xin/nixos-config
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

fix

Browse source
This commit is contained in:
xinyangli 2024-07-30 20:09:41 +08:00
parent c88f86eec2
commit 013d87afdf
Signed by: xin
SSH key fingerprint: SHA256:qZ/tzd8lYRtUFSrfBDBMcUqV4GHKxqeqRA3huItgvbk
1 changed files with 187 additions and 193 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

178
modules/nixos/prometheus.nix
View file

@ -25,7 +25,8 @@ in
};
};
config = mkIf cfg.enable (mkMerge [{
config = mkIf cfg.enable (mkMerge [
{
services.tailscale = {
enable = true;
permitCertUid = config.services.caddy.user;
@ -47,7 +48,10 @@ in
services.gotosocial.settings = mkIf cfg.enable {
metrics-enabled = true;
};
services.prometheus = mkIf cfg.enable {
services.ntfy-sh.settings.enable-metrics = true;
services.prometheus = mkIf cfg.enable
{
enable = true;
port = 9091;
globalConfig.external_labels = { hostname = config.networking.hostName; };
@ -103,9 +107,7 @@ in
alertmanager = {
enable = true;
listenAddress = "127.0.0.1";
extraFlags = [
"--cluster.advertise-address=127.0.0.1:9093"
];
logLevel = "debug";
configuration = {
route = {
receiver = "ntfy";
@ -115,7 +117,12 @@ in
name = "ntfy";
webhook_configs = [
{
url = "https://ntfy.xinyang.life/prometheus-alerts";
url = "https://ntfy.xinyang.life/prometheus-alerts?tpl=yes&m=${lib.escapeURL ''
Alert {{.status}}
{{range .alerts}}-----{{range $k,$v := .labels}}
{{$k}}={{$v}}{{end}}
{{end}}
''}";
send_resolved = true;
}
];
@ -127,7 +134,6 @@ in
alertmanagers = [
{
scheme = "http";
path_prefix = "/alertmanager";
static_configs = [
{
targets = [
@ -138,91 +144,72 @@ in
}
];
rules = let mkRule = condition: { ... }@rule: (if condition then [ rule ] else [ ]); in [
(lib.generators.toYAML { } {
groups = (mkRule true
{
name = "system_alerts";
rules = [
''
groups:
- name: system_alerts
rules:
- alert: SystemdFailedUnits
expr: node_systemd_unit_state{state="failed"} > 0
for: 5m
labels:
severity: critical
annotations:
summary: "Systemd has failed units on {{ $labels.instance }}"
description: "There are {{ $value }} failed units on {{ $labels.instance }}. Immediate attention required!"
- alert: HighLoadAverage
expr: node_load1 > 0.8 * count without (cpu) (node_cpu_seconds_total{mode="idle"})
for: 1m
labels:
severity: warning
annotations:
summary: "High load average detected on {{ $labels.instance }}"
description: "The 1-minute load average ({{ $value }}) exceeds 80% the number of CPUs."
- alert: HighTransmitTraffic
expr: rate(node_network_transmit_bytes_total{device!="lo"}[5m]) > 100000000
for: 1m
labels:
severity: warning
annotations:
summary: "High network transmit traffic on {{ $labels.instance }} ({{ $labels.device }})"
description: "The network interface {{ $labels.device }} on {{ $labels.instance }} is transmitting data at a rate exceeding 100 MB/s for the last 1 minute."
''
(if config.services.restic.server.enable then
''
groups:
- name: restic_alerts
rules:
- alert: ResticCheckFailed
expr: restic_check_success == 0
for: 5m
labels:
severity: critical
annotations:
summary: Restic check failed (instance {{ $labels.instance }})
description: Restic check failed\n VALUE = {{ $value }}\n LABELS = {{ $labels }}
- alert: ResticOutdatedBackup
# 1209600 = 15 days
expr: time() - restic_backup_timestamp > 518400
for: 0m
labels:
severity: critical
annotations:
summary: Restic {{ $labels.client_hostname }} / {{ $labels.client_username }} backup is outdated
description: Restic backup is outdated\n VALUE = {{ $value }}\n LABELS = {{ $labels }}
'' else "")
(if config.services.caddy.enable then ''
groups:
- name: caddy_alerts
rules:
- alert: HighHttpErrorRate
