alertGroups.json 12 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395
  1. {
  2. "href": "http://host:8080/api/v1/clusters/tdk/alert_groups?fields=*",
  3. "items": [
  4. {
  5. "href": "http://host:8080/api/v1/clusters/tdk/alert_groups/1",
  6. "AlertGroup": {
  7. "targets": [],
  8. "cluster_name": "tdk",
  9. "default": true,
  10. "definitions": [ ],
  11. "id": 1,
  12. "name": "SLIDER"
  13. }
  14. },
  15. {
  16. "href": "http://host:8080/api/v1/clusters/tdk/alert_groups/2",
  17. "AlertGroup": {"targets": [],
  18. "cluster_name": "tdk",
  19. "default": true,
  20. "definitions": [
  21. {
  22. "name": "yarn_resourcemanager_rpc_latency",
  23. "label": "ResourceManager RPC Latency",
  24. "enabled": true,
  25. "service_name": "YARN",
  26. "component_name": "RESOURCEMANAGER",
  27. "id": 1,
  28. "source_type": "METRIC"
  29. },
  30. {
  31. "name": "yarn_resourcemanager_webui",
  32. "label": "ResourceManager Web UI",
  33. "enabled": true,
  34. "service_name": "YARN",
  35. "component_name": "RESOURCEMANAGER",
  36. "id": 2,
  37. "source_type": "WEB"
  38. },
  39. {
  40. "name": "yarn_app_timeline_server_webui",
  41. "label": "App Timeline Web UI",
  42. "enabled": true,
  43. "service_name": "YARN",
  44. "component_name": "APP_TIMELINE_SERVER",
  45. "id": 3,
  46. "source_type": "WEB"
  47. },
  48. {
  49. "name": "yarn_nodemanager_webui_percent",
  50. "label": "Percent NodeManagers Available",
  51. "enabled": true,
  52. "service_name": "YARN",
  53. "component_name": null,
  54. "id": 4,
  55. "source_type": "AGGREGATE"
  56. },
  57. {
  58. "name": "yarn_resourcemanager_cpu",
  59. "label": "ResourceManager CPU Utilization",
  60. "enabled": true,
  61. "service_name": "YARN",
  62. "component_name": "RESOURCEMANAGER",
  63. "id": 5,
  64. "source_type": "METRIC"
  65. },
  66. {
  67. "name": "yarn_nodemanager_health",
  68. "label": "NodeManager Health",
  69. "enabled": true,
  70. "service_name": "YARN",
  71. "component_name": "NODEMANAGER",
  72. "id": 6,
  73. "source_type": "SCRIPT"
  74. },
  75. {
  76. "name": "yarn_nodemanager_webui",
  77. "label": "NodeManager Web UI",
  78. "enabled": true,
  79. "service_name": "YARN",
  80. "component_name": "NODEMANAGER",
  81. "id": 7,
  82. "source_type": "WEB"
  83. }
  84. ],
  85. "id": 2,
  86. "name": "YARN"
  87. }
  88. },
  89. {
  90. "href": "http://host:8080/api/v1/clusters/tdk/alert_groups/3",
  91. "AlertGroup": {"targets": [],
  92. "cluster_name": "tdk",
  93. "default": true,
  94. "definitions": [
  95. {
  96. "name": "zookeeper_server_process",
  97. "label": "ZooKeeper Server Process",
  98. "enabled": true,
  99. "service_name": "ZOOKEEPER",
  100. "component_name": "ZOOKEEPER_SERVER",
  101. "id": 8,
  102. "source_type": "PORT"
  103. },
  104. {
  105. "name": "zookeeper_server_process_percent",
  106. "label": "Percent ZooKeeper Servers Available",
  107. "enabled": true,
  108. "service_name": "ZOOKEEPER",
  109. "component_name": null,
  110. "id": 9,
  111. "source_type": "AGGREGATE"
  112. }
  113. ],
  114. "id": 3,
  115. "name": "ZOOKEEPER"
  116. }
  117. },
  118. {
  119. "href": "http://host:8080/api/v1/clusters/tdk/alert_groups/4",
  120. "AlertGroup": {"targets": [],
  121. "cluster_name": "tdk",
  122. "default": true,
  123. "definitions": [
  124. {
  125. "name": "mapreduce_history_server_rpc_latency",
  126. "label": "History Server RPC Latency",
  127. "enabled": true,
  128. "service_name": "MAPREDUCE2",
  129. "component_name": "HISTORYSERVER",
  130. "id": 12,
