| 1 | plugin_name: proc.plugin |
| 2 | modules: |
| 3 | - meta: |
| 4 | plugin_name: proc.plugin |
| 5 | module_name: /proc/stat |
| 6 | monitored_instance: |
| 7 | name: System statistics |
| 8 | link: "" |
| 9 | categories: |
| 10 | - data-collection.operating-systems |
| 11 | icon_filename: "linuxserver.svg" |
| 12 | related_resources: |
| 13 | integrations: |
| 14 | list: [] |
| 15 | info_provided_to_referring_integrations: |
| 16 | description: "" |
| 17 | keywords: |
| 18 | - cpu utilization |
| 19 | - process counts |
| 20 | overview: |
| 21 | data_collection: |
| 22 | metrics_description: | |
| 23 | CPU utilization, states and frequencies and key Linux system performance metrics. |
| 24 | |
| 25 | The `/proc/stat` file provides various types of system statistics: |
| 26 | |
| 27 | - The overall system CPU usage statistics |
| 28 | - Per CPU core statistics |
| 29 | - The total context switching of the system |
| 30 | - The total number of processes running |
| 31 | - The total CPU interrupts |
| 32 | - The total CPU softirqs |
| 33 | |
| 34 | The collector also reads: |
| 35 | |
| 36 | - `/proc/schedstat` for statistics about the process scheduler in the Linux kernel. |
| 37 | - `/sys/devices/system/cpu/[X]/thermal_throttle/core_throttle_count` to get the count of thermal throttling events for a specific CPU core on Linux systems. |
| 38 | - `/sys/devices/system/cpu/[X]/thermal_throttle/package_throttle_count` to get the count of thermal throttling events for a specific CPU package on a Linux system. |
| 39 | - `/sys/devices/system/cpu/[X]/cpufreq/scaling_cur_freq` to get the current operating frequency of a specific CPU core. |
| 40 | - `/sys/devices/system/cpu/[X]/cpufreq/stats/time_in_state` to get the amount of time the CPU has spent in each of its available frequency states. |
| 41 | - `/sys/devices/system/cpu/[X]/cpuidle/state[X]/name` to get the names of the idle states for each CPU core in a Linux system. |
| 42 | - `/sys/devices/system/cpu/[X]/cpuidle/state[X]/time` to get the total time each specific CPU core has spent in each idle state since the system was started. |
| 43 | method_description: "" |
| 44 | supported_platforms: |
| 45 | include: ["linux"] |
| 46 | exclude: [] |
| 47 | multi_instance: false |
| 48 | additional_permissions: |
| 49 | description: "" |
| 50 | default_behavior: |
| 51 | auto_detection: |
| 52 | description: | |
| 53 | The collector auto-detects all metrics. No configuration is needed. |
| 54 | limits: |
| 55 | description: "" |
| 56 | performance_impact: |
| 57 | description: | |
| 58 | The collector disables cpu frequency and idle state monitoring when there are more than 128 CPU cores available. |
| 59 | setup: |
| 60 | prerequisites: |
| 61 | list: [] |
| 62 | configuration: |
| 63 | file: |
| 64 | section_name: "plugin:proc:/proc/stat" |
| 65 | name: "netdata.conf" |
| 66 | description: "" |
| 67 | options: |
| 68 | description: "" |
| 69 | folding: |
| 70 | title: "" |
| 71 | enabled: true |
| 72 | list: |
| 73 | - name: per cpu core utilization |
| 74 | description: Collects CPU usage metrics for each individual core, in addition to the system-wide averages. |
| 75 | default_value: no |
| 76 | required: false |
| 77 | - name: cpu idle states |
| 78 | description: Collects CPU idle state residency metrics for each individual core, showing how much time each core spends in different idle states (C-states). |
| 79 | default_value: no |
| 80 | required: false |
| 81 | examples: |
| 82 | folding: |
| 83 | enabled: true |
| 84 | title: "" |
| 85 | list: [] |
| 86 | troubleshooting: |
| 87 | problems: |
| 88 | list: [] |
| 89 | alerts: |
| 90 | - name: 10min_cpu_usage |
| 91 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cpu.conf |
| 92 | metric: system.cpu |
| 93 | info: average CPU utilization over the last 10 minutes (excluding iowait, nice and steal) |
| 94 | os: "linux" |
| 95 | - name: 10min_cpu_iowait |
| 96 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cpu.conf |
| 97 | metric: system.cpu |
| 98 | info: average CPU iowait time over the last 10 minutes |
| 99 | os: "linux" |
| 100 | - name: 20min_steal_cpu |
| 101 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/cpu.conf |
| 102 | metric: system.cpu |
| 103 | info: average CPU steal time over the last 20 minutes |
| 104 | os: "linux" |
| 105 | metrics: |
| 106 | folding: |
| 107 | title: Metrics |
| 108 | enabled: false |
| 109 | description: "" |
| 110 | availability: [] |
| 111 | scopes: |
| 112 | - name: global |
| 113 | description: "" |
| 114 | labels: [] |
| 115 | metrics: |
| 116 | - name: system.cpu |
| 117 | description: Total CPU utilization |
| 118 | unit: "percentage" |
| 119 | chart_type: stacked |
| 120 | dimensions: |
| 121 | - name: guest_nice |
| 122 | - name: guest |
| 123 | - name: steal |
| 124 | - name: softirq |
| 125 | - name: irq |
| 126 | - name: user |
| 127 | - name: system |
| 128 | - name: nice |
| 129 | - name: iowait |
| 130 | - name: idle |
| 131 | - name: system.intr |
| 132 | description: CPU Interrupts |
| 133 | unit: "interrupts/s" |
| 134 | chart_type: line |
| 135 | dimensions: |
| 136 | - name: interrupts |
| 137 | - name: system.ctxt |
| 138 | description: CPU Context Switches |
| 139 | unit: "context switches/s" |
| 140 | chart_type: line |
| 141 | dimensions: |
| 142 | - name: switches |
| 143 | - name: system.forks |
| 144 | description: Started Processes |
| 145 | unit: "processes/s" |
| 146 | chart_type: line |
| 147 | dimensions: |
| 148 | - name: started |
| 149 | - name: system.processes |
| 150 | description: System Processes |
| 151 | unit: "processes" |
| 152 | chart_type: line |
| 153 | dimensions: |
| 154 | - name: running |
| 155 | - name: blocked |
| 156 | - name: cpu.core_throttling |
| 157 | description: Core Thermal Throttling Events |
| 158 | unit: "events/s" |
| 159 | chart_type: line |
| 160 | dimensions: |
| 161 | - name: a dimension per cpu core |
| 162 | - name: cpu.package_throttling |
| 163 | description: Package Thermal Throttling Events |
| 164 | unit: "events/s" |
| 165 | chart_type: line |
| 166 | dimensions: |
| 167 | - name: a dimension per package |
| 168 | - name: cpu.cpufreq |
| 169 | description: Current CPU Frequency |
| 170 | unit: "MHz" |
| 171 | chart_type: line |
| 172 | dimensions: |
| 173 | - name: a dimension per cpu core |
| 174 | - name: cpu core |
| 175 | description: Per-core CPU metrics. Disabled by default, can be enabled in the [configuration options](#configuration). |
| 176 | labels: |
| 177 | - name: cpu |
| 178 | description: Identifier of the CPU core (e.g., core0, core1, core2). |
| 179 | metrics: |
| 180 | - name: cpu.cpu |
| 181 | description: Core utilization |
| 182 | unit: "percentage" |
| 183 | chart_type: stacked |
| 184 | dimensions: |
| 185 | - name: guest_nice |
| 186 | - name: guest |
| 187 | - name: steal |
| 188 | - name: softirq |
| 189 | - name: irq |
| 190 | - name: user |
| 191 | - name: system |
| 192 | - name: nice |
| 193 | - name: iowait |
| 194 | - name: idle |
| 195 | - name: cpuidle.cpu_cstate_residency_time |
| 196 | description: C-state residency time |
| 197 | unit: "percentage" |
| 198 | chart_type: stacked |
| 199 | dimensions: |
| 200 | - name: a dimension per c-state |
| 201 | - meta: |
| 202 | plugin_name: proc.plugin |
| 203 | module_name: /proc/sys/kernel/random/entropy_avail |
| 204 | monitored_instance: |
| 205 | name: Entropy |
| 206 | link: "" |
| 207 | categories: |
| 208 | - data-collection.operating-systems |
| 209 | icon_filename: "syslog.png" |
| 210 | related_resources: |
| 211 | integrations: |
| 212 | list: [] |
| 213 | info_provided_to_referring_integrations: |
| 214 | description: "" |
| 215 | keywords: |
| 216 | - entropy |
| 217 | overview: |
| 218 | data_collection: |
| 219 | metrics_description: | |
| 220 | Entropy, a measure of the randomness or unpredictability of data. |
| 221 | |
| 222 | In the context of cryptography, entropy is used to generate random numbers or keys that are essential for |
| 223 | secure communication and encryption. Without a good source of entropy, cryptographic protocols can become |
| 224 | vulnerable to attacks that exploit the predictability of the generated keys. |
| 225 | |
| 226 | In most operating systems, entropy is generated by collecting random events from various sources, such as |
| 227 | hardware interrupts, mouse movements, keyboard presses, and disk activity. These events are fed into a pool |
| 228 | of entropy, which is then used to generate random numbers when needed. |
| 229 | |
| 230 | The `/dev/random` device in Linux is one such source of entropy, and it provides an interface for programs |
| 231 | to access the pool of entropy. When a program requests random numbers, it reads from the `/dev/random` device, |
| 232 | which blocks until enough entropy is available to generate the requested numbers. This ensures that the |
| 233 | generated numbers are truly random and not predictable. |
| 234 | |
| 235 | However, if the pool of entropy gets depleted, the `/dev/random` device may block indefinitely, causing |
| 236 | programs that rely on random numbers to slow down or even freeze. This is especially problematic for |
| 237 | cryptographic protocols that require a continuous stream of random numbers, such as SSL/TLS and SSH. |
| 238 | |
| 239 | To avoid this issue, some systems use a hardware random number generator (RNG) to generate high-quality |
| 240 | entropy. A hardware RNG generates random numbers by measuring physical phenomena, such as thermal noise or |
| 241 | radioactive decay. These sources of randomness are considered to be more reliable and unpredictable than |
| 242 | software-based sources. |
| 243 | |
| 244 | One such hardware RNG is the Trusted Platform Module (TPM), which is a dedicated hardware chip that is used |
| 245 | for cryptographic operations and secure boot. The TPM contains a built-in hardware RNG that generates |
| 246 | high-quality entropy, which can be used to seed the pool of entropy in the operating system. |
| 247 | |
| 248 | Alternatively, software-based solutions such as `Haveged` can be used to generate additional entropy by |
| 249 | exploiting sources of randomness in the system, such as CPU utilization and network traffic. These solutions |
| 250 | can help to mitigate the risk of entropy depletion, but they may not be as reliable as hardware-based solutions. |
| 251 | method_description: "" |
| 252 | supported_platforms: |
| 253 | include: ["linux"] |
| 254 | exclude: [] |
| 255 | multi_instance: false |
| 256 | additional_permissions: |
| 257 | description: "" |
| 258 | default_behavior: |
| 259 | auto_detection: |
| 260 | description: "" |
| 261 | limits: |
| 262 | description: "" |
| 263 | performance_impact: |
| 264 | description: "" |
| 265 | setup: |
| 266 | prerequisites: |
| 267 | list: [] |
| 268 | configuration: |
| 269 | file: |
| 270 | name: "" |
| 271 | description: "" |
| 272 | options: |
| 273 | description: "" |
| 274 | folding: |
| 275 | title: "" |
| 276 | enabled: true |
| 277 | list: [] |
| 278 | examples: |
| 279 | folding: |
| 280 | enabled: true |
| 281 | title: "" |
| 282 | list: [] |
| 283 | troubleshooting: |
| 284 | problems: |
| 285 | list: [] |
| 286 | alerts: |
| 287 | - name: lowest_entropy |
| 288 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/entropy.conf |
| 289 | metric: system.entropy |
| 290 | info: minimum number of bits of entropy available for the kernel’s random number generator |
| 291 | metrics: |
| 292 | folding: |
| 293 | title: Metrics |
| 294 | enabled: false |
| 295 | description: "" |
| 296 | availability: [] |
| 297 | scopes: |
| 298 | - name: global |
| 299 | description: "" |
| 300 | labels: [] |
| 301 | metrics: |
| 302 | - name: system.entropy |
| 303 | description: Available Entropy |
| 304 | unit: "entropy" |
| 305 | chart_type: line |
| 306 | dimensions: |
| 307 | - name: entropy |
| 308 | - meta: |
| 309 | plugin_name: proc.plugin |
| 310 | module_name: /proc/uptime |
| 311 | monitored_instance: |
| 312 | name: System Uptime |
| 313 | link: "" |
| 314 | categories: |
| 315 | - data-collection.operating-systems |
| 316 | icon_filename: "linuxserver.svg" |
| 317 | related_resources: |
| 318 | integrations: |
| 319 | list: [] |
| 320 | info_provided_to_referring_integrations: |
| 321 | description: "" |
| 322 | keywords: |
| 323 | - uptime |
| 324 | overview: |
| 325 | data_collection: |
| 326 | metrics_description: | |
| 327 | The amount of time the system has been up (running). |
| 328 | |
| 329 | Uptime is a critical aspect of overall system performance: |
| 330 | |
| 331 | - **Availability**: Uptime monitoring can show whether a server is consistently available or experiences frequent downtimes. |
| 332 | - **Performance Monitoring**: While server uptime alone doesn't provide detailed performance data, analyzing the duration and frequency of downtimes can help identify patterns or trends. |
| 333 | - **Proactive problem detection**: If server uptime monitoring reveals unexpected downtimes or a decreasing uptime trend, it can serve as an early warning sign of potential problems. |
| 334 | - **Root cause analysis**: When investigating server downtime, the uptime metric alone may not provide enough information to pinpoint the exact cause. |
| 335 | - **Load balancing**: Uptime data can indirectly indicate load balancing issues if certain servers have significantly lower uptimes than others. |
| 336 | - **Optimize maintenance efforts**: Servers with consistently low uptimes or frequent downtimes may require more attention. |
| 337 | - **Compliance requirements**: Server uptime data can be used to demonstrate compliance with regulatory requirements or SLAs that mandate a minimum level of server availability. |
| 338 | method_description: "" |
| 339 | supported_platforms: |
| 340 | include: ["linux"] |
| 341 | exclude: [] |
| 342 | multi_instance: false |
| 343 | additional_permissions: |
| 344 | description: "" |
| 345 | default_behavior: |
| 346 | auto_detection: |
| 347 | description: "" |
| 348 | limits: |
| 349 | description: "" |
| 350 | performance_impact: |
| 351 | description: "" |
| 352 | setup: |
| 353 | prerequisites: |
| 354 | list: [] |
| 355 | configuration: |
| 356 | file: |
| 357 | name: "" |
| 358 | description: "" |
| 359 | options: |
| 360 | description: "" |
| 361 | folding: |
| 362 | title: "" |
| 363 | enabled: true |
| 364 | list: [] |
| 365 | examples: |
| 366 | folding: |
| 367 | enabled: true |
| 368 | title: "" |
| 369 | list: [] |
| 370 | troubleshooting: |
| 371 | problems: |
| 372 | list: [] |
| 373 | alerts: [] |
| 374 | metrics: |
| 375 | folding: |
| 376 | title: Metrics |
| 377 | enabled: false |
| 378 | description: "" |
| 379 | availability: [] |
| 380 | scopes: |
| 381 | - name: global |
| 382 | description: "" |
| 383 | labels: [] |
| 384 | metrics: |
| 385 | - name: system.uptime |
| 386 | description: System Uptime |
| 387 | unit: "seconds" |
| 388 | chart_type: line |
| 389 | dimensions: |
| 390 | - name: uptime |
| 391 | - meta: |
| 392 | plugin_name: proc.plugin |
| 393 | module_name: /proc/vmstat |
| 394 | monitored_instance: |
| 395 | name: Memory Statistics |
| 396 | link: "" |
| 397 | categories: |
| 398 | - data-collection.operating-systems |
| 399 | icon_filename: "linuxserver.svg" |
| 400 | related_resources: |
| 401 | integrations: |
| 402 | list: [] |
| 403 | info_provided_to_referring_integrations: |
| 404 | description: "" |
| 405 | keywords: |
| 406 | - swap |
| 407 | - page faults |
| 408 | - oom |
| 409 | - numa |
| 410 | overview: |
| 411 | data_collection: |
| 412 | metrics_description: | |
| 413 | Linux Virtual memory subsystem. |
| 414 | |
| 415 | Information about memory management, indicating how effectively the kernel allocates and frees |
| 416 | memory resources in response to system demands. |
| 417 | |
| 418 | Monitors page faults, which occur when a process requests a portion of its memory that isn't |
| 419 | immediately available. Monitoring these events can help diagnose inefficiencies in memory management and |
| 420 | provide insights into application behavior. |
| 421 | |
| 422 | Tracks swapping activity — a vital aspect of memory management where the kernel moves data from RAM to |
| 423 | swap space, and vice versa, based on memory demand and usage. It also monitors the utilization of zswap, |
| 424 | a compressed cache for swap pages, and provides insights into its usage and performance implications. |
| 425 | |
| 426 | In the context of virtualized environments, it tracks the ballooning mechanism which is used to balance |
| 427 | memory resources between host and guest systems. |
| 428 | |
| 429 | For systems using NUMA architecture, it provides insights into the local and remote memory accesses, which |
| 430 | can impact the performance based on the memory access times. |
| 431 | |
| 432 | The collector also watches for 'Out of Memory' kills, a drastic measure taken by the system when it runs out |
| 433 | of memory resources. |
| 434 | method_description: "" |
| 435 | supported_platforms: |
| 436 | include: ["linux"] |
| 437 | exclude: [] |
| 438 | multi_instance: false |
| 439 | additional_permissions: |
| 440 | description: "" |
| 441 | default_behavior: |
| 442 | auto_detection: |
| 443 | description: "" |
| 444 | limits: |
| 445 | description: "" |
| 446 | performance_impact: |
| 447 | description: "" |
| 448 | setup: |
| 449 | prerequisites: |
| 450 | list: [] |
| 451 | configuration: |
| 452 | file: |
| 453 | name: "" |
| 454 | description: "" |
| 455 | options: |
| 456 | description: "" |
| 457 | folding: |
| 458 | title: "" |
| 459 | enabled: true |
| 460 | list: [] |
| 461 | examples: |
| 462 | folding: |
| 463 | enabled: true |
| 464 | title: "" |
| 465 | list: [] |
| 466 | troubleshooting: |
| 467 | problems: |
| 468 | list: [] |
| 469 | alerts: |
| 470 | - name: 30min_ram_swapped_out |
| 471 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/swap.conf |
| 472 | metric: mem.swapio |
| 473 | info: percentage of the system RAM swapped in the last 30 minutes |
| 474 | os: "linux freebsd" |
| 475 | - name: oom_kill |
| 476 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/ram.conf |
| 477 | metric: mem.oom_kill |
| 478 | info: number of out of memory kills in the last 30 minutes |
| 479 | os: "linux" |
| 480 | metrics: |
| 481 | folding: |
| 482 | title: Metrics |
| 483 | enabled: false |
| 484 | description: "" |
| 485 | availability: [] |
| 486 | scopes: |
| 487 | - name: global |
| 488 | description: "" |
| 489 | labels: [] |
| 490 | metrics: |
| 491 | - name: mem.swapio |
| 492 | description: Swap I/O |
| 493 | unit: "KiB/s" |
| 494 | chart_type: area |
| 495 | dimensions: |
| 496 | - name: in |
| 497 | - name: out |
| 498 | - name: system.pgpgio |
| 499 | description: Memory Paged from/to disk |
| 500 | unit: "KiB/s" |
| 501 | chart_type: area |
| 502 | dimensions: |
| 503 | - name: in |
| 504 | - name: out |
| 505 | - name: system.pgfaults |
| 506 | description: Memory Page Faults |
| 507 | unit: "faults/s" |
| 508 | chart_type: line |
| 509 | dimensions: |
| 510 | - name: minor |
| 511 | - name: major |
| 512 | - name: mem.balloon |
| 513 | description: Memory Ballooning Operations |
| 514 | unit: "KiB/s" |
| 515 | chart_type: line |
| 516 | dimensions: |
| 517 | - name: inflate |
| 518 | - name: deflate |
| 519 | - name: migrate |
| 520 | - name: mem.zswapio |
| 521 | description: ZSwap I/O |
| 522 | unit: "KiB/s" |
| 523 | chart_type: area |
| 524 | dimensions: |
| 525 | - name: in |
| 526 | - name: out |
| 527 | - name: mem.ksm_cow |
| 528 | description: KSM Copy On Write Operations |
| 529 | unit: "KiB/s" |
| 530 | chart_type: line |
| 531 | dimensions: |
| 532 | - name: swapin |
| 533 | - name: write |
| 534 | - name: mem.thp_faults |
| 535 | description: Transparent Huge Page Fault Allocations |
| 536 | unit: "events/s" |
| 537 | chart_type: line |
| 538 | dimensions: |
| 539 | - name: alloc |
| 540 | - name: fallback |
| 541 | - name: fallback_charge |
| 542 | - name: mem.thp_file |
| 543 | description: Transparent Huge Page File Allocations |
| 544 | unit: "events/s" |
| 545 | chart_type: line |
| 546 | dimensions: |
| 547 | - name: alloc |
| 548 | - name: fallback |
| 549 | - name: mapped |
| 550 | - name: fallback_charge |
| 551 | - name: mem.thp_zero |
| 552 | description: Transparent Huge Zero Page Allocations |
| 553 | unit: "events/s" |
| 554 | chart_type: line |
| 555 | dimensions: |
| 556 | - name: alloc |
| 557 | - name: failed |
