initial: yandex-prod gitops infrastructure
Gitea + ArgoCD + cert-manager + Traefik + CNPG + monitoring + loki + alloy Matrix homeservers for mrt0rtikize.ru, t0rt1k.tech, roglog.space
This commit is contained in:
Alexander Rogov
2
.gitignore
vendored
Normal file
2
.gitignore
vendored
Normal file
@@ -0,0 +1,2 @@
|
||||
backups/
|
||||
kubeconfig
|
||||
308
BOOTSTRAP.md
Normal file
308
BOOTSTRAP.md
Normal file
@@ -0,0 +1,308 @@
|
||||
# Yandex Cloud Production Cluster — Bootstrap Guide
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- [ ] `kubeconfig` file placed at `~/infra/yandex-prod/kubeconfig`
|
||||
- [ ] `kubectl` context pointing to the new `yc-prod` cluster
|
||||
- [ ] Domaster `prod.t01tt.tech` DNS managed (can be updated later in Phase 5)
|
||||
- [ ] `git` and `helm` installed locally
|
||||
|
||||
---
|
||||
|
||||
## Phase 0: Verify Cluster Access
|
||||
|
||||
```bash
|
||||
export KUBECONFIG=~/infra/yandex-prod/kubeconfig
|
||||
|
||||
kubectl get nodes
|
||||
# Expected: 3 nodes Ready, 2CPU/8GB each
|
||||
|
||||
kubectl get sc
|
||||
# Expected: yc-network-hdd (default), yc-network-ssd, yc-network-nvme, ...
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 1: Bootstrap Gitea (internal access only)
|
||||
|
||||
Gitea hosts the Git repo that ArgoCD reads. Deploy it first, but without ingress — we access it via port-forward.
|
||||
|
||||
```bash
|
||||
kubectl apply -f bootstrap/gitea/namespace.yaml
|
||||
kubectl apply -f bootstrap/gitea/pvc.yaml
|
||||
kubectl apply -f bootstrap/gitea/deployment.yaml
|
||||
kubectl apply -f bootstrap/gitea/service.yaml
|
||||
# NOTE: Do NOT apply ingress.yaml yet — no Traefik or cert-manager exists
|
||||
```
|
||||
|
||||
Wait for Gitea to be ready, then port-forward and configure:
|
||||
|
||||
```bash
|
||||
kubectl wait deploy/gitea -n gitea --for=condition=available --timeout=120s
|
||||
|
||||
# Port-forward in a separate terminal:
|
||||
kubectl port-forward svc/gitea 3000:3000 -n gitea
|
||||
```
|
||||
|
||||
1. Open **http://localhost:3000** in a browser
|
||||
2. Fill out the install form:
|
||||
- Database: **SQLite3** (default)
|
||||
- Site Title: **Gitea**
|
||||
- Domaster: **git.prod.t01tt.tech**
|
||||
- Application URL: **https://git.prod.t01tt.tech**
|
||||
- Create admin account (username/password/email — save these)
|
||||
3. Click "Install Gitea"
|
||||
4. Create a new repository: **`master`** (must be **public**, owned by admin)
|
||||
5. Close the port-forward (Ctrl+C)
|
||||
|
||||
---
|
||||
|
||||
## Phase 2: Push Repository to Gitea
|
||||
|
||||
```bash
|
||||
cd ~/infra/yandex-prod
|
||||
|
||||
git init
|
||||
git remote add origin http://localhost:3000/admin/master.git
|
||||
# Or, once Gitea ingress works later, use:
|
||||
# git remote add origin https://git.prod.t01tt.tech/admin/master.git
|
||||
|
||||
git add -A
|
||||
git commit -m "initial bootstrap: infrastructure manifests"
|
||||
git push -u origin master
|
||||
# Enter Gitea admin credentials when prompted
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 3: Install ArgoCD (internal access only)
|
||||
|
||||
```bash
|
||||
bash bootstrap/argocd/install.sh
|
||||
# Saves the admin password — copy it
|
||||
```
|
||||
|
||||
Add the Gitea repository to ArgoCD:
|
||||
|
||||
```bash
|
||||
# Via port-forward:
|
||||
kubectl port-forward svc/argocd-server 8080:80 -n argocd &
|
||||
sleep 2
|
||||
|
||||
# Login and add repo:
|
||||
ARGOCD_PASS=$(kubectl -n argocd get secret argocd-initial-admin-secret -o jsonpath="{.data.password}" | base64 -d)
|
||||
argocd login localhost:8080 --username admin --password "${ARGOCD_PASS}" --insecure
|
||||
|
||||
argocd repo add http://gitea.gitea.svc.cluster.local:3000/admin/master.git \
|
||||
--name yandex-prod \
|
||||
--type git
|
||||
```
|
||||
|
||||
Deploy the root app:
|
||||
|
||||
```bash
|
||||
kubectl apply -f argocd/app-of-apps.yaml
|
||||
```
|
||||
|
||||
ArgoCD will now sync child apps according to their sync waves. You can watch progress:
|
||||
|
||||
```bash
|
||||
argocd app list
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 4: Let the Sync Waves Run
|
||||
|
||||
Sync order (automated by ArgoCD via `argocd.argoproj.io/sync-wave` annotations):
|
||||
|
||||
| Wave | App | What happens |
|
||||
|------|-----|-------------|
|
||||
| **-2** | `traefik` | DaemonSet deployed on all 3 nodes. NLB created → external IP provisioned |
|
||||
| **-1** | `cert-manager` | cert-manager operator + CRDs installed |
|
||||
| **0** | `cert-manager-issuers` | `letsencrypt-production` + `letsencrypt-staging` ClusterIssuers created |
|
||||
| **0** | `monitoring` | VM k8s-stack (metrics) + Grafana ingress deployed |
|
||||
| **0** | `loki` | Loki single-binary deployed |
|
||||
| **0** | `cnpg-operator` | CloudNativePG operator installed |
|
||||
| **1** | `cnpg-cluster` | `shared-pg` 3-node PostgreSQL cluster + 8 databases created |
|
||||
|
||||
**Verify Traefik IP:**
|
||||
|
||||
```bash
|
||||
kubectl get svc traefik -n traefik -w
|
||||
# Wait for EXTERNAL-IP to appear. Example output:
|
||||
# traefik LoadBalancer 10.x.x.x <pending> 80:3xxxx/TCP,443:3xxxx/TCP 30s
|
||||
# traefik LoadBalancer 10.x.x.x 158.160.x.x 80:3xxxx/TCP,443:3xxxx/TCP 60s
|
||||
```
|
||||
|
||||
Take the EXTERNAL-IP — this is your NLB IP. You'll need it in Phase 5.
|
||||
|
||||
**Verify state:**
|
||||
|
||||
```bash
|
||||
kubectl get pods -A
|
||||
# Expected running pods:
|
||||
# traefik: traefik-xxxxx (3 pods, DaemonSet)
|
||||
# cert-manager: cert-manager-xxxxx, cert-manager-cainjector-xxxxx, cert-manager-webhook-xxxxx
|
||||
# metrics: vm-k8s-stack-* pods (vmsingle, alertmanager, grafana, node-exporter, kube-state-metrics, vmagent)
|
||||
# metrics: loki-0
|
||||
# cnpg-system: cnpg-operator-xxxxx
|
||||
# cnpg: shared-pg-1, shared-pg-2, shared-pg-3 (may take a minute to start)
|
||||
|
||||
kubectl get clusterissuer
|
||||
# Expected: letsencrypt-production (True), letsencrypt-staging (True)
|
||||
|
||||
kubectl get cluster -n cnpg
|
||||
# Expected: shared-pg (3/3 instances ready)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 5: DNS + Expose Gitea & ArgoCD
|
||||
|
||||
Now that Traefik has an external IP and cert-manager is running, we can:
|
||||
1. Point DNS at the NLB IP
|
||||
2. Create the Gitea and ArgoCD ingress resources (with TLS)
|
||||
|
||||
### 5.1 Update DNS
|
||||
|
||||
Point the following records to the Traefik NLB IP (from Phase 4):
|
||||
|
||||
```
|
||||
git.prod.t01tt.tech → <NLB-IP>
|
||||
argocd.prod.t01tt.tech → <NLB-IP>
|
||||
grafana.prod.t01tt.tech → <NLB-IP>
|
||||
```
|
||||
|
||||
Also create a wildcard for future hosts:
|
||||
```
|
||||
*.prod.t01tt.tech → <NLB-IP>
|
||||
```
|
||||
|
||||
### 5.2 Apply Ingresses
|
||||
|
||||
```bash
|
||||
kubectl apply -f bootstrap/gitea/ingress.yaml
|
||||
kubectl apply -f bootstrap/argocd/ingress.yaml
|
||||
```
|
||||
|
||||
### 5.3 Wait for TLS Certificates
|
||||
|
||||
```bash
|
||||
kubectl get certificate -A -w
|
||||
# Wait for all to show Ready=True:
|
||||
# gitea gitea-tls True
|
||||
# argocd argocd-tls True
|
||||
# metrics grafana-tls True
|
||||
```
|
||||
|
||||
**Troubleshooting:** If certificates are stuck in `Pending`:
|
||||
- Check DNS resolves: `dig git.prod.t01tt.tech` — must return the NLB IP
|
||||
- Check cert-manager logs: `kubectl logs -n cert-manager deploy/cert-manager`
|
||||
- Check challenge: `kubectl get challenges -A`
|
||||
|
||||
---
|
||||
|
||||
## Phase 6: Verify Everything
|
||||
|
||||
### Gitea
|
||||
```
|
||||
https://git.prod.t01tt.tech
|
||||
```
|
||||
Login with the admin credentials from Phase 1. Verify the `yandex-prod` repo exists.
|
||||
|
||||
### ArgoCD
|
||||
```
|
||||
https://argocd.prod.t01tt.tech
|
||||
```
|
||||
Login with `admin` + password from Phase 3. All apps should show green (`Synced` + `Healthy`).
|
||||
|
||||
The Ingress health may show `Healthy` immediately (by design — see `values.yaml` customization).
|
||||
|
||||
### Grafana
|
||||
```
|
||||
https://grafana.prod.t01tt.tech
|
||||
```
|
||||
Login with `admin` / `change-me`. Check that VM k8s-stack dashboards are available.
|
||||
|
||||
### PostgreSQL
|
||||
```bash
|
||||
kubectl get databases -n cnpg
|
||||
# Expected: 8 Database resources, one per homeserver
|
||||
|
||||
kubectl get pods -n cnpg
|
||||
# Expected: shared-pg-1, shared-pg-2, shared-pg-3 (Running)
|
||||
```
|
||||
|
||||
### ArgoCD Repo Connection
|
||||
```bash
|
||||
argocd repo list
|
||||
# Expected: the Gitea repo with status "Successful"
|
||||
```
|
||||
|
||||
If not connected, re-add via ArgoCD CLI:
|
||||
```bash
|
||||
argocd repo add http://gitea.gitea.svc.cluster.local:3000/admin/master.git \
|
||||
--name yandex-prod \
|
||||
--type git
|
||||
```
|
||||
|
||||
Or in the ArgoCD UI: Settings → Repositories → Connect repo.
|
||||
|
||||
---
|
||||
|
||||
## Phase 7: Post-Bootstrap Checklist
|
||||
|
||||
- [ ] All ArgoCD apps `Synced` and `Healthy`
|
||||
- [ ] `https://git.prod.t01tt.tech` — Gitea accessible, SSL valid
|
||||
- [ ] `https://argocd.prod.t01tt.tech` — ArgoCD accessible, SSL valid
|
||||
- [ ] `https://grafana.prod.t01tt.tech` — Grafana accessible, SSL valid, datasources working
|
||||
- [ ] `kubectl get pv` — PVCs bound for all stateful components
|
||||
- [ ] CNPG `shared-pg` cluster status: `kubectl get cluster -n cnpg` shows 3/3 ready
|
||||
- [ ] Certificates all `Ready`: `kubectl get certificate -A | grep False` (should return nothing)
|
||||
|
||||
---
|
||||
|
||||
## Quick Reference: Service URLs
|
||||
|
||||
| Service | URL | Auth |
|
||||
|---------|-----|------|
|
||||
| Gitea | `https://git.prod.t01tt.tech` | Admin user from Phase 1 |
|
||||
| ArgoCD | `https://argocd.prod.t01tt.tech` | `admin` / password from Phase 3 |
|
||||
| Grafana | `https://grafana.prod.t01tt.tech` | `admin` / `change-me` |
|
||||
| Traefik dashboard | `kubectl port-forward -n traefik daemonset/traefik 9000:9000` | Internal only |
|
||||
|
||||
---
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Traefik NLB stuck in `<pending>`
|
||||
Yandex Cloud NLB provisioning can take a few minutes. Check:
|
||||
```bash
|
||||
kubectl describe svc traefik -n traefik
|
||||
```
|
||||
If it's stuck for >5 minutes, verify the Yandex annotations are correct.
|
||||
|
||||
### Certificates stuck in `Pending`
|
||||
1. Verify DNS: `dig git.prod.t01tt.tech` → must return the NLB IP
|
||||
2. Check Traefik is listening: `curl -k https://<NLB-IP> -H "Host: git.prod.t01tt.tech"` → should return 404 (expected, just verifying Traefik responds)
|
||||
3. Check orders: `kubectl get orders -A`
|
||||
|
||||
### CNPG cluster not becoming ready
|
||||
```bash
|
||||
kubectl describe cluster shared-pg -n cnpg
|
||||
kubectl logs -n cnpg-system deploy/cnpg-controller-manager
|
||||
```
|
||||
Common issue: pods can't schedule due to `podAntiAffinityType: required`. Ensure all 3 nodes exist and PVCs can bind.
|
||||
|
||||
### Gitea UI shows wrong URL after first login
|
||||
Gitea caches the ROOT_URL from the `deployment.yaml` env vars. If you change the domaster, update:
|
||||
```bash
|
||||
kubectl set env deploy/gitea -n gitea \
|
||||
GITEA__server__DOMAIN=git.prod.t01tt.tech \
|
||||
GITEA__server__ROOT_URL=https://git.prod.t01tt.tech
|
||||
kubectl rollout restart deploy/gitea -n gitea
|
||||
```
|
||||
|
||||
### ArgoCD apps showing "Unknown" health
|
||||
This is normal for Ingress resources — the custom health check in `bootstrap/argocd/values.yaml` marks all Ingresses as `Healthy` once synced. For other resources, check the app details in ArgoCD UI for the specific error.
|
||||
521
PLAN.md
Normal file
521
PLAN.md
Normal file
@@ -0,0 +1,521 @@
|
||||
# Yandex Cloud Production Matrix Cluster — Migration Plan
|
||||
|
||||
## 0. Current State
|
||||
|
||||
### Existing Clusters
|
||||
|
||||
| Cluster | Type | Nodes | Purpose |
|
||||
|---------|------|-------|---------|
|
||||
| k3s homelab (`~/infra/k3s`) | self-managed k3s | 2 (oracle, sentinel) | GitOps-based, hosts test `mrt0rtikize.ru` ESS Community |
|
||||
| Yandex Cloud prod (`kubectl` default) | managed k8s v1.32.1 | 3x 2CPU/6GB | Manual Helm, hosts 3 production Matrix instances |
|
||||
|
||||
### Current Prod Load (Yandex Cloud)
|
||||
|
||||
| Node | CPU | RAM | What runs there |
|
||||
|------|-----|-----|-----------------|
|
||||
| `ofem` | 6% | 32% | element-web x3, element-call x2, well-known x3, alloy, cert-manager-cainjector |
|
||||
| `uzig` | 19% | **94%** | Grafana(682Mi) + Prometheus(499Mi) + VictoriaMetrics(327Mi) + Synapse-t0rt1k(582Mi) + 3x PostgreSQL + Alertmanager + 3x Redis + 3x LiveKit SFU + Traefik |
|
||||
| `efur` | 10% | 51% | Synapse-roglog(134Mi) + Loki(304Mi) + 2x mas-postgresql + cert-manager + coredns |
|
||||
|
||||
Key issue: **uzig at 94% RAM** — monitoring stack competes with busiest Synapse on same node.
