feat: add service monitoring alerts for Gitea, Postfix, Dovecot, OpenLDAP, and WireGuard, and consolidate alerting rules in Grafana
This commit is contained in:
16
hosts/web-arm/modules/grafana/alerting/service/default.nix
Normal file
16
hosts/web-arm/modules/grafana/alerting/service/default.nix
Normal file
@@ -0,0 +1,16 @@
|
||||
{ lib, pkgs, config, ... }:
|
||||
let
|
||||
serviceDownAlertRules = (import ./service_down.nix { inherit lib pkgs config; }).grafanaAlertRuleDefinitions;
|
||||
|
||||
allServiceRules = serviceDownAlertRules;
|
||||
in
|
||||
{
|
||||
services.grafana.provision.alerting.rules.settings.groups = [
|
||||
{
|
||||
name = "Service Alerts";
|
||||
folder = "Service Monitoring";
|
||||
interval = "1m";
|
||||
rules = allServiceRules;
|
||||
}
|
||||
];
|
||||
}
|
||||
318
hosts/web-arm/modules/grafana/alerting/service/service_down.nix
Normal file
318
hosts/web-arm/modules/grafana/alerting/service/service_down.nix
Normal file
@@ -0,0 +1,318 @@
|
||||
{ lib, pkgs, config, ... }:
|
||||
{
|
||||
grafanaAlertRuleDefinitions = [
|
||||
# Systemd service monitoring alerts
|
||||
{
|
||||
uid = "gitea-service-down-alert-uid";
|
||||
title = "Gitea Service Down";
|
||||
condition = "C";
|
||||
data = [
|
||||
{
|
||||
refId = "A";
|
||||
relativeTimeRange = {
|
||||
from = 300;
|
||||
to = 0;
|
||||
};
|
||||
datasourceUid = "vm-datasource-uid";
|
||||
model = {
|
||||
editorMode = "code";
|
||||
expr = "node_systemd_unit_state{state=\"active\", name=\"container@git.service\"} OR on() vector(0)";
|
||||
hide = false;
|
||||
intervalMs = 1000;
|
||||
legendFormat = "__auto";
|
||||
maxDataPoints = 43200;
|
||||
range = true;
|
||||
refId = "A";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "B";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "reduce";
|
||||
expression = "A";
|
||||
reducer = "last";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "C";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "math";
|
||||
expression = "$B < 1";
|
||||
};
|
||||
}
|
||||
];
|
||||
noDataState = "Alerting";
|
||||
execErrState = "Alerting";
|
||||
for = "5m";
|
||||
annotations = {
|
||||
description = "Gitea service is down on {{ $labels.instance }}";
|
||||
summary = "Gitea Service Down";
|
||||
};
|
||||
labels = {
|
||||
severity = "critical";
|
||||
};
|
||||
}
|
||||
{
|
||||
uid = "gitea-runner-service-down-alert-uid";
|
||||
title = "Gitea Runner Service Down";
|
||||
condition = "C";
|
||||
data = [
|
||||
{
|
||||
refId = "A";
|
||||
relativeTimeRange = {
|
||||
from = 300;
|
||||
to = 0;
|
||||
};
|
||||
datasourceUid = "vm-datasource-uid";
|
||||
model = {
|
||||
editorMode = "code";
|
||||
expr = "node_systemd_unit_state{state=\"active\", name=\"microvm@git-runner-1.service \"} OR on() vector(0)";
|
||||
hide = false;
|
||||
intervalMs = 1000;
|
||||
legendFormat = "__auto";
|
||||
maxDataPoints = 43200;
|
||||
range = true;
|
||||
refId = "A";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "B";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "reduce";
|
||||
expression = "A";
|
||||
reducer = "last";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "C";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "math";
|
||||
expression = "$B < 1";
|
||||
};
|
||||
}
|
||||
];
|
||||
noDataState = "Alerting";
|
||||
execErrState = "Alerting";
|
||||
for = "5m";
|
||||
annotations = {
|
||||
description = "Gitea Runner service is down on {{ $labels.instance }}";
|
||||
summary = "Gitea Runner Service Down";
|
||||
};
|
||||
labels = {
|
||||
severity = "critical";
|
||||
};
|
||||
}
|
||||
{
|
||||
uid = "postfix-service-down-alert-uid";
|
||||
title = "Postfix Service Down";
|
||||
condition = "C";
|
||||
data = [
|
||||
{
|
||||
refId = "A";
|
||||
relativeTimeRange = {
|
||||
from = 300;
|
||||
to = 0;
|
||||
};
|
||||
datasourceUid = "vm-datasource-uid";
|
||||
model = {
|
||||
editorMode = "code";
|
||||
expr = "node_systemd_unit_state{state=\"active\", name=\"postfix.service\"} OR on() vector(0)";
|
||||
hide = false;
|
||||
intervalMs = 1000;
|
||||
legendFormat = "__auto";
|
||||
maxDataPoints = 43200;
|
||||
range = true;
|
||||
refId = "A";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "B";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "reduce";
|