| 558 | - name: mem.thp_collapse |
| 559 | description: Transparent Huge Pages Collapsed by khugepaged |
| 560 | unit: "events/s" |
| 561 | chart_type: line |
| 562 | dimensions: |
| 563 | - name: alloc |
| 564 | - name: failed |
| 565 | - name: mem.thp_split |
| 566 | description: Transparent Huge Page Splits |
| 567 | unit: "events/s" |
| 568 | chart_type: line |
| 569 | dimensions: |
| 570 | - name: split |
| 571 | - name: failed |
| 572 | - name: split_pmd |
| 573 | - name: split_deferred |
| 574 | - name: mem.thp_swapout |
| 575 | description: Transparent Huge Pages Swap Out |
| 576 | unit: "events/s" |
| 577 | chart_type: line |
| 578 | dimensions: |
| 579 | - name: swapout |
| 580 | - name: fallback |
| 581 | - name: mem.thp_compact |
| 582 | description: Transparent Huge Pages Compaction |
| 583 | unit: "events/s" |
| 584 | chart_type: line |
| 585 | dimensions: |
| 586 | - name: success |
| 587 | - name: fail |
| 588 | - name: stall |
| 589 | - name: mem.oom_kill |
| 590 | description: Out of Memory Kills |
| 591 | unit: "kills/s" |
| 592 | chart_type: line |
| 593 | dimensions: |
| 594 | - name: kills |
| 595 | - name: mem.numa |
| 596 | description: NUMA events |
| 597 | unit: "events/s" |
| 598 | chart_type: line |
| 599 | dimensions: |
| 600 | - name: local |
| 601 | - name: foreign |
| 602 | - name: interleave |
| 603 | - name: other |
| 604 | - name: pte_updates |
| 605 | - name: huge_pte_updates |
| 606 | - name: hint_faults |
| 607 | - name: hint_faults_local |
| 608 | - name: pages_migrated |
| 609 | - meta: |
| 610 | plugin_name: proc.plugin |
| 611 | module_name: /proc/interrupts |
| 612 | monitored_instance: |
| 613 | name: Interrupts |
| 614 | link: "" |
| 615 | categories: |
| 616 | - data-collection.operating-systems |
| 617 | icon_filename: "linuxserver.svg" |
| 618 | related_resources: |
| 619 | integrations: |
| 620 | list: [] |
| 621 | info_provided_to_referring_integrations: |
| 622 | description: "" |
| 623 | keywords: |
| 624 | - interrupts |
| 625 | overview: |
| 626 | data_collection: |
| 627 | metrics_description: | |
| 628 | Monitors `/proc/interrupts`, a file organized by CPU and then by the type of interrupt. |
| 629 | The numbers reported are the counts of the interrupts that have occurred of each type. |
| 630 | |
| 631 | An interrupt is a signal to the processor emitted by hardware or software indicating an event that needs |
| 632 | immediate attention. The processor then interrupts its current activities and executes the interrupt handler |
| 633 | to deal with the event. This is part of the way a computer multitasks and handles concurrent processing. |
| 634 | |
| 635 | The types of interrupts include: |
| 636 | |
| 637 | - **I/O interrupts**: These are caused by I/O devices like the keyboard, mouse, printer, etc. For example, when |
| 638 | you type something on the keyboard, an interrupt is triggered so the processor can handle the new input. |
| 639 | |
| 640 | - **Timer interrupts**: These are generated at regular intervals by the system's timer circuit. It's primarily |
| 641 | used to switch the CPU among different tasks. |
| 642 | |
| 643 | - **Software interrupts**: These are generated by a program requiring disk I/O operations, or other system resources. |
| 644 | |
| 645 | - **Hardware interrupts**: These are caused by hardware conditions such as power failure, overheating, etc. |
| 646 | |
| 647 | Monitoring `/proc/interrupts` can be used for: |
| 648 | |
| 649 | - **Performance tuning**: If an interrupt is happening very frequently, it could be a sign that a device is not |
| 650 | configured correctly, or there is a software bug causing unnecessary interrupts. This could lead to system |
| 651 | performance degradation. |
| 652 | |
| 653 | - **System troubleshooting**: If you're seeing a lot of unexpected interrupts, it could be a sign of a hardware problem. |
| 654 | |
| 655 | - **Understanding system behavior**: More generally, keeping an eye on what interrupts are occurring can help you |
| 656 | understand what your system is doing. It can provide insights into the system's interaction with hardware, |
| 657 | drivers, and other parts of the kernel. |
| 658 | method_description: "" |
| 659 | supported_platforms: |
| 660 | include: [] |
| 661 | exclude: [] |
| 662 | multi_instance: true |
| 663 | additional_permissions: |
| 664 | description: "" |
| 665 | default_behavior: |
| 666 | auto_detection: |
| 667 | description: "" |
| 668 | limits: |
| 669 | description: "" |
| 670 | performance_impact: |
| 671 | description: "" |
| 672 | setup: |
| 673 | prerequisites: |
| 674 | list: [] |
| 675 | configuration: |
| 676 | file: |
| 677 | name: "" |
| 678 | description: "" |
| 679 | options: |
| 680 | description: "" |
| 681 | folding: |
| 682 | title: "" |
| 683 | enabled: true |
| 684 | list: [] |
| 685 | examples: |
| 686 | folding: |
| 687 | enabled: true |
| 688 | title: "" |
| 689 | list: [] |
| 690 | troubleshooting: |
| 691 | problems: |
| 692 | list: [] |
| 693 | alerts: [] |
| 694 | metrics: |
| 695 | folding: |
| 696 | title: Metrics |
| 697 | enabled: false |
| 698 | description: "" |
| 699 | availability: [] |
| 700 | scopes: |
| 701 | - name: global |
| 702 | description: "" |
| 703 | labels: [] |
| 704 | metrics: |
| 705 | - name: system.interrupts |
| 706 | description: System interrupts |
| 707 | unit: "interrupts/s" |
| 708 | chart_type: stacked |
| 709 | dimensions: |
| 710 | - name: a dimension per device |
| 711 | - name: cpu core |
| 712 | description: "" |
| 713 | labels: |
| 714 | - name: cpu |
| 715 | description: TBD |
| 716 | metrics: |
| 717 | - name: cpu.interrupts |
| 718 | description: CPU interrupts |
| 719 | unit: "interrupts/s" |
| 720 | chart_type: stacked |
| 721 | dimensions: |
| 722 | - name: a dimension per device |
| 723 | - meta: |
| 724 | plugin_name: proc.plugin |
| 725 | module_name: /proc/loadavg |
| 726 | monitored_instance: |
| 727 | name: System Load Average |
| 728 | link: "" |
| 729 | categories: |
| 730 | - data-collection.operating-systems |
| 731 | icon_filename: "linuxserver.svg" |
| 732 | related_resources: |
| 733 | integrations: |
| 734 | list: [] |
| 735 | info_provided_to_referring_integrations: |
| 736 | description: "" |
| 737 | keywords: |
| 738 | - load |
| 739 | - load average |
| 740 | overview: |
| 741 | data_collection: |
| 742 | metrics_description: | |
| 743 | The `/proc/loadavg` file provides information about the system load average. |
| 744 | |
| 745 | The load average is a measure of the amount of computational work that a system performs. It is a |
| 746 | representation of the average system load over a period of time. |
| 747 | |
| 748 | This file contains three numbers representing the system load averages for the last 1, 5, and 15 minutes, |
| 749 | respectively. It also includes the currently running processes and the total number of processes. |
| 750 | |
| 751 | Monitoring the load average can be used for: |
| 752 | |
| 753 | - **System performance**: If the load average is too high, it may indicate that your system is overloaded. |
| 754 | On a system with a single CPU, if the load average is 1, it means the single CPU is fully utilized. If the |
| 755 | load averages are consistently higher than the number of CPUs/cores, it may indicate that your system is |
| 756 | overloaded and tasks are waiting for CPU time. |
| 757 | |
| 758 | - **Troubleshooting**: If the load average is unexpectedly high, it can be a sign of a problem. This could be |
| 759 | due to a runaway process, a software bug, or a hardware issue. |
| 760 | |
| 761 | - **Capacity planning**: By monitoring the load average over time, you can understand the trends in your |
| 762 | system's workload. This can help with capacity planning and scaling decisions. |
| 763 | |
| 764 | Remember that load average not only considers CPU usage, but also includes processes waiting for disk I/O. |
| 765 | Therefore, high load averages could be due to I/O contention as well as CPU contention. |
| 766 | method_description: "" |
| 767 | supported_platforms: |
| 768 | include: [] |
| 769 | exclude: [] |
| 770 | multi_instance: false |
| 771 | additional_permissions: |
| 772 | description: "" |
| 773 | default_behavior: |
| 774 | auto_detection: |
| 775 | description: "" |
| 776 | limits: |
| 777 | description: "" |
| 778 | performance_impact: |
| 779 | description: "" |
| 780 | setup: |
| 781 | prerequisites: |
| 782 | list: [] |
| 783 | configuration: |
| 784 | file: |
| 785 | name: "" |
| 786 | description: "" |
| 787 | options: |
| 788 | description: "" |
| 789 | folding: |
| 790 | title: "" |
| 791 | enabled: true |
| 792 | list: [] |
| 793 | examples: |
| 794 | folding: |
| 795 | enabled: true |
| 796 | title: "" |
| 797 | list: [] |
| 798 | troubleshooting: |
| 799 | problems: |
| 800 | list: [] |
| 801 | alerts: |
| 802 | - name: load_cpu_number |
| 803 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/load.conf |
| 804 | metric: system.load |
| 805 | info: number of active CPU cores in the system |
| 806 | os: "linux" |
| 807 | - name: load_average_15 |
| 808 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/load.conf |
| 809 | metric: system.load |
| 810 | info: system fifteen-minute load average |
| 811 | os: "linux" |
| 812 | - name: load_average_5 |
| 813 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/load.conf |
| 814 | metric: system.load |
| 815 | info: system five-minute load average |
| 816 | os: "linux" |
| 817 | - name: load_average_1 |
| 818 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/load.conf |
| 819 | metric: system.load |
| 820 | info: system one-minute load average |
| 821 | os: "linux" |
| 822 | - name: active_processes |
| 823 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/processes.conf |
| 824 | metric: system.active_processes |
| 825 | info: system process IDs (PID) space utilization |
| 826 | metrics: |
| 827 | folding: |
| 828 | title: Metrics |
| 829 | enabled: false |
| 830 | description: "" |
| 831 | availability: [] |
| 832 | scopes: |
| 833 | - name: global |
| 834 | description: "" |
| 835 | labels: [] |
| 836 | metrics: |
| 837 | - name: system.load |
| 838 | description: System Load Average |
| 839 | unit: "load" |
| 840 | chart_type: line |
| 841 | dimensions: |
| 842 | - name: load1 |
| 843 | - name: load5 |
| 844 | - name: load15 |
| 845 | - name: system.active_processes |
| 846 | description: System Active Processes |
| 847 | unit: "processes" |
| 848 | chart_type: line |
| 849 | dimensions: |
| 850 | - name: active |
| 851 | - meta: |
| 852 | plugin_name: proc.plugin |
| 853 | module_name: /proc/pressure |
| 854 | monitored_instance: |
| 855 | name: Pressure Stall Information |
| 856 | link: "" |
| 857 | categories: |
| 858 | - data-collection.operating-systems |
| 859 | icon_filename: "linuxserver.svg" |
| 860 | related_resources: |
| 861 | integrations: |
| 862 | list: [] |
| 863 | info_provided_to_referring_integrations: |
| 864 | description: "" |
| 865 | keywords: |
| 866 | - pressure |
| 867 | overview: |
| 868 | data_collection: |
| 869 | metrics_description: | |
| 870 | Introduced in Linux kernel 4.20, `/proc/pressure` provides information about system pressure stall information |
| 871 | (PSI). PSI is a feature that allows the system to track the amount of time the system is stalled due to |
| 872 | resource contention, such as CPU, memory, or I/O. |
| 873 | |
| 874 | The collectors monitored 3 separate files for CPU, memory, and I/O: |
| 875 | |
| 876 | - **cpu**: Tracks the amount of time tasks are stalled due to CPU contention. |
| 877 | - **memory**: Tracks the amount of time tasks are stalled due to memory contention. |
| 878 | - **io**: Tracks the amount of time tasks are stalled due to I/O contention. |
| 879 | - **irq**: Tracks the amount of time tasks are stalled due to IRQ contention. |
| 880 | |
| 881 | Each of them provides metrics for stall time over the last 10 seconds, 1 minute, 5 minutes, and 15 minutes. |
| 882 | |
| 883 | Monitoring the /proc/pressure files can provide important insights into system performance and capacity planning: |
| 884 | |
| 885 | - **Identifying resource contention**: If these metrics are consistently high, it indicates that tasks are |
| 886 | frequently being stalled due to lack of resources, which can significantly degrade system performance. |
| 887 | |
| 888 | - **Troubleshooting performance issues**: If a system is experiencing performance issues, these metrics can |
| 889 | help identify whether resource contention is the cause. |
| 890 | |
| 891 | - **Capacity planning**: By monitoring these metrics over time, you can understand trends in resource |
| 892 | utilization and make informed decisions about when to add more resources to your system. |
| 893 | method_description: "" |
| 894 | supported_platforms: |
| 895 | include: [] |
| 896 | exclude: [] |
| 897 | multi_instance: false |
| 898 | additional_permissions: |
| 899 | description: "" |
| 900 | default_behavior: |
| 901 | auto_detection: |
| 902 | description: "" |
| 903 | limits: |
| 904 | description: "" |
| 905 | performance_impact: |
| 906 | description: "" |
| 907 | setup: |
| 908 | prerequisites: |
| 909 | list: [] |
| 910 | configuration: |
| 911 | file: |
| 912 | name: "" |
| 913 | description: "" |
| 914 | options: |
| 915 | description: "" |
| 916 | folding: |
| 917 | title: "" |
| 918 | enabled: true |
| 919 | list: [] |
| 920 | examples: |
| 921 | folding: |
| 922 | enabled: true |
| 923 | title: "" |
| 924 | list: [] |
| 925 | troubleshooting: |
| 926 | problems: |
| 927 | list: [] |
| 928 | alerts: [] |
| 929 | metrics: |
| 930 | folding: |
| 931 | title: Metrics |
| 932 | enabled: false |
| 933 | description: "" |
| 934 | availability: [] |
| 935 | scopes: |
| 936 | - name: global |
| 937 | description: "" |
| 938 | labels: [] |
| 939 | metrics: |
| 940 | - name: system.cpu_some_pressure |
| 941 | description: CPU some pressure |
| 942 | unit: "percentage" |
| 943 | chart_type: line |
| 944 | dimensions: |
| 945 | - name: some10 |
| 946 | - name: some60 |
| 947 | - name: some300 |
| 948 | - name: system.cpu_some_pressure_stall_time |
| 949 | description: CPU some pressure stall time |
| 950 | unit: "ms" |
| 951 | chart_type: line |
| 952 | dimensions: |
| 953 | - name: time |
| 954 | - name: system.cpu_full_pressure |
| 955 | description: CPU full pressure |
| 956 | unit: "percentage" |
| 957 | chart_type: line |
| 958 | dimensions: |
| 959 | - name: some10 |
| 960 | - name: some60 |
| 961 | - name: some300 |
| 962 | - name: system.cpu_full_pressure_stall_time |
| 963 | description: CPU full pressure stall time |
| 964 | unit: "ms" |
| 965 | chart_type: line |
| 966 | dimensions: |
| 967 | - name: time |
| 968 | - name: system.memory_some_pressure |
| 969 | description: Memory some pressure |
| 970 | unit: "percentage" |
| 971 | chart_type: line |
| 972 | dimensions: |
| 973 | - name: some10 |
| 974 | - name: some60 |
| 975 | - name: some300 |
| 976 | - name: system.memory_some_pressure_stall_time |
| 977 | description: Memory some pressure stall time |
| 978 | unit: "ms" |
| 979 | chart_type: line |
| 980 | dimensions: |
| 981 | - name: time |
| 982 | - name: system.memory_full_pressure |
| 983 | description: Memory full pressure |
| 984 | unit: "percentage" |
| 985 | chart_type: line |
| 986 | dimensions: |
| 987 | - name: some10 |
| 988 | - name: some60 |
| 989 | - name: some300 |
| 990 | - name: system.memory_full_pressure_stall_time |
| 991 | description: Memory full pressure stall time |
| 992 | unit: "ms" |
| 993 | chart_type: line |
| 994 | dimensions: |
| 995 | - name: time |
| 996 | - name: system.io_some_pressure |
| 997 | description: I/O some pressure |
| 998 | unit: "percentage" |
| 999 | chart_type: line |
| 1000 | dimensions: |
| 1001 | - name: some10 |
| 1002 | - name: some60 |
| 1003 | - name: some300 |
| 1004 | - name: system.io_some_pressure_stall_time |
| 1005 | description: I/O some pressure stall time |
| 1006 | unit: "ms" |
| 1007 | chart_type: line |
| 1008 | dimensions: |
| 1009 | - name: time |
| 1010 | - name: system.io_full_pressure |
| 1011 | description: I/O some pressure |
| 1012 | unit: "percentage" |
| 1013 | chart_type: line |
| 1014 | dimensions: |
| 1015 | - name: some10 |
| 1016 | - name: some60 |
| 1017 | - name: some300 |
| 1018 | - name: system.io_full_pressure_stall_time |
| 1019 | description: I/O some pressure stall time |
| 1020 | unit: "ms" |
| 1021 | chart_type: line |
| 1022 | dimensions: |
| 1023 | - name: time |
| 1024 | - meta: |
| 1025 | plugin_name: proc.plugin |
| 1026 | module_name: /proc/softirqs |
| 1027 | monitored_instance: |
| 1028 | name: SoftIRQ statistics |
| 1029 | link: "" |
| 1030 | categories: |
| 1031 | - data-collection.operating-systems |
| 1032 | icon_filename: "linuxserver.svg" |
| 1033 | related_resources: |
| 1034 | integrations: |
| 1035 | list: [] |
| 1036 | info_provided_to_referring_integrations: |
| 1037 | description: "" |
| 1038 | keywords: |
| 1039 | - softirqs |
| 1040 | - interrupts |
| 1041 | overview: |
| 1042 | data_collection: |
| 1043 | metrics_description: | |
| 1044 | In the Linux kernel, handling of hardware interrupts is split into two halves: the top half and the bottom half. |
| 1045 | The top half is the routine that responds immediately to an interrupt, while the bottom half is deferred to be processed later. |
| 1046 | |
| 1047 | Softirqs are a mechanism in the Linux kernel used to handle the bottom halves of interrupts, which can be |
| 1048 | deferred and processed later in a context where it's safe to enable interrupts. |
| 1049 | |
| 1050 | The actual work of handling the interrupt is offloaded to a softirq and executed later when the system |
| 1051 | decides it's a good time to process them. This helps to keep the system responsive by not blocking the top |
| 1052 | half for too long, which could lead to missed interrupts. |
| 1053 | |
| 1054 | Monitoring `/proc/softirqs` is useful for: |
| 1055 | |
| 1056 | - **Performance tuning**: A high rate of softirqs could indicate a performance issue. For instance, a high |
| 1057 | rate of network softirqs (`NET_RX` and `NET_TX`) could indicate a network performance issue. |
| 1058 | |
| 1059 | - **Troubleshooting**: If a system is behaving unexpectedly, checking the softirqs could provide clues about |
| 1060 | what is going on. For example, a sudden increase in block device softirqs (BLOCK) might indicate a problem |
| 1061 | with a disk. |
| 1062 | |
| 1063 | - **Understanding system behavior**: Knowing what types of softirqs are happening can help you understand what |
| 1064 | your system is doing, particularly in terms of how it's interacting with hardware and how it's handling |
| 1065 | interrupts. |
| 1066 | method_description: "" |
| 1067 | supported_platforms: |
| 1068 | include: [] |
| 1069 | exclude: [] |
| 1070 | multi_instance: true |
| 1071 | additional_permissions: |
| 1072 | description: "" |
| 1073 | default_behavior: |
| 1074 | auto_detection: |
| 1075 | description: "" |
| 1076 | limits: |
| 1077 | description: "" |
| 1078 | performance_impact: |
| 1079 | description: "" |
| 1080 | setup: |
| 1081 | prerequisites: |
| 1082 | list: [] |
| 1083 | configuration: |
| 1084 | file: |
| 1085 | name: "" |
| 1086 | description: "" |
| 1087 | options: |
| 1088 | description: "" |
| 1089 | folding: |
| 1090 | title: "" |
| 1091 | enabled: true |
| 1092 | list: [] |
| 1093 | examples: |
| 1094 | folding: |
| 1095 | enabled: true |
| 1096 | title: "" |
| 1097 | list: [] |
| 1098 | troubleshooting: |
| 1099 | problems: |
| 1100 | list: [] |
| 1101 | alerts: [] |
| 1102 | metrics: |
| 1103 | folding: |
| 1104 | title: Metrics |
| 1105 | enabled: false |
| 1106 | description: "" |
| 1107 | availability: [] |
| 1108 | scopes: |
| 1109 | - name: global |
| 1110 | description: "" |
| 1111 | labels: [] |
| 1112 | metrics: |
| 1113 | - name: system.softirqs |
| 1114 | description: System softirqs |
| 1115 | unit: "softirqs/s" |
| 1116 | chart_type: stacked |
| 1117 | dimensions: |
| 1118 | - name: a dimension per softirq |
| 1119 | - name: cpu core |
| 1120 | description: "" |
| 1121 | labels: |
| 1122 | - name: cpu |
| 1123 | description: TBD |
| 1124 | metrics: |
| 1125 | - name: cpu.softirqs |
| 1126 | description: CPU softirqs |
| 1127 | unit: "softirqs/s" |
| 1128 | chart_type: stacked |
| 1129 | dimensions: |
| 1130 | - name: a dimension per softirq |
| 1131 | - meta: |
| 1132 | plugin_name: proc.plugin |
| 1133 | module_name: /proc/net/softnet_stat |
