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

nagios: Remove load monitoring. 

Load monitoring alerts are extremely noisy, and do not reliably
indicate an issue which is affecting users.
This commit is contained in:
Alex Vandiver 2023-09-14 15:38:51 +00:00 committed by Tim Abbott
parent 0e73b5547c
commit f95c8b894a
2 changed files with 0 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
puppet/zulip_ops/files/nagios4/commands.cfg
View File

@ -55,11 +55,6 @@ define command{
command_line /usr/lib/nagios/plugins/check_disk -W$ARG1$ -K$ARG2$ -w $ARG1$ -c $ARG2$ -A -l -X cgroup -X tmpfs -X devtmpfs -X squashfs -X configfs -X tracefs
}
define command{
command_name check_remote_load
command_line /usr/lib/nagios/plugins/check_by_ssh -p $ARG1$ -l nagios -t 30 -i /var/lib/nagios/.ssh/id_ed25519 -H $HOSTADDRESS$ -C '/usr/lib/nagios/plugins/check_load -w $ARG2$ -c $ARG3$'
}
define command{
command_name check_zephyr_mirror_forwarding
command_line /usr/lib/nagios/plugins/check_by_ssh -p $ARG1$ -l nagios -t 30 -i /var/lib/nagios/.ssh/id_ed25519 -H $HOSTADDRESS$ -C '/usr/lib/nagios/plugins/zulip_zephyr_mirror/check_zephyr_mirror'

38
puppet/zulip_ops/files/nagios4/conf.d/services.cfg
View File

@ -58,44 +58,6 @@ define service {
}
### Load
define service {
use generic-service
service_description Load
hostgroup_name fullstack, redis, staging_frontends, smokescreen, other
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
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
retry_check_interval 2
max_check_attempts 5
contact_groups admins
}
### System updates
define service {