||||
expression = "A";
|
||||
reducer = "last";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "C";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "math";
|
||||
expression = "$B < 1";
|
||||
};
|
||||
}
|
||||
];
|
||||
noDataState = "Alerting";
|
||||
execErrState = "Alerting";
|
||||
for = "5m";
|
||||
annotations = {
|
||||
description = "Postfix service is down on {{ $labels.instance }}";
|
||||
summary = "Postfix Service Down";
|
||||
};
|
||||
labels = {
|
||||
severity = "critical";
|
||||
};
|
||||
}
|
||||
{
|
||||
uid = "dovecot-service-down-alert-uid";
|
||||
title = "Dovecot Service Down";
|
||||
condition = "C";
|
||||
data = [
|
||||
{
|
||||
refId = "A";
|
||||
relativeTimeRange = {
|
||||
from = 300;
|
||||
to = 0;
|
||||
};
|
||||
datasourceUid = "vm-datasource-uid";
|
||||
model = {
|
||||
editorMode = "code";
|
||||
expr = "node_systemd_unit_state{state=\"active\", name=\"dovecot2.service\"} OR on() vector(0)";
|
||||
hide = false;
|
||||
intervalMs = 1000;
|
||||
legendFormat = "__auto";
|
||||
maxDataPoints = 43200;
|
||||
range = true;
|
||||
refId = "A";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "B";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "reduce";
|
||||
expression = "A";
|
||||
reducer = "last";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "C";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "math";
|
||||
expression = "$B < 1";
|
||||
};
|
||||
}
|
||||
];
|
||||
noDataState = "Alerting";
|
||||
execErrState = "Alerting";
|
||||
for = "5m";
|
||||
annotations = {
|
||||
description = "Dovecot service is down on {{ $labels.instance }}";
|
||||
summary = "Dovecot Service Down";
|
||||
};
|
||||
labels = {
|
||||
severity = "critical";
|
||||
};
|
||||
}
|
||||
{
|
||||
uid = "openldap-service-down-alert-uid";
|
||||
title = "OpenLDAP Service Down";
|
||||
condition = "C";
|
||||
data = [
|
||||
{
|
||||
refId = "A";
|
||||
relativeTimeRange = {
|
||||
from = 300;
|
||||
to = 0;
|
||||
};
|
||||
datasourceUid = "vm-datasource-uid";
|
||||
model = {
|
||||
editorMode = "code";
|
||||
expr = "node_systemd_unit_state{state=\"active\", name=\"openldap.service\"} OR on() vector(0)";
|
||||
hide = false;
|
||||
intervalMs = 1000;
|
||||
legendFormat = "__auto";
|
||||
maxDataPoints = 43200;
|
||||
range = true;
|
||||
refId = "A";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "B";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "reduce";
|
||||
expression = "A";
|
||||
reducer = "last";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "C";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "math";
|
||||
expression = "$B < 1";
|
||||
};
|
||||
}
|
||||
];
|
||||
noDataState = "Alerting";
|
||||
execErrState = "Alerting";
|
||||
for = "5m";
|
||||
annotations = {
|
||||
description = "OpenLDAP service is down on {{ $labels.instance }}";
|
||||
summary = "OpenLDAP Service Down";
|
||||
};
|
||||
labels = {
|
||||
severity = "critical";
|
||||
};
|
||||
}
|
||||
{
|
||||
uid = "wireguard-service-down-alert-uid";
|
||||
title = "WireGuard Service Down";
|
||||
condition = "C";
|
||||
data = [
|
||||
{
|
||||
refId = "A";
|
||||
relativeTimeRange = {
|
||||
from = 300;
|
||||
to = 0;
|
||||
};
|
||||
datasourceUid = "vm-datasource-uid";
|
||||
model = {
|
||||
editorMode = "code";
|
||||
expr = "node_systemd_unit_state{state=\"active\", name=\"wireguard-wg_cloonar.service\"} OR on() vector(0)";
|
||||
hide = false;
|
||||
intervalMs = 1000;
|
||||
legendFormat = "__auto";
|
||||
maxDataPoints = 43200;
|
||||
range = true;
|
||||
refId = "A";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "B";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "reduce";
|
||||
expression = "A";
|
||||
reducer = "last";
|
||||
};
|
||||
}
|
||||
{
|
||||
refId = "C";
|
||||
datasourceUid = "__expr__";
|
||||
model = {
|
||||
type = "math";
|
||||
expression = "$B < 1";
|
||||
};
|
||||
}
|
||||
];
|
||||
noDataState = "Alerting";
|
||||
execErrState = "Alerting";
|
||||
for = "5m";
|
||||
annotations = {
|
||||
description = "WireGuard service is down on {{ $labels.instance }}";
|
||||
summary = "WireGuard Service Down";
|
||||
};
|
||||
labels = {
|
||||
severity = "critical";
|
||||
};
|
||||
}
|
||||
];
|
||||
}
|
||||
Reference in New Issue
Block a user