vernemq.conf 13 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391
  1. # Socket errors
  2. template: vernemq_socket_errors
  3. on: vernemq.socket_errors
  4. class: Errors
  5. type: Messaging
  6. component: VerneMQ
  7. lookup: sum -1m unaligned absolute of socket_error
  8. units: errors
  9. every: 1m
  10. warn: $this > (($status >= $WARNING) ? (0) : (5))
  11. delay: up 2m down 5m multiplier 1.5 max 2h
  12. summary: VerneMQ socket errors
  13. info: Number of socket errors in the last minute
  14. to: sysadmin
  15. # Queues dropped/expired/unhandled PUBLISH messages
  16. template: vernemq_queue_message_drop
  17. on: vernemq.queue_undelivered_messages
  18. class: Errors
  19. type: Messaging
  20. component: VerneMQ
  21. lookup: average -1m unaligned absolute of queue_message_drop
  22. units: dropped messages
  23. every: 1m
  24. warn: $this > (($status >= $WARNING) ? (0) : (5))
  25. delay: up 2m down 5m multiplier 1.5 max 2h
  26. summary: VerneMQ dropped messages
  27. info: Number of dropped messages due to full queues in the last minute
  28. to: sysadmin
  29. template: vernemq_queue_message_expired
  30. on: vernemq.queue_undelivered_messages
  31. class: Latency
  32. type: Messaging
  33. component: VerneMQ
  34. lookup: average -1m unaligned absolute of queue_message_expired
  35. units: expired messages
  36. every: 1m
  37. warn: $this > (($status >= $WARNING) ? (0) : (5))
  38. delay: up 2m down 5m multiplier 1.5 max 2h
  39. summary: VerneMQ expired messages
  40. info: number of messages which expired before delivery in the last minute
  41. to: sysadmin
  42. template: vernemq_queue_message_unhandled
  43. on: vernemq.queue_undelivered_messages
  44. class: Latency
  45. type: Messaging
  46. component: VerneMQ
  47. lookup: average -1m unaligned absolute of queue_message_unhandled
  48. units: unhandled messages
  49. every: 1m
  50. warn: $this > (($status >= $WARNING) ? (0) : (5))
  51. delay: up 2m down 5m multiplier 1.5 max 2h
  52. summary: VerneMQ unhandled messages
  53. info: Number of unhandled messages (connections with clean session=true) in the last minute
  54. to: sysadmin
  55. # Erlang VM
  56. template: vernemq_average_scheduler_utilization
  57. on: vernemq.average_scheduler_utilization
  58. class: Utilization
  59. type: Messaging
  60. component: VerneMQ
  61. lookup: average -10m unaligned
  62. units: %
  63. every: 1m
  64. warn: $this > (($status >= $WARNING) ? (75) : (85))
  65. crit: $this > (($status == $CRITICAL) ? (85) : (95))
  66. delay: down 15m multiplier 1.5 max 1h
  67. summary: VerneMQ scheduler utilization
  68. info: Average scheduler utilization over the last 10 minutes
  69. to: sysadmin
  70. # Cluster communication and netsplits
  71. template: vernemq_cluster_dropped
  72. on: vernemq.cluster_dropped
  73. class: Errors
  74. type: Messaging
  75. component: VerneMQ
  76. lookup: sum -1m unaligned
  77. units: KiB
  78. every: 1m
  79. warn: $this > 0
  80. delay: up 5m down 5m multiplier 1.5 max 1h
  81. summary: VerneMQ dropped traffic
  82. info: Amount of traffic dropped during communication with the cluster nodes in the last minute
  83. to: sysadmin
  84. template: vernemq_netsplits
  85. on: vernemq.netsplits
  86. class: Workload
  87. type: Messaging
  88. component: VerneMQ
  89. lookup: sum -1m unaligned absolute of netsplit_detected
  90. units: netsplits
  91. every: 10s
  92. warn: $this > 0
  93. delay: down 5m multiplier 1.5 max 2h
  94. summary: VerneMQ netsplits
