we have several http-services that we monitor. Any warning/critical is send to the developers / manager who’s responsible for it
The problem we are facing, is that we (sysadmins) are never going to be notified because we are not a member of that developer/manager-group
When I add our sysadmin-group to that check we get notified when their is an error and that is not what we want because we cannot fix.
The ideal situation will be something like:
Developer/Manager is getting notified when check has issue.
When anyone does not solve this issue within x-minutes, sysadmin is notified.
I tried to create this kind of setup but failed to get it working.
I was curious myself, so I asked the Checkmk AI chat “can notifications be send to other contacts when problems are not acknowledged within specific timeframe?”.
It gave following response:
Yes, notifications can be sent to other contacts if problems are not acknowledged within a specific timeframe in Checkmk. This can be achieved through escalation rules in the notification setup. You can configure escalation by creating additional notification rules that trigger based on the number of notifications sent. For example, you can set notification rules so that initial notifications are sent to primary contacts, and if the problem persists and is not acknowledged, subsequent notifications can be sent to team leaders or management.
Here is an example of how you can set it up:
Create a periodic notification rule to send alerts at fixed intervals until the problem is acknowledged.
Add escalation rules that specify different contacts based on how many notifications have been sent.
Keep in mind that the the duration time is “check-interval * count” , so when you have on service with 1 minute und one with 5 minute intervall the escalation happen in the first case after 3 minutes and in the other case after 15 minutes.
