Move prometheus roles to external file
Some checks failed
Run nix flake check / flake-check (push) Failing after 3m7s
Some checks failed
Run nix flake check / flake-check (push) Failing after 3m7s
This commit is contained in:
parent
071bf948a6
commit
fe2e87658a
SSH Key Fingerprint:
SHA256:KjAds8wHfD2mBYK2H815s/+ABcSdcIHUndwHEdSxml4
@ -41,194 +41,7 @@
|
||||
scrape_interval = "15s";
|
||||
};
|
||||
rules = [
|
||||
''
|
||||
groups:
|
||||
- name: common_rules
|
||||
rules:
|
||||
- alert: node_down
|
||||
expr: up == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Instance {{ $labels.instance }} down"
|
||||
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."
|
||||
- alert: low_disk_space
|
||||
expr: node_filesystem_free_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"} * 100 < 10
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Disk space low on {{ $labels.instance }}"
|
||||
description: "Disk space is low on {{ $labels.instance }}. Please check."
|
||||
- alert: high_cpu_load
|
||||
expr: max(node_load5{}) by (instance) > (count by (instance)(node_cpu_seconds_total{mode="idle"}) * 0.7)
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High CPU load on {{ $labels.instance }}"
|
||||
description: "CPU load is high on {{ $labels.instance }}. Please check."
|
||||
- alert: low_memory
|
||||
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Low available memory on {{ $labels.instance }}
|
||||
description: Node memory is filling up (< 10% left)\n VALUE = {{ $value }}
|
||||
- alert: oom_kill
|
||||
expr: increase(node_vmstat_oom_kill[1m]) > 0
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host OOM kill detected on {{ $labels.instance }}
|
||||
description: OOM kill detected
|
||||
- alert: nixos_upgrade_failed
|
||||
expr: node_systemd_unit_state{name="nixos-upgrade.service", state="failed"} == 1
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "NixOS upgrade failed on {{ $labels.instance }}"
|
||||
description: "NixOS upgrade failed on {{ $labels.instance }}"
|
||||
- alert: promtail_not_running
|
||||
expr: node_systemd_unit_state{name="promtail.service", state="active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Promtail service not running on {{ $labels.instance }}"
|
||||
description: "The promtail service has not been active on {{ $labels.instance }} for 5 minutes."
|
||||
- name: nameserver_rules
|
||||
rules:
|
||||
- alert: unbound_down
|
||||
expr: node_systemd_unit_state {instance =~ "ns.+", name = "unbound.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Unbound not running on {{ $labels.instance }}"
|
||||
description: "Unbound has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- alert: nsd_down
|
||||
expr: node_systemd_unit_state {instance =~ "ns.+", name = "nsd.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "NSD not running on {{ $labels.instance }}"
|
||||
description: "NSD has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- name: http-proxy_rules
|
||||
rules:
|
||||
- alert: caddy_down
|
||||
expr: node_systemd_unit_state {instance="http-proxy.home.2rjus.net:9100", name = "caddy.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Caddy not running on {{ $labels.instance }}"
|
||||
description: "Caddy has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- name: nats_rules
|
||||
rules:
|
||||
- alert: nats_down
|
||||
expr: node_systemd_unit_state {instance="nats1.home.2rjus.net:9100", name = "nats.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "NATS not running on {{ $labels.instance }}"
|
||||
description: "NATS has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- name: nix_cache_rules
|
||||
rules:
|
||||
- alert: build-flakes_service_failed
|
||||
expr: node_systemd_unit_state{instance="nix-cache01.home.2rjus.net:9100", name="build-flakes.service", state="failed"} == 1
|
||||
for: 0m
|
||||
keep_firing_for: 10m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "The build-flakes service on {{ $labels.instance }} has failed"
|
||||
description: "The build-flakes service on {{ $labels.instance }} has failed"
|
||||
- alert: harmonia_down
|
||||
expr: node_systemd_unit_state {instance="nix-cache01.home.2rjus.net:9100", name = "harmonia.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Harmonia not running on {{ $labels.instance }}"
|
||||
description: "Harmonia has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- alert: low_disk_space_nix
|
||||
expr: node_filesystem_free_bytes{instance="nix-cache01.home.2rjus.net:9100", mountpoint="/nix"} / node_filesystem_size_bytes{instance="nix-cache01.home.2rjus.net:9100", mountpoint="/nix"} * 100 < 10
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Disk space low on /nix for {{ $labels.instance }}"
|
||||
description: "Disk space is low on /nix for host {{ $labels.instance }}. Please check."