| 1134 | monitored_instance: |
| 1135 | name: Softnet Statistics |
| 1136 | link: "" |
| 1137 | categories: |
| 1138 | - data-collection.networking |
| 1139 | icon_filename: "linuxserver.svg" |
| 1140 | related_resources: |
| 1141 | integrations: |
| 1142 | list: [] |
| 1143 | info_provided_to_referring_integrations: |
| 1144 | description: "" |
| 1145 | keywords: |
| 1146 | - softnet |
| 1147 | overview: |
| 1148 | data_collection: |
| 1149 | metrics_description: | |
| 1150 | `/proc/net/softnet_stat` provides statistics that relate to the handling of network packets by softirq. |
| 1151 | |
| 1152 | It provides information about: |
| 1153 | |
| 1154 | - Total number of processed packets (`processed`). |
| 1155 | - Times ksoftirq ran out of quota (`dropped`). |
| 1156 | - Times net_rx_action was rescheduled. |
| 1157 | - Number of times processed all lists before quota. |
| 1158 | - Number of times did not process all lists due to quota. |
| 1159 | - Number of times net_rx_action was rescheduled for GRO (Generic Receive Offload) cells. |
| 1160 | - Number of times GRO cells were processed. |
| 1161 | |
| 1162 | Monitoring the /proc/net/softnet_stat file can be useful for: |
| 1163 | |
| 1164 | - **Network performance monitoring**: By tracking the total number of processed packets and how many packets |
| 1165 | were dropped, you can gain insights into your system's network performance. |
| 1166 | |
| 1167 | - **Troubleshooting**: If you're experiencing network-related issues, this collector can provide valuable clues. |
| 1168 | For instance, a high number of dropped packets may indicate a network problem. |
| 1169 | |
| 1170 | - **Capacity planning**: If your system is consistently processing near its maximum capacity of network |
| 1171 | packets, it might be time to consider upgrading your network infrastructure. |
| 1172 | method_description: "" |
| 1173 | supported_platforms: |
| 1174 | include: [] |
| 1175 | exclude: [] |
| 1176 | multi_instance: true |
| 1177 | additional_permissions: |
| 1178 | description: "" |
| 1179 | default_behavior: |
| 1180 | auto_detection: |
| 1181 | description: "" |
| 1182 | limits: |
| 1183 | description: "" |
| 1184 | performance_impact: |
| 1185 | description: "" |
| 1186 | setup: |
| 1187 | prerequisites: |
| 1188 | list: [] |
| 1189 | configuration: |
| 1190 | file: |
| 1191 | name: "" |
| 1192 | description: "" |
| 1193 | options: |
| 1194 | description: "" |
| 1195 | folding: |
| 1196 | title: "" |
| 1197 | enabled: true |
| 1198 | list: [] |
| 1199 | examples: |
| 1200 | folding: |
| 1201 | enabled: true |
| 1202 | title: "" |
| 1203 | list: [] |
| 1204 | troubleshooting: |
| 1205 | problems: |
| 1206 | list: [] |
| 1207 | alerts: |
| 1208 | - name: 1min_netdev_backlog_exceeded |
| 1209 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/softnet.conf |
| 1210 | metric: system.softnet_stat |
| 1211 | info: average number of dropped packets in the last minute due to exceeded net.core.netdev_max_backlog |
| 1212 | os: "linux" |
| 1213 | - name: 1min_netdev_budget_ran_outs |
| 1214 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/softnet.conf |
| 1215 | metric: system.softnet_stat |
| 1216 | info: |
| 1217 | average number of times ksoftirq ran out of sysctl net.core.netdev_budget or net.core.netdev_budget_usecs with work remaining over the last |
| 1218 | minute (this can be a cause for dropped packets) |
| 1219 | os: "linux" |
| 1220 | metrics: |
| 1221 | folding: |
| 1222 | title: Metrics |
| 1223 | enabled: false |
| 1224 | description: "" |
| 1225 | availability: [] |
| 1226 | scopes: |
| 1227 | - name: global |
| 1228 | description: "" |
| 1229 | labels: [] |
| 1230 | metrics: |
| 1231 | - name: system.softnet_stat |
| 1232 | description: System softnet_stat |
| 1233 | unit: "events/s" |
| 1234 | chart_type: line |
| 1235 | dimensions: |
| 1236 | - name: processed |
| 1237 | - name: dropped |
| 1238 | - name: squeezed |
| 1239 | - name: received_rps |
| 1240 | - name: flow_limit_count |
| 1241 | - name: cpu core |
| 1242 | description: "" |
| 1243 | labels: [] |
| 1244 | metrics: |
| 1245 | - name: cpu.softnet_stat |
| 1246 | description: CPU softnet_stat |
| 1247 | unit: "events/s" |
| 1248 | chart_type: line |
| 1249 | dimensions: |
| 1250 | - name: processed |
| 1251 | - name: dropped |
| 1252 | - name: squeezed |
| 1253 | - name: received_rps |
| 1254 | - name: flow_limit_count |
| 1255 | - meta: |
| 1256 | plugin_name: proc.plugin |
| 1257 | module_name: /proc/meminfo |
| 1258 | monitored_instance: |
| 1259 | name: Memory Usage |
| 1260 | link: "" |
| 1261 | categories: |
| 1262 | - data-collection.operating-systems |
| 1263 | icon_filename: "linuxserver.svg" |
| 1264 | related_resources: |
| 1265 | integrations: |
| 1266 | list: [] |
| 1267 | info_provided_to_referring_integrations: |
| 1268 | description: "" |
| 1269 | keywords: |
| 1270 | - memory |
| 1271 | - ram |
| 1272 | - available |
| 1273 | - committed |
| 1274 | overview: |
| 1275 | data_collection: |
| 1276 | metrics_description: | |
| 1277 | `/proc/meminfo` provides detailed information about the system's current memory usage. It includes information |
| 1278 | about different types of memory, RAM, Swap, ZSwap, HugePages, Transparent HugePages (THP), Kernel memory, |
| 1279 | SLAB memory, memory mappings, and more. |
| 1280 | |
| 1281 | Monitoring /proc/meminfo can be useful for: |
| 1282 | |
| 1283 | - **Performance Tuning**: Understanding your system's memory usage can help you make decisions about system |
| 1284 | tuning and optimization. For example, if your system is frequently low on free memory, it might benefit |
| 1285 | from more RAM. |
| 1286 | |
| 1287 | - **Troubleshooting**: If your system is experiencing problems, `/proc/meminfo` can provide clues about |
| 1288 | whether memory usage is a factor. For example, if your system is slow and cached swap is high, it could |
| 1289 | mean that your system is swapping out a lot of memory to disk, which can degrade performance. |
| 1290 | |
| 1291 | - **Capacity Planning**: By monitoring memory usage over time, you can understand trends and make informed |
| 1292 | decisions about future capacity needs. |
| 1293 | method_description: "" |
| 1294 | supported_platforms: |
| 1295 | include: [] |
| 1296 | exclude: [] |
| 1297 | multi_instance: false |
| 1298 | additional_permissions: |
| 1299 | description: "" |
| 1300 | default_behavior: |
| 1301 | auto_detection: |
| 1302 | description: "" |
| 1303 | limits: |
| 1304 | description: "" |
| 1305 | performance_impact: |
| 1306 | description: "" |
| 1307 | setup: |
| 1308 | prerequisites: |
| 1309 | list: [] |
| 1310 | configuration: |
| 1311 | file: |
| 1312 | name: "" |
| 1313 | description: "" |
| 1314 | options: |
| 1315 | description: "" |
| 1316 | folding: |
| 1317 | title: "" |
| 1318 | enabled: true |
| 1319 | list: [] |
| 1320 | examples: |
| 1321 | folding: |
| 1322 | enabled: true |
| 1323 | title: "" |
| 1324 | list: [] |
| 1325 | troubleshooting: |
| 1326 | problems: |
| 1327 | list: [] |
| 1328 | alerts: |
| 1329 | - name: ram_in_use |
| 1330 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/ram.conf |
| 1331 | metric: system.ram |
| 1332 | info: system memory utilization |
| 1333 | os: "linux" |
| 1334 | - name: ram_available |
| 1335 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/ram.conf |
| 1336 | metric: mem.available |
| 1337 | info: percentage of estimated amount of RAM available for userspace processes, without causing swapping |
| 1338 | os: "linux" |
| 1339 | - name: used_swap |
| 1340 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/swap.conf |
| 1341 | metric: mem.swap |
| 1342 | info: swap memory utilization |
| 1343 | os: "linux freebsd" |
| 1344 | - name: 1hour_memory_hw_corrupted |
| 1345 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/memory.conf |
| 1346 | metric: mem.hwcorrupt |
| 1347 | info: amount of memory corrupted due to a hardware failure |
| 1348 | os: "linux" |
| 1349 | metrics: |
| 1350 | folding: |
| 1351 | title: Metrics |
| 1352 | enabled: false |
| 1353 | description: "" |
| 1354 | availability: [] |
| 1355 | scopes: |
| 1356 | - name: global |
| 1357 | description: "" |
| 1358 | labels: [] |
| 1359 | metrics: |
| 1360 | - name: system.ram |
| 1361 | description: System RAM |
| 1362 | unit: "MiB" |
| 1363 | chart_type: stacked |
| 1364 | dimensions: |
| 1365 | - name: free |
| 1366 | - name: used |
| 1367 | - name: cached |
| 1368 | - name: buffers |
| 1369 | - name: mem.available |
| 1370 | description: Available RAM for applications |
| 1371 | unit: "MiB" |
| 1372 | chart_type: area |
| 1373 | dimensions: |
| 1374 | - name: avail |
| 1375 | - name: mem.swap |
| 1376 | description: System Swap |
| 1377 | unit: "MiB" |
| 1378 | chart_type: stacked |
| 1379 | dimensions: |
| 1380 | - name: free |
| 1381 | - name: used |
| 1382 | - name: mem.swap_cached |
| 1383 | description: Swap Memory Cached in RAM |
| 1384 | unit: "MiB" |
| 1385 | chart_type: stacked |
| 1386 | dimensions: |
| 1387 | - name: cached |
| 1388 | - name: mem.zswap |
| 1389 | description: Zswap Usage |
| 1390 | unit: "MiB" |
| 1391 | chart_type: stacked |
| 1392 | dimensions: |
| 1393 | - name: in-ram |
| 1394 | - name: on-disk |
| 1395 | - name: mem.hwcorrupt |
| 1396 | description: Corrupted Memory detected by ECC |
| 1397 | unit: "MiB" |
| 1398 | chart_type: line |
| 1399 | dimensions: |
| 1400 | - name: HardwareCorrupted |
| 1401 | - name: mem.commited |
| 1402 | description: Committed (Allocated) Memory |
| 1403 | unit: "MiB" |
| 1404 | chart_type: area |
| 1405 | dimensions: |
| 1406 | - name: Commited_AS |
| 1407 | - name: mem.writeback |
| 1408 | description: Writeback Memory |
| 1409 | unit: "MiB" |
| 1410 | chart_type: line |
| 1411 | dimensions: |
| 1412 | - name: Dirty |
| 1413 | - name: Writeback |
| 1414 | - name: FuseWriteback |
| 1415 | - name: NfsWriteback |
| 1416 | - name: Bounce |
| 1417 | - name: mem.kernel |
| 1418 | description: Memory Used by Kernel |
| 1419 | unit: "MiB" |
| 1420 | chart_type: stacked |
| 1421 | dimensions: |
| 1422 | - name: Slab |
| 1423 | - name: KernelStack |
| 1424 | - name: PageTables |
| 1425 | - name: VmallocUsed |
| 1426 | - name: Percpu |
| 1427 | - name: mem.slab |
| 1428 | description: Reclaimable Kernel Memory |
| 1429 | unit: "MiB" |
| 1430 | chart_type: stacked |
| 1431 | dimensions: |
| 1432 | - name: reclaimable |
| 1433 | - name: unreclaimable |
| 1434 | - name: mem.hugepages |
| 1435 | description: Dedicated HugePages Memory |
| 1436 | unit: "MiB" |
| 1437 | chart_type: stacked |
| 1438 | dimensions: |
| 1439 | - name: free |
| 1440 | - name: used |
| 1441 | - name: surplus |
| 1442 | - name: reserved |
| 1443 | - name: mem.thp |
| 1444 | description: Transparent HugePages Memory |
| 1445 | unit: "MiB" |
| 1446 | chart_type: stacked |
| 1447 | dimensions: |
| 1448 | - name: anonymous |
| 1449 | - name: shmem |
| 1450 | - name: mem.thp_details |
| 1451 | description: Details of Transparent HugePages Usage |
| 1452 | unit: "MiB" |
| 1453 | chart_type: line |
| 1454 | dimensions: |
| 1455 | - name: ShmemPmdMapped |
| 1456 | - name: FileHugePages |
| 1457 | - name: FilePmdMapped |
| 1458 | - name: mem.reclaiming |
| 1459 | description: Memory Reclaiming |
| 1460 | unit: "MiB" |
| 1461 | chart_type: line |
| 1462 | dimensions: |
| 1463 | - name: Active |
| 1464 | - name: Inactive |
| 1465 | - name: Active(anon) |
| 1466 | - name: Inactive(anon) |
| 1467 | - name: Active(file) |
| 1468 | - name: Inactive(file) |
| 1469 | - name: Unevictable |
| 1470 | - name: Mlocked |
| 1471 | - name: mem.high_low |
| 1472 | description: High and Low Used and Free Memory Areas |
| 1473 | unit: "MiB" |
| 1474 | chart_type: stacked |
| 1475 | dimensions: |
| 1476 | - name: high_used |
| 1477 | - name: low_used |
| 1478 | - name: high_free |
| 1479 | - name: low_free |
| 1480 | - name: mem.cma |
| 1481 | description: Contiguous Memory Allocator (CMA) Memory |
| 1482 | unit: "MiB" |
| 1483 | chart_type: stacked |
| 1484 | dimensions: |
| 1485 | - name: used |
| 1486 | - name: free |
| 1487 | - name: mem.directmaps |
| 1488 | description: Direct Memory Mappings |
| 1489 | unit: "MiB" |
| 1490 | chart_type: stacked |
| 1491 | dimensions: |
| 1492 | - name: 4k |
| 1493 | - name: 2m |
| 1494 | - name: 4m |
| 1495 | - name: 1g |
| 1496 | - meta: |
| 1497 | plugin_name: proc.plugin |
| 1498 | module_name: /proc/pagetypeinfo |
| 1499 | monitored_instance: |
| 1500 | name: Page types |
| 1501 | link: "" |
| 1502 | categories: |
| 1503 | - data-collection.operating-systems |
| 1504 | icon_filename: "microchip.svg" |
| 1505 | related_resources: |
| 1506 | integrations: |
| 1507 | list: [] |
| 1508 | info_provided_to_referring_integrations: |
| 1509 | description: "" |
| 1510 | keywords: |
| 1511 | - memory page types |
| 1512 | overview: |
| 1513 | data_collection: |
| 1514 | metrics_description: "This integration provides metrics about the system's memory page types" |
| 1515 | method_description: "" |
| 1516 | supported_platforms: |
| 1517 | include: [] |
| 1518 | exclude: [] |
| 1519 | multi_instance: false |
| 1520 | additional_permissions: |
| 1521 | description: "" |
| 1522 | default_behavior: |
| 1523 | auto_detection: |
| 1524 | description: "" |
| 1525 | limits: |
| 1526 | description: "" |
| 1527 | performance_impact: |
| 1528 | description: "" |
| 1529 | setup: |
| 1530 | prerequisites: |
| 1531 | list: [] |
| 1532 | configuration: |
| 1533 | file: |
| 1534 | name: "" |
| 1535 | description: "" |
| 1536 | options: |
| 1537 | description: "" |
| 1538 | folding: |
| 1539 | title: "" |
| 1540 | enabled: true |
| 1541 | list: [] |
| 1542 | examples: |
| 1543 | folding: |
| 1544 | enabled: true |
| 1545 | title: "" |
| 1546 | list: [] |
| 1547 | troubleshooting: |
| 1548 | problems: |
| 1549 | list: [] |
| 1550 | alerts: [] |
| 1551 | metrics: |
| 1552 | folding: |
| 1553 | title: Metrics |
| 1554 | enabled: false |
| 1555 | description: "" |
| 1556 | availability: [] |
| 1557 | scopes: |
| 1558 | - name: global |
| 1559 | description: "" |
| 1560 | labels: [] |
| 1561 | metrics: |
| 1562 | - name: mem.pagetype_global |
| 1563 | description: System orders available |
| 1564 | unit: "B" |
| 1565 | chart_type: stacked |
| 1566 | dimensions: |
| 1567 | - name: a dimension per pagesize |
| 1568 | - name: node, zone, type |
| 1569 | description: "" |
| 1570 | labels: |
| 1571 | - name: node_id |
| 1572 | description: TBD |
| 1573 | - name: node_zone |
| 1574 | description: TBD |
| 1575 | - name: node_type |
| 1576 | description: TBD |
| 1577 | metrics: |
| 1578 | - name: mem.pagetype |
| 1579 | description: pagetype_Node{node}_{zone}_{type} |
| 1580 | unit: "B" |
| 1581 | chart_type: stacked |
| 1582 | dimensions: |
| 1583 | - name: a dimension per pagesize |
| 1584 | - meta: |
| 1585 | plugin_name: proc.plugin |
| 1586 | module_name: /sys/devices/system/edac/mc |
| 1587 | monitored_instance: |
| 1588 | name: Memory modules (DIMMs) |
| 1589 | link: "" |
| 1590 | categories: |
| 1591 | - data-collection.hardware-and-sensors |
| 1592 | icon_filename: "microchip.svg" |
| 1593 | related_resources: |
| 1594 | integrations: |
| 1595 | list: [] |
| 1596 | info_provided_to_referring_integrations: |
| 1597 | description: "" |
| 1598 | keywords: |
| 1599 | - edac |
| 1600 | - ecc |
| 1601 | - dimm |
| 1602 | - ram |
| 1603 | - hardware |
| 1604 | overview: |
| 1605 | data_collection: |
| 1606 | metrics_description: | |
| 1607 | The Error Detection and Correction (EDAC) subsystem is detecting and reporting errors in the system's memory, |
| 1608 | primarily ECC (Error-Correcting Code) memory errors. |
| 1609 | |
| 1610 | The collector provides data for: |
| 1611 | |
| 1612 | - Per memory controller (MC): correctable and uncorrectable errors. These can be of 2 kinds: |
| 1613 | - errors related to a DIMM |
| 1614 | - errors that cannot be associated with a DIMM |
| 1615 | |
| 1616 | - Per memory DIMM: correctable and uncorrectable errors. There are 2 kinds: |
| 1617 | - memory controllers that can identify the physical DIMMS and report errors directly for them, |
| 1618 | - memory controllers that report errors for memory address ranges that can be linked to dimms. |
| 1619 | In this case the DIMMS reported may be more than the physical DIMMS installed. |
| 1620 | method_description: "" |
| 1621 | supported_platforms: |
| 1622 | include: [] |
| 1623 | exclude: [] |
| 1624 | multi_instance: true |
| 1625 | additional_permissions: |
| 1626 | description: "" |
| 1627 | default_behavior: |
| 1628 | auto_detection: |
| 1629 | description: "" |
| 1630 | limits: |
| 1631 | description: "" |
| 1632 | performance_impact: |
| 1633 | description: "" |
| 1634 | setup: |
| 1635 | prerequisites: |
| 1636 | list: [] |
| 1637 | configuration: |
| 1638 | file: |
| 1639 | name: "" |
| 1640 | description: "" |
| 1641 | options: |
| 1642 | description: "" |
| 1643 | folding: |
| 1644 | title: "" |
| 1645 | enabled: true |
| 1646 | list: [] |
| 1647 | examples: |
| 1648 | folding: |
| 1649 | enabled: true |
| 1650 | title: "" |
| 1651 | list: [] |
| 1652 | troubleshooting: |
| 1653 | problems: |
| 1654 | list: [] |
| 1655 | alerts: |
| 1656 | - name: ecc_memory_mc_noinfo_correctable |
| 1657 | metric: mem.edac_mc_errors |
| 1658 | info: memory controller ${label:controller} ECC correctable errors (unknown DIMM slot) |
| 1659 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/memory.conf |
| 1660 | - name: ecc_memory_mc_noinfo_uncorrectable |
| 1661 | metric: mem.edac_mc_errors |
| 1662 | info: memory controller ${label:controller} ECC uncorrectable errors (unknown DIMM slot) |
| 1663 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/memory.conf |
| 1664 | - name: ecc_memory_dimm_correctable |
| 1665 | metric: mem.edac_mc_dimm_errors |
| 1666 | info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC correctable errors |
| 1667 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/memory.conf |
| 1668 | - name: ecc_memory_dimm_uncorrectable |
| 1669 | metric: mem.edac_mc_dimm_errors |
| 1670 | info: DIMM ${label:dimm} controller ${label:controller} (location ${label:dimm_location}) ECC uncorrectable errors |
| 1671 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/memory.conf |
| 1672 | metrics: |
| 1673 | folding: |
| 1674 | title: Metrics |
| 1675 | enabled: false |
| 1676 | description: "" |
| 1677 | availability: [] |
| 1678 | scopes: |
| 1679 | - name: memory controller |
| 1680 | description: These metrics refer to the memory controller. |
| 1681 | labels: |
| 1682 | - name: controller |
| 1683 | description: "[mcX](https://www.kernel.org/doc/html/v5.0/admin-guide/ras.html#mcx-directories) directory name of this memory controller." |
| 1684 | - name: mc_name |
| 1685 | description: Memory controller type. |
| 1686 | - name: size_mb |
| 1687 | description: The amount of memory in megabytes that this memory controller manages. |
| 1688 | - name: max_location |
| 1689 | description: Last available memory slot in this memory controller. |
| 1690 | metrics: |
| 1691 | - name: mem.edac_mc_errors |
| 1692 | description: Memory Controller (MC) Error Detection And Correction (EDAC) Errors |
| 1693 | unit: errors |
| 1694 | chart_type: line |
| 1695 | dimensions: |
| 1696 | - name: correctable |
| 1697 | - name: uncorrectable |
| 1698 | - name: correctable_noinfo |
| 1699 | - name: uncorrectable_noinfo |
| 1700 | - name: memory module |
| 1701 | description: These metrics refer to the memory module (or rank, [depends on the memory controller](https://www.kernel.org/doc/html/v5.0/admin-guide/ras.html#f5)). |
| 1702 | labels: |
| 1703 | - name: controller |
| 1704 | description: "[mcX](https://www.kernel.org/doc/html/v5.0/admin-guide/ras.html#mcx-directories) directory name of this memory controller." |
| 1705 | - name: dimm |
| 1706 | description: "[dimmX or rankX](https://www.kernel.org/doc/html/v5.0/admin-guide/ras.html#dimmx-or-rankx-directories) directory name of this memory module." |
| 1707 | - name: dimm_dev_type |
| 1708 | description: Type of DRAM device used in this memory module. For example, x1, x2, x4, x8. |
| 1709 | - name: dimm_edac_mode |
| 1710 | description: Used type of error detection and correction. For example, S4ECD4ED would mean a Chipkill with x4 DRAM. |
| 1711 | - name: dimm_label |
| 1712 | description: Label assigned to this memory module. |
| 1713 | - name: dimm_location |
| 1714 | description: Location of the memory module. |
| 1715 | - name: dimm_mem_type |
