metadata.yaml 16 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429
  1. plugin_name: python.d.plugin
  2. modules:
  3. - meta:
  4. plugin_name: python.d.plugin
  5. module_name: smartd_log
  6. monitored_instance:
  7. name: S.M.A.R.T.
  8. link: "https://linux.die.net/man/8/smartd"
  9. categories:
  10. - data-collection.hardware-devices-and-sensors
  11. icon_filename: "smart.png"
  12. related_resources:
  13. integrations:
  14. list: []
  15. info_provided_to_referring_integrations:
  16. description: ""
  17. keywords:
  18. - smart
  19. - S.M.A.R.T.
  20. - SCSI devices
  21. - ATA devices
  22. most_popular: false
  23. overview:
  24. data_collection:
  25. metrics_description: |
  26. This collector monitors HDD/SSD S.M.A.R.T. metrics about drive health and performance.
  27. method_description: |
  28. It reads `smartd` log files to collect the metrics.
  29. supported_platforms:
  30. include: []
  31. exclude: []
  32. multi_instance: false
  33. additional_permissions:
  34. description: ""
  35. default_behavior:
  36. auto_detection:
  37. description: Upon satisfying the prerequisites, the collector will auto-detect metrics if written in either `/var/log/smartd/` or `/var/lib/smartmontools/`.
  38. limits:
  39. description: ""
  40. performance_impact:
  41. description: ""
  42. setup:
  43. prerequisites:
  44. list:
  45. - title: Configure `smartd` to write attribute information to files.
  46. description: |
  47. `smartd` must be running with `-A` option to write `smartd` attribute information to files.
  48. For this you need to set `smartd_opts` (or `SMARTD_ARGS`, check _smartd.service_ content) in `/etc/default/smartmontools`:
  49. ```
  50. # dump smartd attrs info every 600 seconds
  51. smartd_opts="-A /var/log/smartd/ -i 600"
  52. ```
  53. You may need to create the smartd directory before smartd will write to it:
  54. ```sh
  55. mkdir -p /var/log/smartd
  56. ```
  57. Otherwise, all the smartd `.csv` files may get written to `/var/lib/smartmontools` (default location). See also <https://linux.die.net/man/8/smartd> for more info on the `-A --attributelog=PREFIX` command.
  58. `smartd` appends logs at every run. It's strongly recommended to use `logrotate` for smartd files.
  59. configuration:
  60. file:
  61. name: "python.d/smartd_log.conf"
  62. options:
  63. description: |
  64. This particular collector does not need further configuration to work if permissions are satisfied, but you can always customize it's data collection behavior.
  65. There are 2 sections:
  66. * Global variables
  67. * One or more JOBS that can define multiple different instances to monitor.
  68. The following options can be defined globally: priority, penalty, autodetection_retry, update_every, but can also be defined per JOB to override the global values.
  69. Additionally, the following collapsed table contains all the options that can be configured inside a JOB definition.
  70. Every configuration JOB starts with a `job_name` value which will appear in the dashboard, unless a `name` parameter is specified.
  71. folding:
  72. title: "Config options"
  73. enabled: true
  74. list:
  75. - name: log_path
  76. description: path to smartd log files.
  77. default_value: /var/log/smartd
  78. required: true
  79. - name: exclude_disks
  80. description: Space-separated patterns. If the pattern is in the drive name, the module will not collect data for it.
  81. default_value: ""
  82. required: false
  83. - name: age
  84. description: Time in minutes since the last dump to file.
  85. default_value: 30
  86. required: false
  87. - name: update_every
  88. description: Sets the default data collection frequency.
  89. default_value: 1
  90. required: false
  91. - name: priority
  92. description: Controls the order of charts at the netdata dashboard.
  93. default_value: 60000
  94. required: false
  95. - name: autodetection_retry
  96. description: Sets the job re-check interval in seconds.
  97. default_value: 0
  98. required: false
  99. - name: penalty
  100. description: Indicates whether to apply penalty to update_every in case of failures.
  101. default_value: yes
  102. required: false
  103. - name: name
  104. description: >
  105. Job name. This value will overwrite the `job_name` value. JOBS with the same name are mutually exclusive. Only one of them will be allowed running at any time. This allows autodetection to try several alternatives and pick the one that works.
  106. default_value: ""
  107. required: false
  108. examples:
  109. folding:
  110. enabled: true
  111. title: "Config"
  112. list:
  113. - name: Basic
  114. description: A basic configuration example.