|
||||
|
||||
### Prod Matrix Instances
|
||||
|
||||
| | `matrix-t0rt1k` | `matrix-roglog` |
|
||||
|---|---|---|---|
|
||||
| Domain | `t0rt1k.tech` | `roglog.space` |
|
||||
| Age | 87d | 82d | 82d |
|
||||
| Synapse RAM | 582Mi | 134Mi | 137Mi |
|
||||
| Storage | 10+8+1 Gi (HDD) | 10+8+1 Gi (HDD) | 10+8+1 Gi (HDD) |
|
||||
| Helm chart | `matrix-2.9.17` (NOT ESS) | same | same |
|
||||
| MAS migration | Failed (`syn2mas` job) | OK | OK |
|
||||
| Components per instance | Synapse, Element Web, Element Call, LiveKit SFU + Redis + JWT, MAS, 2x PostgreSQL, well-known | same | same |
|
||||
| Ingress | Traefik, `158.160.164.95` | same LB | same LB |
|
||||
| TLS | cert-manager + `letsencrypt-production` | same | same |
|
||||
|
||||
### Test Instance (k3s homelab)
|
||||
|
||||
| Property | Value |
|
||||
|----------|-------|
|
||||
| Domain | `mrt0rtikize.ru` |
|
||||
| Chart | ESS Community (`oci://ghcr.io/element-hq/ess-helm/matrix-stack` v26.6.1) |
|
||||
| Namespace | `matrix-mrt0rtikize` |
|
||||
| Components | Synapse, MAS, Element Web, Element Admin, Matrix RTC, Hookshot, HAProxy |
|
||||
| PostgreSQL | Built-in (chart-managed) |
|
||||
| Storage | Longhorn |
|
||||
| GitOps | ArgoCD, repo at `gitea.mrt0rtikize.ru` |
|
||||
|
||||
---
|
||||
|
||||
## 1. New Cluster Architecture
|
||||
|
||||
### 1.1 Platform
|
||||
|
||||
- Yandex Cloud Managed Kubernetes (new cluster)
|
||||
- Ability to add external nodes in future (supported experimentally, not needed now)
|
||||
- Managed control plane, self-managed worker nodes
|
||||
|
||||
### 1.2 GitOps Foundation
|
||||
|
||||
| Component | How | Notes |
|
||||
|-----------|-----|-------|
|
||||
| Gitea | `kubectl apply` from `bootstrap/gitea/` | Self-hosted git server, deployed first (before ArgoCD) |
|
||||
| ArgoCD | `helm install` via `bootstrap/argocd/install.sh` | Installed with `--insecure` (same as k3s), points to Gitea |
|
||||
| Root App | `argocd/app-of-apps.yaml` | Scans `argocd/apps/*.yaml` recursively, deploys everything else |
|
||||
|
||||
### 1.3 Infrastructure Components
|
||||
|
||||
| Component | Type | Values | Notes |
|
||||
|-----------|------|--------|-------|
|
||||
| cert-manager | ArgoCD Helm app | `installCRDs: true`, `ClusterIssuer: letsencrypt-production` | TLS for all ingresses |
|
||||
| CloudNativePG Operator | ArgoCD Helm app | `cluster.instances: 3`, `storageClass: yc-network-ssd`, `size: 50Gi`, `podAntiAffinityType: required` | HA PostgreSQL for all Matrix instances |
|
||||
| Prometheus Stack | ArgoCD Helm app | Ported from `k3s/manifests/metrics/kube-prometheus-stack-values.yaml`, remoteWrite to VictoriaMetrics | Monitoring + Alertmanager |
|
||||
| VictoriaMetrics | ArgoCD Helm app | Ported from `k3s/manifests/metrics/victoria-metrics-single-values.yaml` | Long-term metrics storage |
|
||||
| Loki | ArgoCD Helm app | Log aggregation | — |
|
||||
| Alloy/Grafana Alloy | ArgoCD Helm app | Agent for metrics/logs forwarding | — |
|
||||
| Traefik | Managed by Yandex (or DaemonSet) | Cluster's built-in ingress controller | LB external IP provisioned by Yandex Cloud |
|
||||
|
||||
### 1.4 ESS Instances
|
||||
|
||||
Each Matrix homeserver is a separate ArgoCD Application referencing the ESS chart:
|
||||
|
||||
```
|
||||
argocd/apps/
|
||||
├── matrix-mrt0rtikize.yaml (first, test migration)
|
||||
├── matrix-t0rt1k.yaml (production, after procedure proven)
|
||||
└── matrix-roglog.yaml
|
||||
```
|
||||
|
||||
Each uses the **shared CloudNativePG cluster** (not built-in PostgreSQL).
|
||||
|
||||
### 1.5 Directory Structure
|
||||
|
||||
```
|
||||
~/infra/yandex-prod/
|
||||
├── bootstrap/
|
||||
│ ├── gitea/
|
||||
│ │ ├── namespace.yaml
|
||||
│ │ ├── deployment.yaml
|
||||
│ │ ├── service.yaml
|
||||
│ │ ├── ingress.yaml
|
||||
│ │ └── pvc.yaml
|
||||
│ └── argocd/
|
||||
│ ├── install.sh
|
||||
│ └── values.yaml
|
||||
├── argocd/
|
||||
│ ├── app-of-apps.yaml
|
||||
│ └── apps/
|
||||
│ ├── cert-manager.yaml
|
||||
│ ├── cnpg-operator.yaml
|
||||
│ ├── cnpg-cluster.yaml
|
||||
│ ├── monitoring.yaml
|
||||
│ ├── loki.yaml
|
||||
│ ├── matrix-mrt0rtikize.yaml
|
||||
│ ├── matrix-t0rt1k.yaml
|
||||
│ └── matrix-roglog.yaml
|
||||
└── manifests/
|
||||
├── cnpg/
|
||||
│ ├── namespace.yaml
|
||||
│ ├── databases.yaml # Database CRs per homeserver
|
||||
│ └── secrets.yaml # PG credentials per homeserver (or generated)
|
||||
└── matrix-mrt0rtikize/
|
||||
└── (supplemental manifests, if any)
|
||||
```
|
||||
|
||||
### 1.6 CloudNativePG Architecture
|
||||
|
||||
```
|
||||
CloudNativePG Cluster "shared-pg" (namespace: cnpg, 3 instances)
|
||||
├── Instance 1 (node A)
|
||||
├── Instance 2 (node B) ← anti-affinity ensures spread
|
||||
└── Instance 3 (node C)
|
||||
|
||||
Databases (one pair per homeserver):
|
||||
├── synapse_mrt0rtikize (owner: synapse_mrt0rtikize)
|
||||
├── mas_mrt0rtikize (owner: mas_mrt0rtikize)
|
||||
├── synapse_t0rt1k (owner: synapse_t0rt1k)
|
||||
├── mas_t0rt1k (owner: mas_t0rt1k)
|
||||
├── synapse_roglog (owner: synapse_roglog)
|
||||
├── mas_roglog (owner: mas_roglog)
|
||||
|
||||
Service: shared-pg-rw.cnpg.svc.cluster.local:5432 (primary, read-write)
|
||||
shared-pg-ro.cnpg.svc.cluster.local:5432 (replicas, read-only)
|
||||
```
|
||||
|
||||
Each homeserver has a dedicated PostgreSQL role and database within the same cluster.
|
||||
Databases and roles are created via CNPG `Database` CRs (see `manifests/cnpg/databases.yaml`).
|
||||
|
||||
Credentials are stored in per-homeserver Kubernetes Secrets (`manifests/cnpg/secrets.yaml`),
|
||||
referenced by ESS via `existingSecret` / `existingSecretKey`.
|
||||
|
||||
### 1.7 ESS Configuration (per instance)
|
||||
|
||||
```yaml
|
||||
# Shared across all instances:
|
||||
serverName: <domain>
|
||||
certManager:
|
||||
clusterIssuer: letsencrypt-production
|
||||
ingress:
|
||||
className: traefik # or whatever Yandex provides
|
||||
|
||||
# PostgreSQL — external, shared CNPG cluster:
|
||||
postgres:
|
||||
enabled: false
|
||||
|
||||
synapse:
|
||||
postgres:
|
||||
host: shared-pg-rw.cnpg.svc.cluster.local
|
||||
database: synapse_<name>
|
||||
user: synapse_<name>
|
||||
existingSecret: <name>-pg-creds
|
||||
existingSecretKey: synapse
|
||||
media:
|
||||
storage:
|
||||
size: 10Gi # adjustable per instance load
|
||||
storageClassName: yc-network-hdd # media is fine on HDD
|
||||
ingress:
|
||||
host: matrix.<domain>
|
||||
|
||||
matrixAuthenticationService:
|
||||
postgres:
|
||||
host: shared-pg-rw.cnpg.svc.cluster.local
|
||||
database: mas_<name>
|
||||
user: mas_<name>
|
||||
existingSecret: <name>-pg-creds
|
||||
existingSecretKey: mas
|
||||
ingress:
|
||||
host: account.<domain>
|
||||
|
||||
elementWeb:
|
||||
ingress:
|
||||
host: chat.<domain>
|
||||
|
||||
elementAdmin:
|
||||
ingress:
|
||||
host: admin.<domain>
|
||||
|
||||
matrixRTC:
|
||||
ingress:
|
||||
host: mrtc.<domain>
|
||||
|
||||
hookshot:
|
||||
enabled: true
|
||||
# ingress host if needed for webhooks
|
||||
```
|
||||
|
||||
### 1.8 Boot Order
|
||||
|
||||
```
|
||||
Step 1: kubectl apply bootstrap/gitea/
|
||||
Step 2: helm install argocd (bootstrap/argocd/install.sh)
|
||||
Step 3: git push manifests/ + argocd/ to Gitea
|
||||
Step 4: kubectl apply argocd/app-of-apps.yaml
|
||||
Step 5: ArgoCD syncs cert-manager, CNPG operator, CNPG cluster, databases, monitoring, ESS
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 2. Migration Procedure: `mrt0rtikize.ru` (test instance)
|
||||
|
||||
> Perform on the test instance first to validate the procedure before touching production.
|
||||
|
||||
### 2.1 Backup (on k3s homelab)
|
||||
|
||||
```bash
|
||||
NS=matrix-mrt0rtikize
|
||||
|
||||
# 1. Stop Synapse + MAS
|
||||
kubectl scale sts -l "app.kubernetes.io/component=matrix-server" -n $NS --replicas=0
|
||||
kubectl scale deploy -l "app.kubernetes.io/component=matrix-authentication" -n $NS --replicas=0
|
||||
|
||||
# 2. Dump PostgreSQL (built-in PG, release name is "ess" but pods are named matrix-mrt0rtikize-*)
|
||||
# The PG pod is named based on the ESS release. Find it:
|
||||
PG_POD=$(kubectl get pods -n $NS -l "app.kubernetes.io/name=postgres" -o name | head -1)
|
||||
kubectl exec -n $NS $PG_POD -- pg_dumpall -U postgres > dump-mrt0rtikize.sql
|
||||
|
||||
# 3. Backup generated secrets (CRITICAL — contains signing key, MAS encryption key)
|
||||
kubectl get secret matrix-mrt0rtikize-generated -n $NS -o yaml > secrets-mrt0rtikize.yaml
|
||||
|
||||
# 4. Backup deployment markers
|
||||
kubectl get configmap \
|
||||
-l "app.kubernetes.io/managed-by=matrix-tools-deployment-markers" \
|
||||
-n $NS -o yaml > markers-mrt0rtikize.yaml
|
||||
|
||||
# 5. Backup media files
|
||||
# Find PV path from the node:
|
||||
kubectl get pv -n $NS -o yaml | grep -A5 "synapse-media"
|
||||
# Copy from the reported path on the node to a safe location
|
||||
|
||||
# 6. Save ESS values (from the ArgoCD Application or helm get values)
|
||||
kubectl get application matrix-mrt0rtikize -n argocd -o yaml > app-mrt0rtikize.yaml
|
||||
```
|
||||
|
||||
**Critical data that MUST be preserved:**
|
||||
|
||||
| Data | Location | Why |
|
||||
|------|----------|-----|
|
||||
| `SYNAPSE_SIGNING_KEY` | `matrix-mrt0rtikize-generated` secret | Federation identity — all other servers know this key. Lose it = all rooms break. |
|
||||
| `MAS_ENCRYPTION_SECRET` | same secret | User session encryption. Lose it = all users must re-login. |
|
||||
| `MAS_RSA_PRIVATE_KEY` | same secret | OIDC signing. Lose it = re-auth needed. |
|
||||
| `SYNAPSE_MACAROON` | same secret | Admin API access token. |
|
||||
| PostgreSQL dump | `dump-mrt0rtikize.sql` | All user accounts, rooms, messages. |
|
||||
| Media files | Synapse media PV | Uploaded images/files/avatars. |
|
||||
|
||||
### 2.2 Restore (on new Yandex cluster)
|
||||
|
||||
```bash
|
||||
# 1. Create secrets in the matrix-mrt0rtikize namespace
|
||||
NS=matrix-mrt0rtikize
|
||||
kubectl create ns $NS
|
||||
|
||||
# Apply the generated secrets (signing key etc — DO NOT let initSecrets regenerate it)
|
||||
kubectl apply -f secrets-mrt0rtikize.yaml
|
||||
kubectl apply -f markers-mrt0rtikize.yaml
|
||||
|
||||
# 2. Restore PostgreSQL dumps
|
||||
# CNPG service: shared-pg-rw.cnpg.svc.cluster.local
|
||||
# Extract per-DB dumps from pg_dumpall or use pg_restore:
|
||||
PG_POD=$(kubectl get pods -n cnpg -l "cnpg.io/cluster=shared-pg,cnpg.io/podRole=instance" -o name | head -1)
|
||||
|
||||
# Restore Synapse DB:
|
||||
kubectl exec -n cnpg $PG_POD -- psql -U synapse_mrt0rtikize \
|
||||
-d synapse_mrt0rtikize < dump-mrt0rtikize.sql
|
||||
|
||||
# Restore MAS DB:
|
||||
kubectl exec -n cnpg $PG_POD -- psql -U mas_mrt0rtikize \
|
||||
-d mas_mrt0rtikize < dump-mrt0rtikize.sql
|
||||
|
||||
# (Note: pg_dumpall produces a single file for all databases. You may need to
|
||||
# split it per-database first, or use pg_restore per-database.)
|
||||
|
||||
# 3. Restore media files
|
||||
# Copy from backup to the new PV (path depends on storage class)
|
||||
# For Yandex Cloud CSI: mount the PV on a temp pod and copy files in
|
||||
|
||||
# 4. Deploy ESS via ArgoCD
|
||||
# The Application was already committed to git (argocd/apps/matrix-mrt0rtikize.yaml).
|
||||
# ArgoCD syncs it. Since secrets + markers are pre-loaded, the chart initializes
|
||||
# with the existing signing key and database credentials.
|
||||
|
||||
# 5. Verify
|
||||
# - Log in with an existing user
|
||||
# - Check federation: https://federationtester.matrix.org/?server_name=mrt0rtikize.ru
|
||||
# - Test Element Call (VoIP)
|
||||
# - Monitor logs for errors
|
||||
```
|
||||
|
||||
### 2.3 DNS Cutover
|
||||
|
||||
Once validated:
|
||||
```
|
||||
Old records: mrt0rtikize.ru → k3s cluster IP
|
||||
*.mrt0rtikize.ru → k3s cluster IP
|
||||
|
||||
New records: mrt0rtikize.ru → new cluster Traefik LB IP
|
||||
matrix.mrt0rtikize.ru → new cluster LB
|
||||
account.mrt0rtikize.ru → new cluster LB
|
||||
chat.mrt0rtikize.ru → new cluster LB
|
||||
admin.mrt0rtikize.ru → new cluster LB
|
||||
mrtc.mrt0rtikize.ru → new cluster LB
|
||||
```
|
||||
|
||||
Lower DNS TTLs 24h before cutover to minimize propagation delay.
|
||||
|
||||
### 2.4 Rollback
|
||||
|
||||
If migration fails:
|
||||
1. Scale down Synapse + MAS on new cluster
|
||||
2. Revert DNS to k3s cluster IP
|
||||
3. Scale up Synapse + MAS on k3s homelab
|
||||
|
||||
The old instance on k3s should still be functional (just stopped, not deleted).
|
||||
|
||||
---
|
||||
|
||||
## 3. Production Migration (vague plan)
|
||||
|
||||
> Repeat steps from Section 2 for each production instance, one at a time.
|
||||
|
||||
### 3.1 Order
|
||||
|
||||
| # | Instance | Synapse Load | Complexity |
|
||||
|---|----------|--------------|------------|
|
||||
| 1 | `mrt0rtikize.ru` | Minimal (test) | Low — prove procedure |
|
||||
| 2 | `t0rt1k.tech` | **582Mi** (busiest) | High — schedule during low-traffic, may need extended downtime |
|
||||
| 3 | `roglog.space` | 134Mi | Medium |
|
||||
|
||||
|
||||
### 3.2 Pre-migration Checklist (per instance)
|
||||
|
||||
```
|
||||
[ ] Announce maintenance window to users
|
||||
[ ] Lower DNS TTLs (24h before)
|
||||
[ ] Full PostgreSQL dump + verify (pg_restore --list)
|
||||
[ ] Backup media files + verify checksums
|
||||
[ ] Backup generated secrets (verify signing key matches federation)
|
||||
[ ] Save current Helm values (helm get values)
|
||||
[ ] Document current ingress/DNS/Certificate setup
|
||||
[ ] Prepare rollback procedure
|
||||
```
|
||||
|
||||
### 3.3 Migration Steps (per instance)
|
||||
|
||||
```
|
||||
1. Stop Synapse + MAS on old cluster
|
||||
2. Create CNPG databases on new cluster
|
||||
3. Restore PostgreSQL dump to CNPG
|
||||
4. Restore media files to new PV
|
||||
5. Apply secrets (signing key, MAS keys, macaroon)
|
||||
6. Apply deployment markers
|
||||
7. Deploy ESS via ArgoCD on new cluster
|
||||
8. Wait for pods healthy, certs issued
|
||||
9. Test: login, federation, Element Call
|
||||
10. Cut over DNS
|
||||
11. Monitor for 24h
|
||||
12. If stable: remove old instance resources from old cluster
|
||||
```
|
||||
|
||||
### 3.4 Special Considerations for Prod Instances
|
||||
|
||||
**`t0rt1k.tech` (busiest instance, 582Mi Synapse):**
|
||||
- Uses older `matrix-2.9.17` chart (NOT ESS). Migration means switching to ESS Community chart.
|
||||
- Has a **failed `syn2mas` job** — MAS migration was incomplete. When deploying ESS which bundles MAS, the migration may need to be completed or re-done.
|
||||
- The 582Mi memory usage suggests many concurrent users/rooms — dump may be large. Allocate enough storage and time for the SQL dump/restore.
|
||||
- Consider running the new ESS in parallel (different hostnames) first, then switching DNS once proven.
|
||||
|
||||
**`roglog.space`:**
|
||||
- Lower load (134Mi/137Mi) — quicker backups, less downtime risk.
|
||||
- Same chart switch (`matrix-2.9.17` → ESS).
|
||||
- Can be done in shorter windows.
|
||||
|
||||
**Chart migration (`matrix-2.9.17` → ESS):**
|
||||
- The old chart uses separate Helm releases per component (`chat`, `element-call`, `livekit`).
|
||||
- ESS bundles everything into one chart. The database schema may differ.
|
||||
- Key difference: ESS uses MAS for auth (Matrix 2.0), old chart may use legacy Synapse auth.
|
||||
- May need to run `syn2mas` migration or manual user migration. Investigate per-instance before cutover.
|
||||
|
||||
---
|
||||
|
||||
## 4. PostgreSQL Backup (ongoing)
|
||||
|
||||
CloudNativePG has built-in backup to S3-compatible storage. Configure once for automatic daily backups:
|
||||
|
||||
```yaml
|
||||
apiVersion: postgresql.cnpg.io/v1
|
||||
kind: ScheduledBackup
|
||||
metadata:
|
||||
name: shared-pg-daily
|
||||
namespace: cnpg
|
||||
spec:
|
||||
schedule: "0 3 * * *" # 03:00 UTC daily
|
||||
backupOwnerReference: self
|
||||
cluster:
|
||||
name: shared-pg
|
||||
immediate: false
|
||||
target: prefer-standby
|
||||
```
|
||||
|
||||
CNPG also supports continuous WAL archiving to S3 for point-in-time recovery.
