template_openshift_master.yml 10 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291
  1. ---
  2. g_template_openshift_master:
  3. name: Template Openshift Master
  4. zitems:
  5. - name: create_app
  6. applications:
  7. - Openshift Master
  8. key: create_app
  9. - key: openshift.master.registry.healthz
  10. description: "Shows the health status of the cluster's docker registry"
  11. type: int
  12. applications:
  13. - Openshift Master
  14. - key: openshift.master.process.count
  15. description: Shows number of master processes running
  16. type: int
  17. applications:
  18. - Openshift Master
  19. - key: openshift.master.api.ping
  20. description: "Verify that the Openshift API is up"
  21. type: int
  22. applications:
  23. - Openshift Master
  24. - key: openshift.master.api.healthz
  25. description: "Checks the healthz check of the master's api: https://master_host/healthz"
  26. type: int
  27. data_type: bool
  28. applications:
  29. - Openshift Master
  30. - key: openshift.master.user.count
  31. description: Shows number of users in a cluster
  32. type: int
  33. applications:
  34. - Openshift Master
  35. - key: openshift.master.pod.running.count
  36. description: Shows number of pods running
  37. type: int
  38. applications:
  39. - Openshift Master
  40. - key: openshift.master.pod.user.running.count
  41. description: Shows number of user pods running (non infrastructure pods)
  42. type: int
  43. applications:
  44. - Openshift Master
  45. - key: openshift.master.pod.total.count
  46. description: Shows total number of pods (running and non running)
  47. type: int
  48. applications:
  49. - Openshift Master
  50. - key: openshift.master.node.count
  51. description: Shows the total number of nodes found in the Openshift Cluster
  52. type: int
  53. applications:
  54. - Openshift Master
  55. - key: openshift.project.count
  56. description: Shows number of projects on a cluster
  57. type: int
  58. applications:
  59. - Openshift Master
  60. - key: openshift.master.etcd.create.success
  61. description: Show number of successful create actions
  62. type: int
  63. applications:
  64. - Openshift Etcd
  65. - key: openshift.master.etcd.create.fail
  66. description: Show number of failed create actions
  67. type: int
  68. applications:
  69. - Openshift Etcd
  70. - key: openshift.master.etcd.delete.success
  71. description: Show number of successful delete actions
  72. type: int
  73. applications:
  74. - Openshift Etcd
  75. - key: openshift.master.etcd.delete.fail
  76. description: Show number of failed delete actions
  77. type: int
  78. applications:
  79. - Openshift Etcd
  80. - key: openshift.master.etcd.get.success
  81. description: Show number of successful get actions
  82. type: int
  83. applications:
  84. - Openshift Etcd
  85. - key: openshift.master.etcd.get.fail
  86. description: Show number of failed get actions
  87. type: int
  88. applications:
  89. - Openshift Etcd
  90. - key: openshift.master.etcd.set.success
  91. description: Show number of successful set actions
  92. type: int
  93. applications:
  94. - Openshift Etcd
  95. - key: openshift.master.etcd.set.fail
  96. description: Show number of failed set actions
  97. type: int
  98. applications:
  99. - Openshift Etcd
  100. - key: openshift.master.etcd.update.success
  101. description: Show number of successful update actions
  102. type: int
  103. applications:
  104. - Openshift Etcd
  105. - key: openshift.master.etcd.update.fail
  106. description: Show number of failed update actions
  107. type: int
  108. applications:
  109. - Openshift Etcd
  110. - key: openshift.master.etcd.watchers
  111. description: Show number of etcd watchers
  112. type: int
  113. applications:
  114. - Openshift Etcd
  115. - key: openshift.master.etcd.ping
  116. description: etcd ping
  117. type: int
  118. applications:
  119. - Openshift Etcd
  120. - key: openshift.master.metric.ping
  121. description: "This check verifies that the https://master/metrics check is alive and communicating properly."
  122. type: int
  123. applications:
  124. - Openshift Master Metrics
  125. - key: openshift.master.apiserver.latency.summary.pods.quantile.list.5
  126. description: "Value from https://master/metrics. This is the time, in miliseconds, that 50% of the pod operations have taken to completed."
  127. type: int
  128. applications:
  129. - Openshift Master Metrics
  130. - key: openshift.master.apiserver.latency.summary.pods.quantile.list.9
  131. description: "Value from https://master/metrics. This is the time, in miliseconds, that 90% of the pod operations have taken to completed."
  132. type: int
  133. applications:
  134. - Openshift Master Metrics
  135. - key: openshift.master.apiserver.latency.summary.pods.quantile.list.99
  136. description: "Value from https://master/metrics. This is the time, in miliseconds, that 99% of the pod operations have taken to completed."
  137. type: int
  138. applications:
  139. - Openshift Master Metrics
  140. - key: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.5
  141. description: "Value from https://master/metrics. This is the time, in miliseconds, that 50% of the pod operations have taken to completed."
  142. type: int
  143. applications:
  144. - Openshift Master Metrics
  145. - key: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.9
  146. description: "Value from https://master/metrics. This is the time, in miliseconds, that 90% of the pod operations have taken to completed."