expr: rate(caddy_http_request_duration_seconds_count{status_code=~"5.."}[5m]) / rate(caddy_http_request_duration_seconds_count[5m]) > 0.01
for: 10m
labels:
severity: critical
annotations:
summary: "High error rate on {{ $labels.instance }}"
description: "More than 1% of HTTP requests are errors over the last 10 minutes."
- alert: CaddyDown
expr: up{job="caddy"} == 0
for: 5m
labels:
severity: critical
annotations:
summary: "Caddy server down on {{ $labels.instance }}"
description: "Caddy server is down for more than 5 minutes."
- alert: HighRequestLatency
expr: histogram_quantile(0.95, rate(caddy_http_request_duration_seconds_bucket[10m])) > 0.5
for: 2m
labels:
severity: warning
annotations:
summary: "High request latency on {{ $labels.instance }}"
description: "95th percentile of request latency is above 0.5 seconds for the last 2 minutes."
'' else "")
{
alert = "SystemdFailedUnits";
expr = "node_systemd_unit_state{state=\"failed\"} > 0";
for = "5m";
labels = { severity = "critical"; };
annotations = { summary = "Systemd has failed units on {{ $labels.instance }}"; description = "There are {{ $value }} failed units on {{ $labels.instance }}. Immediate attention required!"; };
}
{
alert = "HighLoadAverage";
expr = "node_load1 > 0.8 * count without (cpu) (node_cpu_seconds_total{mode=\"idle\"})";
for = "1m";
labels = { severity = "warning"; };
annotations = { summary = "High load average detected on {{ $labels.instance }}"; description = "The 1-minute load average ({{ $value }}) exceeds 80% the number of CPUs."; };
}
{
alert = "HighTransmitTraffic";
expr = "rate(node_network_transmit_bytes_total{device!=\"lo\"}[5m]) > 100000000";
for = "1m";
labels = { severity = "warning"; };
annotations = { summary = "High network transmit traffic on {{ $labels.instance }} ({{ $labels.device }})"; description = "The network interface {{ $labels.device }} on {{ $labels.instance }} is transmitting data at a rate exceeding 100 MB/s for the last 1 minute."; };
}
];
}) ++ (mkRule config.services.restic.server.enable {
name = "restic_alerts";
rules = [
{
alert = "ResticCheckFailed";
expr = "restic_check_success == 0";
for = "5m";
labels = { severity = "critical"; };
annotations = { summary = "Restic check failed (instance {{ $labels.instance }})"; description = "Restic check failed\\n VALUE = {{ $value }}\\n LABELS = {{ $labels }}"; };
}
{
alert = "ResticOutdatedBackup";
expr = "time() - restic_backup_timestamp > 518400";
for = "0m";
labels = { severity = "critical"; };
annotations = { summary = "Restic {{ $labels.client_hostname }} / {{ $labels.client_username }} backup is outdated"; description = "Restic backup is outdated\\n VALUE = {{ $value }}\\n LABELS = {{ $labels }}"; };
}
];
}) ++ (mkRule config.services.caddy.enable {
name = "caddy_alerts";
rules = [
{
alert = "UpstreamHealthy";
expr = "caddy_reverse_proxy_upstreams_healthy == 0";
for = "5m";
labels = { severity = "critical"; };
annotations = { summary = "Upstream {{ $labels.unstream }} not healthy"; };
}
{
alert = "HighRequestLatency";
expr = "histogram_quantile(0.95, rate(caddy_http_request_duration_seconds_bucket[10m])) > 0.5";
for = "2m";
labels = { severity = "warning"; };
annotations = { summary = "High request latency on {{ $labels.instance }}"; description = "95th percentile of request latency is above 0.5 seconds for the last 2 minutes."; };
}
];
});
})
];
};
}
@ -246,6 +233,13 @@ in
{ targets = [ "localhost:${toString config.services.gotosocial.settings.port}" ]; }
];
})
(mkIf config.services.ntfy-sh.enable {
job_name = "ntfy-sh";
static_configs = [
{ targets = [ "auth.xinyang.life" ]; }
];
})
];
}]);
}
]);
}