From 48f47342d85692e4d342c490085c13518be7a07e Mon Sep 17 00:00:00 2001 From: Christian Pointner Date: Tue, 8 Mar 2022 22:39:30 +0100 Subject: prometheus/alerta: tune some severities --- roles/monitoring/alerta/tasks/main.yml | 1 + roles/monitoring/prometheus/server/defaults/main/rules_node.yml | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'roles/monitoring') diff --git a/roles/monitoring/alerta/tasks/main.yml b/roles/monitoring/alerta/tasks/main.yml index 47df5308..490f5e3d 100644 --- a/roles/monitoring/alerta/tasks/main.yml +++ b/roles/monitoring/alerta/tasks/main.yml @@ -58,6 +58,7 @@ key = aNqBsEyG0ynIKcc3e7acaBVBk5B793o_z7tvlsht endpoint = http://localhost:8080/api amqp_url = redis://localhost:6379 + severities = critical, warning smtp_host = 192.168.28.250 smtp_port = 25 smtp_starttls = False diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml index 75e96bca..d211731a 100644 --- a/roles/monitoring/prometheus/server/defaults/main/rules_node.yml +++ b/roles/monitoring/prometheus/server/defaults/main/rules_node.yml @@ -167,7 +167,7 @@ prometheus_server_rules_node: expr: increase(node_edac_correctable_errors_total[1m]) > 0 for: 0m labels: - severity: info + severity: warning annotations: summary: Host EDAC Correctable Errors detected (instance {{ '{{' }} $labels.instance {{ '}}' }}) description: "Host {{ '{{' }} $labels.instance {{ '}}' }} has had {{ '{{' }} printf \"%.0f\" $value {{ '}}' }} correctable memory errors reported by EDAC in the last 5 minutes.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" @@ -176,7 +176,7 @@ prometheus_server_rules_node: expr: node_edac_uncorrectable_errors_total > 0 for: 0m labels: - severity: warning + severity: critical annotations: summary: Host EDAC Uncorrectable Errors detected (instance {{ '{{' }} $labels.instance {{ '}}' }}) description: "Host {{ '{{' }} $labels.instance {{ '}}' }} has had {{ '{{' }} printf \"%.0f\" $value {{ '}}' }} uncorrectable memory errors reported by EDAC in the last 5 minutes.\n VALUE = {{ '{{' }} $value {{ '}}' }}\n LABELS = {{ '{{' }} $labels {{ '}}' }}" -- cgit v1.2.3