  115. folding:
  116. enabled: false
  117. config: |
  118. custom:
  119. name: smartd_log
  120. log_path: '/var/log/smartd/'
  121. troubleshooting:
  122. problems:
  123. list: []
  124. alerts: []
  125. metrics:
  126. folding:
  127. title: Metrics
  128. enabled: false
  129. description: "The metrics listed below are split in terms of availability on device type, SCSI or ATA."
  130. availability:
  131. - "SCSI"
  132. - "ATA"
  133. scopes:
  134. - name: global
  135. description: "These metrics refer to the entire monitored application."
  136. labels: []
  137. metrics:
  138. - name: smartd_log.read_error_rate
  139. description: Read Error Rate
  140. availability:
  141. - ATA
  142. unit: "value"
  143. chart_type: line
  144. dimensions:
  145. - name: a dimension per device
  146. - name: smartd_log.seek_error_rate
  147. description: Seek Error Rate
  148. availability:
  149. - ATA
  150. unit: "value"
  151. chart_type: line
  152. dimensions:
  153. - name: a dimension per device
  154. - name: smartd_log.soft_read_error_rate
  155. description: Soft Read Error Rate
  156. availability:
  157. - ATA
  158. unit: "errors"
  159. chart_type: line
  160. dimensions:
  161. - name: a dimension per device
  162. - name: smartd_log.write_error_rate
  163. description: Write Error Rate
  164. availability:
  165. - ATA
  166. unit: "value"
  167. chart_type: line
  168. dimensions:
  169. - name: a dimension per device
  170. - name: smartd_log.read_total_err_corrected
  171. description: Read Error Corrected
  172. availability:
  173. - SCSI
  174. unit: "errors"
  175. chart_type: line
  176. dimensions:
  177. - name: a dimension per device
  178. - name: smartd_log.read_total_unc_errors
  179. description: Read Error Uncorrected
  180. availability:
  181. - SCSI
  182. unit: "errors"
  183. chart_type: line
  184. dimensions:
  185. - name: a dimension per device
  186. - name: smartd_log.write_total_err_corrected
  187. description: Write Error Corrected
  188. availability:
  189. - SCSI
  190. unit: "errors"
  191. chart_type: line
  192. dimensions:
  193. - name: a dimension per device
  194. - name: smartd_log.write_total_unc_errors
  195. description: Write Error Uncorrected
  196. availability:
  197. - SCSI
  198. unit: "errors"
  199. chart_type: line
  200. dimensions:
  201. - name: a dimension per device
  202. - name: smartd_log.verify_total_err_corrected
  203. description: Verify Error Corrected
  204. availability:
  205. - SCSI
  206. unit: "errors"
  207. chart_type: line
  208. dimensions:
  209. - name: a dimension per device
  210. - name: smartd_log.verify_total_unc_errors
  211. description: Verify Error Uncorrected
  212. availability:
  213. - SCSI
  214. unit: "errors"
  215. chart_type: line
  216. dimensions:
  217. - name: a dimension per device
  218. - name: smartd_log.sata_interface_downshift
  219. description: SATA Interface Downshift
  220. availability:
  221. - ATA
  222. unit: "events"
  223. chart_type: line
  224. dimensions:
  225. - name: a dimension per device
  226. - name: smartd_log.udma_crc_error_count
  227. description: UDMA CRC Error Count
  228. availability:
  229. - ATA
  230. unit: "errors"
  231. chart_type: line
  232. dimensions:
  233. - name: a dimension per device
  234. - name: smartd_log.throughput_performance
  235. description: Throughput Performance
  236. availability:
  237. - ATA
  238. unit: "value"
  239. chart_type: line
  240. dimensions:
  241. - name: a dimension per device
  242. - name: smartd_log.seek_time_performance
  243. description: Seek Time Performance
  244. availability:
  245. - ATA
  246. unit: "value"
  247. chart_type: line
  248. dimensions:
  249. - name: a dimension per device
  250. - name: smartd_log.start_stop_count
  251. description: Start/Stop Count
  252. availability:
  253. - ATA
  254. unit: "events"
  255. chart_type: line
  256. dimensions:
  257. - name: a dimension per device
  258. - name: smartd_log.power_on_hours_count
  259. description: Power-On Hours Count
  260. availability:
  261. - ATA
  262. unit: "hours"
  263. chart_type: line
  264. dimensions:
  265. - name: a dimension per device
  266. - name: smartd_log.power_cycle_count
  267. description: Power Cycle Count