  95. info: Number of detected netsplits (split brain situation) in the last minute
  96. to: sysadmin
  97. # Unsuccessful CONNACK
  98. template: vernemq_mqtt_connack_sent_reason_unsuccessful
  99. on: vernemq.mqtt_connack_sent_reason
  100. class: Errors
  101. type: Messaging
  102. component: VerneMQ
  103. lookup: average -1m unaligned absolute match-names of !success,*
  104. units: packets
  105. every: 1m
  106. warn: $this > (($status >= $WARNING) ? (0) : (5))
  107. delay: up 2m down 5m multiplier 1.5 max 2h
  108. summary: VerneMQ unsuccessful CONNACK
  109. info: Number of sent unsuccessful v3/v5 CONNACK packets in the last minute
  110. to: sysadmin
  111. # Not normal DISCONNECT
  112. template: vernemq_mqtt_disconnect_received_reason_not_normal
  113. on: vernemq.mqtt_disconnect_received_reason
  114. class: Workload
  115. type: Messaging
  116. component: VerneMQ
  117. lookup: average -1m unaligned absolute match-names of !normal_disconnect,*
  118. units: packets
  119. every: 1m
  120. warn: $this > (($status >= $WARNING) ? (0) : (5))
  121. delay: up 2m down 5m multiplier 1.5 max 2h
  122. summary: VerneMQ received not normal DISCONNECT
  123. info: Number of received not normal v5 DISCONNECT packets in the last minute
  124. to: sysadmin
  125. template: vernemq_mqtt_disconnect_sent_reason_not_normal
  126. on: vernemq.mqtt_disconnect_sent_reason
  127. class: Errors
  128. type: Messaging
  129. component: VerneMQ
  130. lookup: average -1m unaligned absolute match-names of !normal_disconnect,*
  131. units: packets
  132. every: 1m
  133. warn: $this > (($status >= $WARNING) ? (0) : (5))
  134. delay: up 2m down 5m multiplier 1.5 max 2h
  135. summary: VerneMQ sent not normal DISCONNECT
  136. info: Number of sent not normal v5 DISCONNECT packets in the last minute
  137. to: sysadmin
  138. # SUBSCRIBE errors and unauthorized attempts
  139. template: vernemq_mqtt_subscribe_error
  140. on: vernemq.mqtt_subscribe_error
  141. class: Errors
  142. type: Messaging
  143. component: VerneMQ
  144. lookup: average -1m unaligned absolute
  145. units: failed ops
  146. every: 1m
  147. warn: $this > (($status >= $WARNING) ? (0) : (5))
  148. delay: up 2m down 5m multiplier 1.5 max 2h
  149. summary: VerneMQ failed SUBSCRIBE
  150. info: Number of failed v3/v5 SUBSCRIBE operations in the last minute
  151. to: sysadmin
  152. template: vernemq_mqtt_subscribe_auth_error
  153. on: vernemq.mqtt_subscribe_auth_error
  154. class: Workload
  155. type: Messaging
  156. component: VerneMQ
  157. lookup: average -1m unaligned absolute
  158. units: attempts
  159. every: 1m
  160. warn: $this > (($status >= $WARNING) ? (0) : (5))
  161. delay: up 2m down 5m multiplier 1.5 max 2h
  162. summary: VerneMQ unauthorized SUBSCRIBE
  163. info: number of unauthorized v3/v5 SUBSCRIBE attempts in the last minute
  164. to: sysadmin
  165. # UNSUBSCRIBE errors
  166. template: vernemq_mqtt_unsubscribe_error
  167. on: vernemq.mqtt_unsubscribe_error
  168. class: Errors
  169. type: Messaging
  170. component: VerneMQ
  171. lookup: average -1m unaligned absolute
  172. units: failed ops
  173. every: 1m
  174. warn: $this > (($status >= $WARNING) ? (0) : (5))
  175. delay: up 2m down 5m multiplier 1.5 max 2h
  176. summary: VerneMQ failed UNSUBSCRIBE
  177. info: Number of failed v3/v5 UNSUBSCRIBE operations in the last minute
  178. to: sysadmin
  179. # PUBLISH errors and unauthorized attempts
  180. template: vernemq_mqtt_publish_errors
