diff --git a/roles/prometheus-alertmanager/templates/prometheus/alertmanager.yml.j2 b/roles/prometheus-alertmanager/templates/prometheus/alertmanager.yml.j2 index 666c5ffcb20840106b3e79ebca42c98ba5873d3f..bc957ae1e1ff1c3e896e22d113ae05d9faad126a 100644 --- a/roles/prometheus-alertmanager/templates/prometheus/alertmanager.yml.j2 +++ b/roles/prometheus-alertmanager/templates/prometheus/alertmanager.yml.j2 @@ -24,7 +24,7 @@ route: # This way ensures that you get multiple alerts for the same group that start # firing shortly after another are batched together on the first # notification. - group_wait: 30s + group_wait: 1m # When the first notification was sent, wait 'group_interval' to send a batch # of new alerts that started firing for that group. @@ -32,7 +32,7 @@ route: # If an alert has successfully been sent, wait 'repeat_interval' to # resend them. - repeat_interval: 3h + repeat_interval: 12h # A default receiver #receiver: team-roots-mails diff --git a/roles/prometheus/templates/prometheus/alert.rules.yml.j2 b/roles/prometheus/templates/prometheus/alert.rules.yml.j2 index d2fafda591b79e18b0da6bfebae5758f389dc4aa..4a93dbf3fc167133d28d893e268ba7723087f2a9 100644 --- a/roles/prometheus/templates/prometheus/alert.rules.yml.j2 +++ b/roles/prometheus/templates/prometheus/alert.rules.yml.j2 @@ -33,8 +33,8 @@ groups: labels: severity: warning annotations: - summary: "Presque plus de stockage sur {{ $labels.instance }}" - description: "Le disque est presque rempli ({{ $value }}% restant)" + summary: "Presque plus de stockage sur {{ $labels.mountpoint }} sur {{ $labels.instance }}" + description: "La partition est presque remplie ({{ $value }}% restant)" # Alert for out of inode space on disk - alert: OutOfInodes @@ -43,7 +43,7 @@ groups: labels: severity: warning annotations: - summary: "Presque plus d'inodes disque sur {{ $labels.instance }}" + summary: "Presque plus d'inodes disque sur {{ $labels.mountpoint }} sur {{ $labels.instance }}" description: "Le disque est presque à courre d'inodes disponibles ({{ $value }}% restant)" # Alert for high CPU usage