ada/infra
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Capture current Ansible control plane state

Browse Source 
Commit the accumulated infrastructure work that was living only in the
working tree: monitoring stack, emergency access/bot, gyro allocator,
grimmory, adguard, backup audit and the OpenCode agent definitions.

Also ignore Python bytecode, local archives and Nix/direnv artifacts.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GTocXkGUUazHdKKd3r9k71
This commit is contained in:
Dmitry
2026-08-26 21:39:28 +03:00
co-authored by Claude Opus 5
parent 4bafa7d09e
commit c676be81ec
126 changed files with 10583 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ansible/roles/monitoring_server/defaults/main.yml
+14
View File
@@ -0,0 +1,14 @@
---
monitoring_root: /opt/monitoring
monitoring_prometheus_retention: 30d
monitoring_prometheus_retention_size: 8GB
monitoring_grafana_admin_user: admin
monitoring_grafana_admin_password: "{{ lookup('env', 'MONITORING_GRAFANA_ADMIN_PASSWORD') }}"
monitoring_telegram_bot_token: "{{ lookup('env', 'MONITORING_TELEGRAM_BOT_TOKEN') }}"
monitoring_telegram_chat_id: "{{ lookup('env', 'MONITORING_TELEGRAM_CHAT_ID') }}"
monitoring_pve_api_user: "{{ lookup('env', 'MONITORING_PVE_API_USER') }}"
monitoring_pve_api_token_id: "{{ lookup('env', 'MONITORING_PVE_API_TOKEN_ID') }}"
monitoring_pve_api_token_secret: "{{ lookup('env', 'MONITORING_PVE_API_TOKEN_SECRET') }}"
monitoring_lan_cidr: 192.168.1.0/24
monitoring_openvpn_gateway_ip: 192.168.1.23
monitoring_docker_cidr: 172.16.0.0/12
ansible/roles/monitoring_server/files/dashboards/backups.json
+26
View File
@@ -0,0 +1,26 @@
{
"title": "Backups",
"uid": "homelab-backups",
"schemaVersion": 39,
"version": 1,
"panels": [
{
"type": "table",
"title": "Audit Result",
"gridPos": {"h": 10, "w": 12, "x": 0, "y": 0},
"targets": [{"expr": "homelab_backup_audit_success", "format": "table", "instant": true, "refId": "A"}]
},
{
"type": "timeseries",
"title": "Backup Age (Hours)",
"gridPos": {"h": 10, "w": 12, "x": 12, "y": 0},
"targets": [{"expr": "homelab_backup_audit_snapshot_age_hours", "legendFormat": "{{profile}} {{vmid}}", "refId": "A"}]
},
{
"type": "timeseries",
"title": "Audit Levels",
"gridPos": {"h": 10, "w": 24, "x": 0, "y": 10},
"targets": [{"expr": "homelab_backup_audit_level_success", "legendFormat": "{{profile}} {{level}}", "refId": "A"}]
}
]
}
ansible/roles/monitoring_server/files/dashboards/homelab-overview.json
+34
View File
@@ -0,0 +1,34 @@
{
"title": "HomeLab Overview",
"uid": "homelab-overview",
"schemaVersion": 39,
"version": 1,
"panels": [
{
"type": "stat",
"title": "Active Alerts",
"gridPos": {"h": 8, "w": 6, "x": 0, "y": 0},
"targets": [{"expr": "count(ALERTS{alertstate=\"firing\"})", "refId": "A"}],
"options": {"reduceOptions": {"calcs": ["lastNotNull"]}}
},
{
"type": "stat",
"title": "Successful Probes",
"gridPos": {"h": 8, "w": 6, "x": 6, "y": 0},
"targets": [{"expr": "sum(probe_success)", "refId": "A"}],
"options": {"reduceOptions": {"calcs": ["lastNotNull"]}}
},
{
"type": "timeseries",
"title": "Filesystem Free Space",
"gridPos": {"h": 10, "w": 12, "x": 0, "y": 8},
"targets": [{"expr": "node_filesystem_avail_bytes{fstype!~\"tmpfs|overlay\"}", "legendFormat": "{{instance}} {{mountpoint}}", "refId": "A"}]
},
{
"type": "timeseries",
"title": "Backup Audit Success",
"gridPos": {"h": 10, "w": 12, "x": 12, "y": 8},