  268. availability:
  269. - ATA
  270. unit: "events"
  271. chart_type: line
  272. dimensions:
  273. - name: a dimension per device
  274. - name: smartd_log.unexpected_power_loss
  275. description: Unexpected Power Loss
  276. availability:
  277. - ATA
  278. unit: "events"
  279. chart_type: line
  280. dimensions:
  281. - name: a dimension per device
  282. - name: smartd_log.spin_up_time
  283. description: Spin-Up Time
  284. availability:
  285. - ATA
  286. unit: "ms"
  287. chart_type: line
  288. dimensions:
  289. - name: a dimension per device
  290. - name: smartd_log.spin_up_retries
  291. description: Spin-up Retries
  292. availability:
  293. - ATA
  294. unit: "retries"
  295. chart_type: line
  296. dimensions:
  297. - name: a dimension per device
  298. - name: smartd_log.calibration_retries
  299. description: Calibration Retries
  300. availability:
  301. - ATA
  302. unit: "retries"
  303. chart_type: line
  304. dimensions:
  305. - name: a dimension per device
  306. - name: smartd_log.airflow_temperature_celsius
  307. description: Airflow Temperature Celsius
  308. availability:
  309. - ATA
  310. unit: "celsius"
  311. chart_type: line
  312. dimensions:
  313. - name: a dimension per device
  314. - name: smartd_log.temperature_celsius
  315. description: Temperature
  316. availability:
  317. - SCSI
  318. - ATA
  319. unit: "celsius"
  320. chart_type: line
  321. dimensions:
  322. - name: a dimension per device
  323. - name: smartd_log.reallocated_sectors_count
  324. description: Reallocated Sectors Count
  325. availability:
  326. - ATA
  327. unit: "sectors"
  328. chart_type: line
  329. dimensions:
  330. - name: a dimension per device
  331. - name: smartd_log.reserved_block_count
  332. description: Reserved Block Count
  333. availability:
  334. - ATA
  335. unit: "percentage"
  336. chart_type: line
  337. dimensions:
  338. - name: a dimension per device
  339. - name: smartd_log.program_fail_count
  340. description: Program Fail Count
  341. availability:
  342. - ATA
  343. unit: "errors"
  344. chart_type: line
  345. dimensions:
  346. - name: a dimension per device
  347. - name: smartd_log.erase_fail_count
  348. description: Erase Fail Count
  349. availability:
  350. - ATA
  351. unit: "failures"
  352. chart_type: line
  353. dimensions:
  354. - name: a dimension per device
  355. - name: smartd_log.wear_leveller_worst_case_erase_count
  356. description: Wear Leveller Worst Case Erase Count
  357. availability:
  358. - ATA
  359. unit: "erases"
  360. chart_type: line
  361. dimensions:
  362. - name: a dimension per device
  363. - name: smartd_log.unused_reserved_nand_blocks
  364. description: Unused Reserved NAND Blocks
  365. availability:
  366. - ATA
  367. unit: "blocks"
  368. chart_type: line
  369. dimensions:
  370. - name: a dimension per device
  371. - name: smartd_log.reallocation_event_count
  372. description: Reallocation Event Count
  373. availability:
  374. - ATA
  375. unit: "events"
  376. chart_type: line
  377. dimensions:
  378. - name: a dimension per device
  379. - name: smartd_log.current_pending_sector_count
  380. description: Current Pending Sector Count
  381. availability:
  382. - ATA
  383. unit: "sectors"
  384. chart_type: line
  385. dimensions:
  386. - name: a dimension per device
  387. - name: smartd_log.offline_uncorrectable_sector_count
  388. description: Offline Uncorrectable Sector Count
  389. availability:
  390. - ATA
  391. unit: "sectors"
  392. chart_type: line
  393. dimensions:
  394. - name: a dimension per device
  395. - name: smartd_log.percent_lifetime_used
  396. description: Percent Lifetime Used
  397. availability:
  398. - ATA
  399. unit: "percentage"
  400. chart_type: line
  401. dimensions:
  402. - name: a dimension per device
  403. - name: smartd_log.media_wearout_indicator
  404. description: Media Wearout Indicator
  405. availability:
  406. - ATA
  407. unit: "percentage"
  408. chart_type: line
  409. dimensions:
  410. - name: a dimension per device
  411. - name: smartd_log.nand_writes_1gib
  412. description: NAND Writes
  413. availability:
  414. - ATA
  415. unit: "GiB"
  416. chart_type: line
  417. dimensions:
  418. - name: a dimension per device