|
||||
- name: home_assistant_rules
|
||||
rules:
|
||||
- alert: home_assistant_down
|
||||
expr: node_systemd_unit_state {instance="ha1.home.2rjus.net:9100", name="home-assistant.service", state="active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Home assistant not running on {{ $labels.instance }}"
|
||||
description: "Home assistant has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- alert: zigbee2qmtt_down
|
||||
expr: node_systemd_unit_state {instance = "ha1.home.2rjus.net:9100", name = "zigbee2mqtt.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Zigbee2mqtt not running on {{ $labels.instance }}"
|
||||
description: "Zigbee2mqtt has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- alert: mosquitto_down
|
||||
expr: node_systemd_unit_state {instance = "ha1.home.2rjus.net:9100", name = "mosquitto.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Mosquitto not running on {{ $labels.instance }}"
|
||||
description: "Mosquitto has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- name: smartctl_rules
|
||||
rules:
|
||||
- alert: SmartCriticalWarning
|
||||
expr: smartctl_device_critical_warning > 0
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: SMART critical warning (instance {{ $labels.instance }})
|
||||
description: "Disk controller has critical warning on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
- alert: SmartMediaErrors
|
||||
expr: smartctl_device_media_errors > 0
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: SMART media errors (instance {{ $labels.instance }})
|
||||
description: "Disk controller detected media errors on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
- alert: SmartWearoutIndicator
|
||||
expr: smartctl_device_available_spare < smartctl_device_available_spare_threshold
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: SMART Wearout Indicator (instance {{ $labels.instance }})
|
||||
description: "Device is wearing out on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
- name: wireguard_rules
|
||||
rules:
|
||||
- alert: WireguardHandshake
|
||||
expr: (time() - wireguard_latest_handshake_seconds{instance="http-proxy.home.2rjus.net:9586",interface="wg0",public_key="32Rb13wExcy8uI92JTnFdiOfkv0mlQ6f181WA741DHs="}) > 300
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Wireguard handshake timeout on {{ $labels.instance }}"
|
||||
description: "Wireguard handshake timeout on {{ $labels.instance }} for more than 1 minutes."
|
||||
''
|
||||
(builtins.readFile ./rules.yml)
|
||||
];
|
||||
|
||||
scrapeConfigs = [
|
||||
|
||||
186
services/monitoring/rules.yml
Normal file
186
services/monitoring/rules.yml
Normal file
@ -0,0 +1,186 @@
|
||||
groups:
|
||||
- name: common_rules
|
||||
rules:
|
||||
- alert: node_down
|
||||
expr: up == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Instance {{ $labels.instance }} down"
|
||||
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."
|
||||
- alert: low_disk_space
|
||||
expr: node_filesystem_free_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"} * 100 < 10
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Disk space low on {{ $labels.instance }}"
|
||||
description: "Disk space is low on {{ $labels.instance }}. Please check."
|
||||
- alert: high_cpu_load
|
||||
expr: max(node_load5{}) by (instance) > (count by (instance)(node_cpu_seconds_total{mode="idle"}) * 0.7)
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High CPU load on {{ $labels.instance }}"
|
||||
description: "CPU load is high on {{ $labels.instance }}. Please check."
|
||||
- alert: low_memory
|
||||
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Low available memory on {{ $labels.instance }}
|
||||
description: Node memory is filling up (< 10% left)\n VALUE = {{ $value }}
|
||||
- alert: oom_kill
|
||||
expr: increase(node_vmstat_oom_kill[1m]) > 0
|
||||
for: 0m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Host OOM kill detected on {{ $labels.instance }}
|
||||
description: OOM kill detected
|
||||
- alert: nixos_upgrade_failed
|
||||
expr: node_systemd_unit_state{name="nixos-upgrade.service", state="failed"} == 1
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "NixOS upgrade failed on {{ $labels.instance }}"
|
||||
description: "NixOS upgrade failed on {{ $labels.instance }}"
|
||||
- alert: promtail_not_running
|
||||
expr: node_systemd_unit_state{name="promtail.service", state="active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Promtail service not running on {{ $labels.instance }}"
|
||||
description: "The promtail service has not been active on {{ $labels.instance }} for 5 minutes."