|
||||
Configure Yandex Object Storage as the S3 target.
|
||||
|
||||
---
|
||||
|
||||
## 5. Architecture Diagram (text)
|
||||
|
||||
```
|
||||
┌────────────────────────────────────────────────────────────┐
|
||||
│ Yandex Cloud Managed K8s │
|
||||
│ │
|
||||
│ ┌───────────────────┐ ┌──────────────────────────────┐ │
|
||||
│ │ Infrastructure │ │ Matrix Layer │ │
|
||||
│ │ │ │ │ │
|
||||
│ │ Gitea (git) │ │ ┌─────────────────────────┐ │ │
|
||||
│ │ ArgoCD (gitops) │ │ │ matrix-mrt0rtikize (ESS)│ │ │
|
||||
│ │ cert-manager │ │ │ - Synapse │ │ │
|
||||
│ │ Traefik (LB) │ │ │ - MAS │ │ │
|
||||
│ │ Prometheus/Grafana │ │ │ - Element Web/Admin │ │ │
|
||||
│ │ VictoriaMetrics │ │ │ - Matrix RTC (LiveKit) │ │ │
|
||||
│ │ Loki │ │ │ - Hookshot │ │ │
|
||||
│ │ Alloy │ │ │ - HAProxy │ │ │
|
||||
│ └───────────────────┘ │ └──────────┬──────────────┘ │ │
|
||||
│ │ │ │ │
|
||||
│ ┌───────────────────┐ │ ┌──────────▼──────────────┐ │ │
|
||||
│ │ CNPG Cluster │ │ │ matrix-t0rt1k (ESS) │ │ │
|
||||
│ │ (3 nodes, SSD) │◄──┤ │ (same structure) │ │ │
|
||||
│ │ │ │ └─────────────────────────┘ │ │
|
||||
│ │ synapse_mrt0rtikize│ │ ┌─────────────────────────┐ │ │
|
||||
│ │ mas_mrt0rtikize │ │ │ matrix-roglog (ESS) │ │ │
|
||||
│ │ synapse_t0rt1k │ │ │ (same structure) │ │ │
|
||||
│ │ mas_t0rt1k │ │ └─────────────────────────┘ │ │
|
||||
│ │ synapse_roglog │ │ │ │
|
||||
│ │ mas_roglog │ │ │ │
|
||||
│ └───────────────────┘ └──────────────────────────────┘ │
|
||||
│ │
|
||||
│ External LB: <Yandex provisioned IP> │
|
||||
└────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6. Implementation Notes
|
||||
|
||||
### 6.1 Secrets Management
|
||||
|
||||
- ESS `initSecrets` generates 14 credentials. For migration, these MUST be restored from backup (not regenerated).
|
||||
- `SYNAPSE_SIGNING_KEY` is the most critical — it identifies the server to the federation. Changing it breaks all existing rooms and federation relationships.
|
||||
- The `matrix*-generated` secret and deployment markers ConfigMap must be applied **before** the first ArgoCD sync, so the ESS chart does not generate new (wrong) ones.
|
||||
- For fresh ESS instances (new homeservers, not migrations), let `initSecrets` generate them normally.
|
||||
|
||||
### 6.2 Image Registry
|
||||
|
||||
- ESS pulls from `oci.element.io` (Synapse, Element Web, Element Admin, lk-jwt-service) and `ghcr.io` (matrix-tools, hookshot), and `docker.io` (livekit, postgres, redis).
|
||||
- `oci.element.io` S3 backend (`oci-element-io-images-storage-prod.s3.eu-central-1.amazonaws.com`) was observed to fail intermittently from Russia with "connection reset by peer". Images eventually pulled on retry, but consider:
|
||||
- Setting `image.pullPolicy: IfNotPresent` to reduce re-pulls
|
||||
- Setting up a containerd registry mirror or local pull-through cache for `oci.element.io`
|
||||
- Pre-pulling images to nodes during initial setup
|
||||
|
||||
### 6.3 Resource Limits
|
||||
|
||||
Set `resources.requests` and `resources.limits` on all ESS components to prevent the 94% node issue seen in prod:
|
||||
|
||||
```yaml
|
||||
synapse:
|
||||
resources:
|
||||
requests:
|
||||
memory: 256Mi
|
||||
cpu: 100m
|
||||
limits:
|
||||
memory: 1Gi
|
||||
cpu: 1000m
|
||||
```
|
||||
|
||||
Do similar for MAS, element-web, livekit-sfu, etc. ESS chart supports per-component resource configuration.
|
||||
|
||||
### 6.4 Storage Classes
|
||||
|
||||
| Workload | Storage Class | Reason |
|
||||
|----------|--------------|--------|
|
||||
| PostgreSQL (CNPG) | `yc-network-ssd` | Database — needs low latency / high IOPS |
|
||||
| Synapse media | `yc-network-hdd` (default) | Media files — sequential access, SSD benefit is marginal |
|
||||
| Prometheus TSDB | `yc-network-ssd` | Time-series DB — random writes benefit from SSD |
|
||||
| Loki chunks | `yc-network-hdd` | Log storage — sequential writes, HDD is fine |
|
||||
|
||||
---
|
||||
|
||||
## 7. Next Steps (for next session)
|
||||
|
||||
When the new cluster is ready, open a new session and point to this file. The next session should:
|
||||
|
||||
1. Read this plan
|
||||
2. Explore the new cluster (nodes, storage classes, ingress config)
|
||||
3. Implement Phase 0 (bootstrap GitOps foundation):
|
||||
- Create `~/infra/yandex-prod/` directory structure
|
||||
- Write `bootstrap/gitea/` manifests
|
||||
- Write `bootstrap/argocd/install.sh` + `values.yaml`
|
||||
- Write `argocd/app-of-apps.yaml`
|
||||
- Write infrastructure apps (cert-manager, CNPG, monitoring)
|
||||
- Write ESS apps
|
||||
- Push to Gitea
|
||||
4. Execute Phase 1 (backup `mrt0rtikize.ru` from k3s)
|
||||
5. Execute Phase 2 (restore `mrt0rtikize.ru` to new cluster)
|
||||
6. Validate and plan DNS cutover
|
||||
124
STATUS.md
Normal file
124
STATUS.md
Normal file
@@ -0,0 +1,124 @@
|
||||
# Yandex Cloud Production Cluster — Current State
|
||||
|
||||
> Last updated: 2026-06-12
|
||||
|
||||
---
|
||||
|
||||
## Cluster Overview
|
||||
|
||||
| Property | Value |
|
||||
|----------|-------|
|
||||
| Nodes | 3x 2CPU/8GB, zones b/d/e |
|
||||
| Egress | NAT Gateway `k8s-nat-gw` (shared, no per-node IPs) |
|
||||
| Domain base | `*.prod.t01tt.tech` |
|
||||
| NLB IP | `81.26.181.240` |
|
||||
| Git repo (Gitea) | `admin/main.git`, branch `master` |
|
||||
| ArgoCD sync mode | **Manual** (no auto-sync, no auto-prune) |
|
||||
|
||||
---
|
||||
|
||||
## Infrastructure Status
|
||||
|
||||
### Running & Healthy ✅
|
||||
|
||||
| Component | URL / Access | Notes |
|
||||
|-----------|-------------|-------|
|
||||
| Gitea | `https://git.prod.t01tt.tech` | Also `git@git.prod.t01tt.tech:admin/main.git` (SSH via NLB port 22) |
|
||||
| ArgoCD | `https://argocd.prod.t01tt.tech` | Manual sync only |
|
||||
| cert-manager | — | `letsencrypt-production` + `staging` ClusterIssuers |
|
||||
| Traefik | NLB `81.26.181.240` | Ports 80, 443, 22 (SSH for Gitea) |
|
||||
| Monitoring (VM k8s-stack) | — | VMSingle, VMAlertmanager, node-exporter, kube-state-metrics |
|
||||
| Grafana | `https://grafana.prod.t01tt.tech` | `admin`/`change-me`, VictoriaMetrics datasource works |
|
||||
| CNPG Operator | — | v0.28.3, running in `cnpg-system` |
|
||||
| CNPG Cluster `shared-pg` | — | 3/3 nodes healthy, 20Gi SSD each, no databases created yet |
|
||||
| Alloy | — | DaemonSet, collecting pod logs, shipping to Loki |
|
||||
| Loki | `http://loki.metrics.svc.cluster.local:3100` | Single binary, 20Gi HDD, logs flowing, queryable via API |
|
||||
|
||||
### Broken/Incomplete ⚠️
|
||||
|
||||
| Component | Issue | Next Step |
|
||||
|-----------|-------|-----------|
|
||||
| Grafana + Loki | Grafana 13.0.1 has a Loki datasource plugin bug (`unsupported protocol scheme ""`). Loki API itself works (direct queries return data). | Wait for VM k8s-stack Helm chart to bundle a newer Grafana version (13.1.0+). Then add `grafana.image.tag: "13.1.0"` to `monitoring.yaml`. OR: expose Loki via Traefik ingress + use `access: direct` in datasource. |
|
||||
| CNPG Databases | `manifests/cnpg/databases.yaml` — `clusterRef` must be `cluster` (8 occurrences) for CNPG v1 API. `manifests/cnpg/secrets.yaml` — type must be `Opaque` with plain password strings. | Fix when creating ESS Matrix apps — databases and secrets are part of the Matrix instance setup, not standalone infra. |
|
||||
| `cnpg-cluster` ArgoCD app | OutOfSync due to the two files above. | Sync after fixing databases + secrets as part of ESS setup. |
|
||||
|
||||
### ArgoCD App Status
|
||||
|
||||
| App | Sync | Health | Notes |
|
||||
|-----|------|--------|-------|
|
||||
| alloy | OutOfSync | Healthy | Pushed to Gitea, needs manual sync |
|
||||
| cert-manager | Synced | Healthy | |
|
||||
| cert-manager-issuers | Synced | Healthy | |
|
||||
| cnpg-cluster | OutOfSync | Healthy | Blocked by databases.yaml + secrets.yaml |
|
||||
| cnpg-operator | Synced | Healthy | |
|
||||
| loki | OutOfSync | Healthy | Pushed to Gitea, needs manual sync |
|
||||
| monitoring | Synced | Healthy | |
|
||||
| root-app | Synced | Healthy | |
|
||||
| traefik | Synced | Healthy | |
|
||||
|
||||
---
|
||||
|
||||
## Directory Structure
|
||||
|
||||
```
|
||||
~/infra/yandex-prod/
|
||||
├── BOOTSTRAP.md # Step-by-step bootstrap guide
|
||||
├── PLAN.md # Original migration plan
|
||||
├── STATUS.md # This file
|
||||
├── kubeconfig # Cluster kubeconfig
|
||||
├── bootstrap/
|
||||
│ ├── gitea/ # 5 manifests (namespace, pvc, deploy, svc, ingress)
|
||||
│ └── argocd/ # install.sh, values.yaml, ingress.yaml
|
||||
├── argocd/
|
||||
│ ├── app-of-apps.yaml # Root app: watches argocd/apps/*.yaml
|
||||
│ └── apps/
|
||||
│ ├── traefik.yaml # DaemonSet + NLB (wave -2)
|
||||
│ ├── cert-manager.yaml # Helm chart (wave -1)
|
||||
│ ├── cert-manager-issuers.yaml # ClusterIssuer CRs (wave 0)
|
||||
│ ├── cnpg-operator.yaml # CNPG Helm chart
|
||||
│ ├── cnpg-cluster.yaml # Cluster + DB CRs from manifests/cnpg/
|
||||
│ ├── monitoring.yaml # VM k8s-stack (wave 0)
|
||||
│ ├── loki.yaml # Loki single-binary (wave 0)
|
||||
│ └── alloy.yaml # Alloy log collector (wave 0)
|
||||
└── manifests/
|
||||
├── cert-manager/
|
||||
│ └── cluster-issuers.yaml # letsencrypt-production + staging
|
||||
├── cnpg/
|
||||
│ ├── namespace.yaml
|
||||
│ ├── cluster.yaml # shared-pg Cluster CR (3 nodes, 20Gi SSD)
|
||||
│ ├── databases.yaml # 8 Database CRs (BROKEN: clusterRef)
|
||||
│ └── secrets.yaml # 4 PG cred secrets (BROKEN: type+values)
|
||||
├── gitea/
|
||||
│ └── ingressroute-ssh.yaml # Traefik TCP route for Gitea SSH
|
||||
└── metrics/
|
||||
├── grafana/
|
||||
│ ├── namespace.yaml
|
||||
│ ├── ingress.yaml # grafana.prod.t01tt.tech
|
||||
│ └── loki-datasource.yaml # Loki datasource ConfigMap
|
||||
└── (empty — namespace.yaml moved into grafana/)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Key Decisions Made
|
||||
|
||||
| Decision | Why |
|
||||
|----------|-----|
|
||||
| NAT Gateway instead of per-node IPs | IP quota limits; shared egress via `k8s-nat-gw` |
|
||||
| Auto-sync disabled on all apps | Manual control during bootstrapping |
|
||||
| VM k8s-stack instead of kube-prometheus-stack | Single Helm chart for metrics |
|
||||
| Alloy for log collection | Ported working config from old `yc-playground` cluster |
|
||||
| Gryphon the Grafekr 13 Loki bug | MVP: logs are collected and queryable via API; UI integration deferred |
|
||||
|
||||
---
|
||||
|
||||
## Next Session Priorities
|
||||
|
||||
1. **Sync alloy + loki** (already in Gitea, just needs manual ArgoCD sync)
|
||||
2. **Fix Grafana + Loki** — either Grafana 13.1.0 via chart update or Loki ingress workaround
|
||||
3. **Create ESS Matrix app for `mrt0rtikize.ru`** — the test migration (Phase 2 of PLAN.md):
|
||||
- Fix `databases.yaml` and `secrets.yaml` as part of this
|
||||
- Create `argocd/apps/matrix-mrt0rtikize.yaml`
|
||||
- Backup from k3s cluster, restore to new cluster
|
||||
- Test DNS cutover
|
||||
4. **Create ESS apps for prod instances** (`t0rt1k.tech`, `roglog.space`, `uretra.space`)
|
||||
22
argocd/app-of-apps.yaml
Normal file
22
argocd/app-of-apps.yaml
Normal file
@@ -0,0 +1,22 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: root-app
|
||||
namespace: argocd
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: http://gitea.gitea.svc.cluster.local:3000/admin/main.git
|
||||
targetRevision: master
|
||||
path: argocd/apps
|
||||
directory:
|
||||
recurse: true
|
||||
include: "*.yaml"
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: argocd
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
103
argocd/apps/alloy.yaml
Normal file
103
argocd/apps/alloy.yaml
Normal file
@@ -0,0 +1,103 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: alloy
|
||||
namespace: argocd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "0"
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: https://grafana.github.io/helm-charts
|
||||
chart: alloy
|
||||
targetRevision: ">=1.5.0"
|
||||
helm:
|
||||
values: |
|
||||
alloy:
|
||||
configMap:
|
||||
content: |-
|
||||
// Discover Kubernetes pods
|
||||
discovery.kubernetes "pods" {
|
||||
role = "pod"
|
||||
}
|
||||
|
||||
// Relabel pods to intelligently map existing Kubernetes labels to service/component
|
||||
discovery.relabel "pods" {
|
||||
targets = discovery.kubernetes.pods.targets
|
||||
|
||||
// Create service label - try multiple sources in priority order
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_label_app_kubernetes_io_name"]
|
||||
regex = "(.+)"
|
||||
replacement = "${1}"
|
||||
target_label = "service"
|
||||
}
|
||||
// 2. Second priority: app label
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_label_app", "service"]
|
||||
regex = "^(.+);$"
|
||||
replacement = "${1}"
|
||||
target_label = "service"
|
||||
}
|
||||
// 3. Third priority: extract from pod name (remove hash suffix)
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_name", "service"]
|
||||
regex = "^([a-z0-9-]+?)(?:-[a-f0-9]{5,10})?;$"
|
||||
replacement = "${1}"
|
||||
target_label = "service"
|
||||
}
|
||||
|
||||
// Create component label from app.kubernetes.io/component or component label
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_label_app_kubernetes_io_component"]
|
||||
regex = ".+"
|
||||
target_label = "component"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_label_component"]
|
||||
regex = ".+"
|
||||
target_label = "component"
|
||||
}
|
||||
|
||||
// Drop pods that we still can't identify
|
||||
rule {
|
||||
source_labels = ["service"]
|
||||
regex = "^$"
|
||||
action = "drop"
|
||||
}
|
||||
|
||||
// Map standard Kubernetes metadata to Loki labels
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_namespace"]
|
||||
target_label = "namespace"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_name"]
|
||||
target_label = "pod"
|
||||
}
|
||||
rule {
|
||||
source_labels = ["__meta_kubernetes_pod_container_name"]
|
||||
target_label = "container"
|
||||
}
|
||||
}
|
||||
|
||||
// Collect logs from Kubernetes pods using the Kubernetes API
|
||||
loki.source.kubernetes "pods" {
|
||||
targets = discovery.relabel.pods.output
|
||||
forward_to = [loki.write.loki.receiver]
|
||||
}
|
||||
|
||||
// Write logs to Loki
|
||||
loki.write "loki" {
|
||||
endpoint {
|
||||
url = "http://loki.metrics.svc.cluster.local:3100/loki/api/v1/push"
|
||||
}
|
||||
}
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: metrics
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
22
argocd/apps/cert-manager-issuers.yaml
Normal file
22
argocd/apps/cert-manager-issuers.yaml
Normal file
@@ -0,0 +1,22 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: cert-manager-issuers
|
||||
namespace: argocd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "0"
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: http://gitea.gitea.svc.cluster.local:3000/admin/main.git
|
||||
targetRevision: master
|
||||
path: manifests/cert-manager
|
||||
directory:
|
||||
recurse: true
|
||||
include: "*.yaml"
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: cert-manager
|
||||
syncPolicy: {}
|
||||
24
argocd/apps/cert-manager.yaml
Normal file
24
argocd/apps/cert-manager.yaml
Normal file
@@ -0,0 +1,24 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: cert-manager
|
||||
namespace: argocd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "-1"
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: https://charts.jetstack.io
|
||||
chart: cert-manager
|
||||
targetRevision: ">=1.18.0"
|
||||
helm:
|
||||
values: |
|
||||
installCRDs: true
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: cert-manager
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
24
argocd/apps/cnpg-cluster.yaml
Normal file
24
argocd/apps/cnpg-cluster.yaml
Normal file
@@ -0,0 +1,24 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: cnpg-cluster
|
||||
namespace: argocd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "1"
