feat: deploy lightweight observability stack via Ansible

2026-03-02 01:33:41 +00:00
parent 3e020b46c6
commit b30977a158
5 changed files with 225 additions and 2 deletions
--- a/.gitea/workflows/deploy.yml
+++ b/.gitea/workflows/deploy.yml
@@ -226,6 +226,7 @@ jobs:
            -e "hcloud_token=${{ secrets.HCLOUD_TOKEN }}" \
            -e "tailscale_auth_key=${{ secrets.TAILSCALE_AUTH_KEY }}" \
            -e "tailscale_tailnet=${{ secrets.TAILSCALE_TAILNET }}" \
+            -e "grafana_admin_password=${{ secrets.GRAFANA_ADMIN_PASSWORD }}" \
            -e "cluster_name=k8s-cluster"
        env:
          ANSIBLE_HOST_KEY_CHECKING: "False"
@@ -236,6 +237,8 @@ jobs:
          ansible -i inventory.ini 'control_plane[0]' -m command -a "kubectl get nodes -o wide"
          ansible -i inventory.ini 'control_plane[0]' -m command -a "kubectl -n kube-system get pods -o wide"
          ansible -i inventory.ini 'control_plane[0]' -m command -a "kubectl get storageclass"
+          ansible -i inventory.ini 'control_plane[0]' -m command -a "kubectl -n observability get pods -o wide"
+          ansible -i inventory.ini 'control_plane[0]' -m command -a "kubectl -n observability get pvc"
        env:
          ANSIBLE_HOST_KEY_CHECKING: "False"

--- a/README.md
+++ b/README.md
@@ -10,7 +10,7 @@ Production-ready Kubernetes cluster on Hetzner Cloud using Terraform and Ansible
 | **Workers** | 4x CX33 |
 | **Total Cost** | €28.93/mo |
 | **K8s** | k3s (latest, HA) |
-| **Addons** | Hetzner CCM + CSI |
+| **Addons** | Hetzner CCM + CSI + Prometheus + Grafana + Loki |
 | **Access** | SSH/API restricted to Tailnet |
 | **Bootstrap** | Terraform + Ansible |

@@ -166,10 +166,40 @@ Set these in your Gitea repository settings (**Settings** → **Secrets** → **
 | `S3_BUCKET` | S3 bucket name (e.g., `k8s-terraform-state`) |
 | `TAILSCALE_AUTH_KEY` | Tailscale auth key for node bootstrap |
 | `TAILSCALE_TAILNET` | Tailnet domain (e.g., `yourtailnet.ts.net`) |
+| `GRAFANA_ADMIN_PASSWORD` | Optional admin password for Grafana (auto-generated if unset) |
 | `RUNNER_ALLOWED_CIDRS` | Optional CIDR list for CI runner access if you choose to pass it via tfvars/secrets |
 | `SSH_PUBLIC_KEY` | SSH public key content |
 | `SSH_PRIVATE_KEY` | SSH private key content |

