WIP Add prometheus rules, improve alerts

This commit is contained in:
2026-07-06 18:01:22 +02:00
parent 1ae5210813
commit 2a14837f64
4 changed files with 57 additions and 19 deletions
@@ -1,6 +1,10 @@
node.default["kosmos_prometheus"]["version"] = "3.13.0"
node.default["kosmos_prometheus"]["checksum"] = "744d93324cc024d82089921737bd797474d7f1e5dbbfd1c6b387bad258538cb9"
node.default["kosmos_prometheus"]["data_dir"] = "/var/lib/prometheus"
node.default["kosmos_prometheus"]["config_dir"] = "/etc/prometheus"
node.default["kosmos_prometheus"]["rules_dir"] = "#{node["kosmos_prometheus"]["config_dir"]}/rules"
node.default["kosmos_prometheus"]["web"]["port"] = 9090
node.default["kosmos_prometheus"]["alertmanager"]["version"] = "0.33.0"
@@ -12,10 +16,14 @@ node.default["kosmos_prometheus"]["node_exporter"]["checksum"] = "9f5ea48e5bc7b6
node.default["kosmos_prometheus"]["alertmanager"]["route"] = {
"receiver" => "xmpp",
"group_by" => ["alertname"],
"group_wait" => "10s",
"group_wait" => "20s",
"group_interval" => "30s",
"repeat_interval" => "3h",
"routes" => [
{
"receiver" => "xmpp",
"continue" => true,
},
{
"receiver" => "email",
"matchers" => ['severity="critical"'],
@@ -66,5 +74,9 @@ node.default["kosmos_prometheus"]["jobs"] = {
}
node.default["kosmos_prometheus"]["rule_files"] = [
"/etc/prometheus/rules/*.yml"
"#{node["kosmos_prometheus"]["rules_dir"]}/*.yml"
]
node.default["kosmos_prometheus"]["rules"] = [
"node_exporter"
]