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: http://gitea.gitea.svc.cluster.local:3000/admin/main.git
|
||||
targetRevision: master
|
||||
path: manifests/cnpg
|
||||
directory:
|
||||
recurse: true
|
||||
include: "*.yaml"
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: cnpg
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
20
argocd/apps/cnpg-operator.yaml
Normal file
20
argocd/apps/cnpg-operator.yaml
Normal file
@@ -0,0 +1,20 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: cnpg-operator
|
||||
namespace: argocd
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: https://cloudnative-pg.github.io/charts
|
||||
chart: cloudnative-pg
|
||||
targetRevision: ">=0.23.0"
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: cnpg-system
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
- ServerSideApply=true
|
||||
92
argocd/apps/loki.yaml
Normal file
92
argocd/apps/loki.yaml
Normal file
@@ -0,0 +1,92 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: loki
|
||||
namespace: argocd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "0"
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: https://grafana.github.io/helm-charts
|
||||
chart: loki
|
||||
targetRevision: ">=6.0.0"
|
||||
helm:
|
||||
values: |
|
||||
deploymentMode: SingleBinary
|
||||
|
||||
write:
|
||||
replicas: 0
|
||||
read:
|
||||
replicas: 0
|
||||
backend:
|
||||
replicas: 0
|
||||
|
||||
loki:
|
||||
auth_enabled: false
|
||||
storage:
|
||||
bucketNames:
|
||||
chunks: chunks
|
||||
ruler: ruler
|
||||
admin: admin
|
||||
type: filesystem
|
||||
filesystem:
|
||||
chunks_directory: /var/loki/chunks
|
||||
rules_directory: /var/loki/rules
|
||||
structuredConfig:
|
||||
auth_enabled: false
|
||||
|
||||
server:
|
||||
http_listen_port: 3100
|
||||
grpc_listen_port: 9095
|
||||
|
||||
common:
|
||||
path_prefix: /var/loki
|
||||
replication_factor: 1
|
||||
|
||||
schema_config:
|
||||
configs:
|
||||
- from: "2025-01-01"
|
||||
store: tsdb
|
||||
object_store: filesystem
|
||||
schema: v13
|
||||
index:
|
||||
prefix: index_
|
||||
period: 24h
|
||||
|
||||
limits_config:
|
||||
retention_period: 30d
|
||||
reject_old_samples: true
|
||||
reject_old_samples_max_age: 168h
|
||||
|
||||
chunksCache:
|
||||
enabled: false
|
||||
resultsCache:
|
||||
enabled: false
|
||||
gateway:
|
||||
enabled: false
|
||||
test:
|
||||
enabled: false
|
||||
lokiCanary:
|
||||
enabled: false
|
||||
|
||||
singleBinary:
|
||||
replicas: 1
|
||||
persistence:
|
||||
enabled: true
|
||||
size: 20Gi
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 256Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 1Gi
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: metrics
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
89
argocd/apps/matrix-mrt0rtikize.yaml
Normal file
89
argocd/apps/matrix-mrt0rtikize.yaml
Normal file
@@ -0,0 +1,89 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: matrix-mrt0rtikize
|
||||
namespace: argocd
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
sources:
|
||||
- repoURL: http://gitea.gitea.svc.cluster.local:3000/admin/main.git
|
||||
targetRevision: master
|
||||
path: manifests/matrix-mrt0rtikize
|
||||
directory:
|
||||
recurse: true
|
||||
include: "*.yaml"
|
||||
- repoURL: ghcr.io
|
||||
chart: element-hq/ess-helm/matrix-stack
|
||||
targetRevision: 26.6.1
|
||||
helm:
|
||||
values: |
|
||||
serverName: mrt0rtikize.ru
|
||||
|
||||
certManager:
|
||||
clusterIssuer: letsencrypt-production
|
||||
|
||||
ingress:
|
||||
className: traefik
|
||||
|
||||
postgres:
|
||||
enabled: false
|
||||
|
||||
synapse:
|
||||
postgres:
|
||||
host: shared-pg-rw.cnpg.svc.cluster.local
|
||||
database: synapse_mrt0rtikize
|
||||
user: synapse_mrt0rtikize
|
||||
password:
|
||||
secret: pg-creds
|
||||
secretKey: synapse
|
||||
media:
|
||||
storage:
|
||||
size: 10Gi
|
||||
ingress:
|
||||
host: matrix.mrt0rtikize.ru
|
||||
|
||||
matrixAuthenticationService:
|
||||
postgres:
|
||||
host: shared-pg-rw.cnpg.svc.cluster.local
|
||||
database: mas_mrt0rtikize
|
||||
user: mas_mrt0rtikize
|
||||
password:
|
||||
secret: pg-creds
|
||||
secretKey: mas
|
||||
ingress:
|
||||
host: account.mrt0rtikize.ru
|
||||
|
||||
elementWeb:
|
||||
ingress:
|
||||
host: chat.mrt0rtikize.ru
|
||||
|
||||
elementAdmin:
|
||||
ingress:
|
||||
host: admin.mrt0rtikize.ru
|
||||
|
||||
matrixRTC:
|
||||
ingress:
|
||||
host: mrtc.mrt0rtikize.ru
|
||||
sfu:
|
||||
manualIP: "81.26.181.240"
|
||||
useStunToDiscoverPublicIP: false
|
||||
exposedServices:
|
||||
rtcTcp:
|
||||
port: 30009
|
||||
portType: NodePort
|
||||
nodePort: ""
|
||||
rtcMuxedUdp:
|
||||
port: 30008
|
||||
portType: NodePort
|
||||
nodePort: ""
|
||||
|
||||
hookshot:
|
||||
enabled: true
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: matrix-mrt0rtikize
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
89
argocd/apps/matrix-roglog.yaml
Normal file
89
argocd/apps/matrix-roglog.yaml
Normal file
@@ -0,0 +1,89 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: matrix-roglog
|
||||
namespace: argocd
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
sources:
|
||||
- repoURL: http://gitea.gitea.svc.cluster.local:3000/admin/main.git
|
||||
targetRevision: master
|
||||
path: manifests/matrix-roglog
|
||||
directory:
|
||||
recurse: true
|
||||
include: "*.yaml"
|
||||
- repoURL: ghcr.io
|
||||
chart: element-hq/ess-helm/matrix-stack
|
||||
targetRevision: 26.6.1
|
||||
helm:
|
||||
values: |
|
||||
serverName: roglog.space
|
||||
|
||||
certManager:
|
||||
clusterIssuer: letsencrypt-production
|
||||
|
||||
ingress:
|
||||
className: traefik
|
||||
|
||||
postgres:
|
||||
enabled: false
|
||||
|
||||
synapse:
|
||||
postgres:
|
||||
host: shared-pg-rw.cnpg.svc.cluster.local
|
||||
database: synapse_roglog
|
||||
user: synapse_roglog
|
||||
password:
|
||||
secret: pg-creds
|
||||
secretKey: synapse
|
||||
media:
|
||||
storage:
|
||||
size: 10Gi
|
||||
ingress:
|
||||
host: matrix.roglog.space
|
||||
|
||||
matrixAuthenticationService:
|
||||
postgres:
|
||||
host: shared-pg-rw.cnpg.svc.cluster.local
|
||||
database: mas_roglog
|
||||
user: mas_roglog
|
||||
password:
|
||||
secret: pg-creds
|
||||
secretKey: mas
|
||||
ingress:
|
||||
host: auth.roglog.space
|
||||
|
||||
elementWeb:
|
||||
ingress:
|
||||
host: chat.roglog.space
|
||||
|
||||
elementAdmin:
|
||||
ingress:
|
||||
host: admin.roglog.space
|
||||
|
||||
matrixRTC:
|
||||
ingress:
|
||||
host: rtc.roglog.space
|
||||
sfu:
|
||||
manualIP: "81.26.181.240"
|
||||
useStunToDiscoverPublicIP: false
|
||||
exposedServices:
|
||||
rtcTcp:
|
||||
port: 30005
|
||||
portType: NodePort
|
||||
nodePort: ""
|
||||
rtcMuxedUdp:
|
||||
port: 30004
|
||||
portType: NodePort
|
||||
nodePort: ""
|
||||
|
||||
hookshot:
|
||||
enabled: true
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: matrix-roglog
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
160
argocd/apps/matrix-t0rt1k.yaml
Normal file
160
argocd/apps/matrix-t0rt1k.yaml
Normal file
@@ -0,0 +1,160 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: matrix-t0rt1k
|
||||
namespace: argocd
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
sources:
|
||||
- repoURL: http://gitea.gitea.svc.cluster.local:3000/admin/main.git
|
||||
targetRevision: master
|
||||
path: manifests/matrix-t0rt1k
|
||||
directory:
|
||||
recurse: true
|
||||
include: "*.yaml"
|
||||
- repoURL: ghcr.io
|
||||
chart: element-hq/ess-helm/matrix-stack
|
||||
targetRevision: 26.6.1
|
||||
helm:
|
||||
values: |
|
||||
serverName: t0rt1k.tech
|
||||
|
||||
certManager:
|
||||
clusterIssuer: letsencrypt-production
|
||||
|
||||
ingress:
|
||||
className: traefik
|
||||
|
||||
postgres:
|
||||
enabled: false
|
||||
|
||||
synapse:
|
||||
postgres:
|
||||
host: shared-pg-rw.cnpg.svc.cluster.local
|
||||
database: synapse_t0rt1k
|
||||
user: synapse_t0rt1k
|
||||
password:
|
||||
secret: pg-creds
|
||||
secretKey: synapse
|
||||
media:
|
||||
storage:
|
||||
size: 10Gi
|
||||
ingress:
|
||||
host: matrix.t0rt1k.tech
|
||||
resources:
|
||||
requests:
|
||||
memory: 256Mi
|
||||
cpu: 100m
|
||||
limits:
|
||||
memory: 1.5Gi
|
||||
workers:
|
||||
federation-sender:
|
||||
enabled: true
|
||||
resources:
|
||||
requests:
|
||||
memory: 192Mi
|
||||
cpu: 50m
|
||||
limits:
|
||||
memory: 256Mi
|
||||
federation-reader:
|
||||
enabled: true
|
||||
resources:
|
||||
requests:
|
||||
memory: 128Mi
|
||||
cpu: 50m
|
||||
limits:
|
||||
memory: 256Mi
|
||||
client-reader:
|
||||
enabled: true
|
||||
replicas: 1
|
||||
resources:
|
||||
requests:
|
||||
memory: 128Mi
|
||||
cpu: 50m
|
||||
limits:
|
||||
memory: 256Mi
|
||||
initial-synchrotron:
|
||||
enabled: true
|
||||
resources:
|
||||
requests:
|
||||
memory: 128Mi
|
||||
cpu: 50m
|
||||
limits:
|
||||
memory: 256Mi
|
||||
synchrotron:
|
||||
enabled: true
|
||||
replicas: 1
|
||||
resources:
|
||||
requests:
|
||||
memory: 128Mi
|
||||
cpu: 50m
|
||||
limits:
|
||||
memory: 256Mi
|
||||
additional:
|
||||
0-federation-retry:
|
||||
config: |
|
||||
destination_min_retry_interval: "1m"
|
||||
destination_retry_multiplier: 1.5
|
||||
destination_max_retry_interval: "1d"
|
||||
|
||||
matrixAuthenticationService:
|
||||
postgres:
|
||||
host: shared-pg-rw.cnpg.svc.cluster.local
|
||||
database: mas_t0rt1k
|
||||
user: mas_t0rt1k
|
||||
password:
|
||||
secret: pg-creds
|
||||
secretKey: mas
|
||||
ingress:
|
||||
host: auth.t0rt1k.tech
|
||||
resources:
|
||||
limits:
|
||||
memory: 128Mi
|
||||
|
||||
elementWeb:
|
||||
ingress:
|
||||
host: chat.t0rt1k.tech
|
||||
|
||||
elementAdmin:
|
||||
ingress:
|
||||
host: admin.t0rt1k.tech
|
||||
|
||||
matrixRTC:
|
||||
ingress:
|
||||
host: rtc.t0rt1k.tech
|
||||
sfu:
|
||||
manualIP: "81.26.181.240"
|
||||
useStunToDiscoverPublicIP: false
|
||||
exposedServices:
|
||||
rtcTcp:
|
||||
port: 30007
|
||||
portType: NodePort
|
||||
nodePort: ""
|
||||
rtcMuxedUdp:
|
||||
port: 30006
|
||||
portType: NodePort
|
||||
nodePort: ""
|
||||
resources:
|
||||
requests:
|
||||
memory: 64Mi
|
||||
cpu: 50m
|
||||
limits:
|
||||
memory: 512Mi
|
||||
|
||||
hookshot:
|
||||
enabled: true
|
||||
resources:
|
||||
limits:
|
||||
memory: 256Mi
|
||||
ingress:
|
||||
host: hookshot.t0rt1k.tech
|
||||
className: traefik
|
||||
tlsEnabled: true
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: matrix-t0rt1k
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
142
argocd/apps/monitoring.yaml
Normal file
142
argocd/apps/monitoring.yaml
Normal file
@@ -0,0 +1,142 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: monitoring
|
||||
namespace: argocd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "0"
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
sources:
|
||||
- repoURL: http://gitea.gitea.svc.cluster.local:3000/admin/main.git
|
||||
targetRevision: master
|
||||
path: manifests/metrics/grafana
|
||||
directory:
|
||||
recurse: true
|
||||
include: "*.yaml"
|
||||
|
||||
- repoURL: https://victoriametrics.github.io/helm-charts/
|
||||
chart: victoria-metrics-k8s-stack
|
||||
targetRevision: ">=0.30.0"
|
||||
helm:
|
||||
values: |
|
||||
fullnameOverride: vm-k8s-stack
|
||||
namespaceOverride: metrics
|
||||
|
||||
victoria-metrics-operator:
|
||||
resources:
|
||||
requests:
|
||||
memory: 128Mi
|
||||
cpu: 25m
|
||||
limits:
|
||||
memory: 256Mi
|
||||
|
||||
defaultDashboards:
|
||||
dashboards:
|
||||
node-exporter-full:
|
||||
enabled: false
|
||||
|
||||
vmsingle:
|
||||
enabled: true
|
||||
spec:
|
||||
retentionPeriod: "30d"
|
||||
replicaCount: 1
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 256Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 1Gi
|
||||
storage:
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
resources:
|
||||
requests:
|
||||
storage: 30Gi
|
||||
|
||||
alertmanager:
|
||||
enabled: true
|
||||
spec:
|
||||
replicaCount: 1
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 128Mi
|
||||
limits:
|
||||
cpu: 200m
|
||||
memory: 512Mi
|
||||
storage:
|
||||
volumeClaimTemplate:
|
||||
spec:
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
resources:
|
||||
requests:
|
||||
storage: 1Gi
|
||||
config:
|
||||
route:
|
||||
receiver: blackhole
|
||||
receivers:
|
||||
- name: blackhole
|
||||
|
||||
grafana:
|
||||
enabled: true
|
||||
adminUser: admin
|
||||
adminPassword: change-me
|
||||
persistence:
|
||||
enabled: true
|
||||
size: 2Gi
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 256Mi
|
||||
limits:
|
||||
cpu: 200m
|
||||
memory: 512Mi
|
||||
|
||||
prometheus-node-exporter:
|
||||
enabled: true
|
||||
|
||||
kube-state-metrics:
|
||||
enabled: true
|
||||
|
||||
kubelet:
|
||||
enabled: true
|
||||
|
||||
kubeApiServer:
|
||||
enabled: false
|
||||
|
||||
kubeControllerManager:
|
||||
enabled: false
|
||||
|
||||
kubeScheduler:
|
||||
enabled: false
|
||||
|
||||
kubeProxy:
|
||||
enabled: false
|
||||
|
||||
kubeEtcd:
|
||||
enabled: false
|
||||
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: metrics
|
||||
ignoreDifferences:
|
||||
- group: operator.victoriametrics.com
|
||||
kind: VMAlertmanager
|
||||
jsonPointers:
|
||||
- /spec/config
|
||||
- kind: Secret
|
||||
name: monitoring-victoria-metrics-operator-validation
|
||||
jsonPointers:
|
||||
- /data
|
||||
- kind: ValidatingWebhookConfiguration
|
||||
name: monitoring-victoria-metrics-operator-admission
|
||||
jsonPointers:
|
||||
- /webhooks/0/clientConfig/caBundle
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
139
argocd/apps/traefik.yaml
Normal file
139
argocd/apps/traefik.yaml
Normal file
@@ -0,0 +1,139 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: traefik
|
||||
namespace: argocd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "-2"
|
||||
finalizers:
|
||||
- resources-finalizer.argocd.argoproj.io
|
||||
spec:
|
||||
project: default
|
||||
source:
|
||||
repoURL: https://traefik.github.io/charts
|
||||
chart: traefik
|
||||
targetRevision: ">=37.0.0"
|
||||
helm:
|
||||
values: |
|
||||
deployment:
|
||||
kind: DaemonSet
|
||||
podAnnotations:
|
||||
prometheus.io/scrape: "true"
|
||||
prometheus.io/port: "9100"
|
||||
|
||||
ingressClass:
|
||||
enabled: true
|
||||
isDefaultClass: true
|
||||
|
||||
additionalArguments:
|
||||
- "--api.dashboard=true"
|
||||
- "--ping=true"
|
||||
- "--metrics.prometheus=true"
|
||||
- "--metrics.prometheus.entrypoint=metrics"
|
||||
- "--entryPoints.ssh.address=:2222/tcp"
|
||||
- "--entryPoints.rtc-tcp-mrt0rtikize.address=:30009/tcp"
|
||||
- "--entryPoints.rtc-udp-mrt0rtikize.address=:30008/udp"
|
||||
- "--entryPoints.rtc-tcp-t0rt1k.address=:30007/tcp"
|
||||
- "--entryPoints.rtc-udp-t0rt1k.address=:30006/udp"
|
||||
- "--entryPoints.rtc-tcp-roglog.address=:30005/tcp"
|
||||
- "--entryPoints.rtc-udp-roglog.address=:30004/udp"
|
||||
- "--providers.kubernetesingress.ingressclass=traefik"
|
||||
- "--providers.kubernetesingress.ingressendpoint.publishedservice=traefik/traefik"
|
||||
- "--accesslog=true"
|
||||
- "--log.level=INFO"
|
||||
|
||||
ports:
|
||||
web:
|
||||
port: 8080
|
||||
exposedPort: 80
|
||||
http:
|
||||
redirections:
|
||||
entryPoint:
|
||||
to: websecure
|
||||
scheme: https
|
||||
permanent: true
|
||||
websecure:
|
||||
port: 8443
|
||||
exposedPort: 443
|
||||
ssh:
|
||||
port: 2222
|
||||
exposedPort: 22
|
||||
protocol: TCP
|
||||
expose:
|
||||
default: true
|
||||
rtc-tcp-mrt0rtikize:
|
||||
port: 30009
|
||||
exposedPort: 30009
|
||||
protocol: TCP
|
||||
expose:
|
||||
default: true
|
||||
rtc-udp-mrt0rtikize:
|
||||
port: 30008
|
||||
exposedPort: 30008
|
||||
protocol: UDP
|
||||
expose:
|
||||
default: true
|
||||
rtc-tcp-t0rt1k:
|
||||
port: 30007
|
||||
exposedPort: 30007
|
||||
protocol: TCP
|
||||
expose:
|
||||
default: true
|
||||
rtc-udp-t0rt1k:
|
||||
port: 30006
|
||||
exposedPort: 30006
|
||||
protocol: UDP
|
||||
expose:
|
||||
default: true
|
||||
rtc-tcp-roglog:
|
||||
port: 30005
|
||||