| 1716 | description: Type of the memory module. |
| 1717 | - name: size |
| 1718 | description: The amount of memory in megabytes that this memory module manages. |
| 1719 | metrics: |
| 1720 | - name: mem.edac_mc_errors |
| 1721 | description: DIMM Error Detection And Correction (EDAC) Errors |
| 1722 | unit: errors |
| 1723 | chart_type: line |
| 1724 | dimensions: |
| 1725 | - name: correctable |
| 1726 | - name: uncorrectable |
| 1727 | - meta: |
| 1728 | plugin_name: proc.plugin |
| 1729 | module_name: /sys/devices/system/node |
| 1730 | monitored_instance: |
| 1731 | name: Non-Uniform Memory Access |
| 1732 | link: "" |
| 1733 | categories: |
| 1734 | - data-collection.operating-systems |
| 1735 | icon_filename: "linuxserver.svg" |
| 1736 | related_resources: |
| 1737 | integrations: |
| 1738 | list: [] |
| 1739 | info_provided_to_referring_integrations: |
| 1740 | description: "" |
| 1741 | keywords: |
| 1742 | - numa |
| 1743 | overview: |
| 1744 | data_collection: |
| 1745 | metrics_description: | |
| 1746 | Information about NUMA (Non-Uniform Memory Access) nodes on the system. |
| 1747 | |
| 1748 | NUMA is a method of configuring a cluster of microprocessor in a multiprocessing system so that they can |
| 1749 | share memory locally, improving performance and the ability of the system to be expanded. NUMA is used in a |
| 1750 | symmetric multiprocessing (SMP) system. |
| 1751 | |
| 1752 | In a NUMA system, processors, memory, and I/O devices are grouped together into cells, also known as nodes. |
| 1753 | Each node has its own memory and set of I/O devices, and one or more processors. While a processor can access |
| 1754 | memory in any of the nodes, it does so faster when accessing memory within its own node. |
| 1755 | |
| 1756 | The collector provides statistics on memory allocations for processes running on the NUMA nodes, revealing the |
| 1757 | efficiency of memory allocations in multi-node systems. |
| 1758 | method_description: "" |
| 1759 | supported_platforms: |
| 1760 | include: [] |
| 1761 | exclude: [] |
| 1762 | multi_instance: true |
| 1763 | additional_permissions: |
| 1764 | description: "" |
| 1765 | default_behavior: |
| 1766 | auto_detection: |
| 1767 | description: "" |
| 1768 | limits: |
| 1769 | description: "" |
| 1770 | performance_impact: |
| 1771 | description: "" |
| 1772 | setup: |
| 1773 | prerequisites: |
| 1774 | list: [] |
| 1775 | configuration: |
| 1776 | file: |
| 1777 | name: "" |
| 1778 | description: "" |
| 1779 | options: |
| 1780 | description: "" |
| 1781 | folding: |
| 1782 | title: "" |
| 1783 | enabled: true |
| 1784 | list: [] |
| 1785 | examples: |
| 1786 | folding: |
| 1787 | enabled: true |
| 1788 | title: "" |
| 1789 | list: [] |
| 1790 | troubleshooting: |
| 1791 | problems: |
| 1792 | list: [] |
| 1793 | alerts: [] |
| 1794 | metrics: |
| 1795 | folding: |
| 1796 | title: Metrics |
| 1797 | enabled: false |
| 1798 | description: "" |
| 1799 | availability: [] |
| 1800 | scopes: |
| 1801 | - name: numa node |
| 1802 | description: "" |
| 1803 | labels: |
| 1804 | - name: numa_node |
| 1805 | description: TBD |
| 1806 | metrics: |
| 1807 | - name: mem.numa_nodes |
| 1808 | description: NUMA events |
| 1809 | unit: "events/s" |
| 1810 | chart_type: line |
| 1811 | dimensions: |
| 1812 | - name: hit |
| 1813 | - name: miss |
| 1814 | - name: local |
| 1815 | - name: foreign |
| 1816 | - name: interleave |
| 1817 | - name: other |
| 1818 | - meta: |
| 1819 | plugin_name: proc.plugin |
| 1820 | module_name: /sys/kernel/mm/ksm |
| 1821 | monitored_instance: |
| 1822 | name: Kernel Same-Page Merging |
| 1823 | link: "" |
| 1824 | categories: |
| 1825 | - data-collection.operating-systems |
| 1826 | icon_filename: "microchip.svg" |
| 1827 | related_resources: |
| 1828 | integrations: |
| 1829 | list: [] |
| 1830 | info_provided_to_referring_integrations: |
| 1831 | description: "" |
| 1832 | keywords: |
| 1833 | - ksm |
| 1834 | - samepage |
| 1835 | - merging |
| 1836 | overview: |
| 1837 | data_collection: |
| 1838 | metrics_description: | |
| 1839 | Kernel Samepage Merging (KSM) is a memory-saving feature in Linux that enables the kernel to examine the |
| 1840 | memory of different processes and identify identical pages. It then merges these identical pages into a |
| 1841 | single page that the processes share. This is particularly useful for virtualization, where multiple virtual |
| 1842 | machines might be running the same operating system or applications and have many identical pages. |
| 1843 | |
| 1844 | The collector provides information about the operation and effectiveness of KSM on your system. |
| 1845 | method_description: "" |
| 1846 | supported_platforms: |
| 1847 | include: [] |
| 1848 | exclude: [] |
| 1849 | multi_instance: false |
| 1850 | additional_permissions: |
| 1851 | description: "" |
| 1852 | default_behavior: |
| 1853 | auto_detection: |
| 1854 | description: "" |
| 1855 | limits: |
| 1856 | description: "" |
| 1857 | performance_impact: |
| 1858 | description: "" |
| 1859 | setup: |
| 1860 | prerequisites: |
| 1861 | list: [] |
| 1862 | configuration: |
| 1863 | file: |
| 1864 | name: "" |
| 1865 | description: "" |
| 1866 | options: |
| 1867 | description: "" |
| 1868 | folding: |
| 1869 | title: "" |
| 1870 | enabled: true |
| 1871 | list: [] |
| 1872 | examples: |
| 1873 | folding: |
| 1874 | enabled: true |
| 1875 | title: "" |
| 1876 | list: [] |
| 1877 | troubleshooting: |
| 1878 | problems: |
| 1879 | list: [] |
| 1880 | alerts: [] |
| 1881 | metrics: |
| 1882 | folding: |
| 1883 | title: Metrics |
| 1884 | enabled: false |
| 1885 | description: "" |
| 1886 | availability: [] |
| 1887 | scopes: |
| 1888 | - name: global |
| 1889 | description: "" |
| 1890 | labels: [] |
| 1891 | metrics: |
| 1892 | - name: mem.ksm |
| 1893 | description: Kernel Same Page Merging |
| 1894 | unit: "MiB" |
| 1895 | chart_type: stacked |
| 1896 | dimensions: |
| 1897 | - name: shared |
| 1898 | - name: unshared |
| 1899 | - name: sharing |
| 1900 | - name: volatile |
| 1901 | - name: mem.ksm_savings |
| 1902 | description: Kernel Same Page Merging Savings |
| 1903 | unit: "MiB" |
| 1904 | chart_type: area |
| 1905 | dimensions: |
| 1906 | - name: savings |
| 1907 | - name: offered |
| 1908 | - name: mem.ksm_ratios |
| 1909 | description: Kernel Same Page Merging Effectiveness |
| 1910 | unit: "percentage" |
| 1911 | chart_type: line |
| 1912 | dimensions: |
| 1913 | - name: savings |
| 1914 | - meta: |
| 1915 | plugin_name: proc.plugin |
| 1916 | module_name: /sys/block/zram |
| 1917 | monitored_instance: |
| 1918 | name: ZRAM |
| 1919 | link: "" |
| 1920 | categories: |
| 1921 | - data-collection.operating-systems |
| 1922 | icon_filename: "microchip.svg" |
| 1923 | related_resources: |
| 1924 | integrations: |
| 1925 | list: [] |
| 1926 | info_provided_to_referring_integrations: |
| 1927 | description: "" |
| 1928 | keywords: |
| 1929 | - zram |
| 1930 | overview: |
| 1931 | data_collection: |
| 1932 | metrics_description: | |
| 1933 | zRAM, or compressed RAM, is a block device that uses a portion of your system's RAM as a block device. |
| 1934 | The data written to this block device is compressed and stored in memory. |
| 1935 | |
| 1936 | The collectors provides information about the operation and the effectiveness of zRAM on your system. |
| 1937 | method_description: "" |
| 1938 | supported_platforms: |
| 1939 | include: [] |
| 1940 | exclude: [] |
| 1941 | multi_instance: true |
| 1942 | additional_permissions: |
| 1943 | description: "" |
| 1944 | default_behavior: |
| 1945 | auto_detection: |
| 1946 | description: "" |
| 1947 | limits: |
| 1948 | description: "" |
| 1949 | performance_impact: |
| 1950 | description: "" |
| 1951 | setup: |
| 1952 | prerequisites: |
| 1953 | list: [] |
| 1954 | configuration: |
| 1955 | file: |
| 1956 | name: "" |
| 1957 | description: "" |
| 1958 | options: |
| 1959 | description: "" |
| 1960 | folding: |
| 1961 | title: "" |
| 1962 | enabled: true |
| 1963 | list: [] |
| 1964 | examples: |
| 1965 | folding: |
| 1966 | enabled: true |
| 1967 | title: "" |
| 1968 | list: [] |
| 1969 | troubleshooting: |
| 1970 | problems: |
| 1971 | list: [] |
| 1972 | alerts: [] |
| 1973 | metrics: |
| 1974 | folding: |
| 1975 | title: Metrics |
| 1976 | enabled: false |
| 1977 | description: "" |
| 1978 | availability: [] |
| 1979 | scopes: |
| 1980 | - name: zram device |
| 1981 | description: "" |
| 1982 | labels: |
| 1983 | - name: device |
| 1984 | description: TBD |
| 1985 | metrics: |
| 1986 | - name: mem.zram_usage |
| 1987 | description: ZRAM Memory Usage |
| 1988 | unit: "MiB" |
| 1989 | chart_type: area |
| 1990 | dimensions: |
| 1991 | - name: compressed |
| 1992 | - name: metadata |
| 1993 | - name: mem.zram_savings |
| 1994 | description: ZRAM Memory Savings |
| 1995 | unit: "MiB" |
| 1996 | chart_type: area |
| 1997 | dimensions: |
| 1998 | - name: savings |
| 1999 | - name: original |
| 2000 | - name: mem.zram_ratio |
| 2001 | description: ZRAM Compression Ratio (original to compressed) |
| 2002 | unit: "ratio" |
| 2003 | chart_type: line |
| 2004 | dimensions: |
| 2005 | - name: ratio |
| 2006 | - name: mem.zram_efficiency |
| 2007 | description: ZRAM Efficiency |
| 2008 | unit: "percentage" |
| 2009 | chart_type: line |
| 2010 | dimensions: |
| 2011 | - name: percent |
| 2012 | - meta: |
| 2013 | plugin_name: proc.plugin |
| 2014 | module_name: ipc |
| 2015 | monitored_instance: |
| 2016 | name: Inter Process Communication |
| 2017 | link: "" |
| 2018 | categories: |
| 2019 | - data-collection.operating-systems |
| 2020 | icon_filename: "network-wired.svg" |
| 2021 | related_resources: |
| 2022 | integrations: |
| 2023 | list: [] |
| 2024 | info_provided_to_referring_integrations: |
| 2025 | description: "" |
| 2026 | keywords: |
| 2027 | - ipc |
| 2028 | - semaphores |
| 2029 | - shared memory |
| 2030 | overview: |
| 2031 | data_collection: |
| 2032 | metrics_description: | |
| 2033 | IPC stands for Inter-Process Communication. It is a mechanism which allows processes to communicate with each |
| 2034 | other and synchronize their actions. |
| 2035 | |
| 2036 | This collector exposes information about: |
| 2037 | |
| 2038 | - Message Queues: This allows messages to be exchanged between processes. It's a more flexible method that |
| 2039 | allows messages to be placed onto a queue and read at a later time. |
| 2040 | |
| 2041 | - Shared Memory: This method allows for the fastest form of IPC because processes can exchange data by |
| 2042 | reading/writing into shared memory segments. |
| 2043 | |
| 2044 | - Semaphores: They are used to synchronize the operations performed by independent processes. So, if multiple |
| 2045 | processes are trying to access a single shared resource, semaphores can ensure that only one process |
| 2046 | accesses the resource at a given time. |
| 2047 | method_description: "" |
| 2048 | supported_platforms: |
| 2049 | include: [] |
| 2050 | exclude: [] |
| 2051 | multi_instance: false |
| 2052 | additional_permissions: |
| 2053 | description: "" |
| 2054 | default_behavior: |
| 2055 | auto_detection: |
| 2056 | description: "" |
| 2057 | limits: |
| 2058 | description: "" |
| 2059 | performance_impact: |
| 2060 | description: "" |
| 2061 | setup: |
| 2062 | prerequisites: |
| 2063 | list: [] |
| 2064 | configuration: |
| 2065 | file: |
| 2066 | name: "" |
| 2067 | description: "" |
| 2068 | options: |
| 2069 | description: "" |
| 2070 | folding: |
| 2071 | title: "" |
| 2072 | enabled: true |
| 2073 | list: [] |
| 2074 | examples: |
| 2075 | folding: |
| 2076 | enabled: true |
| 2077 | title: "" |
| 2078 | list: [] |
| 2079 | troubleshooting: |
| 2080 | problems: |
| 2081 | list: [] |
| 2082 | alerts: |
| 2083 | - name: semaphores_used |
| 2084 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/ipc.conf |
| 2085 | metric: system.ipc_semaphores |
| 2086 | info: IPC semaphore utilization |
| 2087 | os: "linux" |
| 2088 | - name: semaphore_arrays_used |
| 2089 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/ipc.conf |
| 2090 | metric: system.ipc_semaphore_arrays |
| 2091 | info: IPC semaphore arrays utilization |
| 2092 | os: "linux" |
| 2093 | metrics: |
| 2094 | folding: |
| 2095 | title: Metrics |
| 2096 | enabled: false |
| 2097 | description: "" |
| 2098 | availability: [] |
| 2099 | scopes: |
| 2100 | - name: global |
| 2101 | description: "" |
| 2102 | labels: [] |
| 2103 | metrics: |
| 2104 | - name: system.ipc_semaphores |
| 2105 | description: IPC Semaphores |
| 2106 | unit: "semaphores" |
| 2107 | chart_type: area |
| 2108 | dimensions: |
| 2109 | - name: semaphores |
| 2110 | - name: system.ipc_semaphore_arrays |
| 2111 | description: IPC Semaphore Arrays |
| 2112 | unit: "arrays" |
| 2113 | chart_type: area |
| 2114 | dimensions: |
| 2115 | - name: arrays |
| 2116 | - name: system.message_queue_message |
| 2117 | description: IPC Message Queue Number of Messages |
| 2118 | unit: "messages" |
| 2119 | chart_type: stacked |
| 2120 | dimensions: |
| 2121 | - name: a dimension per queue |
| 2122 | - name: system.message_queue_bytes |
| 2123 | description: IPC Message Queue Used Bytes |
| 2124 | unit: "bytes" |
| 2125 | chart_type: stacked |
| 2126 | dimensions: |
| 2127 | - name: a dimension per queue |
| 2128 | - name: system.shared_memory_segments |
| 2129 | description: IPC Shared Memory Number of Segments |
| 2130 | unit: "segments" |
| 2131 | chart_type: stacked |
| 2132 | dimensions: |
| 2133 | - name: segments |
| 2134 | - name: system.shared_memory_bytes |
| 2135 | description: IPC Shared Memory Used Bytes |
| 2136 | unit: "bytes" |
| 2137 | chart_type: stacked |
| 2138 | dimensions: |
| 2139 | - name: bytes |
| 2140 | - meta: |
| 2141 | plugin_name: proc.plugin |
| 2142 | module_name: /proc/diskstats |
| 2143 | monitored_instance: |
| 2144 | name: Disk Statistics |
| 2145 | link: "" |
| 2146 | categories: |
| 2147 | - data-collection.storage |
| 2148 | icon_filename: "hard-drive.svg" |
| 2149 | related_resources: |
| 2150 | integrations: |
| 2151 | list: [] |
| 2152 | info_provided_to_referring_integrations: |
| 2153 | description: "" |
| 2154 | keywords: |
| 2155 | - disk |
| 2156 | - disks |
| 2157 | - io |
| 2158 | - block devices |
| 2159 | overview: |
| 2160 | data_collection: |
| 2161 | metrics_description: | |
| 2162 | Detailed statistics for each of your system's disk devices and partitions. |
| 2163 | The data is reported by the kernel and can be used to monitor disk activity on a Linux system. |
| 2164 | |
| 2165 | Get valuable insight into how your disks are performing and where potential bottlenecks might be. |
| 2166 | method_description: "" |
| 2167 | supported_platforms: |
| 2168 | include: [] |
| 2169 | exclude: [] |
| 2170 | multi_instance: true |
| 2171 | additional_permissions: |
| 2172 | description: "" |
| 2173 | default_behavior: |
| 2174 | auto_detection: |
| 2175 | description: "" |
| 2176 | limits: |
| 2177 | description: "" |
| 2178 | performance_impact: |
| 2179 | description: "" |
| 2180 | setup: |
| 2181 | prerequisites: |
| 2182 | list: [] |
| 2183 | configuration: |
| 2184 | file: |
| 2185 | name: "" |
| 2186 | description: "" |
| 2187 | options: |
| 2188 | description: "" |
| 2189 | folding: |
| 2190 | title: "" |
| 2191 | enabled: true |
| 2192 | list: [] |
| 2193 | examples: |
| 2194 | folding: |
| 2195 | enabled: true |
| 2196 | title: "" |
| 2197 | list: [] |
| 2198 | troubleshooting: |
| 2199 | problems: |
| 2200 | list: [] |
| 2201 | alerts: |
| 2202 | - name: 10min_disk_backlog |
| 2203 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/disks.conf |
| 2204 | metric: disk.backlog |
| 2205 | info: average backlog size of the ${label:device} disk over the last 10 minutes |
| 2206 | os: "linux" |
| 2207 | - name: 10min_disk_utilization |
| 2208 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/disks.conf |
| 2209 | metric: disk.util |
| 2210 | info: average percentage of time ${label:device} disk was busy over the last 10 minutes |
| 2211 | os: "linux freebsd" |
| 2212 | metrics: |
| 2213 | folding: |
| 2214 | title: Metrics |
| 2215 | enabled: false |
| 2216 | description: "" |
| 2217 | availability: [] |
| 2218 | scopes: |
| 2219 | - name: global |
| 2220 | description: "" |
| 2221 | labels: [] |
| 2222 | metrics: |
| 2223 | - name: system.io |
| 2224 | description: Disk I/O |
| 2225 | unit: "KiB/s" |
| 2226 | chart_type: area |
| 2227 | dimensions: |
| 2228 | - name: in |
| 2229 | - name: out |
| 2230 | - name: disk |
| 2231 | description: "" |
| 2232 | labels: |
| 2233 | - name: device |
| 2234 | description: TBD |
| 2235 | - name: mount_point |
| 2236 | description: TBD |
| 2237 | - name: device_type |
| 2238 | description: TBD |
| 2239 | metrics: |
| 2240 | - name: disk.io |
| 2241 | description: Disk I/O Bandwidth |
| 2242 | unit: "KiB/s" |
| 2243 | chart_type: area |
| 2244 | dimensions: |
| 2245 | - name: reads |
| 2246 | - name: writes |
| 2247 | - name: disk_ext.io |
| 2248 | description: Amount of Discarded Data |
| 2249 | unit: "KiB/s" |
| 2250 | chart_type: area |
| 2251 | dimensions: |
| 2252 | - name: discards |
| 2253 | - name: disk.ops |
| 2254 | description: Disk Completed I/O Operations |
| 2255 | unit: "operations/s" |
| 2256 | chart_type: line |
| 2257 | dimensions: |
| 2258 | - name: reads |
| 2259 | - name: writes |
| 2260 | - name: disk_ext.ops |
| 2261 | description: Disk Completed Extended I/O Operations |
| 2262 | unit: "operations/s" |
| 2263 | chart_type: line |
| 2264 | dimensions: |
| 2265 | - name: discards |
| 2266 | - name: flushes |
| 2267 | - name: disk.qops |
| 2268 | description: Disk Current I/O Operations |
| 2269 | unit: "operations" |
| 2270 | chart_type: line |
| 2271 | dimensions: |
| 2272 | - name: operations |
| 2273 | - name: disk.backlog |
| 2274 | description: Disk Backlog |
| 2275 | unit: "milliseconds" |
| 2276 | chart_type: area |
| 2277 | dimensions: |
| 2278 | - name: backlog |
| 2279 | - name: disk.busy |
| 2280 | description: Disk Busy Time |
| 2281 | unit: "milliseconds" |
| 2282 | chart_type: area |
| 2283 | dimensions: |
| 2284 | - name: busy |
| 2285 | - name: disk.util |
| 2286 | description: Disk Utilization Time |
| 2287 | unit: "% of time working" |
| 2288 | chart_type: area |
| 2289 | dimensions: |
| 2290 | - name: utilization |
| 2291 | - name: disk.mops |
| 2292 | description: Disk Merged Operations |
| 2293 | unit: "merged operations/s" |
| 2294 | chart_type: line |
| 2295 | dimensions: |
| 2296 | - name: reads |
| 2297 | - name: writes |
| 2298 | - name: disk_ext.mops |
| 2299 | description: Disk Merged Discard Operations |
| 2300 | unit: "merged operations/s" |
| 2301 | chart_type: line |
| 2302 | dimensions: |
| 2303 | - name: discards |
| 2304 | - name: disk.iotime |
| 2305 | description: Disk Total I/O Time |
| 2306 | unit: "milliseconds/s" |
| 2307 | chart_type: line |
| 2308 | dimensions: |
| 2309 | - name: reads |
| 2310 | - name: writes |
| 2311 | - name: disk_ext.iotime |
| 2312 | description: Disk Total I/O Time for Extended Operations |
| 2313 | unit: "milliseconds/s" |
| 2314 | chart_type: line |
| 2315 | dimensions: |
| 2316 | - name: discards |
| 2317 | - name: flushes |
| 2318 | - name: disk.await |
| 2319 | description: Average Completed I/O Operation Time |
| 2320 | unit: "milliseconds/operation" |
| 2321 | chart_type: line |
| 2322 | dimensions: |
| 2323 | - name: reads |
| 2324 | - name: writes |
| 2325 | - name: disk_ext.await |
| 2326 | description: Average Completed Extended I/O Operation Time |
| 2327 | unit: "milliseconds/operation" |
| 2328 | chart_type: line |
| 2329 | dimensions: |
| 2330 | - name: discards |
| 2331 | - name: flushes |
| 2332 | - name: disk.avgsz |
| 2333 | description: Average Completed I/O Operation Bandwidth |
| 2334 | unit: "KiB/operation" |
| 2335 | chart_type: area |
| 2336 | dimensions: |
| 2337 | - name: reads |
| 2338 | - name: writes |
| 2339 | - name: disk_ext.avgsz |
| 2340 | description: Average Amount of Discarded Data |
| 2341 | unit: "KiB/operation" |
| 2342 | chart_type: area |
| 2343 | dimensions: |
| 2344 | - name: discards |
| 2345 | - name: disk.svctm |
| 2346 | description: Average Service Time |
| 2347 | unit: "milliseconds/operation" |
| 2348 | chart_type: line |
| 2349 | dimensions: |
| 2350 | - name: svctm |
| 2351 | - meta: |
| 2352 | plugin_name: proc.plugin |
| 2353 | module_name: /sys/fs/bcache |
| 2354 | monitored_instance: |
| 2355 | name: BCache |
| 2356 | link: "https://bcache.evilpiepirate.org/" |