|
||||
- name: nameserver_rules
|
||||
rules:
|
||||
- alert: unbound_down
|
||||
expr: node_systemd_unit_state {instance =~ "ns.+", name = "unbound.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Unbound not running on {{ $labels.instance }}"
|
||||
description: "Unbound has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- alert: nsd_down
|
||||
expr: node_systemd_unit_state {instance =~ "ns.+", name = "nsd.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "NSD not running on {{ $labels.instance }}"
|
||||
description: "NSD has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- name: http-proxy_rules
|
||||
rules:
|
||||
- alert: caddy_down
|
||||
expr: node_systemd_unit_state {instance="http-proxy.home.2rjus.net:9100", name = "caddy.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Caddy not running on {{ $labels.instance }}"
|
||||
description: "Caddy has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- name: nats_rules
|
||||
rules:
|
||||
- alert: nats_down
|
||||
expr: node_systemd_unit_state {instance="nats1.home.2rjus.net:9100", name = "nats.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "NATS not running on {{ $labels.instance }}"
|
||||
description: "NATS has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- name: nix_cache_rules
|
||||
rules:
|
||||
- alert: build-flakes_service_failed
|
||||
expr: node_systemd_unit_state{instance="nix-cache01.home.2rjus.net:9100", name="build-flakes.service", state="failed"} == 1
|
||||
for: 0m
|
||||
keep_firing_for: 10m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "The build-flakes service on {{ $labels.instance }} has failed"
|
||||
description: "The build-flakes service on {{ $labels.instance }} has failed"
|
||||
- alert: harmonia_down
|
||||
expr: node_systemd_unit_state {instance="nix-cache01.home.2rjus.net:9100", name = "harmonia.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Harmonia not running on {{ $labels.instance }}"
|
||||
description: "Harmonia has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- alert: low_disk_space_nix
|
||||
expr: node_filesystem_free_bytes{instance="nix-cache01.home.2rjus.net:9100", mountpoint="/nix"} / node_filesystem_size_bytes{instance="nix-cache01.home.2rjus.net:9100", mountpoint="/nix"} * 100 < 10
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Disk space low on /nix for {{ $labels.instance }}"
|
||||
description: "Disk space is low on /nix for host {{ $labels.instance }}. Please check."
|
||||
- name: home_assistant_rules
|
||||
rules:
|
||||
- alert: home_assistant_down
|
||||
expr: node_systemd_unit_state {instance="ha1.home.2rjus.net:9100", name="home-assistant.service", state="active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Home assistant not running on {{ $labels.instance }}"
|
||||
description: "Home assistant has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- alert: zigbee2qmtt_down
|
||||
expr: node_systemd_unit_state {instance = "ha1.home.2rjus.net:9100", name = "zigbee2mqtt.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Zigbee2mqtt not running on {{ $labels.instance }}"
|
||||
description: "Zigbee2mqtt has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- alert: mosquitto_down
|
||||
expr: node_systemd_unit_state {instance = "ha1.home.2rjus.net:9100", name = "mosquitto.service", state = "active"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Mosquitto not running on {{ $labels.instance }}"
|
||||
description: "Mosquitto has been down on {{ $labels.instance }} more than 5 minutes."
|
||||
- name: smartctl_rules
|
||||
rules:
|
||||
- alert: SmartCriticalWarning
|
||||
expr: smartctl_device_critical_warning > 0
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: SMART critical warning (instance {{ $labels.instance }})
|
||||
description: "Disk controller has critical warning on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
- alert: SmartMediaErrors
|
||||
expr: smartctl_device_media_errors > 0
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: SMART media errors (instance {{ $labels.instance }})
|
||||
description: "Disk controller detected media errors on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
- alert: SmartWearoutIndicator
|
||||
expr: smartctl_device_available_spare < smartctl_device_available_spare_threshold
|
||||
for: 0m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: SMART Wearout Indicator (instance {{ $labels.instance }})
|
||||
description: "Device is wearing out on {{ $labels.instance }} drive {{ $labels.device }})\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
- name: wireguard_rules
|
||||
rules:
|
||||
- alert: WireguardHandshake
|
||||
expr: (time() - wireguard_latest_handshake_seconds{instance="http-proxy.home.2rjus.net:9586",interface="wg0",public_key="32Rb13wExcy8uI92JTnFdiOfkv0mlQ6f181WA741DHs="}) > 300
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Wireguard handshake timeout on {{ $labels.instance }}"
|
||||
description: "Wireguard handshake timeout on {{ $labels.instance }} for more than 1 minutes."
|
||||
Loading…
x
Reference in New Issue
Block a user