exposedPort: 30005
|
||||
protocol: TCP
|
||||
expose:
|
||||
default: true
|
||||
rtc-udp-roglog:
|
||||
port: 30004
|
||||
exposedPort: 30004
|
||||
protocol: UDP
|
||||
expose:
|
||||
default: true
|
||||
metrics:
|
||||
port: 9100
|
||||
expose:
|
||||
default: false
|
||||
traefik:
|
||||
port: 9000
|
||||
expose:
|
||||
default: false
|
||||
|
||||
service:
|
||||
type: LoadBalancer
|
||||
annotations:
|
||||
service.beta.kubernetes.io/yandex-load-balancer-name: traefik
|
||||
service.beta.kubernetes.io/yandex-load-balancer-specification: '{"type": "network-load-balancer"}'
|
||||
service.beta.kubernetes.io/yandex-load-balancer-type: external
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 256Mi
|
||||
|
||||
env:
|
||||
- name: POD_NAME
|
||||
valueFrom:
|
||||
fieldRef:
|
||||
fieldPath: metadata.name
|
||||
- name: POD_NAMESPACE
|
||||
valueFrom:
|
||||
fieldRef:
|
||||
fieldPath: metadata.namespace
|
||||
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: traefik
|
||||
syncPolicy:
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
26
bootstrap/argocd/ingress.yaml
Normal file
26
bootstrap/argocd/ingress.yaml
Normal file
@@ -0,0 +1,26 @@
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: argocd
|
||||
namespace: argocd
|
||||
annotations:
|
||||
cert-manager.io/cluster-issuer: letsencrypt-production
|
||||
traefik.ingress.kubernetes.io/router.entrypoints: websecure
|
||||
traefik.ingress.kubernetes.io/router.tls: "true"
|
||||
spec:
|
||||
ingressClassName: traefik
|
||||
tls:
|
||||
- hosts:
|
||||
- argocd.prod.t01tt.tech
|
||||
secretName: argocd-tls
|
||||
rules:
|
||||
- host: argocd.prod.t01tt.tech
|
||||
http:
|
||||
paths:
|
||||
- path: /
|
||||
pathType: Prefix
|
||||
backend:
|
||||
service:
|
||||
name: argocd-server
|
||||
port:
|
||||
number: 80
|
||||
28
bootstrap/argocd/install.sh
Executable file
28
bootstrap/argocd/install.sh
Executable file
@@ -0,0 +1,28 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
export KUBECONFIG="$(dirname "$(realpath "$0")")/../../kubeconfig"
|
||||
|
||||
echo "=== Installing ArgoCD ==="
|
||||
|
||||
helm repo add argo https://argoproj.github.io/argo-helm 2>/dev/null || true
|
||||
helm repo update argo
|
||||
|
||||
helm upgrade --install argocd argo/argo-cd \
|
||||
--namespace argocd \
|
||||
--create-namespace \
|
||||
--values "$(dirname "$0")/values.yaml" \
|
||||
--wait \
|
||||
--timeout 300s
|
||||
|
||||
echo ""
|
||||
echo "=== ArgoCD installed ==="
|
||||
echo ""
|
||||
echo "To access ArgoCD UI:"
|
||||
echo " kubectl port-forward svc/argocd-server -n argocd 8080:80"
|
||||
echo ""
|
||||
echo "Admin password:"
|
||||
kubectl -n argocd get secret argocd-initial-admin-secret -o jsonpath="{.data.password}" | base64 -d
|
||||
echo ""
|
||||
echo ""
|
||||
echo "Login with username: admin"
|
||||
20
bootstrap/argocd/values.yaml
Normal file
20
bootstrap/argocd/values.yaml
Normal file
@@ -0,0 +1,20 @@
|
||||
server:
|
||||
extraArgs:
|
||||
- --insecure
|
||||
|
||||
configs:
|
||||
params:
|
||||
server.insecure: true
|
||||
cm:
|
||||
timeout.reconciliation: 180s
|
||||
helm.timeoutSeconds: "300"
|
||||
resource.customizations.health.networking.k8s.io_Ingress: |
|
||||
hs = {}
|
||||
hs.status = "Healthy"
|
||||
hs.message = "Ingress is synced"
|
||||
return hs
|
||||
|
||||
redis:
|
||||
image:
|
||||
repository: docker.io/library/redis
|
||||
tag: 7.4-alpine
|
||||
64
bootstrap/gitea/deployment.yaml
Normal file
64
bootstrap/gitea/deployment.yaml
Normal file
@@ -0,0 +1,64 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: gitea
|
||||
namespace: gitea
|
||||
spec:
|
||||
replicas: 1
|
||||
strategy:
|
||||
type: Recreate
|
||||
selector:
|
||||
matchLabels:
|
||||
app: gitea
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: gitea
|
||||
spec:
|
||||
containers:
|
||||
- name: gitea
|
||||
image: gitea/gitea:1.24
|
||||
ports:
|
||||
- containerPort: 3000
|
||||
name: http
|
||||
- containerPort: 22
|
||||
name: ssh
|
||||
env:
|
||||
- name: GITEA__database__DB_TYPE
|
||||
value: sqlite3
|
||||
- name: GITEA__server__DOMAIN
|
||||
value: git.prod.t01tt.tech
|
||||
- name: GITEA__server__ROOT_URL
|
||||
value: https://git.prod.t01tt.tech
|
||||
- name: GITEA__server__HTTP_PORT
|
||||
value: "3000"
|
||||
- name: GITEA__server__SSH_PORT
|
||||
value: "22"
|
||||
- name: GITEA__service__DISABLE_REGISTRATION
|
||||
value: "true"
|
||||
volumeMounts:
|
||||
- name: data
|
||||
mountPath: /data
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 512Mi
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /
|
||||
port: 3000
|
||||
initialDelaySeconds: 10
|
||||
periodSeconds: 10
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /
|
||||
port: 3000
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
volumes:
|
||||
- name: data
|
||||
persistentVolumeClaim:
|
||||
claimName: gitea-data
|
||||
26
bootstrap/gitea/ingress.yaml
Normal file
26
bootstrap/gitea/ingress.yaml
Normal file
@@ -0,0 +1,26 @@
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: gitea
|
||||
namespace: gitea
|
||||
annotations:
|
||||
cert-manager.io/cluster-issuer: letsencrypt-production
|
||||
traefik.ingress.kubernetes.io/router.entrypoints: websecure
|
||||
traefik.ingress.kubernetes.io/router.tls: "true"
|
||||
spec:
|
||||
ingressClassName: traefik
|
||||
tls:
|
||||
- hosts:
|
||||
- git.prod.t01tt.tech
|
||||
secretName: gitea-tls
|
||||
rules:
|
||||
- host: git.prod.t01tt.tech
|
||||
http:
|
||||
paths:
|
||||
- path: /
|
||||
pathType: Prefix
|
||||
backend:
|
||||
service:
|
||||
name: gitea
|
||||
port:
|
||||
number: 3000
|
||||
4
bootstrap/gitea/namespace.yaml
Normal file
4
bootstrap/gitea/namespace.yaml
Normal file
@@ -0,0 +1,4 @@
|
||||
apiVersion: v1
|
||||
kind: Namespace
|
||||
metadata:
|
||||
name: gitea
|
||||
11
bootstrap/gitea/pvc.yaml
Normal file
11
bootstrap/gitea/pvc.yaml
Normal file
@@ -0,0 +1,11 @@
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: gitea-data
|
||||
namespace: gitea
|
||||
spec:
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
resources:
|
||||
requests:
|
||||
storage: 2Gi
|
||||
15
bootstrap/gitea/service.yaml
Normal file
15
bootstrap/gitea/service.yaml
Normal file
@@ -0,0 +1,15 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: gitea
|
||||
namespace: gitea
|
||||
spec:
|
||||
selector:
|
||||
app: gitea
|
||||
ports:
|
||||
- name: http
|
||||
port: 3000
|
||||
targetPort: 3000
|
||||
- name: ssh
|
||||
port: 22
|
||||
targetPort: 22
|
||||
7
fqdns
Normal file
7
fqdns
Normal file
@@ -0,0 +1,7 @@
|
||||
DNS records to add (all → 81.26.181.240)
|
||||
matrix.t0rt1k.tech
|
||||
auth.t0rt1k.tech
|
||||
chat.t0rt1k.tech (already exists, points to old IP)
|
||||
admin.t0rt1k.tech
|
||||
rtc.t0rt1k.tech (already exists, points to old IP)
|
||||
t0rt1k.tech (well-known) — already exists, update IP. call.t0rt1k.tech — remove (no longer needed).
|
||||
29
manifests/cert-manager/cluster-issuers.yaml
Normal file
29
manifests/cert-manager/cluster-issuers.yaml
Normal file
@@ -0,0 +1,29 @@
|
||||
apiVersion: cert-manager.io/v1
|
||||
kind: ClusterIssuer
|
||||
metadata:
|
||||
name: letsencrypt-production
|
||||
spec:
|
||||
acme:
|
||||
email: i_am@rogov.al
|
||||
privateKeySecretRef:
|
||||
name: letsencrypt-production-account-key
|
||||
server: https://acme-v02.api.letsencrypt.org/directory
|
||||
solvers:
|
||||
- http01:
|
||||
ingress:
|
||||
class: traefik
|
||||
---
|
||||
apiVersion: cert-manager.io/v1
|
||||
kind: ClusterIssuer
|
||||
metadata:
|
||||
name: letsencrypt-staging
|
||||
spec:
|
||||
acme:
|
||||
email: i_am@rogov.al
|
||||
privateKeySecretRef:
|
||||
name: letsencrypt-staging-account-key
|
||||
server: https://acme-staging-v02.api.letsencrypt.org/directory
|
||||
solvers:
|
||||
- http01:
|
||||
ingress:
|
||||
class: traefik
|
||||
41
manifests/cnpg/cluster.yaml
Normal file
41
manifests/cnpg/cluster.yaml
Normal file
@@ -0,0 +1,41 @@
|
||||
apiVersion: postgresql.cnpg.io/v1
|
||||
kind: Cluster
|
||||
metadata:
|
||||
name: shared-pg
|
||||
namespace: cnpg
|
||||
spec:
|
||||
instances: 3
|
||||
imageName: ghcr.io/cloudnative-pg/postgresql:16
|
||||
|
||||
resources:
|
||||
requests:
|
||||
memory: 1Gi
|
||||
cpu: 250m
|
||||
limits:
|
||||
memory: 2Gi
|
||||
cpu: 1000m
|
||||
|
||||
storage:
|
||||
size: 20Gi
|
||||
storageClass: yc-network-ssd
|
||||
|
||||
affinity:
|
||||
podAntiAffinityType: required
|
||||
|
||||
bootstrap:
|
||||
initdb:
|
||||
database: postgres
|
||||
owner: postgres
|
||||
|
||||
postgresql:
|
||||
parameters:
|
||||
shared_buffers: "512MB"
|
||||
effective_cache_size: "1536MB"
|
||||
maintenance_work_mem: "64MB"
|
||||
max_connections: "200"
|
||||
work_mem: "16MB"
|
||||
random_page_cost: "1.1"
|
||||
effective_io_concurrency: "200"
|
||||
|
||||
monitoring:
|
||||
enablePodMonitor: true
|
||||
66
manifests/cnpg/databases.yaml
Normal file
66
manifests/cnpg/databases.yaml
Normal file
@@ -0,0 +1,66 @@
|
||||
apiVersion: postgresql.cnpg.io/v1
|
||||
kind: Database
|
||||
metadata:
|
||||
name: synapse-mrt0rtikize
|
||||
namespace: cnpg
|
||||
spec:
|
||||
name: synapse_mrt0rtikize
|
||||
owner: synapse_mrt0rtikize
|
||||
cluster:
|
||||
name: shared-pg
|
||||
---
|
||||
apiVersion: postgresql.cnpg.io/v1
|
||||
kind: Database
|
||||
metadata:
|
||||
name: mas-mrt0rtikize
|
||||
namespace: cnpg
|
||||
spec:
|
||||
name: mas_mrt0rtikize
|
||||
owner: mas_mrt0rtikize
|
||||
cluster:
|
||||
name: shared-pg
|
||||
---
|
||||
apiVersion: postgresql.cnpg.io/v1
|
||||
kind: Database
|
||||
metadata:
|
||||
name: synapse-t0rt1k
|
||||
namespace: cnpg
|
||||
spec:
|
||||
name: synapse_t0rt1k
|
||||
owner: synapse_t0rt1k
|
||||
cluster:
|
||||
name: shared-pg
|
||||
---
|
||||
apiVersion: postgresql.cnpg.io/v1
|
||||
kind: Database
|
||||
metadata:
|
||||
name: mas-t0rt1k
|
||||
namespace: cnpg
|
||||
spec:
|
||||
name: mas_t0rt1k
|
||||
owner: mas_t0rt1k
|
||||
cluster:
|
||||
name: shared-pg
|
||||
---
|
||||
apiVersion: postgresql.cnpg.io/v1
|
||||
kind: Database
|
||||
metadata:
|
||||
name: synapse-roglog
|
||||
namespace: cnpg
|
||||
spec:
|
||||
name: synapse_roglog
|
||||
owner: synapse_roglog
|
||||
cluster:
|
||||
name: shared-pg
|
||||
---
|
||||
apiVersion: postgresql.cnpg.io/v1
|
||||
kind: Database
|
||||
metadata:
|
||||
name: mas-roglog
|
||||
namespace: cnpg
|
||||
spec:
|
||||
name: mas_roglog
|
||||
owner: mas_roglog
|
||||
cluster:
|
||||
name: shared-pg
|
||||
|
||||
4
manifests/cnpg/namespace.yaml
Normal file
4
manifests/cnpg/namespace.yaml
Normal file
@@ -0,0 +1,4 @@
|
||||
apiVersion: v1
|
||||
kind: Namespace
|
||||
metadata:
|
||||
name: cnpg
|
||||
13
manifests/gitea/ingressroute-ssh.yaml
Normal file
13
manifests/gitea/ingressroute-ssh.yaml
Normal file
@@ -0,0 +1,13 @@
|
||||
apiVersion: traefik.io/v1alpha1
|
||||
kind: IngressRouteTCP
|
||||
metadata:
|
||||
name: gitea-ssh
|
||||
namespace: gitea
|
||||
spec:
|
||||
entryPoints:
|
||||
- ssh
|
||||
routes:
|
||||
- match: HostSNI(`*`)
|
||||
services:
|
||||
- name: gitea
|
||||
port: 22
|
||||
13
manifests/matrix-mrt0rtikize/ingressroute-rtc-tcp.yaml
Normal file
13
manifests/matrix-mrt0rtikize/ingressroute-rtc-tcp.yaml
Normal file
@@ -0,0 +1,13 @@
|
||||
apiVersion: traefik.io/v1alpha1
|
||||
kind: IngressRouteTCP
|
||||
metadata:
|
||||
name: rtc-tcp
|
||||
namespace: matrix-mrt0rtikize
|
||||
spec:
|
||||
entryPoints:
|
||||
- rtc-tcp-mrt0rtikize
|
||||
routes:
|
||||
- match: HostSNI(`*`)
|
||||
services:
|
||||
- name: matrix-mrt0rtikize-matrix-rtc-sfu-tcp
|
||||
port: 30009
|
||||
12
manifests/matrix-mrt0rtikize/ingressroute-rtc-udp.yaml
Normal file
12
manifests/matrix-mrt0rtikize/ingressroute-rtc-udp.yaml
Normal file
@@ -0,0 +1,12 @@
|
||||
apiVersion: traefik.io/v1alpha1
|
||||
kind: IngressRouteUDP
|
||||
metadata:
|
||||
name: rtc-udp
|
||||
namespace: matrix-mrt0rtikize
|
||||
spec:
|
||||
entryPoints:
|
||||
- rtc-udp-mrt0rtikize
|
||||
routes:
|
||||
- services:
|
||||
- name: matrix-mrt0rtikize-matrix-rtc-sfu-muxed-udp
|
||||
port: 30008
|
||||
13
manifests/matrix-roglog/ingressroute-rtc-tcp.yaml
Normal file
13
manifests/matrix-roglog/ingressroute-rtc-tcp.yaml
Normal file
@@ -0,0 +1,13 @@
|
||||
apiVersion: traefik.io/v1alpha1
|
||||
kind: IngressRouteTCP
|
||||
metadata:
|
||||
name: rtc-tcp
|
||||
namespace: matrix-roglog
|
||||
spec:
|
||||
entryPoints:
|
||||
- rtc-tcp-roglog
|
||||
routes:
|
||||
- match: HostSNI(`*`)
|
||||
services:
|
||||
- name: matrix-roglog-matrix-rtc-sfu-tcp
|
||||
port: 30005
|
||||
12
manifests/matrix-roglog/ingressroute-rtc-udp.yaml
Normal file
12
manifests/matrix-roglog/ingressroute-rtc-udp.yaml
Normal file
@@ -0,0 +1,12 @@
|
||||
apiVersion: traefik.io/v1alpha1
|
||||
kind: IngressRouteUDP
|
||||
metadata:
|
||||
name: rtc-udp
|
||||
namespace: matrix-roglog
|
||||
spec:
|
||||
entryPoints:
|
||||
- rtc-udp-roglog
|
||||
routes:
|
||||
- services:
|
||||
- name: matrix-roglog-matrix-rtc-sfu-muxed-udp
|
||||
port: 30004
|
||||
13
manifests/matrix-t0rt1k/ingressroute-rtc-tcp.yaml
Normal file
13
manifests/matrix-t0rt1k/ingressroute-rtc-tcp.yaml
Normal file
@@ -0,0 +1,13 @@
|
||||
apiVersion: traefik.io/v1alpha1
|
||||
kind: IngressRouteTCP
|
||||
metadata:
|
||||
name: rtc-tcp
|
||||
namespace: matrix-t0rt1k
|
||||
spec:
|
||||
entryPoints:
|
||||
- rtc-tcp-t0rt1k
|
||||
routes:
|
||||
- match: HostSNI(`*`)
|
||||
services:
|
||||
- name: matrix-t0rt1k-matrix-rtc-sfu-tcp
|
||||
port: 30007
|
||||
12
manifests/matrix-t0rt1k/ingressroute-rtc-udp.yaml
Normal file
12
manifests/matrix-t0rt1k/ingressroute-rtc-udp.yaml
Normal file
@@ -0,0 +1,12 @@
|
||||
apiVersion: traefik.io/v1alpha1
|
||||
kind: IngressRouteUDP
|
||||
metadata:
|
||||
name: rtc-udp
|
||||
namespace: matrix-t0rt1k
|
||||
spec:
|
||||
entryPoints:
|
||||
- rtc-udp-t0rt1k
|
||||
routes:
|
||||
- services:
|
||||
- name: matrix-t0rt1k-matrix-rtc-sfu-muxed-udp
|
||||
port: 30006
|
||||
15
manifests/matrix-t0rt1k/vmpodscrape-synapse.yaml
Normal file
15
manifests/matrix-t0rt1k/vmpodscrape-synapse.yaml
Normal file
@@ -0,0 +1,15 @@
|
||||
apiVersion: operator.victoriametrics.com/v1beta1
|
||||
kind: VMPodScrape
|
||||
metadata:
|
||||
name: synapse
|
||||
namespace: matrix-t0rt1k
|
||||
spec:
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- matrix-t0rt1k
|
||||
podMetricsEndpoints:
|
||||
- port: synapse-metrics
|
||||
path: /metrics
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: matrix-server
|
||||
26
manifests/metrics/grafana/ingress.yaml
Normal file
26
manifests/metrics/grafana/ingress.yaml
Normal file
@@ -0,0 +1,26 @@
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: grafana
|
||||
namespace: metrics
|
||||
annotations:
|
||||
cert-manager.io/cluster-issuer: letsencrypt-production
|
||||
traefik.ingress.kubernetes.io/router.entrypoints: websecure
|
||||
traefik.ingress.kubernetes.io/router.tls: "true"
|
||||
spec:
|
||||
ingressClassName: traefik
|
||||
tls:
|
||||
- hosts:
|
||||
- grafana.prod.t01tt.tech
|
||||
secretName: grafana-tls
|
||||
rules:
|
||||
- host: grafana.prod.t01tt.tech
|
||||
http:
|
||||
paths:
|
||||
- path: /
|
||||
pathType: Prefix
|
||||
backend:
|
||||
service:
|
||||
name: monitoring-grafana
|
||||
port:
|
||||
number: 80
|
||||
17
manifests/metrics/grafana/loki-datasource.yaml
Normal file
17
manifests/metrics/grafana/loki-datasource.yaml
Normal file
@@ -0,0 +1,17 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: loki-grafana-ds
|
||||
namespace: metrics
|
||||
labels:
|
||||
grafana_datasource: "1"
|
||||
data:
|
||||
datasource.yaml: |
|
||||
apiVersion: 1
|
||||
datasources:
|
||||
- access: proxy
|
||||
isDefault: false
|
||||
name: Loki
|
||||
type: loki
|
||||
uid: Loki
|
||||
url: http://loki.metrics.svc.cluster.local:3100
|
||||
4
manifests/metrics/grafana/namespace.yaml
Normal file
4
manifests/metrics/grafana/namespace.yaml
Normal file
@@ -0,0 +1,4 @@
|
||||
apiVersion: v1
|
||||
kind: Namespace
|
||||
metadata:
|
||||
name: metrics
|
||||
244
scripts/backup-mrt0rtikize.sh
Executable file
244
scripts/backup-mrt0rtikize.sh
Executable file
@@ -0,0 +1,244 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
# ================================================================
|
||||
# Backup script for mrt0rtikize.ru Matrix instance (k3s cluster)
|
||||
# ================================================================
|
||||
# Output: backups/mrt0rtikize-YYYYMMDD-HHMMSS/
|
||||
#
|
||||
# Run this BEFORE switching DNS. Ensure TTL is already set to 60s
|
||||
# on all mrt0rtikize.ru DNS records (24h before planned cutover).
|
||||
#
|
||||
# Steps:
|
||||
# 1. Stop Synapse + MAS to prevent DB writes
|
||||
# 2. Dump PostgreSQL (built-in PG from ESS chart)
|
||||
# 3. Export generated secrets (CRITICAL: signing key, MAS keys)
|
||||
# 4. Export deployment markers ConfigMap
|
||||
# 5. Export ESS ArgoCD Application (values reference)
|
||||
# 6. Export media file locations (manual restore, noted in README)
|
||||
# ================================================================
|
||||
|
||||
readonly K3S_KUBECONFIG="${KUBECONFIG:-/home/mrt0rtikize/infra/k3s/config}"
|
||||
readonly NS="matrix-mrt0rtikize"
|
||||
readonly BACKUP_BASE="$(dirname "$(realpath "$0")")/../backups"
|
||||
readonly TIMESTAMP="$(date +%Y%m%d-%H%M%S)"
|
||||
readonly BACKUP_DIR="${BACKUP_BASE}/${NS}-${TIMESTAMP}"
|
||||
|
||||
readonly K="${KUBECTL:-kubectl} --kubeconfig ${K3S_KUBECONFIG}"
|
||||
|
||||
# Colors
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
YELLOW='\033[1;33m'
|
||||
NC='\033[0m'
|
||||
|
||||
log() { echo -e "${GREEN}[$(date +%H:%M:%S)]${NC} $*"; }
|
||||
warn() { echo -e "${YELLOW}[$(date +%H:%M:%S)] WARN:${NC} $*"; }
|
||||
err() { echo -e "${RED}[$(date +%H:%M:%S)] ERROR:${NC} $*"; }
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Prerequisites
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Checking prerequisites ==="
|
||||
|
||||
if ! ${K} get ns "${NS}" >/dev/null 2>&1; then
|
||||
err "Namespace ${NS} not found on k3s cluster. Check KUBECONFIG (${K3S_KUBECONFIG})."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
mkdir -p "${BACKUP_DIR}"
|
||||
log "Backup directory: ${BACKUP_DIR}"
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 1: Backup Synapse media files (BEFORE stopping Synapse)
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 1: Backing up Synapse media ==="
|
||||
|
||||
SYNAPSE_POD_NAME=$( ${K} -n "${NS}" get pods -l "app.kubernetes.io/component=matrix-server" -o jsonpath='{.items[?(@.status.phase=="Running")].metadata.name}' 2>/dev/null)
|
||||
|
||||
if [ -z "${SYNAPSE_POD_NAME}" ]; then
|
||||
warn "No running Synapse pod found. Cannot backup media."
|
||||
else
|
||||
log "Using Synapse pod: ${SYNAPSE_POD_NAME}"
|
||||
${K} exec -n "${NS}" "${SYNAPSE_POD_NAME}" -- tar czf /tmp/synapse-media.tar.gz -C /media media_store/
|
||||
${K} cp "${NS}/${SYNAPSE_POD_NAME}:/tmp/synapse-media.tar.gz" "${BACKUP_DIR}/synapse-media.tar.gz"
|
||||
${K} exec -n "${NS}" "${SYNAPSE_POD_NAME}" -- rm /tmp/synapse-media.tar.gz
|
||||
log "Synapse media saved: ${BACKUP_DIR}/synapse-media.tar.gz ($(du -h "${BACKUP_DIR}/synapse-media.tar.gz" | cut -f1))"
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 2: Stop Synapse + MAS (start downtime window)
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 2: Stopping Synapse + MAS ==="
|
||||
|
||||
SYNAPSE_READY=$(${K} -n "${NS}" get sts "${NS}-synapse-main" -o jsonpath='{.status.readyReplicas}' 2>/dev/null || echo "0")
|
||||
MAS_READY=$(${K} -n "${NS}" get deploy "${NS}-matrix-authentication-service" -o jsonpath='{.status.readyReplicas}' 2>/dev/null || echo "0")
|
||||
|
||||
if [ "${SYNAPSE_READY}" != "0" ]; then
|
||||
log "Scaling Synapse to 0..."
|
||||
${K} -n "${NS}" scale sts "${NS}-synapse-main" --replicas=0
|
||||
else
|
||||
log "Synapse already scaled to 0."
|
||||
fi
|
||||
|
||||
if [ "${MAS_READY}" != "0" ]; then
|
||||
log "Scaling MAS to 0..."
|
||||
${K} -n "${NS}" scale deploy "${NS}-matrix-authentication-service" --replicas=0
|
||||
else
|
||||
log "MAS already scaled to 0."
|
||||
fi
|
||||
|
||||
log "Waiting for Synapse + MAS pods to terminate..."
|
||||
${K} -n "${NS}" wait --for=delete pod -l "app.kubernetes.io/component=matrix-server" --timeout=120s 2>/dev/null || warn "Some Synapse pods may still be terminating."
|
||||
${K} -n "${NS}" wait --for=delete pod -l "app.kubernetes.io/component=matrix-authentication" --timeout=120s 2>/dev/null || warn "Some MAS pods may still be terminating."
|
||||
|
||||
log "Synapse + MAS stopped."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 3: Dump PostgreSQL
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 3: Dumping PostgreSQL ==="
|
||||
|
||||
PG_POD=$(${K} -n "${NS}" get pods -l "app.kubernetes.io/name=postgres" -o jsonpath='{.items[0].metadata.name}' 2>/dev/null)
|
||||
if [ -z "${PG_POD}" ]; then
|
||||
PG_POD=$(${K} -n "${NS}" get pods -o name 2>/dev/null | grep postgres | head -1 | cut -d/ -f2)
|
||||
fi
|
||||
|
||||
if [ -z "${PG_POD}" ]; then
|
||||
err "Could not find PostgreSQL pod in namespace ${NS}."
|
||||
err "Available pods:"
|
||||
${K} -n "${NS}" get pods
|
||||
exit 1
|
||||
fi
|
||||
|
||||
log "Using PostgreSQL pod: ${PG_POD}"
|
||||
|
||||
${K} exec -n "${NS}" "${PG_POD}" -- pg_dumpall -U postgres > "${BACKUP_DIR}/dump-all.sql"
|
||||
log "PostgreSQL dump saved: ${BACKUP_DIR}/dump-all.sql ($(wc -c < "${BACKUP_DIR}/dump-all.sql") bytes)"
|
||||
|
||||
${K} exec -n "${NS}" "${PG_POD}" -- pg_dump -U postgres -d synapse > "${BACKUP_DIR}/dump-synapse.sql" 2>/dev/null || \
|
||||
warn "Could not dump synapse DB individually (will use dump-all.sql for restore)."
|
||||
|
||||
${K} exec -n "${NS}" "${PG_POD}" -- pg_dump -U postgres -d matrixauthenticationservice > "${BACKUP_DIR}/dump-mas.sql" 2>/dev/null || \
|
||||
warn "Could not dump MAS DB individually (will use dump-all.sql for restore)."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 4: Export generated secrets (CRITICAL)
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 4: Exporting generated secrets ==="
|
||||
|
||||
if ${K} -n "${NS}" get secret "${NS}-generated" >/dev/null 2>&1; then
|
||||
${K} -n "${NS}" get secret "${NS}-generated" -o yaml > "${BACKUP_DIR}/secret-generated.yaml"
|
||||
log "Generated secret saved: ${BACKUP_DIR}/secret-generated.yaml"
|
||||
else
|
||||
err "CRITICAL: ${NS}-generated secret NOT FOUND!"
|
||||
err "This contains SYNAPSE_SIGNING_KEY, MAS keys, and MACAROON."
|
||||
err "Without it, federation identity is lost and all rooms break."
|
||||
err "Available secrets:"
|
||||
${K} -n "${NS}" get secrets
|
||||
exit 1
|
||||
fi
|
||||
|
||||
log "Secret contents (verify these exist):"
|
||||
${K} -n "${NS}" get secret "${NS}-generated" -o jsonpath='{.data}' | python3 -c "
|
||||
import json, sys
|
||||
keys = ['SYNAPSE_SIGNING_KEY', 'MAS_ENCRYPTION_SECRET', 'MAS_RSA_PRIVATE_KEY',
|
||||
'SYNAPSE_MACAROON', 'MAS_SYNAPSE_SHARED_SECRET',
|
||||
'POSTGRES_SYNAPSE_PASSWORD', 'POSTGRES_MATRIX_AUTHENTICATION_SERVICE_PASSWORD']
|
||||
d = json.load(sys.stdin)
|
||||
for k in keys:
|
||||
present = 'OK' if k in d else 'MISSING!'
|
||||
print(f' {k}: {present}')
|
||||
" 2>/dev/null || warn "Could not verify secret keys."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 5: Export deployment markers
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 5: Exporting deployment markers ==="
|
||||
|
||||
MARKER_CM=$(${K} -n "${NS}" get cm -l "app.kubernetes.io/managed-by=matrix-tools-deployment-markers" -o jsonpath='{.items[0].metadata.name}' 2>/dev/null)
|
||||
if [ -n "${MARKER_CM}" ]; then
|
||||
${K} -n "${NS}" get cm "${MARKER_CM}" -o yaml > "${BACKUP_DIR}/markers.yaml"
|
||||
log "Deployment markers saved: ${BACKUP_DIR}/markers.yaml"
|
||||
else
|
||||
warn "No deployment markers ConfigMap found (non-critical, ESS may regenerate)."
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 6: Export ESS values from ArgoCD
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 6: Exporting ESS ArgoCD application ==="
|
||||
|
||||
if ${K} -n argocd get application "${NS}" >/dev/null 2>&1; then
|
||||
${K} -n argocd get application "${NS}" -o yaml > "${BACKUP_DIR}/argo-app.yaml"
|
||||
log "ArgoCD Application saved: ${BACKUP_DIR}/argo-app.yaml"
|
||||
else
|
||||
warn "ArgoCD Application '${NS}' not found (running without ArgoCD?)."
|
||||
warn "Save your ESS values manually from helm get values or git."
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Write README
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Writing README ==="
|
||||
|
||||
cat > "${BACKUP_DIR}/README.txt" << READEOF
|
||||
Backup for ${NS} — ${TIMESTAMP}
|
||||
==================================
|
||||
|
||||
Files:
|
||||
dump-all.sql Full PostgreSQL dump (pg_dumpall)
|
||||
secret-generated.yaml CRITICAL: contains SYNAPSE_SIGNING_KEY, MAS keys, MACAROON
|
||||
markers.yaml Deployment markers ConfigMap (ESS state tracking)
|
||||
argo-app.yaml ESS ArgoCD Application (values reference)
|
||||
synapse-media.tar.gz Synapse media files (local + remote content)
|
||||
dump-synapse.sql Synapse DB only (optional, for easier restore)
|
||||
dump-mas.sql MAS DB only (optional, for easier restore)
|
||||
README.txt This file
|
||||
|
||||
CRITICAL: Do NOT lose secret-generated.yaml.
|
||||
- SYNAPSE_SIGNING_KEY identifies this server to the Matrix federation.
|
||||
Changing it breaks all existing rooms and federation relationships.
|
||||
- MAS_ENCRYPTION_SECRET encrypts user sessions.
|
||||
Changing it forces all users to re-login.
|
||||
- SYNAPSE_MACAROON is the admin API token.