  131. "source_type": "METRIC"
  132. },
  133. {
  134. "name": "mapreduce_history_server_cpu",
  135. "label": "History Server CPU Utilization",
  136. "enabled": true,
  137. "service_name": "MAPREDUCE2",
  138. "component_name": "HISTORYSERVER",
  139. "id": 13,
  140. "source_type": "METRIC"
  141. },
  142. {
  143. "name": "mapreduce_history_server_webui",
  144. "label": "History Server Web UI",
  145. "enabled": true,
  146. "service_name": "MAPREDUCE2",
  147. "component_name": "HISTORYSERVER",
  148. "id": 10,
  149. "source_type": "WEB"
  150. },
  151. {
  152. "name": "mapreduce_history_server_process",
  153. "label": "History Server Process",
  154. "enabled": true,
  155. "service_name": "MAPREDUCE2",
  156. "component_name": "HISTORYSERVER",
  157. "id": 11,
  158. "source_type": "PORT"
  159. }
  160. ],
  161. "id": 4,
  162. "name": "MAPREDUCE2"
  163. }
  164. },
  165. {
  166. "href": "http://host:8080/api/v1/clusters/tdk/alert_groups/5",
  167. "AlertGroup": {"targets": [],
  168. "cluster_name": "tdk",
  169. "default": true,
  170. "definitions": [
  171. {
  172. "name": "ganglia_monitor_hbase_master",
  173. "label": "Ganglia HBase Master Process Monitor",
  174. "enabled": true,
  175. "service_name": "GANGLIA",
  176. "component_name": "GANGLIA_SERVER",
  177. "id": 17,
  178. "source_type": "PORT"
  179. },
  180. {
  181. "name": "ganglia_monitor_hdfs_namenode",
  182. "label": "Ganglia NameNode Process Monitor",
  183. "enabled": true,
  184. "service_name": "GANGLIA",
  185. "component_name": "GANGLIA_SERVER",
  186. "id": 16,
  187. "source_type": "PORT"
  188. },
  189. {
  190. "name": "ganglia_server_process",
  191. "label": "Ganglia Server Process",
  192. "enabled": true,
  193. "service_name": "GANGLIA",
  194. "component_name": "GANGLIA_SERVER",
  195. "id": 18,
  196. "source_type": "PORT"
  197. },
  198. {
  199. "name": "ganglia_monitor_mapreduce_history_server",
  200. "label": "Ganglia History Server Process Monitor",
  201. "enabled": true,
  202. "service_name": "GANGLIA",
  203. "component_name": "GANGLIA_SERVER",
  204. "id": 14,
  205. "source_type": "PORT"
  206. },
  207. {
  208. "name": "ganglia_monitor_yarn_resourcemanager",
  209. "label": "Ganglia ResourceManager Process Monitor",
  210. "enabled": true,
  211. "service_name": "GANGLIA",
  212. "component_name": "GANGLIA_SERVER",
  213. "id": 15,
  214. "source_type": "PORT"
  215. }
  216. ],
  217. "id": 5,
  218. "name": "GANGLIA"
  219. }
  220. },
  221. {
  222. "href": "http://host:8080/api/v1/clusters/tdk/alert_groups/6",
  223. "AlertGroup": {"targets": [],
  224. "cluster_name": "tdk",
  225. "default": true,
  226. "definitions": [
  227. {
  228. "name": "datanode_storage",
  229. "label": "DataNode Storage",
  230. "enabled": true,
  231. "service_name": "HDFS",
  232. "component_name": "DATANODE",
  233. "id": 34,
  234. "source_type": "METRIC"
  235. },
  236. {
  237. "name": "datanode_storage_percent",
  238. "label": "Percent DataNodes With Available Space",
  239. "enabled": true,
  240. "service_name": "HDFS",
  241. "component_name": null,
  242. "id": 35,
  243. "source_type": "AGGREGATE"
  244. },
  245. {
  246. "name": "hdfs_zookeeper_failover_controller_process",
  247. "label": "ZooKeeper Failover Controller Process",
  248. "enabled": true,
  249. "service_name": "HDFS",
  250. "component_name": "ZKFC",
  251. "id": 32,
  252. "source_type": "PORT"
  253. },
  254. {
  255. "name": "namenode_directory_status",
  256. "label": "NameNode Directory Status",
  257. "enabled": true,