"targets": [{"expr": "homelab_backup_audit_success", "legendFormat": "{{profile}} {{instance}}", "refId": "A"}]
}
]
}
ansible/roles/monitoring_server/files/dashboards/proxmox-storage.json
+26
View File
@@ -0,0 +1,26 @@
{
"title": "Proxmox and Storage",
"uid": "proxmox-storage",
"schemaVersion": 39,
"version": 1,
"panels": [
{
"type": "timeseries",
"title": "Node CPU Usage",
"gridPos": {"h": 9, "w": 12, "x": 0, "y": 0},
"targets": [{"expr": "1 - avg by(instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m]))", "legendFormat": "{{instance}}", "refId": "A"}]
},
{
"type": "timeseries",
"title": "Node Memory Available",
"gridPos": {"h": 9, "w": 12, "x": 12, "y": 0},
"targets": [{"expr": "node_memory_MemAvailable_bytes", "legendFormat": "{{instance}}", "refId": "A"}]
},
{
"type": "timeseries",
"title": "Disk Read and Write",
"gridPos": {"h": 9, "w": 24, "x": 0, "y": 9},
"targets": [{"expr": "rate(node_disk_read_bytes_total[5m])", "legendFormat": "read {{instance}} {{device}}", "refId": "A"}, {"expr": "rate(node_disk_written_bytes_total[5m])", "legendFormat": "write {{instance}} {{device}}", "refId": "B"}]
}
]
}
ansible/roles/monitoring_server/files/dashboards/services-network.json
+26
View File
@@ -0,0 +1,26 @@
{
"title": "Services and Network",
"uid": "services-network",
"schemaVersion": 39,
"version": 1,
"panels": [
{
"type": "table",
"title": "Probe State",
"gridPos": {"h": 10, "w": 12, "x": 0, "y": 0},
"targets": [{"expr": "probe_success", "format": "table", "instant": true, "refId": "A"}]
},
{
"type": "timeseries",
"title": "Probe Duration",
"gridPos": {"h": 10, "w": 12, "x": 12, "y": 0},
"targets": [{"expr": "probe_duration_seconds", "legendFormat": "{{job}} {{instance}}", "refId": "A"}]
},
{
"type": "timeseries",
"title": "TLS Certificate Remaining",
"gridPos": {"h": 10, "w": 24, "x": 0, "y": 10},
"targets": [{"expr": "(probe_ssl_earliest_cert_expiry - time()) / 86400", "legendFormat": "{{instance}}", "refId": "A"}]
}
]
}
ansible/roles/monitoring_server/files/grafana-dashboard-provider.yml
+11
View File
@@ -0,0 +1,11 @@
apiVersion: 1
providers:
- name: HomeLab
orgId: 1
folder: HomeLab
type: file
disableDeletion: true
editable: false
options:
path: /etc/grafana/dashboards
ansible/roles/monitoring_server/files/grafana-datasource.yml
+10
View File
@@ -0,0 +1,10 @@
apiVersion: 1
datasources:
- name: Prometheus
uid: prometheus
type: prometheus
access: proxy
url: http://prometheus:9090
isDefault: true
editable: false
ansible/roles/monitoring_server/handlers/main.yml
+9
View File
@@ -0,0 +1,9 @@
---
- name: reload systemd
ansible.builtin.systemd:
daemon_reload: true
- name: restart monitoring stack
ansible.builtin.systemd:
name: homelab-monitoring
state: restarted
ansible/roles/monitoring_server/tasks/main.yml
+233
View File
@@ -0,0 +1,233 @@
---
- name: Validate monitoring secrets
ansible.builtin.assert:
that:
- monitoring_telegram_bot_token | length > 0
- monitoring_telegram_bot_token != 'replace-me'
- monitoring_telegram_chat_id | length > 0
- monitoring_telegram_chat_id != 'replace-me'
- monitoring_pve_api_user | length > 0
- monitoring_pve_api_token_id | length > 0
- monitoring_pve_api_token_secret | length > 0
- monitoring_pve_api_token_secret != 'replace-me'
- monitoring_grafana_admin_password | length > 0
- monitoring_grafana_admin_password != 'change-me'
fail_msg: Load monitoring secrets from ignored ansible/.env or Ansible Vault before running this playbook.