|
||||
|
||||
Restore order on new cluster:
|
||||
1. Create CNPG databases + secrets on new cluster (see PLAN.md)
|
||||
2. Deploy ESS chart on new cluster (starts with empty DB)
|
||||
3. Stop Synapse + MAS on new cluster
|
||||
4. Restore PG dump into CNPG shared-pg
|
||||
5. Apply this secret-generated.yaml to new cluster's namespace
|
||||
6. Apply markers.yaml
|
||||
7. Restore media: kubectl cp synapse-media.tar.gz to new Synapse pod, untar to /media/
|
||||
8. Restart Synapse + MAS on new cluster
|
||||
9. Verify: login, federation tester, Element Call
|
||||
10. Cut DNS to new NLB IP
|
||||
READEOF
|
||||
|
||||
log "README saved: ${BACKUP_DIR}/README.txt"
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Summary
|
||||
# -------------------------------------------------------------------
|
||||
cat <<SUMMARY
|
||||
|
||||
${GREEN}========================================${NC}
|
||||
${GREEN} Backup Complete: ${NS}${NC}
|
||||
${GREEN}========================================${NC}
|
||||
|
||||
Directory: ${BACKUP_DIR}
|
||||
Size: $(du -sh "${BACKUP_DIR}" | cut -f1)
|
||||
|
||||
${YELLOW}Next steps:${NC}
|
||||
1. Verify PG dump: head -20 ${BACKUP_DIR}/dump-all.sql
|
||||
2. Verify secrets: grep SYNAPSE_SIGNING_KEY ${BACKUP_DIR}/secret-generated.yaml
|
||||
3. Copy media files from node path (see media-info.txt)
|
||||
4. Proceed with migration on new cluster
|
||||
|
||||
${RED}WARNING: Synapse + MAS are still SCALED TO 0 on k3s.${NC}
|
||||
To restore service on k3s (if migration is postponed):
|
||||
${K} -n ${NS} scale sts ${NS}-synapse-main --replicas=1
|
||||
${K} -n ${NS} scale deploy ${NS}-matrix-authentication-service --replicas=1
|
||||
|
||||
SUMMARY
|
||||
245
scripts/backup-yc-playground.sh
Executable file
245
scripts/backup-yc-playground.sh
Executable file
@@ -0,0 +1,245 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
# ================================================================
|
||||
# Backup script for Matrix instances on yc-playground cluster
|
||||
# ================================================================
|
||||
# Backs up the old chart (matrix-2.9.17) prod instances:
|
||||
# t0rt1k.tech, roglog.space, uretra.space
|
||||
#
|
||||
# Usage: ./backup-yc-playground.sh <name> [--no-downtime]
|
||||
# Example: ./backup-yc-playground.sh t0rt1k
|
||||
# ./backup-yc-playground.sh t0rt1k --no-downtime (test, no scaling)
|
||||
# ================================================================
|
||||
|
||||
readonly YC_CONTEXT="yc-playground"
|
||||
readonly K="${KUBECTL:-kubectl} --context ${YC_CONTEXT}"
|
||||
readonly BACKUP_BASE="$(dirname "$(realpath "$0")")/../backups"
|
||||
readonly TIMESTAMP="$(date +%Y%m%d-%H%M%S)"
|
||||
|
||||
# Colors
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
YELLOW='\033[1;33m'
|
||||
NC='\033[0m'
|
||||
log() { echo -e "${GREEN}[$(date +%H:%M:%S)]${NC} $*"; }
|
||||
warn() { echo -e "${YELLOW}[$(date +%H:%M:%S)] WARN:${NC} $*"; }
|
||||
err() { echo -e "${RED}[$(date +%H:%M:%S)] ERROR:${NC} $*"; }
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Parse args
|
||||
# -------------------------------------------------------------------
|
||||
DOWNTIME=true
|
||||
NAME=""
|
||||
for arg in "$@"; do
|
||||
case "$arg" in
|
||||
--no-downtime) DOWNTIME=false ;;
|
||||
*) NAME="$arg" ;;
|
||||
esac
|
||||
done
|
||||
|
||||
if [ -z "${NAME}" ]; then
|
||||
echo "Usage: $0 <name> [--no-downtime]"
|
||||
echo " name: t0rt1k | roglog | uretra"
|
||||
echo " --no-downtime: skip scale up/down (test run)"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
readonly NS="matrix-${NAME}"
|
||||
readonly BACKUP_DIR="${BACKUP_BASE}/matrix-${NAME}-${TIMESTAMP}"
|
||||
|
||||
# Synapse labels
|
||||
readonly SYNAPSE_LABEL="app.kubernetes.io/instance=chat,app.kubernetes.io/name=matrix"
|
||||
# MAS labels
|
||||
readonly MAS_LABEL="app=mas"
|
||||
readonly MAS_PG_LABEL="app=mas-postgresql"
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Prerequisites
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Backing up ${NS} (downtime=${DOWNTIME}) ==="
|
||||
|
||||
if ! ${K} get ns "${NS}" >/dev/null 2>&1; then
|
||||
err "Namespace ${NS} not found on yc-playground."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
mkdir -p "${BACKUP_DIR}"
|
||||
log "Backup directory: ${BACKUP_DIR}"
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 1: Backup Synapse media
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 1: Backing up Synapse media ==="
|
||||
|
||||
SYNAPSE_POD=$(${K} -n "${NS}" get pods -l "${SYNAPSE_LABEL}" -o jsonpath='{.items[?(@.status.phase=="Running")].metadata.name}' 2>/dev/null)
|
||||
|
||||
if [ -n "${SYNAPSE_POD}" ]; then
|
||||
log "Synapse pod: ${SYNAPSE_POD}"
|
||||
# Check if media directory exists
|
||||
if ${K} exec -n "${NS}" "${SYNAPSE_POD}" -- test -d /data/media_store 2>/dev/null; then
|
||||
${K} exec -n "${NS}" "${SYNAPSE_POD}" -- tar czf /tmp/synapse-media.tar.gz -C /data media_store/
|
||||
${K} cp "${NS}/${SYNAPSE_POD}:/tmp/synapse-media.tar.gz" "${BACKUP_DIR}/synapse-media.tar.gz" 2>/dev/null || \
|
||||
${K} cp "${NS}/${SYNAPSE_POD}:tmp/synapse-media.tar.gz" "${BACKUP_DIR}/synapse-media.tar.gz"
|
||||
${K} exec -n "${NS}" "${SYNAPSE_POD}" -- rm -f /tmp/synapse-media.tar.gz
|
||||
log "Media saved: $(du -h "${BACKUP_DIR}/synapse-media.tar.gz" | cut -f1)"
|
||||
else
|
||||
warn "/data/media_store not found in Synapse pod."
|
||||
fi
|
||||
else
|
||||
warn "No running Synapse pod found — skipping media backup."
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 2: Stop Synapse + MAS
|
||||
# -------------------------------------------------------------------
|
||||
if ${DOWNTIME}; then
|
||||
log "=== Step 2: Stopping Synapse + MAS ==="
|
||||
|
||||
SYNAPSE_READY=$(${K} -n "${NS}" get deploy chat-matrix -o jsonpath='{.status.readyReplicas}' 2>/dev/null || echo "0")
|
||||
MAS_READY=$(${K} -n "${NS}" get deploy mas -o jsonpath='{.status.readyReplicas}' 2>/dev/null || echo "0")
|
||||
|
||||
if [ "${SYNAPSE_READY}" != "0" ]; then
|
||||
${K} -n "${NS}" scale deploy chat-matrix --replicas=0
|
||||
log "Synapse scaled to 0."
|
||||
else
|
||||
log "Synapse already scaled to 0."
|
||||
fi
|
||||
|
||||
if [ "${MAS_READY}" != "0" ]; then
|
||||
${K} -n "${NS}" scale deploy mas --replicas=0
|
||||
log "MAS scaled to 0."
|
||||
else
|
||||
log "MAS already scaled to 0."
|
||||
fi
|
||||
|
||||
${K} -n "${NS}" wait --for=delete pod -l "${SYNAPSE_LABEL}" --timeout=120s 2>/dev/null || warn "Synapse may still be terminating."
|
||||
${K} -n "${NS}" wait --for=delete pod -l "${MAS_LABEL}" --timeout=120s 2>/dev/null || warn "MAS may still be terminating."
|
||||
log "Synapse + MAS stopped."
|
||||
else
|
||||
log "=== Step 2: Skipping downtime (--no-downtime) ==="
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 3: Dump Synapse PostgreSQL
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 3: Dumping Synapse PostgreSQL ==="
|
||||
|
||||
# Get the postgres password from the secret
|
||||
SYNAPSE_PG_PW=$(${K} -n "${NS}" get secret chat-postgresql -o jsonpath='{.data.postgres-password}' 2>/dev/null | base64 -d)
|
||||
|
||||
if [ -z "${SYNAPSE_PG_PW}" ]; then
|
||||
SYNAPSE_PG_PW=$(${K} -n "${NS}" get secret chat-postgresql -o jsonpath='{.data.password}' 2>/dev/null | base64 -d)
|
||||
fi
|
||||
|
||||
if [ -z "${SYNAPSE_PG_PW}" ]; then
|
||||
warn "Could not read chat-postgresql secret — trying env var from pod."
|
||||
SYNAPSE_PG_PW=$(${K} exec -n "${NS}" chat-postgresql-0 -c postgresql -- bash -c 'echo $POSTGRES_POSTGRES_PASSWORD' 2>/dev/null)
|
||||
fi
|
||||
|
||||
${K} exec -n "${NS}" chat-postgresql-0 -c postgresql -- bash -c "env PGPASSWORD='${SYNAPSE_PG_PW}' pg_dump -U postgres -d matrix -f /bitnami/postgresql/data/dump.sql" 2>&1
|
||||
${K} cp "${NS}/chat-postgresql-0:/bitnami/postgresql/data/dump.sql" "${BACKUP_DIR}/dump-synapse.sql" 2>/dev/null || true
|
||||
${K} exec -n "${NS}" chat-postgresql-0 -c postgresql -- rm -f /bitnami/postgresql/data/dump.sql
|
||||
log "Synapse dump saved: ${BACKUP_DIR}/dump-synapse.sql ($(wc -c < "${BACKUP_DIR}/dump-synapse.sql") bytes)"
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 4: Dump MAS PostgreSQL
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 4: Dumping MAS PostgreSQL ==="
|
||||
|
||||
MAS_PG_POD=$(${K} -n "${NS}" get pods -l "${MAS_PG_LABEL}" -o jsonpath='{.items[0].metadata.name}' 2>/dev/null)
|
||||
|
||||
if [ -n "${MAS_PG_POD}" ]; then
|
||||
MAS_PG_PW=$(${K} exec -n "${NS}" "${MAS_PG_POD}" -c postgresql -- bash -c 'echo $POSTGRESQL_PASSWORD' 2>/dev/null)
|
||||
MAS_DB=$(${K} exec -n "${NS}" "${MAS_PG_POD}" -c postgresql -- bash -c 'echo $POSTGRESQL_DATABASE' 2>/dev/null)
|
||||
|
||||
if [ -n "${MAS_PG_PW}" ]; then
|
||||
${K} exec -n "${NS}" "${MAS_PG_POD}" -c postgresql -- bash -c "env PGPASSWORD='${MAS_PG_PW}' pg_dump -U '${MAS_DB:-mas}' -d '${MAS_DB:-mas}' -f /bitnami/postgresql/data/dump.sql" 2>&1
|
||||
${K} cp "${NS}/${MAS_PG_POD}:/bitnami/postgresql/data/dump.sql" "${BACKUP_DIR}/dump-mas.sql" 2>/dev/null || true
|
||||
${K} exec -n "${NS}" "${MAS_PG_POD}" -c postgresql -- rm -f /bitnami/postgresql/data/dump.sql
|
||||
log "MAS dump saved: ${BACKUP_DIR}/dump-mas.sql ($(wc -c < "${BACKUP_DIR}/dump-mas.sql") bytes)"
|
||||
else
|
||||
warn "Could not read MAS PG password — skipping MAS dump."
|
||||
fi
|
||||
else
|
||||
warn "No MAS PG pod found — skipping MAS dump."
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 5: Export secrets
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 5: Exporting secrets ==="
|
||||
|
||||
for secret in chat-matrix chat-postgresql mas matrixrtc-livekit; do
|
||||
if ${K} -n "${NS}" get secret "${secret}" >/dev/null 2>&1; then
|
||||
${K} -n "${NS}" get secret "${secret}" -o yaml > "${BACKUP_DIR}/secret-${secret}.yaml"
|
||||
log "Secret saved: secret-${secret}.yaml"
|
||||
else
|
||||
warn "Secret '${secret}' not found."
|
||||
fi
|
||||
done
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 6: Restart Synapse + MAS
|
||||
# -------------------------------------------------------------------
|
||||
if ${DOWNTIME}; then
|
||||
log "=== Step 6: Restarting Synapse + MAS ==="
|
||||
${K} -n "${NS}" scale deploy chat-matrix --replicas=1 2>/dev/null || warn "Could not scale Synapse."
|
||||
${K} -n "${NS}" scale deploy mas --replicas=1 2>/dev/null || warn "Could not scale MAS."
|
||||
log "Synapse + MAS restarted."
|
||||
else
|
||||
log "=== Step 6: Skipped (--no-downtime) ==="
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 7: Write README
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 7: Writing README ==="
|
||||
|
||||
cat > "${BACKUP_DIR}/README.txt" << READEOF
|
||||
Backup for ${NS} — ${TIMESTAMP}
|
||||
==================================
|
||||
|
||||
Instance: ${NAME} (namespace: ${NS})
|
||||
Chart: matrix-2.9.17 (old chart, NOT ESS)
|
||||
Dump PG: Synapse (chat-postgresql) + MAS (mas-postgresql)
|
||||
|
||||
Files:
|
||||
dump-synapse.sql Synapse PostgreSQL dump (pg_dump -U postgres -d matrix)
|
||||
dump-mas.sql MAS PostgreSQL dump (pg_dump -U mas -d mas)
|
||||
synapse-media.tar.gz Synapse media files (/data/media_store/)
|
||||
secret-chat-matrix.yaml Synapse secrets (signing.key, macaroon, etc.)
|
||||
secret-chat-postgresql.yaml PG passwords
|
||||
secret-mas.yaml MAS secrets (encryption-key, signing-key, shared-secret)
|
||||
secret-matrixrtc-livekit.yaml LiveKit secrets
|
||||
|
||||
CRITICAL for restore:
|
||||
- secret-chat-matrix.yaml (SYNAPSE_SIGNING_KEY for federation identity)
|
||||
- secret-mas.yaml (MAS encryption-key for user sessions)
|
||||
- dump-synapse.sql (all user data, rooms, messages)
|
||||
- dump-mas.sql (MAS user auth data)
|
||||
|
||||
Migration to ESS chart notes:
|
||||
- The old chart uses separate Helm releases per component (chat, element-call, livekit).
|
||||
- ESS bundles everything into the matrix-stack chart.
|
||||
- PostgreSQL is external (CNPG) on the new cluster.
|
||||
- MAS keys must be restored EXACTLY as-is for user auth to work.
|
||||
- The Synapse signing.key MUST match the federation identity.
|
||||
READEOF
|
||||
|
||||
log "README saved."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Summary
|
||||
# -------------------------------------------------------------------
|
||||
cat <<SUMMARY
|
||||
|
||||
${GREEN}========================================${NC}
|
||||
${GREEN} Backup Complete: ${NS}${NC}
|
||||
${GREEN}========================================${NC}
|
||||
|
||||
Directory: ${BACKUP_DIR}
|
||||
Size: $(du -sh "${BACKUP_DIR}" | cut -f1)
|
||||
Downtime: ${DOWNTIME}
|
||||
|
||||
SUMMARY
|
||||
224
scripts/restore-mrt0rtikize.sh
Executable file
224
scripts/restore-mrt0rtikize.sh
Executable file
@@ -0,0 +1,224 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
# ================================================================
|
||||
# Restore script for mrt0rtikize.ru Matrix instance
|
||||
# ================================================================
|
||||
# Reads a backup directory created by backup-mrt0rtikize.sh
|
||||
# and restores it to the new yandex-prod cluster.
|
||||
#
|
||||
# Usage: ./restore-mrt0rtikize.sh <backup-dir>
|
||||
#
|
||||
# Steps:
|
||||
# 1. Scale Synapse + MAS to 0 on new cluster
|
||||
# 2. Restore PostgreSQL dumps to CNPG shared-pg
|
||||
# 3. Apply generated secrets (signing key, MAS keys, macaroon)
|
||||
# 4. Apply deployment markers
|
||||
# 5. Scale Synapse to 1 (now has signing key + DB)
|
||||
# 6. Restore media files
|
||||
# 7. Scale MAS to 1
|
||||
# ================================================================
|
||||
|
||||
readonly YC_KUBECONFIG="${KUBECONFIG:-/home/mrt0rtikize/infra/yandex-prod/kubeconfig}"
|
||||
readonly K="${KUBECTL:-kubectl} --kubeconfig ${YC_KUBECONFIG}"
|
||||
|
||||
readonly NS="matrix-mrt0rtikize"
|
||||
readonly CNPG_NS="cnpg"
|
||||
readonly CNPG_POD="shared-pg-1"
|
||||
|
||||
# Colors
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
YELLOW='\033[1;33m'
|
||||
NC='\033[0m'
|
||||
|
||||
log() { echo -e "${GREEN}[$(date +%H:%M:%S)]${NC} $*"; }
|
||||
warn() { echo -e "${YELLOW}[$(date +%H:%M:%S)] WARN:${NC} $*"; }
|
||||
err() { echo -e "${RED}[$(date +%H:%M:%S)] ERROR:${NC} $*"; }
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Usage
|
||||
# -------------------------------------------------------------------
|
||||
if [ $# -ne 1 ]; then
|
||||
echo "Usage: $0 <backup-dir>"
|
||||
echo ""
|
||||
echo "Example: $0 backups/matrix-mrt0rtikize-20260613-192010/"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
readonly BACKUP_DIR="$1"
|
||||
|
||||
if [ ! -d "${BACKUP_DIR}" ]; then
|
||||
err "Backup directory not found: ${BACKUP_DIR}"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Verify critical files exist
|
||||
for f in dump-synapse.sql dump-mas.sql secret-generated.yaml markers.yaml synapse-media.tar.gz; do
|
||||
if [ ! -f "${BACKUP_DIR}/${f}" ]; then
|
||||
warn "Missing: ${f}"
|
||||
fi
|
||||
done
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Prerequisites
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Checking prerequisites ==="
|
||||
|
||||
if ! ${K} get ns "${NS}" >/dev/null 2>&1; then
|
||||
err "Namespace ${NS} not found on new cluster. Deploy the ESS app first."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if ! ${K} -n "${CNPG_NS}" get pod "${CNPG_POD}" >/dev/null 2>&1; then
|
||||
err "CNPG pod ${CNPG_POD} not found. Is the CNPG cluster running?"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
log "Cluster access verified."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 1: Scale Synapse + MAS to 0
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 1: Stopping Synapse + MAS ==="
|
||||
|
||||
${K} -n "${NS}" scale sts -l "app.kubernetes.io/component=matrix-server" --replicas=0 2>/dev/null || \
|
||||
${K} -n "${NS}" scale sts "${NS}-synapse-main" --replicas=0 2>/dev/null || \
|
||||
warn "Could not scale Synapse via known names, trying by label..."
|
||||
|
||||
${K} -n "${NS}" scale deploy -l "app.kubernetes.io/component=matrix-authentication" --replicas=0 2>/dev/null || \
|
||||
${K} -n "${NS}" scale deploy "${NS}-matrix-authentication-service" --replicas=0 2>/dev/null || \
|
||||
warn "Could not scale MAS via known names..."
|
||||
|
||||
log "Waiting for Synapse + MAS pods to terminate..."
|
||||
${K} -n "${NS}" wait --for=delete pod -l "app.kubernetes.io/component=matrix-server" --timeout=120s 2>/dev/null || warn "Some Synapse pods may still be terminating."
|
||||
${K} -n "${NS}" wait --for=delete pod -l "app.kubernetes.io/component=matrix-authentication" --timeout=120s 2>/dev/null || warn "Some MAS pods may still be terminating."