  181. on: vernemq.mqtt_publish_errors
  182. class: Errors
  183. type: Messaging
  184. component: VerneMQ
  185. lookup: average -1m unaligned absolute
  186. units: failed ops
  187. every: 1m
  188. warn: $this > (($status >= $WARNING) ? (0) : (5))
  189. delay: up 2m down 5m multiplier 1.5 max 2h
  190. summary: VerneMQ failed PUBLISH
  191. info: Number of failed v3/v5 PUBLISH operations in the last minute
  192. to: sysadmin
  193. template: vernemq_mqtt_publish_auth_errors
  194. on: vernemq.mqtt_publish_auth_errors
  195. class: Workload
  196. type: Messaging
  197. component: VerneMQ
  198. lookup: average -1m unaligned absolute
  199. units: attempts
  200. every: 1m
  201. warn: $this > (($status >= $WARNING) ? (0) : (5))
  202. delay: up 2m down 5m multiplier 1.5 max 2h
  203. summary: VerneMQ unauthorized PUBLISH
  204. info: Number of unauthorized v3/v5 PUBLISH attempts in the last minute
  205. to: sysadmin
  206. # Unsuccessful and unexpected PUBACK
  207. template: vernemq_mqtt_puback_received_reason_unsuccessful
  208. on: vernemq.mqtt_puback_received_reason
  209. class: Errors
  210. type: Messaging
  211. component: VerneMQ
  212. lookup: average -1m unaligned absolute match-names of !success,*
  213. units: packets
  214. every: 1m
  215. warn: $this > (($status >= $WARNING) ? (0) : (5))
  216. delay: up 2m down 5m multiplier 1.5 max 2h
  217. summary: VerneMQ unsuccessful received PUBACK
  218. info: Number of received unsuccessful v5 PUBACK packets in the last minute
  219. to: sysadmin
  220. template: vernemq_mqtt_puback_sent_reason_unsuccessful
  221. on: vernemq.mqtt_puback_sent_reason
  222. class: Errors
  223. type: Messaging
  224. component: VerneMQ
  225. lookup: average -1m unaligned absolute match-names of !success,*
  226. units: packets
  227. every: 1m
  228. warn: $this > (($status >= $WARNING) ? (0) : (5))
  229. delay: up 2m down 5m multiplier 1.5 max 2h
  230. summary: VerneMQ unsuccessful sent PUBACK
  231. info: Number of sent unsuccessful v5 PUBACK packets in the last minute
  232. to: sysadmin
  233. template: vernemq_mqtt_puback_unexpected
  234. on: vernemq.mqtt_puback_invalid_error
  235. class: Workload
  236. type: Messaging
  237. component: VerneMQ
  238. lookup: average -1m unaligned absolute
  239. units: messages
  240. every: 1m
  241. warn: $this > (($status >= $WARNING) ? (0) : (5))
  242. delay: up 2m down 5m multiplier 1.5 max 2h
  243. summary: VerneMQ unnexpected recieved PUBACK
  244. info: Number of received unexpected v3/v5 PUBACK packets in the last minute
  245. to: sysadmin
  246. # Unsuccessful and unexpected PUBREC
  247. template: vernemq_mqtt_pubrec_received_reason_unsuccessful
  248. on: vernemq.mqtt_pubrec_received_reason
  249. class: Errors
  250. type: Messaging
  251. component: VerneMQ
  252. lookup: average -1m unaligned absolute match-names of !success,*
  253. units: packets
  254. every: 1m
  255. warn: $this > (($status >= $WARNING) ? (0) : (5))
  256. delay: up 2m down 5m multiplier 1.5 max 2h
  257. summary: VerneMQ unsuccessful received PUBREC
  258. info: Number of received unsuccessful v5 PUBREC packets in the last minute
  259. to: sysadmin
  260. template: vernemq_mqtt_pubrec_sent_reason_unsuccessful
  261. on: vernemq.mqtt_pubrec_sent_reason
  262. class: Errors
  263. type: Messaging
  264. component: VerneMQ
  265. lookup: average -1m unaligned absolute match-names of !success,*
  266. units: packets
  267. every: 1m
  268. warn: $this > (($status >= $WARNING) ? (0) : (5))