  258. "service_name": "HDFS",
  259. "component_name": "NAMENODE",
  260. "id": 33,
  261. "source_type": "METRIC"
  262. },
  263. {
  264. "name": "journalnode_process_percent",
  265. "label": "Percent JournalNodes Available",
  266. "enabled": true,
  267. "service_name": "HDFS",
  268. "component_name": null,
  269. "id": 36,
  270. "source_type": "AGGREGATE"
  271. },
  272. {
  273. "name": "secondary_namenode_process",
  274. "label": "Secondary NameNode Process",
  275. "enabled": true,
  276. "service_name": "HDFS",
  277. "component_name": "SECONDARY_NAMENODE",
  278. "id": 19,
  279. "source_type": "PORT"
  280. },
  281. {
  282. "name": "datanode_webui",
  283. "label": "DataNode Web UI",
  284. "enabled": true,
  285. "service_name": "HDFS",
  286. "component_name": "DATANODE",
  287. "id": 21,
  288. "source_type": "WEB"
  289. },
  290. {
  291. "name": "namenode_ha_health",
  292. "label": "NameNode High Availability Health",
  293. "enabled": true,
  294. "service_name": "HDFS",
  295. "component_name": "NAMENODE",
  296. "id": 20,
  297. "source_type": "SCRIPT"
  298. },
  299. {
  300. "name": "namenode_rpc_latency",
  301. "label": "NameNode RPC Latency",
  302. "enabled": true,
  303. "service_name": "HDFS",
  304. "component_name": "NAMENODE",
  305. "id": 23,
  306. "source_type": "METRIC"
  307. },
  308. {
  309. "name": "namenode_cpu",
  310. "label": "NameNode Host CPU Utilization",
  311. "enabled": true,
  312. "service_name": "HDFS",
  313. "component_name": "NAMENODE",
  314. "id": 22,
  315. "source_type": "METRIC"
  316. },
  317. {
  318. "name": "namenode_webui",
  319. "label": "NameNode Web UI",
  320. "enabled": true,
  321. "service_name": "HDFS",
  322. "component_name": "NAMENODE",
  323. "id": 25,
  324. "source_type": "WEB"
  325. },
  326. {
  327. "name": "namenode_hdfs_blocks_health",
  328. "label": "NameNode Blocks Health",
  329. "enabled": true,
  330. "service_name": "HDFS",
  331. "component_name": "NAMENODE",
  332. "id": 24,
  333. "source_type": "METRIC"
  334. },
  335. {
  336. "name": "datanode_process_percent",
  337. "label": "Percent DataNodes Available",
  338. "enabled": true,
  339. "service_name": "HDFS",
  340. "component_name": null,
  341. "id": 27,
  342. "source_type": "AGGREGATE"
  343. },
  344. {
  345. "name": "datanode_process",
  346. "label": "DateNode Process",
  347. "enabled": true,
  348. "service_name": "HDFS",
  349. "component_name": "DATANODE",
  350. "id": 26,
  351. "source_type": "PORT"
  352. },
  353. {
  354. "name": "namenode_hdfs_capacity_utilization",
  355. "label": "HDFS Capacity Utilization",
  356. "enabled": true,
  357. "service_name": "HDFS",
  358. "component_name": "NAMENODE",
  359. "id": 29,
  360. "source_type": "METRIC"
  361. },
  362. {
  363. "name": "namenode_process",
  364. "label": "NameNode Process",
  365. "enabled": true,
  366. "service_name": "HDFS",
  367. "component_name": "NAMENODE",
  368. "id": 28,
  369. "source_type": "PORT"
  370. },
  371. {
  372. "name": "journalnode_process",
  373. "label": "JournalNode Process",
  374. "enabled": true,
  375. "service_name": "HDFS",
  376. "component_name": "JOURNALNODE",
  377. "id": 31,
  378. "source_type": "PORT"
  379. },
  380. {
  381. "name": "namenode_last_checkpoint",
  382. "label": "NameNode Last Checkpoint",
  383. "enabled": true,
  384. "service_name": "HDFS",
  385. "component_name": "NAMENODE",
  386. "id": 30,
  387. "source_type": "SCRIPT"
  388. }
  389. ],
  390. "id": 6,
  391. "name": "HDFS"
  392. }
  393. }
  394. ]
  395. }