| 2357 | categories: |
| 2358 | - data-collection.storage |
| 2359 | icon_filename: "hard-drive.svg" |
| 2360 | related_resources: |
| 2361 | integrations: |
| 2362 | list: [] |
| 2363 | info_provided_to_referring_integrations: |
| 2364 | description: "" |
| 2365 | keywords: |
| 2366 | - bcache |
| 2367 | - cache |
| 2368 | - ssd |
| 2369 | - block devices |
| 2370 | overview: |
| 2371 | data_collection: |
| 2372 | metrics_description: | |
| 2373 | Statistics for BCache (block layer cache) devices, including cache hit ratios, I/O operations, cache allocations, and bypass activity. |
| 2374 | method_description: "" |
| 2375 | supported_platforms: |
| 2376 | include: |
| 2377 | - Linux |
| 2378 | exclude: [] |
| 2379 | multi_instance: true |
| 2380 | additional_permissions: |
| 2381 | description: "" |
| 2382 | default_behavior: |
| 2383 | auto_detection: |
| 2384 | description: | |
| 2385 | Automatically detects BCache devices by reading stats from `/sys/block/*/bcache/`. |
| 2386 | limits: |
| 2387 | description: "" |
| 2388 | performance_impact: |
| 2389 | description: "" |
| 2390 | setup: |
| 2391 | prerequisites: |
| 2392 | list: [] |
| 2393 | configuration: |
| 2394 | file: |
| 2395 | name: "netdata.conf" |
| 2396 | options: |
| 2397 | description: "" |
| 2398 | folding: |
| 2399 | title: "" |
| 2400 | enabled: false |
| 2401 | list: [] |
| 2402 | examples: |
| 2403 | folding: |
| 2404 | title: "" |
| 2405 | enabled: false |
| 2406 | list: [] |
| 2407 | troubleshooting: |
| 2408 | problems: |
| 2409 | list: [] |
| 2410 | alerts: |
| 2411 | - name: bcache_cache_dirty |
| 2412 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/bcache.conf |
| 2413 | metric: disk.bcache_cache_alloc |
| 2414 | info: percentage of cache space used for dirty data and metadata (this usually means your SSD cache is too small) |
| 2415 | - name: bcache_cache_errors |
| 2416 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/bcache.conf |
| 2417 | metric: disk.bcache_cache_read_races |
| 2418 | info: > |
| 2419 | number of times data was read from the cache, the bucket was reused and invalidated in the last 10 minutes |
| 2420 | (when this occurs the data is reread from the backing device) |
| 2421 | metrics: |
| 2422 | folding: |
| 2423 | title: Metrics |
| 2424 | enabled: false |
| 2425 | description: "" |
| 2426 | availability: [] |
| 2427 | scopes: |
| 2428 | - name: disk |
| 2429 | description: "" |
| 2430 | labels: |
| 2431 | - name: device |
| 2432 | description: TBD |
| 2433 | - name: mount_point |
| 2434 | description: TBD |
| 2435 | - name: device_type |
| 2436 | description: TBD |
| 2437 | metrics: |
| 2438 | - name: disk.bcache_cache_alloc |
| 2439 | description: BCache Cache Allocations |
| 2440 | unit: "percentage" |
| 2441 | chart_type: stacked |
| 2442 | dimensions: |
| 2443 | - name: ununsed |
| 2444 | - name: dirty |
| 2445 | - name: clean |
| 2446 | - name: metadata |
| 2447 | - name: undefined |
| 2448 | - name: disk.bcache_hit_ratio |
| 2449 | description: BCache Cache Hit Ratio |
| 2450 | unit: "percentage" |
| 2451 | chart_type: line |
| 2452 | dimensions: |
| 2453 | - name: 5min |
| 2454 | - name: 1hour |
| 2455 | - name: 1day |
| 2456 | - name: ever |
| 2457 | - name: disk.bcache_rates |
| 2458 | description: BCache Rates |
| 2459 | unit: "KiB/s" |
| 2460 | chart_type: area |
| 2461 | dimensions: |
| 2462 | - name: congested |
| 2463 | - name: writeback |
| 2464 | - name: disk.bcache_size |
| 2465 | description: BCache Cache Sizes |
| 2466 | unit: "MiB" |
| 2467 | chart_type: area |
| 2468 | dimensions: |
| 2469 | - name: dirty |
| 2470 | - name: disk.bcache_usage |
| 2471 | description: BCache Cache Usage |
| 2472 | unit: "percentage" |
| 2473 | chart_type: area |
| 2474 | dimensions: |
| 2475 | - name: avail |
| 2476 | - name: disk.bcache_cache_read_races |
| 2477 | description: BCache Cache Read Races |
| 2478 | unit: "operations/s" |
| 2479 | chart_type: line |
| 2480 | dimensions: |
| 2481 | - name: races |
| 2482 | - name: errors |
| 2483 | - name: disk.bcache |
| 2484 | description: BCache Cache I/O Operations |
| 2485 | unit: "operations/s" |
| 2486 | chart_type: line |
| 2487 | dimensions: |
| 2488 | - name: hits |
| 2489 | - name: misses |
| 2490 | - name: collisions |
| 2491 | - name: readaheads |
| 2492 | - name: disk.bcache_bypass |
| 2493 | description: BCache Cache Bypass I/O Operations |
| 2494 | unit: "operations/s" |
| 2495 | chart_type: line |
| 2496 | dimensions: |
| 2497 | - name: hits |
| 2498 | - name: misses |
| 2499 | - meta: |
| 2500 | plugin_name: proc.plugin |
| 2501 | module_name: /proc/mdstat |
| 2502 | monitored_instance: |
| 2503 | name: MD RAID |
| 2504 | link: "" |
| 2505 | categories: |
| 2506 | - data-collection.storage |
| 2507 | icon_filename: "hard-drive.svg" |
| 2508 | related_resources: |
| 2509 | integrations: |
| 2510 | list: [] |
| 2511 | info_provided_to_referring_integrations: |
| 2512 | description: "" |
| 2513 | keywords: |
| 2514 | - raid |
| 2515 | - mdadm |
| 2516 | - mdstat |
| 2517 | - raid |
| 2518 | overview: |
| 2519 | data_collection: |
| 2520 | metrics_description: "This integration monitors the status of MD RAID devices." |
| 2521 | method_description: "" |
| 2522 | supported_platforms: |
| 2523 | include: [] |
| 2524 | exclude: [] |
| 2525 | multi_instance: true |
| 2526 | additional_permissions: |
| 2527 | description: "" |
| 2528 | default_behavior: |
| 2529 | auto_detection: |
| 2530 | description: "" |
| 2531 | limits: |
| 2532 | description: "" |
| 2533 | performance_impact: |
| 2534 | description: "" |
| 2535 | setup: |
| 2536 | prerequisites: |
| 2537 | list: [] |
| 2538 | configuration: |
| 2539 | file: |
| 2540 | name: "" |
| 2541 | description: "" |
| 2542 | options: |
| 2543 | description: "" |
| 2544 | folding: |
| 2545 | title: "" |
| 2546 | enabled: true |
| 2547 | list: [] |
| 2548 | examples: |
| 2549 | folding: |
| 2550 | enabled: true |
| 2551 | title: "" |
| 2552 | list: [] |
| 2553 | troubleshooting: |
| 2554 | problems: |
| 2555 | list: [] |
| 2556 | alerts: |
| 2557 | - name: mdstat_last_collected |
| 2558 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/mdstat.conf |
| 2559 | metric: md.disks |
| 2560 | info: number of seconds since the last successful data collection |
| 2561 | - name: mdstat_disks |
| 2562 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/mdstat.conf |
| 2563 | metric: md.disks |
| 2564 | info: |
| 2565 | number of devices in the down state for the ${label:device} ${label:raid_level} array. Any number > 0 indicates that the array is degraded. |
| 2566 | - name: mdstat_mismatch_cnt |
| 2567 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/mdstat.conf |
| 2568 | metric: md.mismatch_cnt |
| 2569 | info: number of unsynchronized blocks for the ${label:device} ${label:raid_level} array |
| 2570 | - name: mdstat_nonredundant_last_collected |
| 2571 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/mdstat.conf |
| 2572 | metric: md.nonredundant |
| 2573 | info: number of seconds since the last successful data collection |
| 2574 | metrics: |
| 2575 | folding: |
| 2576 | title: Metrics |
| 2577 | enabled: false |
| 2578 | description: "" |
| 2579 | availability: [] |
| 2580 | scopes: |
| 2581 | - name: global |
| 2582 | description: "" |
| 2583 | labels: [] |
| 2584 | metrics: |
| 2585 | - name: md.health |
| 2586 | description: Faulty Devices In MD |
| 2587 | unit: "failed disks" |
| 2588 | chart_type: line |
| 2589 | dimensions: |
| 2590 | - name: a dimension per md array |
| 2591 | - name: md array |
| 2592 | description: "" |
| 2593 | labels: |
| 2594 | - name: device |
| 2595 | description: TBD |
| 2596 | - name: raid_level |
| 2597 | description: TBD |
| 2598 | metrics: |
| 2599 | - name: md.disks |
| 2600 | description: Disks Stats |
| 2601 | unit: "disks" |
| 2602 | chart_type: stacked |
| 2603 | dimensions: |
| 2604 | - name: inuse |
| 2605 | - name: down |
| 2606 | - name: md.mismatch_cnt |
| 2607 | description: Mismatch Count |
| 2608 | unit: "unsynchronized blocks" |
| 2609 | chart_type: line |
| 2610 | dimensions: |
| 2611 | - name: count |
| 2612 | - name: md.status |
| 2613 | description: Current Status |
| 2614 | unit: "percent" |
| 2615 | chart_type: line |
| 2616 | dimensions: |
| 2617 | - name: check |
| 2618 | - name: resync |
| 2619 | - name: recovery |
| 2620 | - name: reshape |
| 2621 | - name: md.expected_time_until_operation_finish |
| 2622 | description: Approximate Time Until Finish |
| 2623 | unit: "seconds" |
| 2624 | chart_type: line |
| 2625 | dimensions: |
| 2626 | - name: finish_in |
| 2627 | - name: md.operation_speed |
| 2628 | description: Operation Speed |
| 2629 | unit: "KiB/s" |
| 2630 | chart_type: line |
| 2631 | dimensions: |
| 2632 | - name: speed |
| 2633 | - name: md.nonredundant |
| 2634 | description: Nonredundant Array Availability |
| 2635 | unit: "boolean" |
| 2636 | chart_type: line |
| 2637 | dimensions: |
| 2638 | - name: available |
| 2639 | - meta: |
| 2640 | plugin_name: proc.plugin |
| 2641 | module_name: /proc/net/dev |
| 2642 | monitored_instance: |
| 2643 | name: Network interfaces |
| 2644 | link: "" |
| 2645 | categories: |
| 2646 | - data-collection.networking |
| 2647 | icon_filename: "network-wired.svg" |
| 2648 | related_resources: |
| 2649 | integrations: |
| 2650 | list: [] |
| 2651 | info_provided_to_referring_integrations: |
| 2652 | description: "" |
| 2653 | keywords: |
| 2654 | - network interfaces |
| 2655 | overview: |
| 2656 | data_collection: |
| 2657 | metrics_description: "Monitor network interface metrics about bandwidth, state, errors and more." |
| 2658 | method_description: "" |
| 2659 | supported_platforms: |
| 2660 | include: [] |
| 2661 | exclude: [] |
| 2662 | multi_instance: true |
| 2663 | additional_permissions: |
| 2664 | description: "" |
| 2665 | default_behavior: |
| 2666 | auto_detection: |
| 2667 | description: "" |
| 2668 | limits: |
| 2669 | description: "" |
| 2670 | performance_impact: |
| 2671 | description: "" |
| 2672 | setup: |
| 2673 | prerequisites: |
| 2674 | list: [] |
| 2675 | configuration: |
| 2676 | file: |
| 2677 | name: "" |
| 2678 | description: "" |
| 2679 | options: |
| 2680 | description: "" |
| 2681 | folding: |
| 2682 | title: "" |
| 2683 | enabled: true |
| 2684 | list: [] |
| 2685 | examples: |
| 2686 | folding: |
| 2687 | enabled: true |
| 2688 | title: "" |
| 2689 | list: [] |
| 2690 | troubleshooting: |
| 2691 | problems: |
| 2692 | list: [] |
| 2693 | alerts: |
| 2694 | - name: interface_speed |
| 2695 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/net.conf |
| 2696 | metric: net.net |
| 2697 | info: network interface ${label:device} current speed |
| 2698 | os: "*" |
| 2699 | - name: 1m_received_traffic_overflow |
| 2700 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/net.conf |
| 2701 | metric: net.net |
| 2702 | info: average inbound utilization for the network interface ${label:device} over the last minute |
| 2703 | os: "linux" |
| 2704 | - name: 1m_sent_traffic_overflow |
| 2705 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/net.conf |
| 2706 | metric: net.net |
| 2707 | info: average outbound utilization for the network interface ${label:device} over the last minute |
| 2708 | os: "linux" |
| 2709 | - name: inbound_packets_dropped_ratio |
| 2710 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/net.conf |
| 2711 | metric: net.drops |
| 2712 | info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes |
| 2713 | os: "linux" |
| 2714 | - name: outbound_packets_dropped_ratio |
| 2715 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/net.conf |
| 2716 | metric: net.drops |
| 2717 | info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes |
| 2718 | os: "linux" |
| 2719 | - name: wifi_inbound_packets_dropped_ratio |
| 2720 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/net.conf |
| 2721 | metric: net.drops |
| 2722 | info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes |
| 2723 | os: "linux" |
| 2724 | - name: wifi_outbound_packets_dropped_ratio |
| 2725 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/net.conf |
| 2726 | metric: net.drops |
| 2727 | info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes |
| 2728 | os: "linux" |
| 2729 | - name: 1m_received_packets_rate |
| 2730 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/net.conf |
| 2731 | metric: net.packets |
| 2732 | info: average number of packets received by the network interface ${label:device} over the last minute |
| 2733 | os: "linux freebsd" |
| 2734 | - name: 10s_received_packets_storm |
| 2735 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/net.conf |
| 2736 | metric: net.packets |
| 2737 | info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over the last minute |
| 2738 | os: "linux freebsd" |
| 2739 | - name: 10min_fifo_errors |
| 2740 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/net.conf |
| 2741 | metric: net.fifo |
| 2742 | info: number of FIFO errors for the network interface ${label:device} in the last 10 minutes |
| 2743 | os: "linux" |
| 2744 | metrics: |
| 2745 | folding: |
| 2746 | title: Metrics |
| 2747 | enabled: false |
| 2748 | description: "" |
| 2749 | availability: [] |
| 2750 | scopes: |
| 2751 | - name: global |
| 2752 | description: "" |
| 2753 | labels: [] |
| 2754 | metrics: |
| 2755 | - name: system.net |
| 2756 | description: Physical Network Interfaces Aggregated Bandwidth |
| 2757 | unit: "kilobits/s" |
| 2758 | chart_type: area |
| 2759 | dimensions: |
| 2760 | - name: received |
| 2761 | - name: sent |
| 2762 | - name: network device |
| 2763 | description: "" |
| 2764 | labels: |
| 2765 | - name: interface_type |
| 2766 | description: TBD |
| 2767 | - name: device |
| 2768 | description: TBD |
| 2769 | metrics: |
| 2770 | - name: net.net |
| 2771 | description: Bandwidth |
| 2772 | unit: "kilobits/s" |
| 2773 | chart_type: area |
| 2774 | dimensions: |
| 2775 | - name: received |
| 2776 | - name: sent |
| 2777 | - name: net.speed |
| 2778 | description: Interface Speed |
| 2779 | unit: "kilobits/s" |
| 2780 | chart_type: line |
| 2781 | dimensions: |
| 2782 | - name: speed |
| 2783 | - name: net.duplex |
| 2784 | description: Interface Duplex State |
| 2785 | unit: "state" |
| 2786 | chart_type: line |
| 2787 | dimensions: |
| 2788 | - name: full |
| 2789 | - name: half |
| 2790 | - name: unknown |
| 2791 | - name: net.operstate |
| 2792 | description: Interface Operational State |
| 2793 | unit: "state" |
| 2794 | chart_type: line |
| 2795 | dimensions: |
| 2796 | - name: up |
| 2797 | - name: down |
| 2798 | - name: notpresent |
| 2799 | - name: lowerlayerdown |
| 2800 | - name: testing |
| 2801 | - name: dormant |
| 2802 | - name: unknown |
| 2803 | - name: net.carrier |
| 2804 | description: Interface Physical Link State |
| 2805 | unit: "state" |
| 2806 | chart_type: line |
| 2807 | dimensions: |
| 2808 | - name: up |
| 2809 | - name: down |
| 2810 | - name: net.mtu |
| 2811 | description: Interface MTU |
| 2812 | unit: "octets" |
| 2813 | chart_type: line |
| 2814 | dimensions: |
| 2815 | - name: mtu |
| 2816 | - name: net.packets |
| 2817 | description: Packets |
| 2818 | unit: "packets/s" |
| 2819 | chart_type: line |
| 2820 | dimensions: |
| 2821 | - name: received |
| 2822 | - name: sent |
| 2823 | - name: multicast |
| 2824 | - name: net.errors |
| 2825 | description: Interface Errors |
| 2826 | unit: "errors/s" |
| 2827 | chart_type: line |
| 2828 | dimensions: |
| 2829 | - name: inbound |
| 2830 | - name: outbound |
| 2831 | - name: net.drops |
| 2832 | description: Interface Drops |
| 2833 | unit: "drops/s" |
| 2834 | chart_type: line |
| 2835 | dimensions: |
| 2836 | - name: inbound |
| 2837 | - name: outbound |
| 2838 | - name: net.fifo |
| 2839 | description: Interface FIFO Buffer Errors |
| 2840 | unit: "errors" |
| 2841 | chart_type: line |
| 2842 | dimensions: |
| 2843 | - name: receive |
| 2844 | - name: transmit |
| 2845 | - name: net.compressed |
| 2846 | description: Compressed Packets |
| 2847 | unit: "packets/s" |
| 2848 | chart_type: line |
| 2849 | dimensions: |
| 2850 | - name: received |
| 2851 | - name: sent |
| 2852 | - name: net.events |
| 2853 | description: Network Interface Events |
| 2854 | unit: "events/s" |
| 2855 | chart_type: line |
| 2856 | dimensions: |
| 2857 | - name: frames |
| 2858 | - name: collisions |
| 2859 | - name: carrier |
| 2860 | - meta: |
| 2861 | plugin_name: proc.plugin |
| 2862 | module_name: /proc/net/wireless |
| 2863 | monitored_instance: |
| 2864 | name: Wireless network interfaces |
| 2865 | link: "" |
| 2866 | categories: |
| 2867 | - data-collection.networking |
| 2868 | icon_filename: "network-wired.svg" |
| 2869 | related_resources: |
| 2870 | integrations: |
| 2871 | list: [] |
| 2872 | info_provided_to_referring_integrations: |
| 2873 | description: "" |
| 2874 | keywords: |
| 2875 | - wireless devices |
| 2876 | overview: |
| 2877 | data_collection: |
| 2878 | metrics_description: "Monitor wireless devices with metrics about status, link quality, signal level, noise level and more." |
| 2879 | method_description: "" |
| 2880 | supported_platforms: |
| 2881 | include: [] |
| 2882 | exclude: [] |
| 2883 | multi_instance: true |
| 2884 | additional_permissions: |
| 2885 | description: "" |
| 2886 | default_behavior: |
| 2887 | auto_detection: |
| 2888 | description: "" |
| 2889 | limits: |
| 2890 | description: "" |
| 2891 | performance_impact: |
| 2892 | description: "" |
| 2893 | setup: |
| 2894 | prerequisites: |
| 2895 | list: [] |
| 2896 | configuration: |
| 2897 | file: |
| 2898 | name: "" |
| 2899 | description: "" |
| 2900 | options: |
| 2901 | description: "" |
| 2902 | folding: |
| 2903 | title: "" |
| 2904 | enabled: true |
| 2905 | list: [] |
| 2906 | examples: |
| 2907 | folding: |
| 2908 | enabled: true |
| 2909 | title: "" |
| 2910 | list: [] |
| 2911 | troubleshooting: |
| 2912 | problems: |
| 2913 | list: [] |
| 2914 | alerts: [] |
| 2915 | metrics: |
| 2916 | folding: |
| 2917 | title: Metrics |
| 2918 | enabled: false |
| 2919 | description: "" |
| 2920 | availability: [] |
| 2921 | scopes: |
| 2922 | - name: wireless device |
| 2923 | description: "" |
| 2924 | labels: [] |
| 2925 | metrics: |
| 2926 | - name: wireless.status |
| 2927 | description: Internal status reported by interface. |
| 2928 | unit: "status" |
| 2929 | chart_type: line |
| 2930 | dimensions: |
| 2931 | - name: status |
| 2932 | - name: wireless.link_quality |
| 2933 | description: Overall quality of the link. This is an aggregate value, and depends on the driver and hardware. |
| 2934 | unit: "value" |
| 2935 | chart_type: line |
| 2936 | dimensions: |
| 2937 | - name: link_quality |
| 2938 | - name: wireless.signal_level |
| 2939 | description: |
| 2940 | The signal level is the wireless signal power level received by the wireless client. The closer the value is to 0, the stronger the |
| 2941 | signal. |
| 2942 | unit: "dBm" |
| 2943 | chart_type: line |
| 2944 | dimensions: |
| 2945 | - name: signal_level |
| 2946 | - name: wireless.noise_level |
| 2947 | description: |
| 2948 | The noise level indicates the amount of background noise in your environment. The closer the value to 0, the greater the noise level. |
| 2949 | unit: "dBm" |
| 2950 | chart_type: line |
| 2951 | dimensions: |
| 2952 | - name: noise_level |
| 2953 | - name: wireless.discarded_packets |
| 2954 | description: Packet discarded in the wireless adapter due to wireless specific problems. |
| 2955 | unit: "packets/s" |
| 2956 | chart_type: line |
| 2957 | dimensions: |
| 2958 | - name: nwid |
| 2959 | - name: crypt |
| 2960 | - name: frag |
| 2961 | - name: retry |
| 2962 | - name: misc |
| 2963 | - name: wireless.missed_beacons |
| 2964 | description: Number of missed beacons. |
| 2965 | unit: "frames/s" |
| 2966 | chart_type: line |
| 2967 | dimensions: |
| 2968 | - name: missed_beacons |
| 2969 | - meta: |
| 2970 | plugin_name: proc.plugin |
| 2971 | module_name: /sys/class/infiniband |
| 2972 | monitored_instance: |
| 2973 | name: InfiniBand |
| 2974 | link: "" |
| 2975 | categories: |
| 2976 | - data-collection.networking |
| 2977 | icon_filename: "network-wired.svg" |
| 2978 | related_resources: |
| 2979 | integrations: |
| 2980 | list: [] |
| 2981 | info_provided_to_referring_integrations: |
| 2982 | description: "" |
| 2983 | keywords: |
| 2984 | - infiniband |
| 2985 | - rdma |
| 2986 | overview: |
| 2987 | data_collection: |
| 2988 | metrics_description: "This integration monitors InfiniBand network inteface statistics." |
