134 | - name: body |
| 135 | description: Request body (e.g., for POST/PUT). |
| 136 | default_value: "" |
| 137 | required: false |
| 138 | group: Request |
| 139 | - name: headers |
| 140 | description: "Additional HTTP headers (one per line as key: value)." |
| 141 | default_value: "" |
| 142 | required: false |
| 143 | group: Request |
| 144 | - name: not_follow_redirects |
| 145 | description: Do not follow HTTP redirects. |
| 146 | default_value: no |
| 147 | required: false |
| 148 | group: Request |
| 149 | - name: force_http2 |
| 150 | description: Force HTTP/2 (including h2c over TCP). |
| 151 | default_value: no |
| 152 | required: false |
| 153 | group: Request |
| 154 | |
| 155 | - name: vnode |
| 156 | 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). |
| 157 | default_value: "" |
| 158 | required: false |
| 159 | group: Virtual Node |
| 160 | examples: |
| 161 | folding: |
| 162 | title: Config |
| 163 | enabled: true |
| 164 | list: |
| 165 | - name: Basic |
| 166 | folding: |
| 167 | enabled: false |
| 168 | description: A basic example configuration. |
| 169 | config: | |
| 170 | jobs: |
| 171 | - name: local |
| 172 | url: http://127.0.0.1:9870/jmx |
| 173 | - name: HTTP authentication |
| 174 | description: Basic HTTP authentication. |
| 175 | config: | |
| 176 | jobs: |
| 177 | - name: local |
| 178 | url: http://127.0.0.1:9870/jmx |
| 179 | username: username |
| 180 | password: password |
| 181 | - name: HTTPS with self-signed certificate |
| 182 | description: | |
| 183 | Do not validate server certificate chain and hostname. |
| 184 | config: | |
| 185 | jobs: |
| 186 | - name: local |
| 187 | url: https://127.0.0.1:9870/jmx |
| 188 | tls_skip_verify: yes |
| 189 | - name: Multi-instance |
| 190 | description: | |
| 191 | > **Note**: When you define multiple jobs, their names must be unique. |
| 192 | |
| 193 | Collecting metrics from local and remote instances. |
| 194 | config: | |
| 195 | jobs: |
| 196 | - name: local |
| 197 | url: http://127.0.0.1:9870/jmx |
| 198 | |
| 199 | - name: remote |
| 200 | url: http://192.0.2.1:9870/jmx |
| 201 | troubleshooting: |
| 202 | problems: |
| 203 | list: [] |
| 204 | alerts: |
| 205 | - name: hdfs_capacity_usage |
| 206 | metric: hdfs.capacity |
| 207 | info: summary datanodes space capacity utilization |
| 208 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/hdfs.conf |
| 209 | - name: hdfs_missing_blocks |
| 210 | metric: hdfs.blocks |
| 211 | info: number of missing blocks |
| 212 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/hdfs.conf |
| 213 | - name: hdfs_stale_nodes |
| 214 | metric: hdfs.data_nodes |
| 215 | info: number of datanodes marked stale due to delayed heartbeat |
| 216 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/hdfs.conf |
| 217 | - name: hdfs_dead_nodes |
| 218 | metric: hdfs.data_nodes |
| 219 | info: number of datanodes which are currently dead |
| 220 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/hdfs.conf |
| 221 | - name: hdfs_num_failed_volumes |
| 222 | metric: hdfs.num_failed_volumes |
| 223 | info: number of failed volumes |
| 224 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/hdfs.conf |
| 225 | metrics: |
| 226 | folding: |
| 227 | title: Metrics |
| 228 | enabled: false |
| 229 | description: "" |
| 230 | availability: |
| 231 | - DataNode |
| 232 | - NameNode |
| 233 | scopes: |
| 234 | - name: global |
| 235 | description: These metrics refer to the entire monitored application. |
| 236 | labels: [] |
| 237 | metrics: |
| 238 | - name: hdfs.heap_memory |
| 239 | description: Heap Memory |
| 240 | unit: MiB |
| 241 | chart_type: area |
| 242 | dimensions: |
| 243 | - name: committed |
| 244 | - name: used |
| 245 | - name: hdfs.gc_count_total |
| 246 | description: GC Events |
| 247 | unit: events/s |
| 248 | chart_type: line |
| 249 | dimensions: |
| 250 | - name: gc |
| 251 | - name: hdfs.gc_time_total |
| 252 | description: GC Time |
| 253 | unit: ms |
| 254 | chart_type: line |
| 255 | dimensions: |
| 256 | - name: ms |
| 257 | - name: hdfs.gc_threshold |
| 258 | description: Number of Times That the GC Threshold is Exceeded |
| 259 | unit: events/s |
| 260 | chart_type: line |
| 261 | dimensions: |
| 262 | - name: info |
| 263 | - name: warn |
| 264 | - name: hdfs.threads |
| 265 | description: Number of Threads |
| 266 | unit: num |
| 267 | chart_type: stacked |
| 268 | dimensions: |
| 269 | - name: new |
| 270 | - name: runnable |
