0

在 icinga2 监控中，我希望能够在服务关闭一段时间后升级问题通知，或者在停止工作时降级。我想在服务恢复时收到一个通知。

当我将“service-test-down-1”和“service-test-down-2”都设置为所有类型和状态时，当服务正常时，我会收到两条“OK”消息。当我像下面这样设置它时，将 OK 消息和 Not-OK 消息分开，我从来没有得到任何 OK。我觉得这应该是直截了当的，但我还没有取得任何进展。

apply Notification "service-test-down-1" to Service {
  command = "dispatch-service"
  states = [ Warning, Critical, Unknown ]
  types = [ Problem, Custom, FlappingStart, FlappingEnd,
            DowntimeStart, DowntimeEnd, DowntimeRemoved ]
  users = ["russ"]
  period = "24x7"
  assign where "tests" in service.groups
  vars.priority = "medium"
  times.begin = 0m
  times.end = 3m
  interval = 1m
}

apply Notification "service-test-down-2" to Service {
  command = "dispatch-service"
  states = [ Warning, Critical, Unknown ]
  types = [ Problem, Custom, FlappingStart, FlappingEnd,
            DowntimeStart, DowntimeEnd, DowntimeRemoved ]
  period = "24x7"
  users = ["russ"]
  assign where "tests" in service.groups
  vars.priority = "medium"
  times.begin = 3m
  times.end = 12h
  interval = 2m
}
apply Notification "service-test-recovery" to Service {
  command = "dispatch-service"
  states = [ OK ]
  types = [ Acknowledgement, Recovery ]
  users = ["russ"]
  period = "24x7"
  vars.priority = "medium"
  assign where "tests" in service.groups
  interval = 1
}

apply Service "NotificationTest" {
  enable_active_checks = true
  check_command = "passive"
  max_check_attempts = 1

  ignore where host.vars.noservices == true
  groups += ["tests"]
  assign where host.name == "icinga2.acceleration.net"
  max_check_attempts = 5
  check_interval = 5m
  retry_interval = 5m
}

此配置由 icinga 打印为：

~# icinga2 object list --name service-test-* 
Object 'icinga2.acceleration.net!NotificationTest!service-test-down-1' of type 'Notification':
  % declared in '/opt/icinga2lib/lib.conf.d//test.conf', lines 2:1-2:51
  * __name = "icinga2.acceleration.net!NotificationTest!service-test-down-1"
  * command = "dispatch-service"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 3:3-3:30
  * command_endpoint = ""
  * host_name = "icinga2.acceleration.net"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 2:1-2:51
  * interval = 60
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 13:3-13:15
  * name = "service-test-down-1"
  * package = "_etc"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 2:1-2:51
  * period = "24x7"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 8:3-8:17
  * service_name = "NotificationTest"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 2:1-2:51
  * states = [ "Warning", "Critical", "Unknown" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 4:3-4:41
  * templates = [ "service-test-down-1" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 2:1-2:51
  * times
    * begin = 0
      % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 11:3-11:18
    * end = 180
      % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 12:3-12:16
  * type = "Notification"
  * types = [ "Problem", "Custom", "FlappingStart", "FlappingEnd", "DowntimeStart", "DowntimeEnd", "DowntimeRemoved" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 5:3-6:57
  * user_groups = null
  * users = [ "russ" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 7:3-7:18
  * vars
    * priority = "medium"
      % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 10:3-10:26
  * zone = ""

Object 'icinga2.acceleration.net!NotificationTest!service-test-down-2' of type 'Notification':
  % declared in '/opt/icinga2lib/lib.conf.d//test.conf', lines 16:1-16:51
  * __name = "icinga2.acceleration.net!NotificationTest!service-test-down-2"
  * command = "dispatch-service"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 17:3-17:30
  * command_endpoint = ""
  * host_name = "icinga2.acceleration.net"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 16:1-16:51
  * interval = 120
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 27:3-27:15
  * name = "service-test-down-2"
  * package = "_etc"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 16:1-16:51
  * period = "24x7"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 21:3-21:17
  * service_name = "NotificationTest"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 16:1-16:51
  * states = [ "Warning", "Critical", "Unknown" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 18:3-18:41
  * templates = [ "service-test-down-2" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 16:1-16:51
  * times
    * begin = 180
      % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 25:3-25:18
    * end = 43200
      % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 26:3-26:17
  * type = "Notification"
  * types = [ "Problem", "Custom", "FlappingStart", "FlappingEnd", "DowntimeStart", "DowntimeEnd", "DowntimeRemoved" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 19:3-20:57
  * user_groups = null
  * users = [ "russ" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 22:3-22:18
  * vars
    * priority = "medium"
      % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 24:3-24:26
  * zone = ""

Object 'icinga2.acceleration.net!NotificationTest!service-test-recovery' of type 'Notification':
  % declared in '/opt/icinga2lib/lib.conf.d//test.conf', lines 29:1-29:53
  * __name = "icinga2.acceleration.net!NotificationTest!service-test-recovery"
  * command = "dispatch-service"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 30:3-30:30
  * command_endpoint = ""
  * host_name = "icinga2.acceleration.net"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 29:1-29:53
  * interval = 1
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 37:3-37:14
  * name = "service-test-recovery"
  * package = "_etc"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 29:1-29:53
  * period = "24x7"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 34:3-34:17
  * service_name = "NotificationTest"
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 29:1-29:53
  * states = [ "OK" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 31:3-31:17
  * templates = [ "service-test-recovery" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 29:1-29:53
  * times = null
  * type = "Notification"
  * types = [ "Acknowledgement", "Recovery" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 32:3-32:39
  * user_groups = null
  * users = [ "russ" ]
    % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 33:3-33:18
  * vars
    * priority = "medium"
      % = modified in '/opt/icinga2lib/lib.conf.d//test.conf', lines 35:3-35:26
  * zone = ""

相关文档链接： https ://www.icinga.com/docs/icinga2/latest/doc/03-monitoring-basics/#notification-escalations

交叉发布：https ://github.com/Icinga/icinga2/issues/5478

4

1 回答 1

0

icinga2 的开发人员（在 github 上：https ://github.com/Icinga/icinga2/issues/5478 ）提供的答案是，当您有通知升级时，无法从 icinga2 中发送单个恢复通知。

每个升级都是一个单独的通知对象，每个通知问题的通知都将发送一个 RECOVERY 消息。不会向任何从未发送过问题通知的通知对象发送任何 RECOVERY 通知（这似乎是错误的，但无论如何）。

建议的解决方案是拥有一个通知代理来为您删除重复消息。鉴于不希望有状态代理，我做了一个函数来设置正在通知的主机/服务上的 current_escalation，这样只有当前的升级才会真正发送 RECOVERY 消息，而我们的代理仍然可以是无状态的。github上的示例代码。

于 2017-08-09T19:08:02.703 回答