felix/nixos
1
0
Fork 0
mirror of https://github.com/Stunkymonkey/nixos.git synced 2025-05-24 09:54:40 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

treewide: avoid repetitive keys in attrSets

Browse source
This commit is contained in:
Felix Buehler 2023-11-12 23:36:30 +01:00
parent 2a3f606557
commit 4b21221569
19 changed files with 994 additions and 947 deletions
Download patch file Download diff file Expand all files Collapse all files

214
modules/services/prometheus/default.nix
View file

@ -78,112 +78,116 @@ in
};
config = lib.mkIf cfg.enable {
services.prometheus = {
enable = true;
webExternalUrl = "https://monitor.${domain}";
inherit (cfg) port;
listenAddress = "127.0.0.1";
inherit (cfg) retentionTime;
globalConfig = {
scrape_interval = cfg.scrapeInterval;
};
ruleFiles = [
(pkgs.writeText "prometheus-rules.yml" (builtins.toJSON {
groups = [
{
name = "alerting-rules";
rules = lib.mapAttrsToList
(name: opts: {
alert = name;
expr = opts.condition;
for = opts.time;
inherit (opts) labels;
annotations = {
inherit (opts) description;
grafana = lib.optionalString config.services.grafana.enable "https://visualization.${domain}";
};
})
cfg.rules;
}
];
}))
];
scrapeConfigs = [
{
job_name = "prometheus";
static_configs = [{
targets = [ "127.0.0.1:${toString cfg.port}" ];
labels = {
instance = config.networking.hostName;
};
}];
}
];
};
my.services.node-exporter.enable = true;
services.grafana.provision = {
datasources.settings.datasources = [
{
name = "Prometheus";
type = "prometheus";
isDefault = true;
url = "http://127.0.0.1:${toString config.services.prometheus.port}";
jsonData = {
prometheusType = "Prometheus";
prometheusVersion = toString pkgs.prometheus.version;
timeInterval = config.services.prometheus.globalConfig.scrape_interval;
};
}
];
dashboards.settings.providers = [
{
name = "Prometheus";
options.path = pkgs.grafana-dashboards.prometheus;
disableDeletion = true;
}
];
};
my.services.prometheus.rules = {
prometheus_too_many_restarts = {
condition = ''changes(process_start_time_seconds{job=~"prometheus|alertmanager"}[15m]) > 2'';
description = "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping";
};
alert_manager_config_not_synced = {
condition = ''count(count_values("config_hash", alertmanager_config_hash)) > 1'';
description = "Configurations of AlertManager cluster instances are out of sync";
};
prometheus_not_connected_to_alertmanager = {
condition = "prometheus_notifications_alertmanagers_discovered < 1";
description = "Prometheus cannot connect the alertmanager\n VALUE = {{ $value }}\n LABELS = {{ $labels }}";
};
prometheus_rule_evaluation_failures = {
condition = "increase(prometheus_rule_evaluation_failures_total[3m]) > 0";
description = "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}";
};
prometheus_template_expansion_failures = {
condition = "increase(prometheus_template_text_expansion_failures_total[3m]) > 0";
time = "0m";
description = "Prometheus encountered {{ $value }} template text expansion failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}";
};
};
my.services.nginx.virtualHosts = [
{
subdomain = "monitor";
services = {
prometheus = {
enable = true;
webExternalUrl = "https://monitor.${domain}";
inherit (cfg) port;
}
];
listenAddress = "127.0.0.1";
inherit (cfg) retentionTime;
globalConfig = {
scrape_interval = cfg.scrapeInterval;
};
ruleFiles = [
(pkgs.writeText "prometheus-rules.yml" (builtins.toJSON {
groups = [
{
name = "alerting-rules";
rules = lib.mapAttrsToList
(name: opts: {
alert = name;
expr = opts.condition;
for = opts.time;
inherit (opts) labels;
annotations = {
inherit (opts) description;
grafana = lib.optionalString config.services.grafana.enable "https://visualization.${domain}";
};
})
cfg.rules;
}
];
}))
];
scrapeConfigs = [
{
job_name = "prometheus";
static_configs = [{
targets = [ "127.0.0.1:${toString cfg.port}" ];
labels = {
instance = config.networking.hostName;
};
}];
}
];
};
grafana.provision = {
datasources.settings.datasources = [
{
name = "Prometheus";
type = "prometheus";
isDefault = true;
url = "http://127.0.0.1:${toString config.services.prometheus.port}";
jsonData = {
prometheusType = "Prometheus";
prometheusVersion = toString pkgs.prometheus.version;
timeInterval = config.services.prometheus.globalConfig.scrape_interval;
};
}
];
dashboards.settings.providers = [
{
name = "Prometheus";
options.path = pkgs.grafana-dashboards.prometheus;
disableDeletion = true;
}
];
};
};
my.services = {
node-exporter.enable = true;
prometheus.rules = {
prometheus_too_many_restarts = {
condition = ''changes(process_start_time_seconds{job=~"prometheus|alertmanager"}[15m]) > 2'';
description = "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping";
};
alert_manager_config_not_synced = {
condition = ''count(count_values("config_hash", alertmanager_config_hash)) > 1'';
description = "Configurations of AlertManager cluster instances are out of sync";
};
prometheus_not_connected_to_alertmanager = {
condition = "prometheus_notifications_alertmanagers_discovered < 1";
description = "Prometheus cannot connect the alertmanager\n VALUE = {{ $value }}\n LABELS = {{ $labels }}";
};
prometheus_rule_evaluation_failures = {
condition = "increase(prometheus_rule_evaluation_failures_total[3m]) > 0";
description = "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}";
};
prometheus_template_expansion_failures = {
condition = "increase(prometheus_template_text_expansion_failures_total[3m]) > 0";
time = "0m";
description = "Prometheus encountered {{ $value }} template text expansion failures\n VALUE = {{ $value }}\n LABELS = {{ $labels }}";
};
};
nginx.virtualHosts = [
{
subdomain = "monitor";
inherit (cfg) port;
}
];
};
webapps.apps = {
prometheus.dashboard = {