Mirror
/
zulip
mirror of https://github.com/zulip/zulip.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

nagios: Adjust load alerting by hostgroup. 

Even the `pageable_servers` group did not page for high load -- in
part because what was "high" depends on the servers.  Set slightly
better limits based on server role.
This commit is contained in:
Alex Vandiver 2022-06-13 16:44:57 -07:00 committed by Alex Vandiver
parent 2a14aa5180
commit 83c82c8e15
1 changed files with 18 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
puppet/zulip_ops/files/nagios4/conf.d/services.cfg
View File

@ -74,22 +74,30 @@ define service {
define service {
use generic-service
service_description Load
hostgroup_name pageable_servers
check_command check_remote_load!22!14.0,12.0,10.0!18.0,16.0,14.0
contact_groups admins
}
define service {
use generic-service
service_description Load
hostgroup_name not_pageable_servers
hostgroup_name fullstack, redis, staging_frontends, smokescreen
check_command check_remote_load!22!7.0,6.0,5.0!10.0,8.0,6.0
contact_groups admins
}
define service {
use generic-service
service_description Load for flaky machines
service_description Load
hostgroup_name postgresql
check_command check_remote_load!22!9.0,8.0,7.0!11.0,10.0,9.0
contact_groups admins
}
define service {
use generic-service
service_description Load
hostgroup_name prod_frontends
check_command check_remote_load!22!15.0,14.0,12.0!18.0,16.0,14.0
contact_groups admins
}
define service {
use generic-service
service_description Load
hostgroup_name flaky_servers
check_command check_remote_load!22!5.0,4.0,3.0!10.0,6.0,4.0
normal_check_interval 2