| 2989 | method_description: "" |
| 2990 | supported_platforms: |
| 2991 | include: [] |
| 2992 | exclude: [] |
| 2993 | multi_instance: true |
| 2994 | additional_permissions: |
| 2995 | description: "" |
| 2996 | default_behavior: |
| 2997 | auto_detection: |
| 2998 | description: "" |
| 2999 | limits: |
| 3000 | description: "" |
| 3001 | performance_impact: |
| 3002 | description: "" |
| 3003 | setup: |
| 3004 | prerequisites: |
| 3005 | list: [] |
| 3006 | configuration: |
| 3007 | file: |
| 3008 | name: "" |
| 3009 | description: "" |
| 3010 | options: |
| 3011 | description: "" |
| 3012 | folding: |
| 3013 | title: "" |
| 3014 | enabled: true |
| 3015 | list: [] |
| 3016 | examples: |
| 3017 | folding: |
| 3018 | enabled: true |
| 3019 | title: "" |
| 3020 | list: [] |
| 3021 | troubleshooting: |
| 3022 | problems: |
| 3023 | list: [] |
| 3024 | alerts: [] |
| 3025 | metrics: |
| 3026 | folding: |
| 3027 | title: Metrics |
| 3028 | enabled: false |
| 3029 | description: "" |
| 3030 | availability: [] |
| 3031 | scopes: |
| 3032 | - name: infiniband port |
| 3033 | description: "" |
| 3034 | labels: [] |
| 3035 | metrics: |
| 3036 | - name: ib.bytes |
| 3037 | description: Bandwidth usage |
| 3038 | unit: "kilobits/s" |
| 3039 | chart_type: area |
| 3040 | dimensions: |
| 3041 | - name: Received |
| 3042 | - name: Sent |
| 3043 | - name: ib.packets |
| 3044 | description: Packets Statistics |
| 3045 | unit: "packets/s" |
| 3046 | chart_type: area |
| 3047 | dimensions: |
| 3048 | - name: Received |
| 3049 | - name: Sent |
| 3050 | - name: Mcast_rcvd |
| 3051 | - name: Mcast_sent |
| 3052 | - name: Ucast_rcvd |
| 3053 | - name: Ucast_sent |
| 3054 | - name: ib.errors |
| 3055 | description: Error Counters |
| 3056 | unit: "errors/s" |
| 3057 | chart_type: line |
| 3058 | dimensions: |
| 3059 | - name: Pkts_malformated |
| 3060 | - name: Pkts_rcvd_discarded |
| 3061 | - name: Pkts_sent_discarded |
| 3062 | - name: Tick_Wait_to_send |
| 3063 | - name: Pkts_missed_resource |
| 3064 | - name: Buffer_overrun |
| 3065 | - name: Link_Downed |
| 3066 | - name: Link_recovered |
| 3067 | - name: Link_integrity_err |
| 3068 | - name: Link_minor_errors |
| 3069 | - name: Pkts_rcvd_with_EBP |
| 3070 | - name: Pkts_rcvd_discarded_by_switch |
| 3071 | - name: Pkts_sent_discarded_by_switch |
| 3072 | - name: ib.hwerrors |
| 3073 | description: Hardware Errors |
| 3074 | unit: "errors/s" |
| 3075 | chart_type: line |
| 3076 | dimensions: |
| 3077 | - name: Duplicated_packets |
| 3078 | - name: Pkt_Seq_Num_gap |
| 3079 | - name: Ack_timer_expired |
| 3080 | - name: Drop_missing_buffer |
| 3081 | - name: Drop_out_of_sequence |
| 3082 | - name: NAK_sequence_rcvd |
| 3083 | - name: CQE_err_Req |
| 3084 | - name: CQE_err_Resp |
| 3085 | - name: CQE_Flushed_err_Req |
| 3086 | - name: CQE_Flushed_err_Resp |
| 3087 | - name: Remote_access_err_Req |
| 3088 | - name: Remote_access_err_Resp |
| 3089 | - name: Remote_invalid_req |
| 3090 | - name: Local_length_err_Resp |
| 3091 | - name: RNR_NAK_Packets |
| 3092 | - name: CNP_Pkts_ignored |
| 3093 | - name: RoCE_ICRC_Errors |
| 3094 | - name: ib.hwpackets |
| 3095 | description: Hardware Packets Statistics |
| 3096 | unit: "packets/s" |
| 3097 | chart_type: line |
| 3098 | dimensions: |
| 3099 | - name: RoCEv2_Congestion_sent |
| 3100 | - name: RoCEv2_Congestion_rcvd |
| 3101 | - name: IB_Congestion_handled |
| 3102 | - name: ATOMIC_req_rcvd |
| 3103 | - name: Connection_req_rcvd |
| 3104 | - name: Read_req_rcvd |
| 3105 | - name: Write_req_rcvd |
| 3106 | - name: RoCE_retrans_adaptive |
| 3107 | - name: RoCE_retrans_timeout |
| 3108 | - name: RoCE_slow_restart |
| 3109 | - name: RoCE_slow_restart_congestion |
| 3110 | - name: RoCE_slow_restart_count |
| 3111 | - meta: |
| 3112 | plugin_name: proc.plugin |
| 3113 | module_name: /proc/net/netstat |
| 3114 | monitored_instance: |
| 3115 | name: Network statistics |
| 3116 | link: "" |
| 3117 | categories: |
| 3118 | - data-collection.networking |
| 3119 | icon_filename: "network-wired.svg" |
| 3120 | related_resources: |
| 3121 | integrations: |
| 3122 | list: [] |
| 3123 | info_provided_to_referring_integrations: |
| 3124 | description: "" |
| 3125 | keywords: |
| 3126 | - ip |
| 3127 | - udp |
| 3128 | - udplite |
| 3129 | - icmp |
| 3130 | - netstat |
| 3131 | - snmp |
| 3132 | overview: |
| 3133 | data_collection: |
| 3134 | metrics_description: "This integration provides metrics from the `netstat`, `snmp` and `snmp6` modules." |
| 3135 | method_description: "" |
| 3136 | supported_platforms: |
| 3137 | include: [] |
| 3138 | exclude: [] |
| 3139 | multi_instance: true |
| 3140 | additional_permissions: |
| 3141 | description: "" |
| 3142 | default_behavior: |
| 3143 | auto_detection: |
| 3144 | description: "" |
| 3145 | limits: |
| 3146 | description: "" |
| 3147 | performance_impact: |
| 3148 | description: "" |
| 3149 | setup: |
| 3150 | prerequisites: |
| 3151 | list: [] |
| 3152 | configuration: |
| 3153 | file: |
| 3154 | name: "" |
| 3155 | description: "" |
| 3156 | options: |
| 3157 | description: "" |
| 3158 | folding: |
| 3159 | title: "" |
| 3160 | enabled: true |
| 3161 | list: [] |
| 3162 | examples: |
| 3163 | folding: |
| 3164 | enabled: true |
| 3165 | title: "" |
| 3166 | list: [] |
| 3167 | troubleshooting: |
| 3168 | problems: |
| 3169 | list: [] |
| 3170 | alerts: |
| 3171 | - name: 1m_tcp_syn_queue_drops |
| 3172 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_listen.conf |
| 3173 | metric: ip.tcp_syn_queue |
| 3174 | info: average number of SYN requests was dropped due to the full TCP SYN queue over the last minute (SYN cookies were not enabled) |
| 3175 | os: "linux" |
| 3176 | - name: 1m_tcp_syn_queue_cookies |
| 3177 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_listen.conf |
| 3178 | metric: ip.tcp_syn_queue |
| 3179 | info: average number of sent SYN cookies due to the full TCP SYN queue over the last minute |
| 3180 | os: "linux" |
| 3181 | - name: 1m_tcp_accept_queue_overflows |
| 3182 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_listen.conf |
| 3183 | metric: ip.tcp_accept_queue |
| 3184 | info: average number of overflows in the TCP accept queue over the last minute |
| 3185 | os: "linux" |
| 3186 | - name: 1m_tcp_accept_queue_drops |
| 3187 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_listen.conf |
| 3188 | metric: ip.tcp_accept_queue |
| 3189 | info: average number of dropped packets in the TCP accept queue over the last minute |
| 3190 | os: "linux" |
| 3191 | - name: tcp_connections |
| 3192 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_conn.conf |
| 3193 | metric: ip.tcpsock |
| 3194 | info: TCP connections utilization |
| 3195 | os: "linux" |
| 3196 | - name: 1m_ip_tcp_resets_sent |
| 3197 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_resets.conf |
| 3198 | metric: ip.tcphandshake |
| 3199 | info: average number of sent TCP RESETS over the last minute |
| 3200 | os: "linux" |
| 3201 | - name: 10s_ip_tcp_resets_sent |
| 3202 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_resets.conf |
| 3203 | metric: ip.tcphandshake |
| 3204 | info: |
| 3205 | average number of sent TCP RESETS over the last 10 seconds. This can indicate a port scan, or that a service running on this host has |
| 3206 | crashed. Netdata will not send a clear notification for this alarm. |
| 3207 | os: "linux" |
| 3208 | - name: 1m_ip_tcp_resets_received |
| 3209 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_resets.conf |
| 3210 | metric: ip.tcphandshake |
| 3211 | info: average number of received TCP RESETS over the last minute |
| 3212 | os: "linux freebsd" |
| 3213 | - name: 10s_ip_tcp_resets_received |
| 3214 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_resets.conf |
| 3215 | metric: ip.tcphandshake |
| 3216 | info: |
| 3217 | average number of received TCP RESETS over the last 10 seconds. This can be an indication that a service this host needs has crashed. |
| 3218 | Netdata will not send a clear notification for this alarm. |
| 3219 | os: "linux freebsd" |
| 3220 | - name: 1m_ipv4_udp_receive_buffer_errors |
| 3221 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/udp_errors.conf |
| 3222 | metric: ipv4.udperrors |
| 3223 | info: average number of UDP receive buffer errors over the last minute |
| 3224 | os: "linux freebsd" |
| 3225 | - name: 1m_ipv4_udp_send_buffer_errors |
| 3226 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/udp_errors.conf |
| 3227 | metric: ipv4.udperrors |
| 3228 | info: average number of UDP send buffer errors over the last minute |
| 3229 | os: "linux" |
| 3230 | metrics: |
| 3231 | folding: |
| 3232 | title: Metrics |
| 3233 | enabled: false |
| 3234 | description: "" |
| 3235 | availability: [] |
| 3236 | scopes: |
| 3237 | - name: global |
| 3238 | description: "" |
| 3239 | labels: [] |
| 3240 | metrics: |
| 3241 | - name: system.ip |
| 3242 | description: IPv4 Bandwidth |
| 3243 | unit: "kilobits/s" |
| 3244 | chart_type: area |
| 3245 | dimensions: |
| 3246 | - name: received |
| 3247 | - name: sent |
| 3248 | - name: ip.tcpmemorypressures |
| 3249 | description: TCP Memory Pressures |
| 3250 | unit: "events/s" |
| 3251 | chart_type: line |
| 3252 | dimensions: |
| 3253 | - name: pressures |
| 3254 | - name: ip.tcpconnaborts |
| 3255 | description: TCP Connection Aborts |
| 3256 | unit: "connections/s" |
| 3257 | chart_type: line |
| 3258 | dimensions: |
| 3259 | - name: baddata |
| 3260 | - name: userclosed |
| 3261 | - name: nomemory |
| 3262 | - name: timeout |
| 3263 | - name: linger |
| 3264 | - name: failed |
| 3265 | - name: ip.tcpreorders |
| 3266 | description: TCP Reordered Packets by Detection Method |
| 3267 | unit: "packets/s" |
| 3268 | chart_type: line |
| 3269 | dimensions: |
| 3270 | - name: timestamp |
| 3271 | - name: sack |
| 3272 | - name: fack |
| 3273 | - name: reno |
| 3274 | - name: ip.tcpofo |
| 3275 | description: TCP Out-Of-Order Queue |
| 3276 | unit: "packets/s" |
| 3277 | chart_type: line |
| 3278 | dimensions: |
| 3279 | - name: inqueue |
| 3280 | - name: dropped |
| 3281 | - name: merged |
| 3282 | - name: pruned |
| 3283 | - name: ip.tcpsyncookies |
| 3284 | description: TCP SYN Cookies |
| 3285 | unit: "packets/s" |
| 3286 | chart_type: line |
| 3287 | dimensions: |
| 3288 | - name: received |
| 3289 | - name: sent |
| 3290 | - name: failed |
| 3291 | - name: ip.tcp_syn_queue |
| 3292 | description: TCP SYN Queue Issues |
| 3293 | unit: "packets/s" |
| 3294 | chart_type: line |
| 3295 | dimensions: |
| 3296 | - name: drops |
| 3297 | - name: cookies |
| 3298 | - name: ip.tcp_accept_queue |
| 3299 | description: TCP Accept Queue Issues |
| 3300 | unit: "packets/s" |
| 3301 | chart_type: line |
| 3302 | dimensions: |
| 3303 | - name: overflows |
| 3304 | - name: drops |
| 3305 | - name: ip.tcpsock |
| 3306 | description: IPv4 TCP Connections |
| 3307 | unit: "active connections" |
| 3308 | chart_type: line |
| 3309 | dimensions: |
| 3310 | - name: connections |
| 3311 | - name: ip.tcppackets |
| 3312 | description: IPv4 TCP Packets |
| 3313 | unit: "packets/s" |
| 3314 | chart_type: line |
| 3315 | dimensions: |
| 3316 | - name: received |
| 3317 | - name: sent |
| 3318 | - name: ip.tcperrors |
| 3319 | description: IPv4 TCP Errors |
| 3320 | unit: "packets/s" |
| 3321 | chart_type: line |
| 3322 | dimensions: |
| 3323 | - name: InErrs |
| 3324 | - name: InCsumErrors |
| 3325 | - name: RetransSegs |
| 3326 | - name: ip.tcpopens |
| 3327 | description: IPv4 TCP Opens |
| 3328 | unit: "connections/s" |
| 3329 | chart_type: line |
| 3330 | dimensions: |
| 3331 | - name: active |
| 3332 | - name: passive |
| 3333 | - name: ip.tcphandshake |
| 3334 | description: IPv4 TCP Handshake Issues |
| 3335 | unit: "events/s" |
| 3336 | chart_type: line |
| 3337 | dimensions: |
| 3338 | - name: EstabResets |
| 3339 | - name: OutRsts |
| 3340 | - name: AttemptFails |
| 3341 | - name: SynRetrans |
| 3342 | - name: ipv4.packets |
| 3343 | description: IPv4 Packets |
| 3344 | unit: "packets/s" |
| 3345 | chart_type: line |
| 3346 | dimensions: |
| 3347 | - name: received |
| 3348 | - name: sent |
| 3349 | - name: forwarded |
| 3350 | - name: delivered |
| 3351 | - name: ipv4.errors |
| 3352 | description: IPv4 Errors |
| 3353 | unit: "packets/s" |
| 3354 | chart_type: line |
| 3355 | dimensions: |
| 3356 | - name: InDiscards |
| 3357 | - name: OutDiscards |
| 3358 | - name: InNoRoutes |
| 3359 | - name: OutNoRoutes |
| 3360 | - name: InHdrErrors |
| 3361 | - name: InAddrErrors |
| 3362 | - name: InTruncatedPkts |
| 3363 | - name: InCsumErrors |
| 3364 | - name: ipv4.bcast |
| 3365 | description: IP Broadcast Bandwidth |
| 3366 | unit: "kilobits/s" |
| 3367 | chart_type: area |
| 3368 | dimensions: |
| 3369 | - name: received |
| 3370 | - name: sent |
| 3371 | - name: ipv4.bcastpkts |
| 3372 | description: IP Broadcast Packets |
| 3373 | unit: "packets/s" |
| 3374 | chart_type: line |
| 3375 | dimensions: |
| 3376 | - name: received |
| 3377 | - name: sent |
| 3378 | - name: ipv4.mcast |
| 3379 | description: IPv4 Multicast Bandwidth |
| 3380 | unit: "kilobits/s" |
| 3381 | chart_type: area |
| 3382 | dimensions: |
| 3383 | - name: received |
| 3384 | - name: sent |
| 3385 | - name: ipv4.mcastpkts |
| 3386 | description: IP Multicast Packets |
| 3387 | unit: "packets/s" |
| 3388 | chart_type: line |
| 3389 | dimensions: |
| 3390 | - name: received |
| 3391 | - name: sent |
| 3392 | - name: ipv4.icmp |
| 3393 | description: IPv4 ICMP Packets |
| 3394 | unit: "packets/s" |
| 3395 | chart_type: line |
| 3396 | dimensions: |
| 3397 | - name: received |
| 3398 | - name: sent |
| 3399 | - name: ipv4.icmpmsg |
| 3400 | description: IPv4 ICMP Messages |
| 3401 | unit: "packets/s" |
| 3402 | chart_type: line |
| 3403 | dimensions: |
| 3404 | - name: InEchoReps |
| 3405 | - name: OutEchoReps |
| 3406 | - name: InDestUnreachs |
| 3407 | - name: OutDestUnreachs |
| 3408 | - name: InRedirects |
| 3409 | - name: OutRedirects |
| 3410 | - name: InEchos |
| 3411 | - name: OutEchos |
| 3412 | - name: InRouterAdvert |
| 3413 | - name: OutRouterAdvert |
| 3414 | - name: InRouterSelect |
| 3415 | - name: OutRouterSelect |
| 3416 | - name: InTimeExcds |
| 3417 | - name: OutTimeExcds |
| 3418 | - name: InParmProbs |
| 3419 | - name: OutParmProbs |
| 3420 | - name: InTimestamps |
| 3421 | - name: OutTimestamps |
| 3422 | - name: InTimestampReps |
| 3423 | - name: OutTimestampReps |
| 3424 | - name: ipv4.icmp_errors |
| 3425 | description: IPv4 ICMP Errors |
| 3426 | unit: "packets/s" |
| 3427 | chart_type: line |
| 3428 | dimensions: |
| 3429 | - name: InErrors |
| 3430 | - name: OutErrors |
| 3431 | - name: InCsumErrors |
| 3432 | - name: ipv4.udppackets |
| 3433 | description: IPv4 UDP Packets |
| 3434 | unit: "packets/s" |
| 3435 | chart_type: line |
| 3436 | dimensions: |
| 3437 | - name: received |
| 3438 | - name: sent |
| 3439 | - name: ipv4.udperrors |
| 3440 | description: IPv4 UDP Errors |
| 3441 | unit: "events/s" |
| 3442 | chart_type: line |
| 3443 | dimensions: |
| 3444 | - name: RcvbufErrors |
| 3445 | - name: SndbufErrors |
| 3446 | - name: InErrors |
| 3447 | - name: NoPorts |
| 3448 | - name: InCsumErrors |
| 3449 | - name: IgnoredMulti |
| 3450 | - name: ipv4.udplite |
| 3451 | description: IPv4 UDPLite Packets |
| 3452 | unit: "packets/s" |
| 3453 | chart_type: line |
| 3454 | dimensions: |
| 3455 | - name: received |
| 3456 | - name: sent |
| 3457 | - name: ipv4.udplite_errors |
| 3458 | description: IPv4 UDPLite Errors |
| 3459 | unit: "packets/s" |
| 3460 | chart_type: line |
| 3461 | dimensions: |
| 3462 | - name: RcvbufErrors |
| 3463 | - name: SndbufErrors |
| 3464 | - name: InErrors |
| 3465 | - name: NoPorts |
| 3466 | - name: InCsumErrors |
| 3467 | - name: IgnoredMulti |
| 3468 | - name: ipv4.ecnpkts |
| 3469 | description: IP ECN Statistics |
| 3470 | unit: "packets/s" |
| 3471 | chart_type: line |
| 3472 | dimensions: |
| 3473 | - name: CEP |
| 3474 | - name: NoECTP |
| 3475 | - name: ECTP0 |
| 3476 | - name: ECTP1 |
| 3477 | - name: ipv4.fragsin |
| 3478 | description: IPv4 Fragments Reassembly |
| 3479 | unit: "packets/s" |
| 3480 | chart_type: line |
| 3481 | dimensions: |
| 3482 | - name: ok |
| 3483 | - name: failed |
| 3484 | - name: all |
| 3485 | - name: ipv4.fragsout |
| 3486 | description: IPv4 Fragments Sent |
| 3487 | unit: "packets/s" |
| 3488 | chart_type: line |
| 3489 | dimensions: |
| 3490 | - name: ok |
| 3491 | - name: failed |
| 3492 | - name: created |
| 3493 | - name: system.ipv6 |
| 3494 | description: IPv6 Bandwidth |
| 3495 | unit: "kilobits/s" |
| 3496 | chart_type: area |
| 3497 | dimensions: |
| 3498 | - name: received |
| 3499 | - name: sent |
| 3500 | - name: ipv6.packets |
| 3501 | description: IPv6 Packets |
| 3502 | unit: "packets/s" |
| 3503 | chart_type: line |
| 3504 | dimensions: |
| 3505 | - name: received |
| 3506 | - name: sent |
| 3507 | - name: forwarded |
| 3508 | - name: delivers |
| 3509 | - name: ipv6.errors |
| 3510 | description: IPv6 Errors |
| 3511 | unit: "packets/s" |
| 3512 | chart_type: line |
| 3513 | dimensions: |
| 3514 | - name: InDiscards |
| 3515 | - name: OutDiscards |
| 3516 | - name: InHdrErrors |
| 3517 | - name: InAddrErrors |
| 3518 | - name: InUnknownProtos |
| 3519 | - name: InTooBigErrors |
| 3520 | - name: InTruncatedPkts |
| 3521 | - name: InNoRoutes |
| 3522 | - name: OutNoRoutes |
| 3523 | - name: ipv6.bcast |
| 3524 | description: IPv6 Broadcast Bandwidth |
| 3525 | unit: "kilobits/s" |
| 3526 | chart_type: area |
| 3527 | dimensions: |
| 3528 | - name: received |
| 3529 | - name: sent |
| 3530 | - name: ipv6.mcast |
| 3531 | description: IPv6 Multicast Bandwidth |
| 3532 | unit: "kilobits/s" |
| 3533 | chart_type: area |
| 3534 | dimensions: |
| 3535 | - name: received |
| 3536 | - name: sent |
| 3537 | - name: ipv6.mcastpkts |
| 3538 | description: IPv6 Multicast Packets |
| 3539 | unit: "packets/s" |
| 3540 | chart_type: line |
| 3541 | dimensions: |
| 3542 | - name: received |
| 3543 | - name: sent |
| 3544 | - name: ipv6.udppackets |
| 3545 | description: IPv6 UDP Packets |
| 3546 | unit: "packets/s" |
| 3547 | chart_type: line |
| 3548 | dimensions: |
| 3549 | - name: received |
| 3550 | - name: sent |
| 3551 | - name: ipv6.udperrors |
| 3552 | description: IPv6 UDP Errors |
| 3553 | unit: "events/s" |
| 3554 | chart_type: line |
| 3555 | dimensions: |
| 3556 | - name: RcvbufErrors |
| 3557 | - name: SndbufErrors |
| 3558 | - name: InErrors |
| 3559 | - name: NoPorts |
| 3560 | - name: InCsumErrors |
| 3561 | - name: IgnoredMulti |
| 3562 | - name: ipv6.udplitepackets |
| 3563 | description: IPv6 UDPlite Packets |
| 3564 | unit: "packets/s" |
| 3565 | chart_type: line |
| 3566 | dimensions: |
| 3567 | - name: received |
| 3568 | - name: sent |
| 3569 | - name: ipv6.udpliteerrors |
| 3570 | description: IPv6 UDP Lite Errors |
| 3571 | unit: "events/s" |
| 3572 | chart_type: line |
| 3573 | dimensions: |
| 3574 | - name: RcvbufErrors |
| 3575 | - name: SndbufErrors |
| 3576 | - name: InErrors |
| 3577 | - name: NoPorts |
| 3578 | - name: InCsumErrors |
| 3579 | - name: ipv6.icmp |
| 3580 | description: IPv6 ICMP Messages |
| 3581 | unit: "messages/s" |
| 3582 | chart_type: line |
| 3583 | dimensions: |
| 3584 | - name: received |
| 3585 | - name: sent |
| 3586 | - name: ipv6.icmpredir |
| 3587 | description: IPv6 ICMP Redirects |
| 3588 | unit: "redirects/s" |
| 3589 | chart_type: line |
| 3590 | dimensions: |
| 3591 | - name: received |
| 3592 | - name: sent |
| 3593 | - name: ipv6.icmperrors |
| 3594 | description: IPv6 ICMP Errors |
| 3595 | unit: "errors/s" |
| 3596 | chart_type: line |
| 3597 | dimensions: |
| 3598 | - name: InErrors |
| 3599 | - name: OutErrors |
| 3600 | - name: InCsumErrors |
| 3601 | - name: InDestUnreachs |
| 3602 | - name: InPktTooBigs |
| 3603 | - name: InTimeExcds |
| 3604 | - name: InParmProblems |
| 3605 | - name: OutDestUnreachs |
| 3606 | - name: OutPktTooBigs |
| 3607 | - name: OutTimeExcds |
| 3608 | - name: OutParmProblems |
| 3609 | - name: ipv6.icmpechos |
| 3610 | description: IPv6 ICMP Echo |
| 3611 | unit: "messages/s" |
| 3612 | chart_type: line |
| 3613 | dimensions: |
| 3614 | - name: InEchos |
| 3615 | - name: OutEchos |
| 3616 | - name: InEchoReplies |
| 3617 | - name: OutEchoReplies |
| 3618 | - name: ipv6.groupmemb |
| 3619 | description: IPv6 ICMP Group Membership |
| 3620 | unit: "messages/s" |
| 3621 | chart_type: line |
| 3622 | dimensions: |
| 3623 | - name: InQueries |
| 3624 | - name: OutQueries |
