vernemq.conf 12 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365
  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. info: number of socket errors in the last minute
  13. to: sysadmin
  14. # Queues dropped/expired/unhandled PUBLISH messages
  15. template: vernemq_queue_message_drop
  16. on: vernemq.queue_undelivered_messages
  17. class: Errors
  18. type: Messaging
  19. component: VerneMQ
  20. lookup: average -1m unaligned absolute of queue_message_drop
  21. units: dropped messages
  22. every: 1m
  23. warn: $this > (($status >= $WARNING) ? (0) : (5))
  24. delay: up 2m down 5m multiplier 1.5 max 2h
  25. info: number of dropped messaged due to full queues in the last minute
  26. to: sysadmin
  27. template: vernemq_queue_message_expired
  28. on: vernemq.queue_undelivered_messages
  29. class: Latency
  30. type: Messaging
  31. component: VerneMQ
  32. lookup: average -1m unaligned absolute of queue_message_expired
  33. units: expired messages
  34. every: 1m
  35. warn: $this > (($status >= $WARNING) ? (0) : (5))
  36. delay: up 2m down 5m multiplier 1.5 max 2h
  37. info: number of messages which expired before delivery in the last minute
  38. to: sysadmin
  39. template: vernemq_queue_message_unhandled
  40. on: vernemq.queue_undelivered_messages
  41. class: Latency
  42. type: Messaging
  43. component: VerneMQ
  44. lookup: average -1m unaligned absolute of queue_message_unhandled
  45. units: unhandled messages
  46. every: 1m
  47. warn: $this > (($status >= $WARNING) ? (0) : (5))
  48. delay: up 2m down 5m multiplier 1.5 max 2h
  49. info: number of unhandled messages (connections with clean session=true) in the last minute
  50. to: sysadmin
  51. # Erlang VM
  52. template: vernemq_average_scheduler_utilization
  53. on: vernemq.average_scheduler_utilization
  54. class: Utilization
  55. type: Messaging
  56. component: VerneMQ
  57. lookup: average -10m unaligned
  58. units: %
  59. every: 1m
  60. warn: $this > (($status >= $WARNING) ? (75) : (85))
  61. crit: $this > (($status == $CRITICAL) ? (85) : (95))
  62. delay: down 15m multiplier 1.5 max 1h
  63. info: average scheduler utilization over the last 10 minutes
  64. to: sysadmin
  65. # Cluster communication and netsplits
  66. template: vernemq_cluster_dropped
  67. on: vernemq.cluster_dropped
  68. class: Errors
  69. type: Messaging
  70. component: VerneMQ
  71. lookup: sum -1m unaligned
  72. units: KiB
  73. every: 1m
  74. warn: $this > 0
  75. delay: up 5m down 5m multiplier 1.5 max 1h
  76. info: amount of traffic dropped during communication with the cluster nodes in the last minute
  77. to: sysadmin
  78. template: vernemq_netsplits
  79. on: vernemq.netsplits
  80. class: Workload
  81. type: Messaging
  82. component: VerneMQ
  83. lookup: sum -1m unaligned absolute of netsplit_detected
  84. units: netsplits
  85. every: 10s
  86. warn: $this > 0
  87. delay: down 5m multiplier 1.5 max 2h
  88. info: number of detected netsplits (split brain situation) in the last minute
  89. to: sysadmin
  90. # Unsuccessful CONNACK
  91. template: vernemq_mqtt_connack_sent_reason_unsuccessful
  92. on: vernemq.mqtt_connack_sent_reason
  93. class: Errors
  94. type: Messaging
  95. component: VerneMQ
  96. lookup: average -1m unaligned absolute match-names of !success,*
  97. units: packets
  98. every: 1m
  99. warn: $this > (($status >= $WARNING) ? (0) : (5))
  100. delay: up 2m down 5m multiplier 1.5 max 2h
  101. info: number of sent unsuccessful v3/v5 CONNACK packets in the last minute
  102. to: sysadmin
  103. # Not normal DISCONNECT
  104. template: vernemq_mqtt_disconnect_received_reason_not_normal
  105. on: vernemq.mqtt_disconnect_received_reason
  106. class: Workload
  107. type: Messaging
  108. component: VerneMQ
  109. lookup: average -1m unaligned absolute match-names of !normal_disconnect,*
  110. units: packets
  111. every: 1m
  112. warn: $this > (($status >= $WARNING) ? (0) : (5))
  113. delay: up 2m down 5m multiplier 1.5 max 2h
  114. info: number of received not normal v5 DISCONNECT packets in the last minute
  115. to: sysadmin
  116. template: vernemq_mqtt_disconnect_sent_reason_not_normal