+## Observability Stack
+
+The Ansible playbook deploys a lightweight observability stack in the `observability` namespace:
+
+- `kube-prometheus-stack` (Prometheus + Grafana)
+- `loki`
+- `promtail`
+
+Services are kept internal for tailnet-first access.
+
+### Access Grafana and Prometheus
+
+Run from a tailnet-connected machine:
+
+```bash
+export KUBECONFIG=$(pwd)/outputs/kubeconfig
+
+kubectl -n observability port-forward svc/kube-prometheus-stack-grafana 3000:80
+kubectl -n observability port-forward svc/kube-prometheus-stack-prometheus 9090:9090
+```
+
+Then open:
+
+- Grafana: http://127.0.0.1:3000
+- Prometheus: http://127.0.0.1:9090
+
+Grafana user: `admin`
+Grafana password: value of `GRAFANA_ADMIN_PASSWORD` secret (or the generated value shown by Ansible output)
+
 ## File Structure

 ```
@@ -192,7 +222,8 @@ Set these in your Gitea repository settings (**Settings** → **Secrets** → **
 │   │   ├── k3s-server/
 │   │   ├── k3s-agent/
 │   │   ├── ccm/
-│   │   └── csi/
+│   │   ├── csi/
+│   │   └── observability/
 │   └── ansible.cfg
 ├── .gitea/
 │   └── workflows/
--- a/ansible/roles/observability/defaults/main.yml
+++ b/ansible/roles/observability/defaults/main.yml
@@ -0,0 +1,16 @@
+---
+observability_namespace: "observability"
+
+prometheus_chart_version: "68.4.4"
+loki_chart_version: "6.24.0"
+promtail_chart_version: "6.16.6"
+
+grafana_admin_password: ""
+
+prometheus_storage_size: "10Gi"
+grafana_storage_size: "5Gi"
+loki_storage_size: "10Gi"
+
+prometheus_storage_class: "local-path"
+grafana_storage_class: "local-path"
+loki_storage_class: "local-path"
--- a/ansible/roles/observability/tasks/main.yml
+++ b/ansible/roles/observability/tasks/main.yml
@@ -0,0 +1,166 @@
+---
+- name: Check if Helm is installed
+  command: helm version --short
+  register: helm_check
+  changed_when: false
+  failed_when: false
+
+- name: Install Helm
+  shell: curl -fsSL https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
+  when: helm_check.rc != 0
+  changed_when: true
+
+- name: Ensure observability namespace exists
+  command: kubectl create namespace {{ observability_namespace }}
+  register: create_observability_ns
+  failed_when: create_observability_ns.rc != 0 and "AlreadyExists" not in create_observability_ns.stderr
+  changed_when: create_observability_ns.rc == 0
+
+- name: Set Grafana admin password
+  set_fact:
+    grafana_password_effective: "{{ grafana_admin_password if grafana_admin_password | length > 0 else lookup('password', '/dev/null length=32 chars=ascii_letters,digits') }}"
+
+- name: Write kube-prometheus-stack values
+  copy:
+    dest: /tmp/kube-prometheus-stack-values.yaml
+    mode: "0644"
+    content: |
+      grafana:
+        enabled: true
+        adminPassword: {{ grafana_password_effective }}
+        persistence:
+          enabled: true
+          storageClassName: {{ grafana_storage_class }}
+          size: {{ grafana_storage_size }}
+        service:
+          type: ClusterIP
+      prometheus:
+        prometheusSpec:
+          retention: 7d
+          storageSpec:
+            volumeClaimTemplate:
+              spec:
+                storageClassName: {{ prometheus_storage_class }}
+                accessModes: ["ReadWriteOnce"]
+                resources:
+                  requests:
+                    storage: {{ prometheus_storage_size }}
+      alertmanager:
+        enabled: false
+      kubeEtcd:
+        enabled: false
+      kubeControllerManager:
+        enabled: false
+      kubeScheduler:
+        enabled: false
+
+- name: Add Prometheus Helm repo
+  command: helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
+  register: add_prom_repo
+  failed_when: add_prom_repo.rc != 0 and "already exists" not in add_prom_repo.stderr
+  changed_when: add_prom_repo.rc == 0
+
+- name: Add Grafana Helm repo
+  command: helm repo add grafana https://grafana.github.io/helm-charts
+  register: add_grafana_repo
+  failed_when: add_grafana_repo.rc != 0 and "already exists" not in add_grafana_repo.stderr
+  changed_when: add_grafana_repo.rc == 0
+
+- name: Update Helm repos
+  command: helm repo update
+  changed_when: false
+
+- name: Install kube-prometheus-stack
+  command: >-
+    helm upgrade --install kube-prometheus-stack prometheus-community/kube-prometheus-stack
+    --namespace {{ observability_namespace }}
+    --version {{ prometheus_chart_version }}
+    --values /tmp/kube-prometheus-stack-values.yaml
+    --wait
+    --timeout 10m
+  changed_when: true
+
+- name: Write Loki values
+  copy:
+    dest: /tmp/loki-values.yaml
+    mode: "0644"
+    content: |
+      loki:
+        auth_enabled: false
+        commonConfig:
+          replication_factor: 1
+        storage:
+          type: filesystem
+      singleBinary:
+        replicas: 1
+        persistence:
+          enabled: true
+          storageClass: {{ loki_storage_class }}
+          size: {{ loki_storage_size }}
+      test:
+        enabled: false
+      monitoring:
+        selfMonitoring:
+          enabled: false
+        lokiCanary:
+          enabled: false
+
+- name: Install Loki
+  command: >-
+    helm upgrade --install loki grafana/loki
+    --namespace {{ observability_namespace }}
+    --version {{ loki_chart_version }}
+    --values /tmp/loki-values.yaml
+    --wait
+    --timeout 10m
+  changed_when: true
+
+- name: Write Promtail values
+  copy:
+    dest: /tmp/promtail-values.yaml
+    mode: "0644"
+    content: |
+      config:
+        clients:
+          - url: http://loki-gateway.{{ observability_namespace }}.svc.cluster.local/loki/api/v1/push
+
+- name: Install Promtail
+  command: >-
+    helm upgrade --install promtail grafana/promtail
+    --namespace {{ observability_namespace }}
+    --version {{ promtail_chart_version }}
+    --values /tmp/promtail-values.yaml
+    --wait
+    --timeout 10m
+  changed_when: true
+
+- name: Create Grafana Loki datasource
+  command: kubectl apply -f -
+  args:
+    stdin: |
+      apiVersion: v1
+      kind: ConfigMap
+      metadata:
+        name: grafana-datasource-loki
+        namespace: {{ observability_namespace }}
+        labels:
+          grafana_datasource: "1"
+      data:
+        loki-datasource.yaml: |
+          apiVersion: 1
+          datasources:
+            - name: Loki
+              type: loki
+              access: proxy
+              url: http://loki-gateway.{{ observability_namespace }}.svc.cluster.local
+              isDefault: false
+  changed_when: true
+
+- name: Show observability access details
+  debug:
+    msg: |
+      Observability stack deployed.
+      Namespace: {{ observability_namespace }}
+      Grafana (tailnet): kubectl -n {{ observability_namespace }} port-forward svc/kube-prometheus-stack-grafana 3000:80
+      Prometheus (tailnet): kubectl -n {{ observability_namespace }} port-forward svc/kube-prometheus-stack-prometheus 9090:9090
+      Grafana admin password: {{ grafana_password_effective }}
--- a/ansible/site.yml
+++ b/ansible/site.yml
@@ -89,6 +89,13 @@
  roles:
    - csi

+- name: Deploy observability stack
+  hosts: control_plane[0]
+  become: true
+
+  roles:
+    - observability
+
 - name: Finalize
  hosts: localhost
  connection: local