| 3625 | - name: InResponses |
| 3626 | - name: OutResponses |
| 3627 | - name: InReductions |
| 3628 | - name: OutReductions |
| 3629 | - name: ipv6.icmprouter |
| 3630 | description: IPv6 Router Messages |
| 3631 | unit: "messages/s" |
| 3632 | chart_type: line |
| 3633 | dimensions: |
| 3634 | - name: InSolicits |
| 3635 | - name: OutSolicits |
| 3636 | - name: InAdvertisements |
| 3637 | - name: OutAdvertisements |
| 3638 | - name: ipv6.icmpneighbor |
| 3639 | description: IPv6 Neighbor Messages |
| 3640 | unit: "messages/s" |
| 3641 | chart_type: line |
| 3642 | dimensions: |
| 3643 | - name: InSolicits |
| 3644 | - name: OutSolicits |
| 3645 | - name: InAdvertisements |
| 3646 | - name: OutAdvertisements |
| 3647 | - name: ipv6.icmpmldv2 |
| 3648 | description: IPv6 ICMP MLDv2 Reports |
| 3649 | unit: "reports/s" |
| 3650 | chart_type: line |
| 3651 | dimensions: |
| 3652 | - name: received |
| 3653 | - name: sent |
| 3654 | - name: ipv6.icmptypes |
| 3655 | description: IPv6 ICMP Types |
| 3656 | unit: "messages/s" |
| 3657 | chart_type: line |
| 3658 | dimensions: |
| 3659 | - name: InType1 |
| 3660 | - name: InType128 |
| 3661 | - name: InType129 |
| 3662 | - name: InType136 |
| 3663 | - name: OutType1 |
| 3664 | - name: OutType128 |
| 3665 | - name: OutType129 |
| 3666 | - name: OutType133 |
| 3667 | - name: OutType135 |
| 3668 | - name: OutType143 |
| 3669 | - name: ipv6.ect |
| 3670 | description: IPv6 ECT Packets |
| 3671 | unit: "packets/s" |
| 3672 | chart_type: line |
| 3673 | dimensions: |
| 3674 | - name: InNoECTPkts |
| 3675 | - name: InECT1Pkts |
| 3676 | - name: InECT0Pkts |
| 3677 | - name: InCEPkts |
| 3678 | - name: ipv6.fragsin |
| 3679 | description: IPv6 Fragments Reassembly |
| 3680 | unit: "packets/s" |
| 3681 | chart_type: line |
| 3682 | dimensions: |
| 3683 | - name: ok |
| 3684 | - name: failed |
| 3685 | - name: timeout |
| 3686 | - name: all |
| 3687 | - name: ipv6.fragsout |
| 3688 | description: IPv6 Fragments Sent |
| 3689 | unit: "packets/s" |
| 3690 | chart_type: line |
| 3691 | dimensions: |
| 3692 | - name: ok |
| 3693 | - name: failed |
| 3694 | - name: all |
| 3695 | - meta: |
| 3696 | plugin_name: proc.plugin |
| 3697 | module_name: /proc/net/sockstat |
| 3698 | monitored_instance: |
| 3699 | name: Socket statistics |
| 3700 | link: "" |
| 3701 | categories: |
| 3702 | - data-collection.networking |
| 3703 | icon_filename: "network-wired.svg" |
| 3704 | related_resources: |
| 3705 | integrations: |
| 3706 | list: [] |
| 3707 | info_provided_to_referring_integrations: |
| 3708 | description: "" |
| 3709 | keywords: |
| 3710 | - sockets |
| 3711 | overview: |
| 3712 | data_collection: |
| 3713 | metrics_description: "This integration provides socket statistics." |
| 3714 | method_description: "" |
| 3715 | supported_platforms: |
| 3716 | include: [] |
| 3717 | exclude: [] |
| 3718 | multi_instance: true |
| 3719 | additional_permissions: |
| 3720 | description: "" |
| 3721 | default_behavior: |
| 3722 | auto_detection: |
| 3723 | description: "" |
| 3724 | limits: |
| 3725 | description: "" |
| 3726 | performance_impact: |
| 3727 | description: "" |
| 3728 | setup: |
| 3729 | prerequisites: |
| 3730 | list: [] |
| 3731 | configuration: |
| 3732 | file: |
| 3733 | name: "" |
| 3734 | description: "" |
| 3735 | options: |
| 3736 | description: "" |
| 3737 | folding: |
| 3738 | title: "" |
| 3739 | enabled: true |
| 3740 | list: [] |
| 3741 | examples: |
| 3742 | folding: |
| 3743 | enabled: true |
| 3744 | title: "" |
| 3745 | list: [] |
| 3746 | troubleshooting: |
| 3747 | problems: |
| 3748 | list: [] |
| 3749 | alerts: |
| 3750 | - name: tcp_orphans |
| 3751 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_orphans.conf |
| 3752 | metric: ipv4.sockstat_tcp_sockets |
| 3753 | info: orphan IPv4 TCP sockets utilization |
| 3754 | os: "linux" |
| 3755 | - name: tcp_memory |
| 3756 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/tcp_mem.conf |
| 3757 | metric: ipv4.sockstat_tcp_mem |
| 3758 | info: TCP memory utilization |
| 3759 | os: "linux" |
| 3760 | metrics: |
| 3761 | folding: |
| 3762 | title: Metrics |
| 3763 | enabled: false |
| 3764 | description: "" |
| 3765 | availability: [] |
| 3766 | scopes: |
| 3767 | - name: global |
| 3768 | description: "" |
| 3769 | labels: [] |
| 3770 | metrics: |
| 3771 | - name: ip.sockstat_sockets |
| 3772 | description: Sockets used for all address families |
| 3773 | unit: "sockets" |
| 3774 | chart_type: line |
| 3775 | dimensions: |
| 3776 | - name: used |
| 3777 | - name: ipv4.sockstat_tcp_sockets |
| 3778 | description: IPv4 TCP Sockets |
| 3779 | unit: "sockets" |
| 3780 | chart_type: line |
| 3781 | dimensions: |
| 3782 | - name: alloc |
| 3783 | - name: orphan |
| 3784 | - name: inuse |
| 3785 | - name: timewait |
| 3786 | - name: ipv4.sockstat_tcp_mem |
| 3787 | description: IPv4 TCP Sockets Memory |
| 3788 | unit: "KiB" |
| 3789 | chart_type: area |
| 3790 | dimensions: |
| 3791 | - name: mem |
| 3792 | - name: ipv4.sockstat_udp_sockets |
| 3793 | description: IPv4 UDP Sockets |
| 3794 | unit: "sockets" |
| 3795 | chart_type: line |
| 3796 | dimensions: |
| 3797 | - name: inuse |
| 3798 | - name: ipv4.sockstat_udp_mem |
| 3799 | description: IPv4 UDP Sockets Memory |
| 3800 | unit: "sockets" |
| 3801 | chart_type: line |
| 3802 | dimensions: |
| 3803 | - name: mem |
| 3804 | - name: ipv4.sockstat_udplite_sockets |
| 3805 | description: IPv4 UDPLITE Sockets |
| 3806 | unit: "sockets" |
| 3807 | chart_type: line |
| 3808 | dimensions: |
| 3809 | - name: inuse |
| 3810 | - name: ipv4.sockstat_raw_sockets |
| 3811 | description: IPv4 RAW Sockets |
| 3812 | unit: "sockets" |
| 3813 | chart_type: line |
| 3814 | dimensions: |
| 3815 | - name: inuse |
| 3816 | - name: ipv4.sockstat_frag_sockets |
| 3817 | description: IPv4 FRAG Sockets |
| 3818 | unit: "fragments" |
| 3819 | chart_type: line |
| 3820 | dimensions: |
| 3821 | - name: inuse |
| 3822 | - name: ipv4.sockstat_frag_mem |
| 3823 | description: IPv4 FRAG Sockets Memory |
| 3824 | unit: "KiB" |
| 3825 | chart_type: area |
| 3826 | dimensions: |
| 3827 | - name: mem |
| 3828 | - meta: |
| 3829 | plugin_name: proc.plugin |
| 3830 | module_name: /proc/net/sockstat6 |
| 3831 | monitored_instance: |
| 3832 | name: IPv6 Socket Statistics |
| 3833 | link: "" |
| 3834 | categories: |
| 3835 | - data-collection.networking |
| 3836 | icon_filename: "network-wired.svg" |
| 3837 | related_resources: |
| 3838 | integrations: |
| 3839 | list: [] |
| 3840 | info_provided_to_referring_integrations: |
| 3841 | description: "" |
| 3842 | keywords: |
| 3843 | - ipv6 sockets |
| 3844 | overview: |
| 3845 | data_collection: |
| 3846 | metrics_description: "This integration provides IPv6 socket statistics." |
| 3847 | method_description: "" |
| 3848 | supported_platforms: |
| 3849 | include: [] |
| 3850 | exclude: [] |
| 3851 | multi_instance: true |
| 3852 | additional_permissions: |
| 3853 | description: "" |
| 3854 | default_behavior: |
| 3855 | auto_detection: |
| 3856 | description: "" |
| 3857 | limits: |
| 3858 | description: "" |
| 3859 | performance_impact: |
| 3860 | description: "" |
| 3861 | setup: |
| 3862 | prerequisites: |
| 3863 | list: [] |
| 3864 | configuration: |
| 3865 | file: |
| 3866 | name: "" |
| 3867 | description: "" |
| 3868 | options: |
| 3869 | description: "" |
| 3870 | folding: |
| 3871 | title: "" |
| 3872 | enabled: true |
| 3873 | list: [] |
| 3874 | examples: |
| 3875 | folding: |
| 3876 | enabled: true |
| 3877 | title: "" |
| 3878 | list: [] |
| 3879 | troubleshooting: |
| 3880 | problems: |
| 3881 | list: [] |
| 3882 | alerts: [] |
| 3883 | metrics: |
| 3884 | folding: |
| 3885 | title: Metrics |
| 3886 | enabled: false |
| 3887 | description: "" |
| 3888 | availability: [] |
| 3889 | scopes: |
| 3890 | - name: global |
| 3891 | description: "" |
| 3892 | labels: [] |
| 3893 | metrics: |
| 3894 | - name: ipv6.sockstat6_tcp_sockets |
| 3895 | description: IPv6 TCP Sockets |
| 3896 | unit: "sockets" |
| 3897 | chart_type: line |
| 3898 | dimensions: |
| 3899 | - name: inuse |
| 3900 | - name: ipv6.sockstat6_udp_sockets |
| 3901 | description: IPv6 UDP Sockets |
| 3902 | unit: "sockets" |
| 3903 | chart_type: line |
| 3904 | dimensions: |
| 3905 | - name: inuse |
| 3906 | - name: ipv6.sockstat6_udplite_sockets |
| 3907 | description: IPv6 UDPLITE Sockets |
| 3908 | unit: "sockets" |
| 3909 | chart_type: line |
| 3910 | dimensions: |
| 3911 | - name: inuse |
| 3912 | - name: ipv6.sockstat6_raw_sockets |
| 3913 | description: IPv6 RAW Sockets |
| 3914 | unit: "sockets" |
| 3915 | chart_type: line |
| 3916 | dimensions: |
| 3917 | - name: inuse |
| 3918 | - name: ipv6.sockstat6_frag_sockets |
| 3919 | description: IPv6 FRAG Sockets |
| 3920 | unit: "fragments" |
| 3921 | chart_type: line |
| 3922 | dimensions: |
| 3923 | - name: inuse |
| 3924 | - meta: |
| 3925 | plugin_name: proc.plugin |
| 3926 | module_name: /proc/net/ip_vs_stats |
| 3927 | monitored_instance: |
| 3928 | name: IP Virtual Server |
| 3929 | link: "" |
| 3930 | categories: |
| 3931 | - data-collection.networking |
| 3932 | icon_filename: "network-wired.svg" |
| 3933 | related_resources: |
| 3934 | integrations: |
| 3935 | list: [] |
| 3936 | info_provided_to_referring_integrations: |
| 3937 | description: "" |
| 3938 | keywords: |
| 3939 | - ip virtual server |
| 3940 | overview: |
| 3941 | data_collection: |
| 3942 | metrics_description: "This integration monitors IP Virtual Server statistics" |
| 3943 | method_description: "" |
| 3944 | supported_platforms: |
| 3945 | include: [] |
| 3946 | exclude: [] |
| 3947 | multi_instance: true |
| 3948 | additional_permissions: |
| 3949 | description: "" |
| 3950 | default_behavior: |
| 3951 | auto_detection: |
| 3952 | description: "" |
| 3953 | limits: |
| 3954 | description: "" |
| 3955 | performance_impact: |
| 3956 | description: "" |
| 3957 | setup: |
| 3958 | prerequisites: |
| 3959 | list: [] |
| 3960 | configuration: |
| 3961 | file: |
| 3962 | name: "" |
| 3963 | description: "" |
| 3964 | options: |
| 3965 | description: "" |
| 3966 | folding: |
| 3967 | title: "" |
| 3968 | enabled: true |
| 3969 | list: [] |
| 3970 | examples: |
| 3971 | folding: |
| 3972 | enabled: true |
| 3973 | title: "" |
| 3974 | list: [] |
| 3975 | troubleshooting: |
| 3976 | problems: |
| 3977 | list: [] |
| 3978 | alerts: [] |
| 3979 | metrics: |
| 3980 | folding: |
| 3981 | title: Metrics |
| 3982 | enabled: false |
| 3983 | description: "" |
| 3984 | availability: [] |
| 3985 | scopes: |
| 3986 | - name: global |
| 3987 | description: "" |
| 3988 | labels: [] |
| 3989 | metrics: |
| 3990 | - name: ipvs.sockets |
| 3991 | description: IPVS New Connections |
| 3992 | unit: "connections/s" |
| 3993 | chart_type: line |
| 3994 | dimensions: |
| 3995 | - name: connections |
| 3996 | - name: ipvs.packets |
| 3997 | description: IPVS Packets |
| 3998 | unit: "packets/s" |
| 3999 | chart_type: line |
| 4000 | dimensions: |
| 4001 | - name: received |
| 4002 | - name: sent |
| 4003 | - name: ipvs.net |
| 4004 | description: IPVS Bandwidth |
| 4005 | unit: "kilobits/s" |
| 4006 | chart_type: area |
| 4007 | dimensions: |
| 4008 | - name: received |
| 4009 | - name: sent |
| 4010 | - meta: |
| 4011 | plugin_name: proc.plugin |
| 4012 | module_name: /proc/net/rpc/nfs |
| 4013 | monitored_instance: |
| 4014 | name: NFS Client |
| 4015 | link: "" |
| 4016 | categories: |
| 4017 | - data-collection.storage |
| 4018 | icon_filename: "nfs.png" |
| 4019 | related_resources: |
| 4020 | integrations: |
| 4021 | list: [] |
| 4022 | info_provided_to_referring_integrations: |
| 4023 | description: "" |
| 4024 | keywords: |
| 4025 | - nfs client |
| 4026 | - filesystem |
| 4027 | overview: |
| 4028 | data_collection: |
| 4029 | metrics_description: "This integration provides statistics from the Linux kernel's NFS Client." |
| 4030 | method_description: "" |
| 4031 | supported_platforms: |
| 4032 | include: [] |
| 4033 | exclude: [] |
| 4034 | multi_instance: true |
| 4035 | additional_permissions: |
| 4036 | description: "" |
| 4037 | default_behavior: |
| 4038 | auto_detection: |
| 4039 | description: "" |
| 4040 | limits: |
| 4041 | description: "" |
| 4042 | performance_impact: |
| 4043 | description: "" |
| 4044 | setup: |
| 4045 | prerequisites: |
| 4046 | list: [] |
| 4047 | configuration: |
| 4048 | file: |
| 4049 | name: "" |
| 4050 | description: "" |
| 4051 | options: |
| 4052 | description: "" |
| 4053 | folding: |
| 4054 | title: "" |
| 4055 | enabled: true |
| 4056 | list: [] |
| 4057 | examples: |
| 4058 | folding: |
| 4059 | enabled: true |
| 4060 | title: "" |
| 4061 | list: [] |
| 4062 | troubleshooting: |
| 4063 | problems: |
| 4064 | list: [] |
| 4065 | alerts: [] |
| 4066 | metrics: |
| 4067 | folding: |
| 4068 | title: Metrics |
| 4069 | enabled: false |
| 4070 | description: "" |
| 4071 | availability: [] |
| 4072 | scopes: |
| 4073 | - name: global |
| 4074 | description: "" |
| 4075 | labels: [] |
| 4076 | metrics: |
| 4077 | - name: nfs.net |
| 4078 | description: NFS Client Network |
| 4079 | unit: "operations/s" |
| 4080 | chart_type: stacked |
| 4081 | dimensions: |
| 4082 | - name: udp |
| 4083 | - name: tcp |
| 4084 | - name: nfs.rpc |
| 4085 | description: NFS Client Remote Procedure Calls Statistics |
| 4086 | unit: "calls/s" |
| 4087 | chart_type: line |
| 4088 | dimensions: |
| 4089 | - name: calls |
| 4090 | - name: retransmits |
| 4091 | - name: auth_refresh |
| 4092 | - name: nfs.proc2 |
| 4093 | description: NFS v2 Client Remote Procedure Calls |
| 4094 | unit: "calls/s" |
| 4095 | chart_type: stacked |
| 4096 | dimensions: |
| 4097 | - name: a dimension per proc2 call |
| 4098 | - name: nfs.proc3 |
| 4099 | description: NFS v3 Client Remote Procedure Calls |
| 4100 | unit: "calls/s" |
| 4101 | chart_type: stacked |
| 4102 | dimensions: |
| 4103 | - name: a dimension per proc3 call |
| 4104 | - name: nfs.proc4 |
| 4105 | description: NFS v4 Client Remote Procedure Calls |
| 4106 | unit: "calls/s" |
| 4107 | chart_type: stacked |
| 4108 | dimensions: |
| 4109 | - name: a dimension per proc4 call |
| 4110 | - meta: |
| 4111 | plugin_name: proc.plugin |
| 4112 | module_name: /proc/net/rpc/nfsd |
| 4113 | monitored_instance: |
| 4114 | name: NFS Server |
| 4115 | link: "" |
| 4116 | categories: |
| 4117 | - data-collection.storage |
| 4118 | icon_filename: "nfs.png" |
| 4119 | related_resources: |
| 4120 | integrations: |
| 4121 | list: [] |
| 4122 | info_provided_to_referring_integrations: |
| 4123 | description: "" |
| 4124 | keywords: |
| 4125 | - nfs server |
| 4126 | - filesystem |
| 4127 | overview: |
| 4128 | data_collection: |
| 4129 | metrics_description: "This integration provides statistics from the Linux kernel's NFS Server." |
| 4130 | method_description: "" |
| 4131 | supported_platforms: |
| 4132 | include: [] |
| 4133 | exclude: [] |
| 4134 | multi_instance: true |
| 4135 | additional_permissions: |
| 4136 | description: "" |
| 4137 | default_behavior: |
| 4138 | auto_detection: |
| 4139 | description: "" |
| 4140 | limits: |
| 4141 | description: "" |
| 4142 | performance_impact: |
| 4143 | description: "" |
| 4144 | setup: |
| 4145 | prerequisites: |
| 4146 | list: [] |
| 4147 | configuration: |
| 4148 | file: |
| 4149 | name: "" |
| 4150 | description: "" |
| 4151 | options: |
| 4152 | description: "" |
| 4153 | folding: |
| 4154 | title: "" |
| 4155 | enabled: true |
| 4156 | list: [] |
| 4157 | examples: |
| 4158 | folding: |
| 4159 | enabled: true |
| 4160 | title: "" |
| 4161 | list: [] |
| 4162 | troubleshooting: |
| 4163 | problems: |
| 4164 | list: [] |
| 4165 | alerts: [] |
| 4166 | metrics: |
| 4167 | folding: |
| 4168 | title: Metrics |
| 4169 | enabled: false |
| 4170 | description: "" |
| 4171 | availability: [] |
| 4172 | scopes: |
| 4173 | - name: global |
| 4174 | description: "" |
| 4175 | labels: [] |
| 4176 | metrics: |
| 4177 | - name: nfsd.readcache |
| 4178 | description: NFS Server Read Cache |
| 4179 | unit: "reads/s" |
| 4180 | chart_type: stacked |
| 4181 | dimensions: |
| 4182 | - name: hits |
| 4183 | - name: misses |
| 4184 | - name: nocache |
| 4185 | - name: nfsd.filehandles |
| 4186 | description: NFS Server File Handles |
| 4187 | unit: "handles/s" |
| 4188 | chart_type: line |
| 4189 | dimensions: |
| 4190 | - name: stale |
| 4191 | - name: nfsd.io |
| 4192 | description: NFS Server I/O |
| 4193 | unit: "kilobytes/s" |
| 4194 | chart_type: area |
| 4195 | dimensions: |
| 4196 | - name: read |
| 4197 | - name: write |
| 4198 | - name: nfsd.threads |
| 4199 | description: NFS Server Threads |
| 4200 | unit: "threads" |
| 4201 | chart_type: line |
| 4202 | dimensions: |
| 4203 | - name: threads |
| 4204 | - name: nfsd.net |
| 4205 | description: NFS Server Network Statistics |
| 4206 | unit: "packets/s" |
| 4207 | chart_type: line |
| 4208 | dimensions: |
| 4209 | - name: udp |
| 4210 | - name: tcp |
| 4211 | - name: nfsd.rpc |
| 4212 | description: NFS Server Remote Procedure Calls Statistics |
| 4213 | unit: "calls/s" |
| 4214 | chart_type: line |
| 4215 | dimensions: |
| 4216 | - name: calls |
| 4217 | - name: bad_format |
| 4218 | - name: bad_auth |
| 4219 | - name: nfsd.proc2 |
| 4220 | description: NFS v2 Server Remote Procedure Calls |
| 4221 | unit: "calls/s" |
| 4222 | chart_type: stacked |
| 4223 | dimensions: |
| 4224 | - name: a dimension per proc2 call |
| 4225 | - name: nfsd.proc3 |
| 4226 | description: NFS v3 Server Remote Procedure Calls |
| 4227 | unit: "calls/s" |
| 4228 | chart_type: stacked |
| 4229 | dimensions: |
| 4230 | - name: a dimension per proc3 call |
| 4231 | - name: nfsd.proc4 |
| 4232 | description: NFS v4 Server Remote Procedure Calls |
| 4233 | unit: "calls/s" |
| 4234 | chart_type: stacked |
| 4235 | dimensions: |
| 4236 | - name: a dimension per proc4 call |
| 4237 | - name: nfsd.proc4ops |
| 4238 | description: NFS v4 Server Operations |
| 4239 | unit: "operations/s" |
| 4240 | chart_type: stacked |
| 4241 | dimensions: |
| 4242 | - name: a dimension per proc4 operation |
| 4243 | - meta: |
| 4244 | plugin_name: proc.plugin |
| 4245 | module_name: /proc/net/sctp/snmp |
| 4246 | monitored_instance: |
| 4247 | name: SCTP Statistics |
| 4248 | link: "" |
| 4249 | categories: |
| 4250 | - data-collection.networking |
| 4251 | icon_filename: "network-wired.svg" |
| 4252 | related_resources: |
| 4253 | integrations: |
| 4254 | list: [] |
| 4255 | info_provided_to_referring_integrations: |
| 4256 | description: "" |
| 4257 | keywords: |
| 4258 | - sctp |
| 4259 | - stream control transmission protocol |
| 4260 | overview: |
| 4261 | data_collection: |
| 4262 | metrics_description: "This integration provides statistics about the Stream Control Transmission Protocol (SCTP)." |
| 4263 | method_description: "" |
| 4264 | supported_platforms: |
| 4265 | include: [] |
| 4266 | exclude: [] |
| 4267 | multi_instance: true |
| 4268 | additional_permissions: |
| 4269 | description: "" |
| 4270 | default_behavior: |
| 4271 | auto_detection: |
| 4272 | description: "" |
| 4273 | limits: |
| 4274 | description: "" |
| 4275 | performance_impact: |
| 4276 | description: "" |
| 4277 | setup: |
| 4278 | prerequisites: |
| 4279 | list: [] |
| 4280 | configuration: |
| 4281 | file: |
| 4282 | name: "" |
| 4283 | description: "" |
| 4284 | options: |
| 4285 | description: "" |
| 4286 | folding: |
| 4287 | title: "" |
| 4288 | enabled: true |
| 4289 | list: [] |
| 4290 | examples: |
| 4291 | folding: |
| 4292 | enabled: true |
| 4293 | title: "" |
| 4294 | list: [] |
| 4295 | troubleshooting: |
| 4296 | problems: |
| 4297 | list: [] |
| 4298 | alerts: [] |
| 4299 | metrics: |
| 4300 | folding: |
| 4301 | title: Metrics |
| 4302 | enabled: false |
| 4303 | description: "" |
| 4304 | availability: [] |
| 4305 | scopes: |
| 4306 | - name: global |
| 4307 | description: "" |
| 4308 | labels: [] |
| 4309 | metrics: |
| 4310 | - name: sctp.established |
| 4311 | description: SCTP current total number of established associations |
| 4312 | unit: "associations" |
| 4313 | chart_type: line |
| 4314 | dimensions: |
| 4315 | - name: established |
| 4316 | - name: sctp.transitions |
| 4317 | description: SCTP Association Transitions |
| 4318 | unit: "transitions/s" |
| 4319 | chart_type: line |
| 4320 | dimensions: |
| 4321 | - name: active |
| 4322 | - name: passive |
| 4323 | - name: aborted |
| 4324 | - name: shutdown |
| 4325 | - name: sctp.packets |
| 4326 | description: SCTP Packets |
| 4327 | unit: "packets/s" |
| 4328 | chart_type: line |