no_log: true
- name: Install monitoring runtime packages
ansible.builtin.apt:
name:
- ca-certificates
- docker.io
- docker-compose
- ufw
state: present
update_cache: true
- name: Ensure Docker is enabled and running
ansible.builtin.systemd:
name: docker
enabled: true
state: started
- name: Allow SSH and Grafana access from the LAN
community.general.ufw:
rule: allow
port: "{{ item }}"
proto: tcp
src: "{{ monitoring_lan_cidr }}"
loop:
- "22"
- "3000"
- name: Allow Pushgateway only from the OpenVPN gateway
community.general.ufw:
rule: allow
port: "9091"
proto: tcp
src: "{{ monitoring_openvpn_gateway_ip }}"
- name: Allow local Prometheus container to scrape Node Exporter
community.general.ufw:
rule: allow
port: "9100"
proto: tcp
src: "{{ monitoring_docker_cidr }}"
- name: Enable monitoring LXC firewall
community.general.ufw:
state: enabled
policy: deny
direction: incoming
- name: Create monitoring directories
ansible.builtin.file:
path: "{{ item }}"
state: directory
owner: root
group: root
mode: "0755"
loop:
- "{{ monitoring_root }}"
- "{{ monitoring_root }}/prometheus"
- "{{ monitoring_root }}/alertmanager"
- "{{ monitoring_root }}/grafana"
- "{{ monitoring_root }}/grafana/provisioning"
- "{{ monitoring_root }}/grafana/provisioning/dashboards"
- "{{ monitoring_root }}/grafana/provisioning/datasources"
- "{{ monitoring_root }}/grafana/dashboards"
- "{{ monitoring_root }}/pve-exporter"
- name: Grant Prometheus access to its data directory
ansible.builtin.file:
path: "{{ monitoring_root }}/prometheus/data"
state: directory
owner: "65534"
group: "65534"
mode: "0755"
- name: Install monitoring compose definition
ansible.builtin.template:
src: compose.yml.j2
dest: "{{ monitoring_root }}/compose.yml"
owner: root
group: root
mode: "0600"
no_log: true
notify: restart monitoring stack
- name: Install Prometheus configuration
ansible.builtin.template:
src: prometheus.yml.j2
dest: "{{ monitoring_root }}/prometheus/prometheus.yml"
owner: root
group: root
mode: "0644"
notify: restart monitoring stack
- name: Install Prometheus alert rules
ansible.builtin.template:
src: alerts.yml.j2
dest: "{{ monitoring_root }}/prometheus/alerts.yml"
owner: root
group: root
mode: "0644"
notify: restart monitoring stack
- name: Install central Blackbox configuration
ansible.builtin.template:
src: blackbox.yml.j2
dest: "{{ monitoring_root }}/blackbox.yml"
owner: root
group: root
mode: "0644"
notify: restart monitoring stack
- name: Install Alertmanager configuration
ansible.builtin.template:
src: alertmanager.yml.j2
dest: "{{ monitoring_root }}/alertmanager/alertmanager.yml"
owner: root
group: root
mode: "0640"
no_log: true
notify: restart monitoring stack
- name: Install PVE exporter configuration
ansible.builtin.template:
src: pve.yml.j2
dest: "{{ monitoring_root }}/pve-exporter/pve.yml"
owner: root
group: root
mode: "0600"
no_log: true
notify: restart monitoring stack
- name: Provision Grafana datasource
ansible.builtin.copy:
src: grafana-datasource.yml
dest: "{{ monitoring_root }}/grafana/provisioning/datasources/prometheus.yml"
owner: root
group: root
mode: "0644"
notify: restart monitoring stack
- name: Provision Grafana dashboard provider
ansible.builtin.copy:
src: grafana-dashboard-provider.yml
dest: "{{ monitoring_root }}/grafana/provisioning/dashboards/homelab.yml"
owner: root
group: root
mode: "0644"
notify: restart monitoring stack
- name: Install Grafana dashboards
ansible.builtin.copy:
src: "dashboards/{{ item }}"
dest: "{{ monitoring_root }}/grafana/dashboards/{{ item }}"
owner: root
group: root
mode: "0644"
loop:
- homelab-overview.json
- proxmox-storage.json
- services-network.json
- backups.json
notify: restart monitoring stack
- name: Validate Docker Compose configuration
ansible.builtin.command: >-
docker-compose -f {{ monitoring_root }}/compose.yml config --quiet
changed_when: false
no_log: true
- name: Validate Prometheus configuration
ansible.builtin.command: >-
docker run --rm --network none
-v {{ monitoring_root }}/prometheus:/etc/prometheus:ro
--entrypoint promtool prom/prometheus:v3.2.1
check config /etc/prometheus/prometheus.yml
changed_when: false
- name: Validate Alertmanager configuration
ansible.builtin.command: >-
docker run --rm --network none
-v {{ monitoring_root }}/alertmanager:/etc/alertmanager:ro
--user 0:0
--entrypoint amtool prom/alertmanager:v0.28.0
check-config /etc/alertmanager/alertmanager.yml
changed_when: false
no_log: true
- name: Install monitoring systemd unit
ansible.builtin.copy:
dest: /etc/systemd/system/homelab-monitoring.service
owner: root
group: root
mode: "0644"
content: |
[Unit]
Description=HomeLab monitoring stack
Requires=docker.service
After=docker.service
[Service]
Type=oneshot
RemainAfterExit=yes
WorkingDirectory={{ monitoring_root }}
ExecStart=/usr/bin/docker-compose -f {{ monitoring_root }}/compose.yml up -d --remove-orphans
ExecStop=/usr/bin/docker-compose -f {{ monitoring_root }}/compose.yml down
[Install]
WantedBy=multi-user.target
notify:
- reload systemd
- restart monitoring stack
- name: Enable monitoring stack
ansible.builtin.systemd:
name: homelab-monitoring
daemon_reload: true
enabled: true
state: started
ansible/roles/monitoring_server/templates/alertmanager.yml.j2
+40
View File
@@ -0,0 +1,40 @@
global:
resolve_timeout: 5m
route:
receiver: telegram-warning
group_by: [alertname, instance]
group_wait: 30s
group_interval: 10m
repeat_interval: 6h
routes:
- matchers:
- severity="critical"
receiver: telegram-critical
repeat_interval: 2h
inhibit_rules:
- source_matchers:
- alertname="ExporterDown"
target_matchers:
- alertname="LanServiceUnavailable"
equal: [instance]
receivers:
- name: telegram-warning
telegram_configs:
- bot_token: "{{ monitoring_telegram_bot_token }}"
chat_id: {{ monitoring_telegram_chat_id }}
send_resolved: true
message: |-
[{{ "{{" }} .Status | toUpper {{ "}}" }}] {{ "{{" }} .CommonLabels.alertname {{ "}}" }}
{{ "{{" }} .CommonAnnotations.summary {{ "}}" }}
- name: telegram-critical
telegram_configs:
- bot_token: "{{ monitoring_telegram_bot_token }}"
chat_id: {{ monitoring_telegram_chat_id }}
send_resolved: true
message: |-
[{{ "{{" }} .Status | toUpper {{ "}}" }}] CRITICAL: {{ "{{" }} .CommonLabels.alertname {{ "}}" }}
{{ "{{" }} .CommonAnnotations.summary {{ "}}" }}
ansible/roles/monitoring_server/templates/alerts.yml.j2
+134
View File
@@ -0,0 +1,134 @@
groups:
- name: homelab-availability
rules:
- alert: ExporterDown
expr: up{job=~"node|smartctl|pve"} == 0
for: 10m
labels:
severity: warning
annotations:
summary: "Exporter unavailable: {{ '{{' }} $labels.job {{ '}}' }} {{ '{{' }} $labels.instance {{ '}}' }}"
- alert: CriticalServiceUnavailable
expr: probe_success{job="blackbox-vps"} == 0
for: 5m
labels:
severity: critical
annotations:
summary: "External or VPN check failed: {{ '{{' }} $labels.probe_name {{ '}}' }}"
- alert: RuVpsMonitoringStale
expr: time() - homelab_vps_probe_timestamp_seconds > 5 * 60
for: 5m
labels:
severity: critical
annotations:
summary: "ru-vps has not pushed monitoring metrics through OpenVPN"
- alert: RuVpsMonitoringMissing
expr: absent(homelab_vps_probe_timestamp_seconds{job="blackbox-vps"})
for: 10m
labels:
