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

puppet: Add Nagios checks for other consumers.

This commit is contained in:
Tim Abbott 2016-08-12 19:29:11 -07:00 committed by Tim Abbott
parent f1fa4397f3
commit 32d244dbe5
1 changed files with 90 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

90
puppet/zulip_ops/files/nagios3/conf.d/services.cfg
View File

@ -354,6 +354,17 @@ define service {
contact_groups page_admins
}
define service {
use generic-service
service_description Check rabbitmq tornado_return consumers
check_command check_rabbitmq_consumers!tornado_return
# Workaround weird checks 40s after first error causing alerts
# from a single failure because cron hasn't run again yet
max_check_attempts 3
hostgroup_name frontends
contact_groups page_admins
}
define service {
use generic-service
service_description Check rabbitmq user_activity consumers
@ -409,6 +420,85 @@ define service {
contact_groups admins
}
define service {
use generic-service
service_description Check rabbitmq digest email consumers
check_command check_rabbitmq_consumers!digest_emails
# Workaround weird checks 40s after first error causing alerts
# from a single failure because cron hasn't run again yet
max_check_attempts 3
hostgroup_name frontends
contact_groups admins
}
define service {
use generic-service
service_description Check rabbitmq email mirror consumers
check_command check_rabbitmq_consumers!email_mirror
# Workaround weird checks 40s after first error causing alerts
# from a single failure because cron hasn't run again yet
max_check_attempts 3
hostgroup_name frontends
contact_groups admins
}
define service {
use generic-service
service_description Check rabbitmq feedback messages consumers
check_command check_rabbitmq_consumers!feedback_messages
# Workaround weird checks 40s after first error causing alerts
# from a single failure because cron hasn't run again yet
max_check_attempts 3
hostgroup_name frontends
contact_groups admins
}
define service {
use generic-service
service_description Check rabbitmq message sender consumers
check_command check_rabbitmq_consumers!message_sender
# Workaround weird checks 40s after first error causing alerts
# from a single failure because cron hasn't run again yet
max_check_attempts 3
hostgroup_name frontends
contact_groups admins
}
### The missedmessage_emails queue processor batches events, so don't monitor it this way
# define service {
# use generic-service
# service_description Check rabbitmq missedmessage emails consumers
# check_command check_rabbitmq_consumers!missedmessage_emails
# # Workaround weird checks 40s after first error causing alerts
# # from a single failure because cron hasn't run again yet
# max_check_attempts 3
# hostgroup_name frontends
# contact_groups admins
# }
define service {
use generic-service
service_description Check rabbitmq missedmessage mobile notifications consumers
check_command check_rabbitmq_consumers!missedmessage_mobile_notifications
# Workaround weird checks 40s after first error causing alerts
# from a single failure because cron hasn't run again yet
max_check_attempts 3
hostgroup_name frontends
contact_groups admins
}
### The slow_queries queue consumer batches events, so don't monitor it this way
# define service {
# use generic-service
# service_description Check rabbitmq slow queries consumers
# check_command check_rabbitmq_consumers!slow_queries
# # Workaround weird checks 40s after first error causing alerts
# # from a single failure because cron hasn't run again yet
# max_check_attempts 3
# hostgroup_name frontends
# contact_groups admins
# }
define service {
use generic-service
service_description Check missedmessage_emails queue processor