| 4329 | dimensions: |
| 4330 | - name: received |
| 4331 | - name: sent |
| 4332 | - name: sctp.packet_errors |
| 4333 | description: SCTP Packet Errors |
| 4334 | unit: "packets/s" |
| 4335 | chart_type: line |
| 4336 | dimensions: |
| 4337 | - name: invalid |
| 4338 | - name: checksum |
| 4339 | - name: sctp.fragmentation |
| 4340 | description: SCTP Fragmentation |
| 4341 | unit: "packets/s" |
| 4342 | chart_type: line |
| 4343 | dimensions: |
| 4344 | - name: reassembled |
| 4345 | - name: fragmented |
| 4346 | - meta: |
| 4347 | plugin_name: proc.plugin |
| 4348 | module_name: /proc/net/stat/nf_conntrack |
| 4349 | monitored_instance: |
| 4350 | name: Conntrack |
| 4351 | link: "" |
| 4352 | categories: |
| 4353 | - data-collection.networking |
| 4354 | icon_filename: "firewall.svg" |
| 4355 | related_resources: |
| 4356 | integrations: |
| 4357 | list: [] |
| 4358 | info_provided_to_referring_integrations: |
| 4359 | description: "" |
| 4360 | keywords: |
| 4361 | - connection tracking mechanism |
| 4362 | - netfilter |
| 4363 | - conntrack |
| 4364 | overview: |
| 4365 | data_collection: |
| 4366 | metrics_description: "This integration monitors the connection tracking mechanism of Netfilter in the Linux Kernel." |
| 4367 | method_description: "" |
| 4368 | supported_platforms: |
| 4369 | include: [] |
| 4370 | exclude: [] |
| 4371 | multi_instance: true |
| 4372 | additional_permissions: |
| 4373 | description: "" |
| 4374 | default_behavior: |
| 4375 | auto_detection: |
| 4376 | description: "" |
| 4377 | limits: |
| 4378 | description: "" |
| 4379 | performance_impact: |
| 4380 | description: "" |
| 4381 | setup: |
| 4382 | prerequisites: |
| 4383 | list: [] |
| 4384 | configuration: |
| 4385 | file: |
| 4386 | name: "" |
| 4387 | description: "" |
| 4388 | options: |
| 4389 | description: "" |
| 4390 | folding: |
| 4391 | title: "" |
| 4392 | enabled: true |
| 4393 | list: [] |
| 4394 | examples: |
| 4395 | folding: |
| 4396 | enabled: true |
| 4397 | title: "" |
| 4398 | list: [] |
| 4399 | troubleshooting: |
| 4400 | problems: |
| 4401 | list: [] |
| 4402 | alerts: |
| 4403 | - name: netfilter_conntrack_full |
| 4404 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/netfilter.conf |
| 4405 | metric: netfilter.conntrack_sockets |
| 4406 | info: netfilter connection tracker table size utilization |
| 4407 | os: "linux" |
| 4408 | metrics: |
| 4409 | folding: |
| 4410 | title: Metrics |
| 4411 | enabled: false |
| 4412 | description: "" |
| 4413 | availability: [] |
| 4414 | scopes: |
| 4415 | - name: global |
| 4416 | description: "" |
| 4417 | labels: [] |
| 4418 | metrics: |
| 4419 | - name: netfilter.conntrack_sockets |
| 4420 | description: Connection Tracker Connections |
| 4421 | unit: "active connections" |
| 4422 | chart_type: line |
| 4423 | dimensions: |
| 4424 | - name: connections |
| 4425 | - name: netfilter.conntrack_new |
| 4426 | description: Connection Tracker New Connections |
| 4427 | unit: "connections/s" |
| 4428 | chart_type: line |
| 4429 | dimensions: |
| 4430 | - name: new |
| 4431 | - name: ignore |
| 4432 | - name: invalid |
| 4433 | - name: netfilter.conntrack_changes |
| 4434 | description: Connection Tracker Changes |
| 4435 | unit: "changes/s" |
| 4436 | chart_type: line |
| 4437 | dimensions: |
| 4438 | - name: inserted |
| 4439 | - name: deleted |
| 4440 | - name: delete_list |
| 4441 | - name: netfilter.conntrack_expect |
| 4442 | description: Connection Tracker Expectations |
| 4443 | unit: "expectations/s" |
| 4444 | chart_type: line |
| 4445 | dimensions: |
| 4446 | - name: created |
| 4447 | - name: deleted |
| 4448 | - name: new |
| 4449 | - name: netfilter.conntrack_search |
| 4450 | description: Connection Tracker Searches |
| 4451 | unit: "searches/s" |
| 4452 | chart_type: line |
| 4453 | dimensions: |
| 4454 | - name: searched |
| 4455 | - name: restarted |
| 4456 | - name: found |
| 4457 | - name: netfilter.conntrack_errors |
| 4458 | description: Connection Tracker Errors |
| 4459 | unit: "events/s" |
| 4460 | chart_type: line |
| 4461 | dimensions: |
| 4462 | - name: icmp_error |
| 4463 | - name: error_failed |
| 4464 | - name: drop |
| 4465 | - name: early_drop |
| 4466 | - meta: |
| 4467 | plugin_name: proc.plugin |
| 4468 | module_name: /proc/net/stat/synproxy |
| 4469 | monitored_instance: |
| 4470 | name: Synproxy |
| 4471 | link: "" |
| 4472 | categories: |
| 4473 | - data-collection.networking |
| 4474 | icon_filename: "firewall.svg" |
| 4475 | related_resources: |
| 4476 | integrations: |
| 4477 | list: [] |
| 4478 | info_provided_to_referring_integrations: |
| 4479 | description: "" |
| 4480 | keywords: |
| 4481 | - synproxy |
| 4482 | overview: |
| 4483 | data_collection: |
| 4484 | metrics_description: "This integration provides statistics about the Synproxy netfilter module." |
| 4485 | method_description: "" |
| 4486 | supported_platforms: |
| 4487 | include: [] |
| 4488 | exclude: [] |
| 4489 | multi_instance: true |
| 4490 | additional_permissions: |
| 4491 | description: "" |
| 4492 | default_behavior: |
| 4493 | auto_detection: |
| 4494 | description: "" |
| 4495 | limits: |
| 4496 | description: "" |
| 4497 | performance_impact: |
| 4498 | description: "" |
| 4499 | setup: |
| 4500 | prerequisites: |
| 4501 | list: [] |
| 4502 | configuration: |
| 4503 | file: |
| 4504 | name: "" |
| 4505 | description: "" |
| 4506 | options: |
| 4507 | description: "" |
| 4508 | folding: |
| 4509 | title: "" |
| 4510 | enabled: true |
| 4511 | list: [] |
| 4512 | examples: |
| 4513 | folding: |
| 4514 | enabled: true |
| 4515 | title: "" |
| 4516 | list: [] |
| 4517 | troubleshooting: |
| 4518 | problems: |
| 4519 | list: [] |
| 4520 | alerts: [] |
| 4521 | metrics: |
| 4522 | folding: |
| 4523 | title: Metrics |
| 4524 | enabled: false |
| 4525 | description: "" |
| 4526 | availability: [] |
| 4527 | scopes: |
| 4528 | - name: global |
| 4529 | description: "" |
| 4530 | labels: [] |
| 4531 | metrics: |
| 4532 | - name: netfilter.synproxy_syn_received |
| 4533 | description: SYNPROXY SYN Packets received |
| 4534 | unit: "packets/s" |
| 4535 | chart_type: line |
| 4536 | dimensions: |
| 4537 | - name: received |
| 4538 | - name: netfilter.synproxy_conn_reopened |
| 4539 | description: SYNPROXY Connections Reopened |
| 4540 | unit: "connections/s" |
| 4541 | chart_type: line |
| 4542 | dimensions: |
| 4543 | - name: reopened |
| 4544 | - name: netfilter.synproxy_cookies |
| 4545 | description: SYNPROXY TCP Cookies |
| 4546 | unit: "cookies/s" |
| 4547 | chart_type: line |
| 4548 | dimensions: |
| 4549 | - name: valid |
| 4550 | - name: invalid |
| 4551 | - name: retransmits |
| 4552 | - meta: |
| 4553 | plugin_name: proc.plugin |
| 4554 | module_name: /proc/spl/kstat/zfs/arcstats |
| 4555 | monitored_instance: |
| 4556 | name: ZFS Adaptive Replacement Cache |
| 4557 | link: "" |
| 4558 | categories: |
| 4559 | - data-collection.storage |
| 4560 | icon_filename: "filesystem.svg" |
| 4561 | related_resources: |
| 4562 | integrations: |
| 4563 | list: [] |
| 4564 | info_provided_to_referring_integrations: |
| 4565 | description: "" |
| 4566 | keywords: |
| 4567 | - zfs arc |
| 4568 | - arc |
| 4569 | - zfs |
| 4570 | - filesystem |
| 4571 | overview: |
| 4572 | data_collection: |
| 4573 | metrics_description: "This integration monitors ZFS Adadptive Replacement Cache (ARC) statistics." |
| 4574 | method_description: "" |
| 4575 | supported_platforms: |
| 4576 | include: [] |
| 4577 | exclude: [] |
| 4578 | multi_instance: true |
| 4579 | additional_permissions: |
| 4580 | description: "" |
| 4581 | default_behavior: |
| 4582 | auto_detection: |
| 4583 | description: "" |
| 4584 | limits: |
| 4585 | description: "" |
| 4586 | performance_impact: |
| 4587 | description: "" |
| 4588 | setup: |
| 4589 | prerequisites: |
| 4590 | list: [] |
| 4591 | configuration: |
| 4592 | file: |
| 4593 | name: "" |
| 4594 | description: "" |
| 4595 | options: |
| 4596 | description: "" |
| 4597 | folding: |
| 4598 | title: "" |
| 4599 | enabled: true |
| 4600 | list: [] |
| 4601 | examples: |
| 4602 | folding: |
| 4603 | enabled: true |
| 4604 | title: "" |
| 4605 | list: [] |
| 4606 | troubleshooting: |
| 4607 | problems: |
| 4608 | list: [] |
| 4609 | alerts: |
| 4610 | - name: zfs_memory_throttle |
| 4611 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/zfs.conf |
| 4612 | metric: zfs.memory_ops |
| 4613 | info: number of times ZFS had to limit the ARC growth in the last 10 minutes |
| 4614 | metrics: |
| 4615 | folding: |
| 4616 | title: Metrics |
| 4617 | enabled: false |
| 4618 | description: "" |
| 4619 | availability: [] |
| 4620 | scopes: |
| 4621 | - name: global |
| 4622 | description: "" |
| 4623 | labels: [] |
| 4624 | metrics: |
| 4625 | - name: zfs.arc_size |
| 4626 | description: ZFS ARC Size |
| 4627 | unit: "MiB" |
| 4628 | chart_type: area |
| 4629 | dimensions: |
| 4630 | - name: arcsz |
| 4631 | - name: target |
| 4632 | - name: min |
| 4633 | - name: max |
| 4634 | - name: zfs.l2_size |
| 4635 | description: ZFS L2 ARC Size |
| 4636 | unit: "MiB" |
| 4637 | chart_type: area |
| 4638 | dimensions: |
| 4639 | - name: actual |
| 4640 | - name: size |
| 4641 | - name: zfs.reads |
| 4642 | description: ZFS Reads |
| 4643 | unit: "reads/s" |
| 4644 | chart_type: area |
| 4645 | dimensions: |
| 4646 | - name: arc |
| 4647 | - name: demand |
| 4648 | - name: prefetch |
| 4649 | - name: metadata |
| 4650 | - name: l2 |
| 4651 | - name: zfs.bytes |
| 4652 | description: ZFS ARC L2 Read/Write Rate |
| 4653 | unit: "KiB/s" |
| 4654 | chart_type: area |
| 4655 | dimensions: |
| 4656 | - name: read |
| 4657 | - name: write |
| 4658 | - name: zfs.hits |
| 4659 | description: ZFS ARC Hits |
| 4660 | unit: "percentage" |
| 4661 | chart_type: stacked |
| 4662 | dimensions: |
| 4663 | - name: hits |
| 4664 | - name: misses |
| 4665 | - name: zfs.hits_rate |
| 4666 | description: ZFS ARC Hits Rate |
| 4667 | unit: "events/s" |
| 4668 | chart_type: stacked |
| 4669 | dimensions: |
| 4670 | - name: hits |
| 4671 | - name: misses |
| 4672 | - name: zfs.dhits |
| 4673 | description: ZFS Demand Hits |
| 4674 | unit: "percentage" |
| 4675 | chart_type: stacked |
| 4676 | dimensions: |
| 4677 | - name: hits |
| 4678 | - name: misses |
| 4679 | - name: zfs.dhits_rate |
| 4680 | description: ZFS Demand Hits Rate |
| 4681 | unit: "events/s" |
| 4682 | chart_type: stacked |
| 4683 | dimensions: |
| 4684 | - name: hits |
| 4685 | - name: misses |
| 4686 | - name: zfs.phits |
| 4687 | description: ZFS Prefetch Hits |
| 4688 | unit: "percentage" |
| 4689 | chart_type: stacked |
| 4690 | dimensions: |
| 4691 | - name: hits |
| 4692 | - name: misses |
| 4693 | - name: zfs.phits_rate |
| 4694 | description: ZFS Prefetch Hits Rate |
| 4695 | unit: "events/s" |
| 4696 | chart_type: stacked |
| 4697 | dimensions: |
| 4698 | - name: hits |
| 4699 | - name: misses |
| 4700 | - name: zfs.mhits |
| 4701 | description: ZFS Metadata Hits |
| 4702 | unit: "percentage" |
| 4703 | chart_type: stacked |
| 4704 | dimensions: |
| 4705 | - name: hits |
| 4706 | - name: misses |
| 4707 | - name: zfs.mhits_rate |
| 4708 | description: ZFS Metadata Hits Rate |
| 4709 | unit: "events/s" |
| 4710 | chart_type: stacked |
| 4711 | dimensions: |
| 4712 | - name: hits |
| 4713 | - name: misses |
| 4714 | - name: zfs.l2hits |
| 4715 | description: ZFS L2 Hits |
| 4716 | unit: "percentage" |
| 4717 | chart_type: stacked |
| 4718 | dimensions: |
| 4719 | - name: hits |
| 4720 | - name: misses |
| 4721 | - name: zfs.l2hits_rate |
| 4722 | description: ZFS L2 Hits Rate |
| 4723 | unit: "events/s" |
| 4724 | chart_type: stacked |
| 4725 | dimensions: |
| 4726 | - name: hits |
| 4727 | - name: misses |
| 4728 | - name: zfs.list_hits |
| 4729 | description: ZFS List Hits |
| 4730 | unit: "hits/s" |
| 4731 | chart_type: area |
| 4732 | dimensions: |
| 4733 | - name: mfu |
| 4734 | - name: mfu_ghost |
| 4735 | - name: mru |
| 4736 | - name: mru_ghost |
| 4737 | - name: zfs.arc_size_breakdown |
| 4738 | description: ZFS ARC Size Breakdown |
| 4739 | unit: "percentage" |
| 4740 | chart_type: stacked |
| 4741 | dimensions: |
| 4742 | - name: recent |
| 4743 | - name: frequent |
| 4744 | - name: zfs.memory_ops |
| 4745 | description: ZFS Memory Operations |
| 4746 | unit: "operations/s" |
| 4747 | chart_type: line |
| 4748 | dimensions: |
| 4749 | - name: direct |
| 4750 | - name: throttled |
| 4751 | - name: indirect |
| 4752 | - name: zfs.important_ops |
| 4753 | description: ZFS Important Operations |
| 4754 | unit: "operations/s" |
| 4755 | chart_type: line |
| 4756 | dimensions: |
| 4757 | - name: evict_skip |
| 4758 | - name: deleted |
| 4759 | - name: mutex_miss |
| 4760 | - name: hash_collisions |
| 4761 | - name: zfs.actual_hits |
| 4762 | description: ZFS Actual Cache Hits |
| 4763 | unit: "percentage" |
| 4764 | chart_type: stacked |
| 4765 | dimensions: |
| 4766 | - name: hits |
| 4767 | - name: misses |
| 4768 | - name: zfs.actual_hits_rate |
| 4769 | description: ZFS Actual Cache Hits Rate |
| 4770 | unit: "events/s" |
| 4771 | chart_type: stacked |
| 4772 | dimensions: |
| 4773 | - name: hits |
| 4774 | - name: misses |
| 4775 | - name: zfs.demand_data_hits |
| 4776 | description: ZFS Data Demand Efficiency |
| 4777 | unit: "percentage" |
| 4778 | chart_type: stacked |
| 4779 | dimensions: |
| 4780 | - name: hits |
| 4781 | - name: misses |
| 4782 | - name: zfs.demand_data_hits_rate |
| 4783 | description: ZFS Data Demand Efficiency Rate |
| 4784 | unit: "events/s" |
| 4785 | chart_type: stacked |
| 4786 | dimensions: |
| 4787 | - name: hits |
| 4788 | - name: misses |
| 4789 | - name: zfs.prefetch_data_hits |
| 4790 | description: ZFS Data Prefetch Efficiency |
| 4791 | unit: "percentage" |
| 4792 | chart_type: stacked |
| 4793 | dimensions: |
| 4794 | - name: hits |
| 4795 | - name: misses |
| 4796 | - name: zfs.prefetch_data_hits_rate |
| 4797 | description: ZFS Data Prefetch Efficiency Rate |
| 4798 | unit: "events/s" |
| 4799 | chart_type: stacked |
| 4800 | dimensions: |
| 4801 | - name: hits |
| 4802 | - name: misses |
| 4803 | - name: zfs.hash_elements |
| 4804 | description: ZFS ARC Hash Elements |
| 4805 | unit: "elements" |
| 4806 | chart_type: line |
| 4807 | dimensions: |
| 4808 | - name: current |
| 4809 | - name: max |
| 4810 | - name: zfs.hash_chains |
| 4811 | description: ZFS ARC Hash Chains |
| 4812 | unit: "chains" |
| 4813 | chart_type: line |
| 4814 | dimensions: |
| 4815 | - name: current |
| 4816 | - name: max |
| 4817 | - meta: |
| 4818 | plugin_name: proc.plugin |
| 4819 | module_name: /sys/fs/btrfs |
| 4820 | monitored_instance: |
| 4821 | name: BTRFS |
| 4822 | link: "" |
| 4823 | categories: |
| 4824 | - data-collection.storage |
| 4825 | icon_filename: "filesystem.svg" |
| 4826 | related_resources: |
| 4827 | integrations: |
| 4828 | list: [] |
| 4829 | info_provided_to_referring_integrations: |
| 4830 | description: "" |
| 4831 | keywords: |
| 4832 | - btrfs |
| 4833 | - filesystem |
| 4834 | overview: |
| 4835 | data_collection: |
| 4836 | metrics_description: "This integration provides usage and error statistics from the BTRFS filesystem." |
| 4837 | method_description: "" |
| 4838 | supported_platforms: |
| 4839 | include: [] |
| 4840 | exclude: [] |
| 4841 | multi_instance: true |
| 4842 | additional_permissions: |
| 4843 | description: "" |
| 4844 | default_behavior: |
| 4845 | auto_detection: |
| 4846 | description: "" |
| 4847 | limits: |
| 4848 | description: "" |
| 4849 | performance_impact: |
| 4850 | description: "" |
| 4851 | setup: |
| 4852 | prerequisites: |
| 4853 | list: [] |
| 4854 | configuration: |
| 4855 | file: |
| 4856 | name: "" |
| 4857 | description: "" |
| 4858 | options: |
| 4859 | description: "" |
| 4860 | folding: |
| 4861 | title: "" |
| 4862 | enabled: true |
| 4863 | list: [] |
| 4864 | examples: |
| 4865 | folding: |
| 4866 | enabled: true |
| 4867 | title: "" |
| 4868 | list: [] |
| 4869 | troubleshooting: |
| 4870 | problems: |
| 4871 | list: [] |
| 4872 | alerts: |
| 4873 | - name: btrfs_allocated |
| 4874 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/btrfs.conf |
| 4875 | metric: btrfs.disk |
| 4876 | info: percentage of allocated BTRFS physical disk space |
| 4877 | os: "*" |
| 4878 | - name: btrfs_data |
| 4879 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/btrfs.conf |
| 4880 | metric: btrfs.data |
| 4881 | info: utilization of BTRFS data space |
| 4882 | os: "*" |
| 4883 | - name: btrfs_metadata |
| 4884 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/btrfs.conf |
| 4885 | metric: btrfs.metadata |
| 4886 | info: utilization of BTRFS metadata space |
| 4887 | os: "*" |
| 4888 | - name: btrfs_system |
| 4889 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/btrfs.conf |
| 4890 | metric: btrfs.system |
| 4891 | info: utilization of BTRFS system space |
| 4892 | os: "*" |
| 4893 | - name: btrfs_device_read_errors |
| 4894 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/btrfs.conf |
| 4895 | metric: btrfs.device_errors |
| 4896 | info: number of encountered BTRFS read errors |
| 4897 | os: "*" |
| 4898 | - name: btrfs_device_write_errors |
| 4899 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/btrfs.conf |
| 4900 | metric: btrfs.device_errors |
| 4901 | info: number of encountered BTRFS write errors |
| 4902 | os: "*" |
| 4903 | - name: btrfs_device_flush_errors |
| 4904 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/btrfs.conf |
| 4905 | metric: btrfs.device_errors |
| 4906 | info: number of encountered BTRFS flush errors |
| 4907 | os: "*" |
| 4908 | - name: btrfs_device_corruption_errors |
| 4909 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/btrfs.conf |
| 4910 | metric: btrfs.device_errors |
| 4911 | info: number of encountered BTRFS corruption errors |
| 4912 | os: "*" |
| 4913 | - name: btrfs_device_generation_errors |
| 4914 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/btrfs.conf |
| 4915 | metric: btrfs.device_errors |
| 4916 | info: number of encountered BTRFS generation errors |
| 4917 | os: "*" |
| 4918 | metrics: |
| 4919 | folding: |
| 4920 | title: Metrics |
| 4921 | enabled: false |
| 4922 | description: "" |
| 4923 | availability: [] |
| 4924 | scopes: |
| 4925 | - name: btrfs filesystem |
| 4926 | description: "" |
| 4927 | labels: |
| 4928 | - name: filesystem_uuid |
| 4929 | description: TBD |
| 4930 | - name: filesystem_label |
| 4931 | description: TBD |
| 4932 | metrics: |
| 4933 | - name: btrfs.disk |
| 4934 | description: BTRFS Physical Disk Allocation |
| 4935 | unit: "MiB" |
| 4936 | chart_type: stacked |
| 4937 | dimensions: |
| 4938 | - name: unallocated |
| 4939 | - name: data_free |
| 4940 | - name: data_used |
| 4941 | - name: meta_free |
| 4942 | - name: meta_used |
| 4943 | - name: sys_free |
| 4944 | - name: sys_used |
| 4945 | - name: btrfs.data |
| 4946 | description: BTRFS Data Allocation |
| 4947 | unit: "MiB" |
| 4948 | chart_type: stacked |
| 4949 | dimensions: |
| 4950 | - name: free |
| 4951 | - name: used |
| 4952 | - name: btrfs.metadata |
| 4953 | description: BTRFS Metadata Allocation |
| 4954 | unit: "MiB" |
| 4955 | chart_type: stacked |
| 4956 | dimensions: |
| 4957 | - name: free |
| 4958 | - name: used |
| 4959 | - name: reserved |
| 4960 | - name: btrfs.system |
| 4961 | description: BTRFS System Allocation |
| 4962 | unit: "MiB" |
| 4963 | chart_type: stacked |
| 4964 | dimensions: |
| 4965 | - name: free |
| 4966 | - name: used |
| 4967 | - name: btrfs.commits |
| 4968 | description: BTRFS Commits |
| 4969 | unit: "commits" |
| 4970 | chart_type: line |
| 4971 | dimensions: |
| 4972 | - name: commits |
| 4973 | - name: btrfs.commits_perc_time |
| 4974 | description: BTRFS Commits Time Share |
| 4975 | unit: "percentage" |
| 4976 | chart_type: line |
| 4977 | dimensions: |
| 4978 | - name: commits |
| 4979 | - name: btrfs.commit_timings |
| 4980 | description: BTRFS Commit Timings |
| 4981 | unit: "ms" |
| 4982 | chart_type: line |
| 4983 | dimensions: |
| 4984 | - name: last |
| 4985 | - name: max |
| 4986 | - name: btrfs device |
| 4987 | description: "" |
| 4988 | labels: |
| 4989 | - name: device_id |
| 4990 | description: TBD |
| 4991 | - name: filesystem_uuid |
| 4992 | description: TBD |
| 4993 | - name: filesystem_label |
| 4994 | description: TBD |
| 4995 | metrics: |
| 4996 | - name: btrfs.device_errors |
| 4997 | description: BTRFS Device Errors |
| 4998 | unit: "errors" |
| 4999 | chart_type: line |
| 5000 | dimensions: |
Showing first 5,000 of 5,254 lines.
View raw