  147. type: int
  148. applications:
  149. - Openshift Master Metrics
  150. - key: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.99
  151. description: "Value from https://master/metrics. This is the time, in miliseconds, that 99% of the pod operations have taken to completed."
  152. type: int
  153. applications:
  154. - Openshift Master Metrics
  155. - key: openshift.master.scheduler.e2e.scheduling.latency.quantile.5
  156. description: "Value from https://master/metrics. This is the time, in miliseconds, that 50% of the end to end scheduling operations have taken to completed."
  157. type: int
  158. applications:
  159. - Openshift Master Metrics
  160. - key: openshift.master.scheduler.e2e.scheduling.latency.quantile.9
  161. description: "Value from https://master/metrics. This is the time, in miliseconds, that 90% of the end to end scheduling operations have taken to completed."
  162. type: int
  163. applications:
  164. - Openshift Master Metrics
  165. - key: openshift.master.scheduler.e2e.scheduling.latency.quantile.99
  166. description: "Value from https://master/metrics. This is the time, in miliseconds, that 99% of the end to end scheduling operations have taken to completed."
  167. type: int
  168. applications:
  169. - Openshift Master Metrics
  170. ztriggers:
  171. - name: 'Application creation has failed on {HOST.NAME}'
  172. expression: '{Template Openshift Master:create_app.last(#1)}=1 and {Template Openshift Master:create_app.last(#2)}=1'
  173. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_create_app.asciidoc'
  174. priority: avg
  175. - name: 'Openshift Master API health check is failing on {HOST.NAME}'
  176. expression: '{Template Openshift Master:openshift.master.api.healthz.max(#3)}<1'
  177. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
  178. priority: high
  179. - name: 'Openshift Master API PING check is failing on {HOST.NAME}'
  180. expression: '{Template Openshift Master:openshift.master.api.ping.max(#3)}<1'
  181. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
  182. priority: high
  183. - name: 'Openshift Master metric PING check is failing on {HOST.NAME}'
  184. expression: '{Template Openshift Master:openshift.master.metric.ping.max(#3)}<1'
  185. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
  186. priority: avg
  187. - name: 'Openshift Master process not running on {HOST.NAME}'
  188. expression: '{Template Openshift Master:openshift.master.process.count.max(#3)}<1'
  189. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
  190. priority: high
  191. - name: 'Too many Openshift Master processes running on {HOST.NAME}'
  192. expression: '{Template Openshift Master:openshift.master.process.count.min(#3)}>1'
  193. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
  194. priority: high
  195. - name: 'Number of users for Openshift Master on {HOST.NAME}'
  196. expression: '{Template Openshift Master:openshift.master.user.count.last()}=0'
  197. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
  198. priority: info
  199. - name: 'There are no projects running on {HOST.NAME}'
  200. expression: '{Template Openshift Master:openshift.project.count.last()}=0'
  201. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
  202. priority: info
  203. - name: 'Low number of etcd watchers on {HOST.NAME}'
  204. expression: '{Template Openshift Master:openshift.master.etcd.watchers.last(#1)}<10 and {Template Openshift Master:openshift.master.etcd.watchers.last(#2)}<10'
  205. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_etcd.asciidoc'
  206. priority: avg
  207. - name: 'Etcd ping failed on {HOST.NAME}'
  208. expression: '{Template Openshift Master:openshift.master.etcd.ping.last(#1)}=0 and {Template Openshift Master:openshift.master.etcd.ping.last(#2)}=0'
  209. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/check_etcd.asciidoc'
  210. priority: high
  211. - name: 'Docker Registry check failed on {HOST.NAME}'
  212. expression: '{Template Openshift Master:openshift.master.registry.healthz.max(#2)}<1'
  213. url: 'https://github.com/openshift/ops-sop/blob/master/V3/Alerts/openshift_master.asciidoc'
  214. priority: high
  215. zgraphs:
  216. - name: Openshift Master API Server Latency Pods LIST Quantiles
  217. width: 900
  218. height: 200
  219. graph_items:
  220. - item_name: openshift.master.apiserver.latency.summary.pods.quantile.list.5
  221. color: red
  222. - item_name: openshift.master.apiserver.latency.summary.pods.quantile.list.9
  223. color: blue
  224. - item_name: openshift.master.apiserver.latency.summary.pods.quantile.list.99
  225. color: orange
  226. - name: Openshift Master API Server Latency Pods WATCHLIST Quantiles
  227. width: 900
  228. height: 200
  229. graph_items:
  230. - item_name: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.5
  231. color: red
  232. - item_name: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.9
  233. color: blue
  234. - item_name: openshift.master.apiserver.latency.summary.pods.quantile.watchlist.99
  235. color: orange
  236. - name: Openshift Master Scheduler End to End Latency Quantiles
  237. width: 900
  238. height: 200
  239. graph_items:
  240. - item_name: openshift.master.scheduler.e2e.scheduling.latency.quantile.5
  241. color: red
  242. - item_name: openshift.master.scheduler.e2e.scheduling.latency.quantile.9
  243. color: blue
  244. - item_name: openshift.master.scheduler.e2e.scheduling.latency.quantile.99
  245. color: orange