SebastianStork/nixos-config
1
0
Fork 0
mirror of https://github.com/SebastianStork/nixos-config.git synced 2026-03-22 22:29:06 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

Compare commits

base: SebastianStork:f2258ac79c1e1ca76640b1acdbe9a92cf3f3092b
Branches Tags
SebastianStork:main
SebastianStork:dependabot/github_actions/cachix/cachix-action-17
SebastianStork:deploy
SebastianStork:deployed/srv-core
SebastianStork:deployed/vps-ns
SebastianStork:deployed/vps-www
SebastianStork:testing-srv-core
..
compare: SebastianStork:8cf724fb97698c28ad90d28463db4188be2ceadb
Branches Tags
SebastianStork:dependabot/github_actions/cachix/cachix-action-17
SebastianStork:deploy
SebastianStork:deployed/srv-core
SebastianStork:deployed/vps-ns
SebastianStork:deployed/vps-www
SebastianStork:main
SebastianStork:testing-srv-core

No commits in common. "f2258ac79c1e1ca76640b1acdbe9a92cf3f3092b" and "8cf724fb97698c28ad90d28463db4188be2ceadb" have entirely different histories.
f2258ac79c ... 8cf724fb97

3 changed files with 47 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

8
modules/nixos/services/alertmanager.nix
View file

@ -63,14 +63,6 @@ in
name = "ntfy";
webhook_configs = lib.singleton { url = "http://localhost:${toString cfg.ntfyBridgePort}/hook"; };
};
inhibit_rules = lib.singleton {
source_matchers = [
''alertname="InstanceDown"''
''job="node"''
];
target_matchers = lib.singleton ''alertname!="InstanceDown"'';
equal = [ "instance" ];
};
};
};

7
modules/nixos/services/nameservers/public.nix
View file

@ -46,12 +46,7 @@ let
in
inputs.dns.lib.toString zone {
SOA = {
nameServer =
nsRecords
|> lib.map (record: record.name)
|> lib.naturalSort
|> lib.head
|> (hostName: "${hostName}.${zone}.");
nameServer = "${netCfg.hostName}.${zone}.";
adminEmail = "hostmaster@sstork.dev";
serial = 1;
};

108
modules/nixos/services/prometheus.nix
View file

@ -58,25 +58,25 @@ in
scrapeConfigs = [
{
job_name = "prometheus";
static_configs =
allHosts
|> lib.attrValues
|> lib.filter (host: host.config.custom.services.prometheus.enable)
|> lib.map (host: {
targets = lib.singleton host.config.custom.services.prometheus.domain;
labels.instance = host.config.networking.hostName;
});
static_configs = lib.singleton {
targets =
allHosts
|> lib.attrValues
|> lib.map (host: host.config.custom.services.prometheus)
|> lib.filter (prometheus: prometheus.enable)
|> lib.map (prometheus: prometheus.domain);
};
}
{
job_name = "alertmanager";
static_configs =
allHosts
|> lib.attrValues
|> lib.filter (host: host.config.custom.services.alertmanager.enable)
|> lib.map (host: {
targets = lib.singleton host.config.custom.services.alertmanager.domain;
labels.instance = host.config.networking.hostName;
});
static_configs = lib.singleton {
targets =
allHosts
|> lib.attrValues
|> lib.map (host: host.config.custom.services.alertmanager)
|> lib.filter (alertmanager: alertmanager.enable)
|> lib.map (alertmanager: alertmanager.domain);
};
}
];
@ -84,55 +84,39 @@ in
{
groups = lib.singleton {
name = "Rules";
rules =
(
allHosts
|> lib.attrValues
|> lib.filter (host: host.config.custom.services.alloy.enable)
|> lib.filter (host: host.config.custom.networking.overlay.role == "server")
|> lib.map (host: host.config.networking.hostName)
|> lib.map (hostName: {
alert = "InstanceDown";
expr = ''absent_over_time(up{instance="${hostName}", job="node"}[2m])'';
labels.severity = "critical";
annotations = {
summary = "${hostName} is DOWN";
description = "${hostName} has not reported any metrics for more than 2 minutes.";
};
})
)
++ [
{
alert = "ServiceDown";
expr = ''up{job=~"prometheus|alertmanager"} == 0'';
for = "2m";
annotations = {
summary = "{{ $labels.job }} on {{ $labels.instance }} is DOWN";
description = "{{ $labels.job }} on {{ $labels.instance }} has been down for more than 2 minutes.";
};
}
{
alert = "CominDeploymentFailed";
expr = ''comin_deployment_info{status!="done"}'';
annotations = {
summary = "{{ $labels.instance }} deployment failed";
description = "The deployment of {{ $labels.instance }} with comin is failing.";
};
}
{
alert = "CominDeploymentCommitMismatch";
expr = "count(count by (commit_id) (comin_deployment_info)) > 1";
for = "10m";
annotations = {
summary = "Hosts are running different commits";
description = "Not all hosts are running the same git commit, which may indicate a failed deployment and could lead to incompatible configurations.";
};
}
];
rules = [
{
alert = "InstanceDown";
expr = "up == 0";
for = "2m";
labels.severity = "critical";
annotations = {
summary = "{{ $labels.instance }} is DOWN";
description = "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 2 minutes.";
};
}
{
alert = "CominDeploymentFailed";
expr = ''comin_deployment_info{status!="done"}'';
annotations = {
summary = "{{ $labels.instance }} deployment failed";
description = "The deployment of {{ $labels.instance }} with comin is failing.";
};
}
{
alert = "CominDeploymentCommitMismatch";
expr = "count(count by (commit_id) (comin_deployment_info)) > 1";
for = "10m";
annotations = {
summary = "Hosts are running different commits";
description = "Not all hosts are running the same git commit, which may indicate a failed deployment and could lead to incompatible configurations.";
};
}
];
};
}
|> lib.strings.toJSON
|> pkgs.writeText "prometheus-rules"
|> pkgs.writeText "prometheus-instance-down-rule"
|> toString
|> lib.singleton;
};