  269. delay: up 2m down 5m multiplier 1.5 max 2h
  270. summary: VerneMQ unsuccessful sent PUBREC
  271. info: Number of sent unsuccessful v5 PUBREC packets in the last minute
  272. to: sysadmin
  273. template: vernemq_mqtt_pubrec_invalid_error
  274. on: vernemq.mqtt_pubrec_invalid_error
  275. class: Workload
  276. type: Messaging
  277. component: VerneMQ
  278. lookup: average -1m unaligned absolute
  279. units: messages
  280. every: 1m
  281. warn: $this > (($status >= $WARNING) ? (0) : (5))
  282. delay: up 2m down 5m multiplier 1.5 max 2h
  283. summary: VerneMQ invalid received PUBREC
  284. info: Number of received invalid v3 PUBREC packets in the last minute
  285. to: sysadmin
  286. # Unsuccessful PUBREL
  287. template: vernemq_mqtt_pubrel_received_reason_unsuccessful
  288. on: vernemq.mqtt_pubrel_received_reason
  289. class: Errors
  290. type: Messaging
  291. component: VerneMQ
  292. lookup: average -1m unaligned absolute match-names of !success,*
  293. units: packets
  294. every: 1m
  295. warn: $this > (($status >= $WARNING) ? (0) : (5))
  296. delay: up 2m down 5m multiplier 1.5 max 2h
  297. summary: VerneMQ unsuccessful received PUBREL
  298. info: Number of received unsuccessful v5 PUBREL packets in the last minute
  299. to: sysadmin
  300. template: vernemq_mqtt_pubrel_sent_reason_unsuccessful
  301. on: vernemq.mqtt_pubrel_sent_reason
  302. class: Errors
  303. type: Messaging
  304. component: VerneMQ
  305. lookup: average -1m unaligned absolute match-names of !success,*
  306. units: packets
  307. every: 1m
  308. warn: $this > (($status >= $WARNING) ? (0) : (5))
  309. delay: up 2m down 5m multiplier 1.5 max 2h
  310. summary: VerneMQ unsuccessful sent PUBREL
  311. info: number of sent unsuccessful v5 PUBREL packets in the last minute
  312. to: sysadmin
  313. # Unsuccessful and unexpected PUBCOMP
  314. template: vernemq_mqtt_pubcomp_received_reason_unsuccessful
  315. on: vernemq.mqtt_pubcomp_received_reason
  316. class: Errors
  317. type: Messaging
  318. component: VerneMQ
  319. lookup: average -1m unaligned absolute match-names of !success,*
  320. units: packets
  321. every: 1m
  322. warn: $this > (($status >= $WARNING) ? (0) : (5))
  323. delay: up 2m down 5m multiplier 1.5 max 2h
  324. summary: VerneMQ unsuccessful received PUBCOMP
  325. info: Number of received unsuccessful v5 PUBCOMP packets in the last minute
  326. to: sysadmin
  327. template: vernemq_mqtt_pubcomp_sent_reason_unsuccessful
  328. on: vernemq.mqtt_pubcomp_sent_reason
  329. class: Errors
  330. type: Messaging
  331. component: VerneMQ
  332. lookup: average -1m unaligned absolute match-names of !success,*
  333. units: packets
  334. every: 1m
  335. warn: $this > (($status >= $WARNING) ? (0) : (5))
  336. delay: up 2m down 5m multiplier 1.5 max 2h
  337. summary: VerneMQ unsuccessful sent PUBCOMP
  338. info: number of sent unsuccessful v5 PUBCOMP packets in the last minute
  339. to: sysadmin
  340. template: vernemq_mqtt_pubcomp_unexpected
  341. on: vernemq.mqtt_pubcomp_invalid_error
  342. class: Workload
  343. type: Messaging
  344. component: VerneMQ
  345. lookup: average -1m unaligned absolute
  346. units: messages
  347. every: 1m
  348. warn: $this > (($status >= $WARNING) ? (0) : (5))
  349. delay: up 2m down 5m multiplier 1.5 max 2h
  350. summary: VerneMQ unexpected received PUBCOMP
  351. info: number of received unexpected v3/v5 PUBCOMP packets in the last minute
  352. to: sysadmin