  117. on: vernemq.mqtt_disconnect_sent_reason
  118. class: Errors
  119. type: Messaging
  120. component: VerneMQ
  121. lookup: average -1m unaligned absolute match-names of !normal_disconnect,*
  122. units: packets
  123. every: 1m
  124. warn: $this > (($status >= $WARNING) ? (0) : (5))
  125. delay: up 2m down 5m multiplier 1.5 max 2h
  126. info: number of sent not normal v5 DISCONNECT packets in the last minute
  127. to: sysadmin
  128. # SUBSCRIBE errors and unauthorized attempts
  129. template: vernemq_mqtt_subscribe_error
  130. on: vernemq.mqtt_subscribe_error
  131. class: Errors
  132. type: Messaging
  133. component: VerneMQ
  134. lookup: average -1m unaligned absolute
  135. units: failed ops
  136. every: 1m
  137. warn: $this > (($status >= $WARNING) ? (0) : (5))
  138. delay: up 2m down 5m multiplier 1.5 max 2h
  139. info: number of failed v3/v5 SUBSCRIBE operations in the last minute
  140. to: sysadmin
  141. template: vernemq_mqtt_subscribe_auth_error
  142. on: vernemq.mqtt_subscribe_auth_error
  143. class: Workload
  144. type: Messaging
  145. component: VerneMQ
  146. lookup: average -1m unaligned absolute
  147. units: attempts
  148. every: 1m
  149. warn: $this > (($status >= $WARNING) ? (0) : (5))
  150. delay: up 2m down 5m multiplier 1.5 max 2h
  151. info: number of unauthorized v3/v5 SUBSCRIBE attempts in the last minute
  152. to: sysadmin
  153. # UNSUBSCRIBE errors
  154. template: vernemq_mqtt_unsubscribe_error
  155. on: vernemq.mqtt_unsubscribe_error
  156. class: Errors
  157. type: Messaging
  158. component: VerneMQ
  159. lookup: average -1m unaligned absolute
  160. units: failed ops
  161. every: 1m
  162. warn: $this > (($status >= $WARNING) ? (0) : (5))
  163. delay: up 2m down 5m multiplier 1.5 max 2h
  164. info: number of failed v3/v5 UNSUBSCRIBE operations in the last minute
  165. to: sysadmin
  166. # PUBLISH errors and unauthorized attempts
  167. template: vernemq_mqtt_publish_errors
  168. on: vernemq.mqtt_publish_errors
  169. class: Errors
  170. type: Messaging
  171. component: VerneMQ
  172. lookup: average -1m unaligned absolute
  173. units: failed ops
  174. every: 1m
  175. warn: $this > (($status >= $WARNING) ? (0) : (5))
  176. delay: up 2m down 5m multiplier 1.5 max 2h
  177. info: number of failed v3/v5 PUBLISH operations in the last minute
  178. to: sysadmin
  179. template: vernemq_mqtt_publish_auth_errors
  180. on: vernemq.mqtt_publish_auth_errors
  181. class: Workload
  182. type: Messaging
  183. component: VerneMQ
  184. lookup: average -1m unaligned absolute
  185. units: attempts
  186. every: 1m
  187. warn: $this > (($status >= $WARNING) ? (0) : (5))
  188. delay: up 2m down 5m multiplier 1.5 max 2h
  189. info: number of unauthorized v3/v5 PUBLISH attempts in the last minute
  190. to: sysadmin
  191. # Unsuccessful and unexpected PUBACK
  192. template: vernemq_mqtt_puback_received_reason_unsuccessful
  193. on: vernemq.mqtt_puback_received_reason
  194. class: Errors
  195. type: Messaging
  196. component: VerneMQ
  197. lookup: average -1m unaligned absolute match-names of !success,*
  198. units: packets
  199. every: 1m
  200. warn: $this > (($status >= $WARNING) ? (0) : (5))
  201. delay: up 2m down 5m multiplier 1.5 max 2h
  202. info: number of received unsuccessful v5 PUBACK packets in the last minute
  203. to: sysadmin
  204. template: vernemq_mqtt_puback_sent_reason_unsuccessful
  205. on: vernemq.mqtt_puback_sent_reason
  206. class: Errors
  207. type: Messaging
  208. component: VerneMQ
  209. lookup: average -1m unaligned absolute match-names of !success,*
  210. units: packets
  211. every: 1m
  212. warn: $this > (($status >= $WARNING) ? (0) : (5))
  213. delay: up 2m down 5m multiplier 1.5 max 2h
  214. info: number of sent unsuccessful v5 PUBACK packets in the last minute
  215. to: sysadmin
  216. template: vernemq_mqtt_puback_unexpected
  217. on: vernemq.mqtt_puback_invalid_error
  218. class: Workload
  219. type: Messaging
  220. component: VerneMQ
  221. lookup: average -1m unaligned absolute
  222. units: messages
  223. every: 1m
  224. warn: $this > (($status >= $WARNING) ? (0) : (5))