severity: critical
annotations:
summary: "ru-vps has no monitoring metrics in Pushgateway"
- alert: LanServiceUnavailable
expr: probe_success{job=~"blackbox-lan-http|blackbox-lan-tcp"} == 0
for: 10m
labels:
severity: warning
annotations:
summary: "LAN service unavailable: {{ '{{' }} $labels.instance {{ '}}' }}"
- alert: TLSCertificateExpiringSoon
expr: (probe_ssl_earliest_cert_expiry - time()) < 14 * 24 * 3600
for: 1h
labels:
severity: warning
annotations:
summary: "TLS certificate expires within 14 days: {{ '{{' }} $labels.instance {{ '}}' }}"
- name: homelab-capacity
rules:
- alert: FilesystemAlmostFull
expr: (node_filesystem_avail_bytes{fstype!~"tmpfs|overlay"} / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"}) < 0.15
for: 15m
labels:
severity: warning
annotations:
summary: "Filesystem is more than 85% full: {{ '{{' }} $labels.instance {{ '}}' }} {{ '{{' }} $labels.mountpoint {{ '}}' }}"
- alert: FilesystemWillFillSoon
expr: predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs|overlay"}[6h], 7 * 24 * 3600) < 0
for: 30m
labels:
severity: warning
annotations:
summary: "Filesystem may fill within seven days: {{ '{{' }} $labels.instance {{ '}}' }} {{ '{{' }} $labels.mountpoint {{ '}}' }}"
- alert: HostMemoryPressure
expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) < 0.1
for: 20m
labels:
severity: warning
annotations:
summary: "Memory pressure on {{ '{{' }} $labels.instance {{ '}}' }}"
- alert: SMARTDeviceFailed
expr: homelab_smart_device_healthy == 0
for: 5m
labels:
severity: critical
annotations:
summary: "SMART health check failed: {{ '{{' }} $labels.instance {{ '}}' }} {{ '{{' }} $labels.device {{ '}}' }}"
- alert: NVMECriticalWarning
expr: homelab_smart_nvme_critical_warning > 0
for: 5m
labels:
severity: critical
annotations:
summary: "NVMe critical warning: {{ '{{' }} $labels.instance {{ '}}' }} {{ '{{' }} $labels.device {{ '}}' }}"
- name: homelab-backups
rules:
- alert: BackupAuditFailed
expr: homelab_backup_audit_success == 0
for: 5m
labels:
severity: critical
annotations:
summary: "Backup audit failed: {{ '{{' }} $labels.profile {{ '}}' }} on {{ '{{' }} $labels.instance {{ '}}' }}"
- alert: BackupAuditStale
expr: time() - homelab_backup_audit_timestamp_seconds > 48 * 3600
for: 15m
labels:
severity: critical
annotations:
summary: "Backup audit result is stale: {{ '{{' }} $labels.profile {{ '}}' }} on {{ '{{' }} $labels.instance {{ '}}' }}"
- alert: BackupAuditMissing
expr: absent(homelab_backup_audit_timestamp_seconds{profile="pbs"}) or absent(homelab_backup_audit_timestamp_seconds{profile="gitea"}) or absent(homelab_backup_audit_timestamp_seconds{profile="vaultwarden"}) or absent(homelab_backup_audit_timestamp_seconds{profile="grimmory"})
for: 12h
labels:
severity: critical
annotations:
summary: "Expected backup audit metric has not been published"
- alert: ResticBackupTooOld
expr: homelab_backup_audit_snapshot_age_hours{profile=~"gitea|vaultwarden|grimmory"} > 36
for: 15m
labels:
severity: critical
annotations:
summary: "Restic backup is older than 36 hours: {{ '{{' }} $labels.profile {{ '}}' }}"
- alert: PBSBackupTooOld
expr: homelab_backup_audit_snapshot_age_hours{profile="pbs"} > 48
for: 15m
labels:
severity: critical
annotations:
summary: "PBS backup is older than 48 hours: VMID {{ '{{' }} $labels.vmid {{ '}}' }}"
ansible/roles/monitoring_server/templates/blackbox.yml.j2
+10
View File
@@ -0,0 +1,10 @@
modules:
http_2xx:
prober: http
timeout: 10s
http:
preferred_ip_protocol: ip4
valid_status_codes: [200, 301, 302]
tcp_connect:
prober: tcp
timeout: 10s