| 271 | - name: blocked |
| 272 | - name: waiting |
| 273 | - name: timed_waiting |
| 274 | - name: terminated |
| 275 | - name: hdfs.logs_total |
| 276 | description: Number of Logs |
| 277 | unit: logs/s |
| 278 | chart_type: stacked |
| 279 | dimensions: |
| 280 | - name: info |
| 281 | - name: error |
| 282 | - name: warn |
| 283 | - name: fatal |
| 284 | - name: hdfs.rpc_bandwidth |
| 285 | description: RPC Bandwidth |
| 286 | unit: kilobits/s |
| 287 | chart_type: area |
| 288 | dimensions: |
| 289 | - name: received |
| 290 | - name: sent |
| 291 | - name: hdfs.rpc_calls |
| 292 | description: RPC Calls |
| 293 | unit: calls/s |
| 294 | chart_type: line |
| 295 | dimensions: |
| 296 | - name: calls |
| 297 | - name: hdfs.open_connections |
| 298 | description: RPC Open Connections |
| 299 | unit: connections |
| 300 | chart_type: line |
| 301 | dimensions: |
| 302 | - name: open |
| 303 | - name: hdfs.call_queue_length |
| 304 | description: RPC Call Queue Length |
| 305 | unit: num |
| 306 | chart_type: line |
| 307 | dimensions: |
| 308 | - name: length |
| 309 | - name: hdfs.avg_queue_time |
| 310 | description: RPC Avg Queue Time |
| 311 | unit: ms |
| 312 | chart_type: line |
| 313 | dimensions: |
| 314 | - name: time |
| 315 | - name: hdfs.avg_processing_time |
| 316 | description: RPC Avg Processing Time |
| 317 | unit: ms |
| 318 | chart_type: line |
| 319 | dimensions: |
| 320 | - name: time |
| 321 | - name: hdfs.capacity |
| 322 | description: Capacity Across All Datanodes |
| 323 | unit: KiB |
| 324 | chart_type: stacked |
| 325 | availability: |
| 326 | - NameNode |
| 327 | dimensions: |
| 328 | - name: remaining |
| 329 | - name: used |
| 330 | - name: hdfs.used_capacity |
| 331 | description: Used Capacity Across All Datanodes |
| 332 | unit: KiB |
| 333 | chart_type: stacked |
| 334 | availability: |
| 335 | - NameNode |
| 336 | dimensions: |
| 337 | - name: dfs |
| 338 | - name: non_dfs |
| 339 | - name: hdfs.load |
| 340 | description: Number of Concurrent File Accesses (read/write) Across All DataNodes |
| 341 | unit: load |
| 342 | chart_type: line |
| 343 | availability: |
| 344 | - NameNode |
| 345 | dimensions: |
| 346 | - name: load |
| 347 | - name: hdfs.volume_failures_total |
| 348 | description: Number of Volume Failures Across All Datanodes |
| 349 | unit: events/s |
| 350 | chart_type: line |
| 351 | availability: |
| 352 | - NameNode |
| 353 | dimensions: |
| 354 | - name: failures |
| 355 | - name: hdfs.files_total |
| 356 | description: Number of Tracked Files |
| 357 | unit: num |
| 358 | chart_type: line |
| 359 | availability: |
| 360 | - NameNode |
| 361 | dimensions: |
| 362 | - name: files |
| 363 | - name: hdfs.blocks_total |
| 364 | description: Number of Allocated Blocks in the System |
| 365 | unit: num |
| 366 | chart_type: line |
| 367 | availability: |
| 368 | - NameNode |
| 369 | dimensions: |
| 370 | - name: blocks |
| 371 | - name: hdfs.blocks |
| 372 | description: Number of Problem Blocks (can point to an unhealthy cluster) |
| 373 | unit: num |
| 374 | chart_type: line |
| 375 | availability: |
| 376 | - NameNode |
| 377 | dimensions: |
| 378 | - name: corrupt |
| 379 | - name: missing |
| 380 | - name: under_replicated |
| 381 | - name: hdfs.data_nodes |
| 382 | description: Number of Data Nodes By Status |
| 383 | unit: num |
| 384 | chart_type: stacked |
| 385 | availability: |
| 386 | - NameNode |
| 387 | dimensions: |
| 388 | - name: live |
| 389 | - name: dead |
| 390 | - name: stale |
| 391 | - name: hdfs.datanode_capacity |
| 392 | description: Capacity |
| 393 | unit: KiB |
| 394 | chart_type: stacked |
| 395 | availability: |
| 396 | - DataNode |
| 397 | dimensions: |
| 398 | - name: remaining |
| 399 | - name: used |
| 400 | - name: hdfs.datanode_used_capacity |
| 401 | description: Used Capacity |
| 402 | unit: KiB |
| 403 | chart_type: stacked |
| 404 | availability: |
| 405 | - DataNode |
| 406 | dimensions: |
| 407 | - name: dfs |
| 408 | - name: non_dfs |
| 409 | - name: hdfs.datanode_failed_volumes |
| 410 | description: Number of Failed Volumes |
| 411 | unit: num |
| 412 | chart_type: line |
| 413 | availability: |
| 414 | - DataNode |
| 415 | dimensions: |
| 416 | - name: failed volumes |
| 417 | - name: hdfs.datanode_bandwidth |
| 418 | description: Bandwidth |
| 419 | unit: KiB/s |
| 420 | chart_type: area |
| 421 | availability: |
| 422 | - DataNode |
| 423 | dimensions: |
| 424 | - name: reads |
| 425 | - name: writes |