  225. delay: up 2m down 5m multiplier 1.5 max 2h
  226. info: number of received unexpected v3/v5 PUBACK packets in the last minute
  227. to: sysadmin
  228. # Unsuccessful and unexpected PUBREC
  229. template: vernemq_mqtt_pubrec_received_reason_unsuccessful
  230. on: vernemq.mqtt_pubrec_received_reason
  231. class: Errors
  232. type: Messaging
  233. component: VerneMQ
  234. lookup: average -1m unaligned absolute match-names of !success,*
  235. units: packets
  236. every: 1m
  237. warn: $this > (($status >= $WARNING) ? (0) : (5))
  238. delay: up 2m down 5m multiplier 1.5 max 2h
  239. info: number of received unsuccessful v5 PUBREC packets in the last minute
  240. to: sysadmin
  241. template: vernemq_mqtt_pubrec_sent_reason_unsuccessful
  242. on: vernemq.mqtt_pubrec_sent_reason
  243. class: Errors
  244. type: Messaging
  245. component: VerneMQ
  246. lookup: average -1m unaligned absolute match-names of !success,*
  247. units: packets
  248. every: 1m
  249. warn: $this > (($status >= $WARNING) ? (0) : (5))
  250. delay: up 2m down 5m multiplier 1.5 max 2h
  251. info: number of sent unsuccessful v5 PUBREC packets in the last minute
  252. to: sysadmin
  253. template: vernemq_mqtt_pubrec_invalid_error
  254. on: vernemq.mqtt_pubrec_invalid_error
  255. class: Workload
  256. type: Messaging
  257. component: VerneMQ
  258. lookup: average -1m unaligned absolute
  259. units: messages
  260. every: 1m
  261. warn: $this > (($status >= $WARNING) ? (0) : (5))
  262. delay: up 2m down 5m multiplier 1.5 max 2h
  263. info: number of received unexpected v3 PUBREC packets in the last minute
  264. to: sysadmin
  265. # Unsuccessful PUBREL
  266. template: vernemq_mqtt_pubrel_received_reason_unsuccessful
  267. on: vernemq.mqtt_pubrel_received_reason
  268. class: Errors
  269. type: Messaging
  270. component: VerneMQ
  271. lookup: average -1m unaligned absolute match-names of !success,*
  272. units: packets
  273. every: 1m
  274. warn: $this > (($status >= $WARNING) ? (0) : (5))
  275. delay: up 2m down 5m multiplier 1.5 max 2h
  276. info: number of received unsuccessful v5 PUBREL packets in the last minute
  277. to: sysadmin
  278. template: vernemq_mqtt_pubrel_sent_reason_unsuccessful
  279. on: vernemq.mqtt_pubrel_sent_reason
  280. class: Errors
  281. type: Messaging
  282. component: VerneMQ
  283. lookup: average -1m unaligned absolute match-names of !success,*
  284. units: packets
  285. every: 1m
  286. warn: $this > (($status >= $WARNING) ? (0) : (5))
  287. delay: up 2m down 5m multiplier 1.5 max 2h
  288. info: number of sent unsuccessful v5 PUBREL packets in the last minute
  289. to: sysadmin
  290. # Unsuccessful and unexpected PUBCOMP
  291. template: vernemq_mqtt_pubcomp_received_reason_unsuccessful
  292. on: vernemq.mqtt_pubcomp_received_reason
  293. class: Errors
  294. type: Messaging
  295. component: VerneMQ
  296. lookup: average -1m unaligned absolute match-names of !success,*
  297. units: packets
  298. every: 1m
  299. warn: $this > (($status >= $WARNING) ? (0) : (5))
  300. delay: up 2m down 5m multiplier 1.5 max 2h
  301. info: number of received unsuccessful v5 PUBCOMP packets in the last minute
  302. to: sysadmin
  303. template: vernemq_mqtt_pubcomp_sent_reason_unsuccessful
  304. on: vernemq.mqtt_pubcomp_sent_reason
  305. class: Errors
  306. type: Messaging
  307. component: VerneMQ
  308. lookup: average -1m unaligned absolute match-names of !success,*
  309. units: packets
  310. every: 1m
  311. warn: $this > (($status >= $WARNING) ? (0) : (5))
  312. delay: up 2m down 5m multiplier 1.5 max 2h
  313. info: number of sent unsuccessful v5 PUBCOMP packets in the last minute
  314. to: sysadmin
  315. template: vernemq_mqtt_pubcomp_unexpected
  316. on: vernemq.mqtt_pubcomp_invalid_error
  317. class: Workload
  318. type: Messaging
  319. component: VerneMQ
  320. lookup: average -1m unaligned absolute
  321. units: messages
  322. every: 1m
  323. warn: $this > (($status >= $WARNING) ? (0) : (5))
  324. delay: up 2m down 5m multiplier 1.5 max 2h
  325. info: number of received unexpected v3/v5 PUBCOMP packets in the last minute
  326. to: sysadmin