ansible/roles/monitoring_server/templates/compose.yml.j2
+63
View File
@@ -0,0 +1,63 @@
services:
prometheus:
image: prom/prometheus:v3.2.1
command:
- --config.file=/etc/prometheus/prometheus.yml
- --storage.tsdb.path=/prometheus
- --storage.tsdb.retention.time={{ monitoring_prometheus_retention }}
- --storage.tsdb.retention.size={{ monitoring_prometheus_retention_size }}
- --web.enable-lifecycle
volumes:
- ./prometheus:/etc/prometheus:ro
- ./prometheus/data:/prometheus
restart: unless-stopped
alertmanager:
image: prom/alertmanager:v0.28.0
user: "0:0"
command:
- --config.file=/etc/alertmanager/alertmanager.yml
- --storage.path=/alertmanager
volumes:
- ./alertmanager:/etc/alertmanager:ro
restart: unless-stopped
grafana:
image: grafana/grafana:11.5.1
environment:
GF_SECURITY_ADMIN_USER: {{ monitoring_grafana_admin_user | to_json }}
GF_SECURITY_ADMIN_PASSWORD: {{ monitoring_grafana_admin_password | to_json }}
GF_USERS_ALLOW_SIGN_UP: "false"
ports:
- "192.168.1.30:3000:3000"
volumes:
- ./grafana/provisioning:/etc/grafana/provisioning:ro
- ./grafana/dashboards:/etc/grafana/dashboards:ro
- grafana-data:/var/lib/grafana
restart: unless-stopped
blackbox-exporter:
image: prom/blackbox-exporter:v0.25.0
command:
- --config.file=/config/blackbox.yml
volumes:
- ./blackbox.yml:/config/blackbox.yml:ro
restart: unless-stopped
pve-exporter:
image: prompve/prometheus-pve-exporter:3.5.5
user: "0:0"
command:
- --config.file=/etc/pve-exporter/pve.yml
volumes:
- ./pve-exporter/pve.yml:/etc/pve-exporter/pve.yml:ro
restart: unless-stopped
pushgateway:
image: prom/pushgateway:v1.11.0
ports:
- "192.168.1.30:9091:9091"
restart: unless-stopped
volumes:
grafana-data:
ansible/roles/monitoring_server/templates/prometheus.yml.j2
+94
View File
@@ -0,0 +1,94 @@
global:
scrape_interval: 30s
evaluation_interval: 30s
alerting:
alertmanagers:
- static_configs:
- targets: ["alertmanager:9093"]
rule_files:
- /etc/prometheus/alerts.yml
scrape_configs:
- job_name: prometheus
static_configs:
- targets: ["localhost:9090"]
- job_name: node
static_configs:
- targets:
- "192.168.1.5:9100"
- "192.168.1.10:9100"
- "192.168.1.20:9100"
- "192.168.1.23:9100"
- "192.168.1.24:9100"
- "192.168.1.25:9100"
- "192.168.1.26:9100"
- "192.168.1.27:9100"
- "192.168.1.28:9100"
- "192.168.1.30:9100"
- "192.168.1.34:9100"
- job_name: pve
metrics_path: /pve
params:
module: [default]
static_configs:
- targets:
- "192.168.1.5"
- "192.168.1.10"
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: pve-exporter:9221
- job_name: blackbox-lan-http
metrics_path: /probe
params:
module: [http_2xx]
static_configs:
- targets:
- "http://192.168.1.24"
- "http://192.168.1.25:3000"
- "http://192.168.1.27:8080"
- "http://192.168.1.28"
- "http://192.168.1.34:6060/api/v1/healthcheck"
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: blackbox-exporter:9115
- target_label: probe_location
replacement: lan
- job_name: blackbox-lan-tcp
metrics_path: /probe
params:
module: [tcp_connect]
static_configs:
- targets:
- "192.168.1.5:8006"
- "192.168.1.10:8006"
- "192.168.1.20:8007"
- "192.168.1.25:2222"
- "192.168.1.27:9090"
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__
replacement: blackbox-exporter:9115
- target_label: probe_location
replacement: lan
- job_name: pushgateway
honor_labels: true
static_configs:
- targets: ["pushgateway:9091"]
ansible/roles/monitoring_server/templates/pve.yml.j2
+5
View File
@@ -0,0 +1,5 @@
default:
user: "{{ monitoring_pve_api_user }}"
token_name: "{{ monitoring_pve_api_token_id }}"
token_value: "{{ monitoring_pve_api_token_secret }}"
verify_ssl: false