From: Tom Hughes Date: Fri, 4 Aug 2023 09:01:48 +0000 (+0100) Subject: Change switch alerts to use junos exporter metrics X-Git-Url: https://git.openstreetmap.org/chef.git/commitdiff_plain/be5a228b5a0cef503d517e5e109b652c5501ee40 Change switch alerts to use junos exporter metrics --- diff --git a/cookbooks/prometheus/templates/default/alert_rules.yml.erb b/cookbooks/prometheus/templates/default/alert_rules.yml.erb index 899c765e4..f52f87748 100644 --- a/cookbooks/prometheus/templates/default/alert_rules.yml.erb +++ b/cookbooks/prometheus/templates/default/alert_rules.yml.erb @@ -4,7 +4,7 @@ groups: - name: amsterdam rules: - alert: uplink - expr: ifOperStatus{site="amsterdam",ifName=~"ge-[01]/2/2"} != 1 + expr: junos_interface_up{site="amsterdam",name=~"ge-[01]/2/2"} != 1 for: 6m labels: alertgroup: "amsterdam" @@ -117,7 +117,7 @@ groups: - name: dublin rules: - alert: uplink - expr: ifOperStatus{site="dublin",ifName=~"ge-[01]/2/2"} != 1 + expr: junos_interface_up{site="dublin",name=~"ge-[01]/2/2"} != 1 for: 6m labels: alertgroup: "dublin" @@ -273,7 +273,7 @@ groups: - name: juniper rules: - alert: juniper cpu alarm - expr: jnxOperating5MinLoadAvg{jnxOperatingContentsIndex="9"} / 200 > 0.5 + expr: junos_route_engine_load_average_five > 0.5 for: 5m labels: alertgroup: "{{ $labels.site }}" @@ -285,7 +285,7 @@ groups: labels: alertgroup: "{{ $labels.site }}" - alert: juniper power alarm - expr: jnxOperatingState{jnxOperatingContentsIndex="2",jnxOperatingState!~"running.*"} > 0 + expr: junos_environment_power_up != 1 for: 5m labels: alertgroup: "{{ $labels.site }}"