|
||||
|
||||
log "Synapse + MAS stopped."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 2: Clean schemas (DROP SCHEMA CASCADE — no connection races)
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 2: Cleaning database schemas ==="
|
||||
|
||||
log "Reading PG credentials from cluster..."
|
||||
SYNAPSE_PW=$(${K} get secret pg-creds -n "${NS}" -o jsonpath='{.data.synapse}' | base64 -d)
|
||||
MAS_PW=$(${K} get secret pg-creds -n "${NS}" -o jsonpath='{.data.mas}' | base64 -d)
|
||||
|
||||
log "Wiping synapse schema..."
|
||||
${K} exec -n "${CNPG_NS}" "${CNPG_POD}" -- env PGPASSWORD="${SYNAPSE_PW}" \
|
||||
psql -U synapse_mrt0rtikize -d synapse_mrt0rtikize -h localhost -c \
|
||||
"DROP SCHEMA public CASCADE; CREATE SCHEMA public; GRANT ALL ON SCHEMA public TO synapse_mrt0rtikize;" 2>/dev/null || true
|
||||
|
||||
log "Wiping MAS schema..."
|
||||
${K} exec -n "${CNPG_NS}" "${CNPG_POD}" -- env PGPASSWORD="${MAS_PW}" \
|
||||
psql -U mas_mrt0rtikize -d mas_mrt0rtikize -h localhost -c \
|
||||
"DROP SCHEMA public CASCADE; CREATE SCHEMA public; GRANT ALL ON SCHEMA public TO mas_mrt0rtikize;" 2>/dev/null || true
|
||||
|
||||
log "Schemas cleaned."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 3: Restore PostgreSQL dumps
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 3: Restoring PostgreSQL dumps ==="
|
||||
|
||||
log "Restoring Synapse database..."
|
||||
${K} exec -i -n "${CNPG_NS}" "${CNPG_POD}" -- env PGPASSWORD="${SYNAPSE_PW}" \
|
||||
psql -U synapse_mrt0rtikize -d synapse_mrt0rtikize -h localhost < "${BACKUP_DIR}/dump-synapse.sql"
|
||||
log "Synapse database restored."
|
||||
|
||||
log "Restoring MAS database..."
|
||||
${K} exec -i -n "${CNPG_NS}" "${CNPG_POD}" -- env PGPASSWORD="${MAS_PW}" \
|
||||
psql -U mas_mrt0rtikize -d mas_mrt0rtikize -h localhost < "${BACKUP_DIR}/dump-mas.sql"
|
||||
log "MAS database restored."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 3: Apply generated secrets (CRITICAL)
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 4: Applying generated secrets ==="
|
||||
|
||||
if [ -f "${BACKUP_DIR}/secret-generated.yaml" ]; then
|
||||
${K} replace --force -f "${BACKUP_DIR}/secret-generated.yaml"
|
||||
log "Generated secret replaced: ${NS}-generated (original signing key from backup)"
|
||||
else
|
||||
err "CRITICAL: secret-generated.yaml not found in backup!"
|
||||
err "SYNAPSE_SIGNING_KEY and MAS keys will NOT be restored."
|
||||
err "Federation identity is lost without this file."
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 4: Apply deployment markers
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 5: Applying deployment markers ==="
|
||||
|
||||
if [ -f "${BACKUP_DIR}/markers.yaml" ]; then
|
||||
${K} replace --force -f "${BACKUP_DIR}/markers.yaml"
|
||||
log "Deployment markers replaced."
|
||||
else
|
||||
warn "markers.yaml not found in backup (non-critical)."
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 5: Scale Synapse to 1
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 6: Starting Synapse ==="
|
||||
|
||||
${K} -n "${NS}" scale sts -l "app.kubernetes.io/component=matrix-server" --replicas=1 2>/dev/null || \
|
||||
${K} -n "${NS}" scale sts "${NS}-synapse-main" --replicas=1 2>/dev/null
|
||||
|
||||
log "Waiting for Synapse to start..."
|
||||
${K} -n "${NS}" wait --for=condition=ready pod -l "app.kubernetes.io/component=matrix-server" --timeout=300s 2>/dev/null || warn "Synapse is not ready yet, check logs."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 6: Restore media files
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 7: Restoring media files ==="
|
||||
|
||||
if [ -f "${BACKUP_DIR}/synapse-media.tar.gz" ]; then
|
||||
SYNAPSE_POD=$( ${K} -n "${NS}" get pods -l "app.kubernetes.io/component=matrix-server" -o jsonpath='{.items[?(@.status.phase=="Running")].metadata.name}' 2>/dev/null)
|
||||
if [ -z "${SYNAPSE_POD}" ]; then
|
||||
warn "No running Synapse pod found for media restore. Skip media."
|
||||
warn "Re-run this step after Synapse is up:"
|
||||
warn " kubectl cp synapse-media.tar.gz ${NS}/<synapse-pod>:/tmp/ && kubectl exec <synapse-pod> -- tar xzf /tmp/synapse-media.tar.gz -C /media/"
|
||||
else
|
||||
log "Copying media to Synapse pod: ${SYNAPSE_POD}"
|
||||
${K} cp "${BACKUP_DIR}/synapse-media.tar.gz" "${NS}/${SYNAPSE_POD}:/tmp/synapse-media.tar.gz"
|
||||
${K} exec -n "${NS}" "${SYNAPSE_POD}" -- tar xzf /tmp/synapse-media.tar.gz -C /media/
|
||||
${K} exec -n "${NS}" "${SYNAPSE_POD}" -- rm /tmp/synapse-media.tar.gz
|
||||
log "Media files restored."
|
||||
fi
|
||||
else
|
||||
warn "synapse-media.tar.gz not found in backup."
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 7: Scale MAS to 1
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 8: Starting MAS ==="
|
||||
|
||||
${K} -n "${NS}" scale deploy -l "app.kubernetes.io/component=matrix-authentication" --replicas=1 2>/dev/null || \
|
||||
${K} -n "${NS}" scale deploy "${NS}-matrix-authentication-service" --replicas=1 2>/dev/null
|
||||
|
||||
log "Waiting for MAS to start..."
|
||||
${K} -n "${NS}" wait --for=condition=ready pod -l "app.kubernetes.io/component=matrix-authentication" --timeout=120s 2>/dev/null || warn "MAS is not ready yet, check logs."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Summary
|
||||
# -------------------------------------------------------------------
|
||||
cat <<SUMMARY
|
||||
|
||||
${GREEN}========================================${NC}
|
||||
${GREEN} Restore Complete: ${NS}${NC}
|
||||
${GREEN}========================================${NC}
|
||||
|
||||
${YELLOW}Verification steps:${NC}
|
||||
1. Check Synapse logs:
|
||||
${K} logs -n ${NS} -l "app.kubernetes.io/component=matrix-server" --tail=30
|
||||
2. Check Synapse has correct signing key:
|
||||
${K} exec -n ${NS} deploy/${NS}-synapse-main -- ls /secrets/${NS}-generated/SYNAPSE_SIGNING_KEY
|
||||
3. Test login at: https://chat.mrt0rtikize.ru
|
||||
4. Federation tester: https://federationtester.matrix.org/?server_name=mrt0rtikize.ru
|
||||
5. Check certificates:
|
||||
${K} get certificates -n ${NS}
|
||||
|
||||
SUMMARY
|
||||
351
scripts/restore-prod.sh
Executable file
351
scripts/restore-prod.sh
Executable file
@@ -0,0 +1,351 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
# ================================================================
|
||||
# Restore script for prod Matrix instances (yc-playground → yandex-prod)
|
||||
# ================================================================
|
||||
# Reads a backup created by backup-yc-playground.sh and restores
|
||||
# it to the new yandex-prod cluster with ESS chart.
|
||||
#
|
||||
# Usage: ./restore-prod.sh <name> <backup-dir>
|
||||
# Example: ./restore-prod.sh t0rt1k backups/matrix-t0rt1k-20260614-161207/
|
||||
# ================================================================
|
||||
|
||||
readonly YC_KUBECONFIG="${KUBECONFIG:-/home/mrt0rtikize/infra/yandex-prod/kubeconfig}"
|
||||
readonly K="${KUBECTL:-kubectl} --kubeconfig ${YC_KUBECONFIG}"
|
||||
|
||||
readonly CNPG_NS="cnpg"
|
||||
readonly CNPG_POD="shared-pg-1"
|
||||
|
||||
# Colors
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
YELLOW='\033[1;33m'
|
||||
NC='\033[0m'
|
||||
log() { echo -e "${GREEN}[$(date +%H:%M:%S)]${NC} $*"; }
|
||||
warn() { echo -e "${YELLOW}[$(date +%H:%M:%S)] WARN:${NC} $*"; }
|
||||
err() { echo -e "${RED}[$(date +%H:%M:%S)] ERROR:${NC} $*"; }
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Parse args
|
||||
# -------------------------------------------------------------------
|
||||
if [ $# -ne 2 ]; then
|
||||
echo "Usage: $0 <name> <backup-dir>"
|
||||
echo ""
|
||||
echo " name: t0rt1k | roglog | uretra"
|
||||
echo " backup-dir: path to backup directory from backup-yc-playground.sh"
|
||||
echo ""
|
||||
echo "Example: $0 t0rt1k backups/matrix-t0rt1k-20260614-161207/"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
readonly NAME="$1"
|
||||
readonly NS="matrix-${NAME}"
|
||||
readonly DB_SYNAPSE="synapse_${NAME}"
|
||||
readonly DB_MAS="mas_${NAME}"
|
||||
readonly BACKUP_DIR="$2"
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Prerequisites
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Restoring ${NS} from ${BACKUP_DIR} ==="
|
||||
|
||||
if [ ! -d "${BACKUP_DIR}" ]; then
|
||||
err "Backup directory not found: ${BACKUP_DIR}"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
for f in dump-synapse.sql dump-mas.sql secret-chat-matrix.yaml secret-mas.yaml secret-chat-postgresql.yaml; do
|
||||
if [ ! -f "${BACKUP_DIR}/${f}" ]; then
|
||||
err "Missing: ${f}"
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
|
||||
if ! ${K} get ns "${NS}" >/dev/null 2>&1; then
|
||||
err "Namespace ${NS} not found. Deploy the ESS app and sync first."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if ! ${K} -n "${CNPG_NS}" get pod "${CNPG_POD}" >/dev/null 2>&1; then
|
||||
err "CNPG pod ${CNPG_POD} not found."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
log "Prerequisites OK."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 1: Stop Synapse + MAS
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 1: Stopping Synapse + MAS ==="
|
||||
|
||||
${K} -n "${NS}" scale deploy -l "app.kubernetes.io/component=matrix-server" --replicas=0 2>/dev/null || \
|
||||
${K} -n "${NS}" scale sts "${NS}-synapse-main" --replicas=0 2>/dev/null || \
|
||||
${K} -n "${NS}" scale deploy chat-matrix --replicas=0 2>/dev/null || \
|
||||
warn "Could not scale Synapse."
|
||||
|
||||
${K} -n "${NS}" scale deploy -l "app.kubernetes.io/component=matrix-authentication" --replicas=0 2>/dev/null || \
|
||||
${K} -n "${NS}" scale deploy "${NS}-matrix-authentication-service" --replicas=0 2>/dev/null || \
|
||||
${K} -n "${NS}" scale deploy mas --replicas=0 2>/dev/null || \
|
||||
warn "Could not scale MAS."
|
||||
|
||||
log "Waiting for pods to terminate..."
|
||||
${K} -n "${NS}" wait --for=delete pod -l "app.kubernetes.io/component=matrix-server" --timeout=120s 2>/dev/null || warn "Synapse may still be terminating."
|
||||
${K} -n "${NS}" wait --for=delete pod -l "app.kubernetes.io/component=matrix-authentication" --timeout=120s 2>/dev/null || warn "MAS may still be terminating."
|
||||
${K} -n "${NS}" wait --for=delete pod -l "app=mas" --timeout=60s 2>/dev/null || true
|
||||
|
||||
log "Synapse + MAS stopped."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 2: Clean schemas
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 2: Cleaning database schemas ==="
|
||||
|
||||
log "Reading PG credentials..."
|
||||
SYNAPSE_PW=$(${K} get secret pg-creds -n "${NS}" -o jsonpath='{.data.synapse}' 2>/dev/null | base64 -d)
|
||||
MAS_PW=$(${K} get secret pg-creds -n "${NS}" -o jsonpath='{.data.mas}' 2>/dev/null | base64 -d)
|
||||
|
||||
log "Wiping ${DB_SYNAPSE} schema..."
|
||||
${K} exec -n "${CNPG_NS}" "${CNPG_POD}" -- env PGPASSWORD="${SYNAPSE_PW}" \
|
||||
psql -U "${DB_SYNAPSE}" -d "${DB_SYNAPSE}" -h localhost -c \
|
||||
"DROP SCHEMA public CASCADE; CREATE SCHEMA public; GRANT ALL ON SCHEMA public TO ${DB_SYNAPSE};" 2>/dev/null || true
|
||||
|
||||
log "Wiping ${DB_MAS} schema..."
|
||||
${K} exec -n "${CNPG_NS}" "${CNPG_POD}" -- env PGPASSWORD="${MAS_PW}" \
|
||||
psql -U "${DB_MAS}" -d "${DB_MAS}" -h localhost -c \
|
||||
"DROP SCHEMA public CASCADE; CREATE SCHEMA public; GRANT ALL ON SCHEMA public TO ${DB_MAS};" 2>/dev/null || true
|
||||
|
||||
log "Schemas cleaned."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 3: Restore PostgreSQL dumps
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 3: Restoring PostgreSQL dumps ==="
|
||||
|
||||
log "Restoring Synapse database..."
|
||||
# Old chart used 'matrix' role — create it as superuser to suppress OWNER TO errors
|
||||
${K} exec -n "${CNPG_NS}" "${CNPG_POD}" -- psql -U postgres -c \
|
||||
"DO \$\$ BEGIN IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = 'matrix') THEN CREATE ROLE matrix; END IF; END \$\$;" 2>/dev/null || true
|
||||
${K} exec -n "${CNPG_NS}" "${CNPG_POD}" -- psql -U postgres -c \
|
||||
"GRANT matrix TO ${DB_SYNAPSE};" 2>/dev/null || true
|
||||
|
||||
${K} exec -i -n "${CNPG_NS}" "${CNPG_POD}" -- env PGPASSWORD="${SYNAPSE_PW}" \
|
||||
psql -U "${DB_SYNAPSE}" -d "${DB_SYNAPSE}" -h localhost < "${BACKUP_DIR}/dump-synapse.sql"
|
||||
log "Synapse database restored."
|
||||
|
||||
log "Restoring MAS database..."
|
||||
# Old chart used 'mas' role — create it as superuser to suppress OWNER TO errors
|
||||
${K} exec -n "${CNPG_NS}" "${CNPG_POD}" -- psql -U postgres -c \
|
||||
"DO \$\$ BEGIN IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = 'mas') THEN CREATE ROLE mas; END IF; END \$\$;" 2>/dev/null || true
|
||||
${K} exec -n "${CNPG_NS}" "${CNPG_POD}" -- psql -U postgres -c \
|
||||
"GRANT mas TO ${DB_MAS};" 2>/dev/null || true
|
||||
${K} exec -i -n "${CNPG_NS}" "${CNPG_POD}" -- env PGPASSWORD="${MAS_PW}" \
|
||||
psql -U "${DB_MAS}" -d "${DB_MAS}" -h localhost < "${BACKUP_DIR}/dump-mas.sql"
|
||||
log "MAS database restored."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 4: Construct and apply the ESS -generated secret
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 4: Constructing ESS generated secret ==="
|
||||
|
||||
# Read existing auto-generated secret (has keys the old chart didn't: ECDSA, LiveKit, Hookshot, etc.)
|
||||
EXISTING_KEY_ECDSA=""
|
||||
EXISTING_KEY_LIVEKIT=""
|
||||
EXISTING_KEY_HOOKSHOT_REG=""
|
||||
EXISTING_KEY_HOOKSHOT_PASS=""
|
||||
EXISTING_KEY_SYNAPSE_EXTRA=""
|
||||
EXISTING_KEY_PG_ADMIN=""
|
||||
|
||||
if ${K} -n "${NS}" get secret "${NS}-generated" >/dev/null 2>&1; then
|
||||
log "Reading existing auto-generated secret for non-migrated keys..."
|
||||
EXISTING_KEY_ECDSA=$(${K} -n "${NS}" get secret "${NS}-generated" -o jsonpath='{.data.MAS_ECDSA_PRIME256V1_PRIVATE_KEY}' 2>/dev/null || echo "")
|
||||
EXISTING_KEY_LIVEKIT=$(${K} -n "${NS}" get secret "${NS}-generated" -o jsonpath='{.data.ELEMENT_CALL_LIVEKIT_SECRET}' 2>/dev/null || echo "")
|
||||
EXISTING_KEY_HOOKSHOT_REG=$(${K} -n "${NS}" get secret "${NS}-generated" -o jsonpath='{.data.HOOKSHOT_REGISTRATION}' 2>/dev/null || echo "")
|
||||
EXISTING_KEY_HOOKSHOT_PASS=$(${K} -n "${NS}" get secret "${NS}-generated" -o jsonpath='{.data.HOOKSHOT_RSA_PASSKEY}' 2>/dev/null || echo "")
|
||||
EXISTING_KEY_SYNAPSE_EXTRA=$(${K} -n "${NS}" get secret "${NS}-generated" -o jsonpath='{.data.SYNAPSE_EXTRA}' 2>/dev/null || echo "")
|
||||
EXISTING_KEY_PG_ADMIN=$(${K} -n "${NS}" get secret "${NS}-generated" -o jsonpath='{.data.POSTGRES_ADMIN_PASSWORD}' 2>/dev/null || echo "")
|
||||
log "Preserved non-migrated keys from existing secret."
|
||||
else
|
||||
warn "No existing ${NS}-generated secret found. Some keys may be missing."
|
||||
fi
|
||||
|
||||
# Read old secrets from backup
|
||||
log "Reading old secrets from backup..."
|
||||
OLD_SIGNING_KEY=$(python3 -c "
|
||||
import yaml, sys
|
||||
with open('${BACKUP_DIR}/secret-chat-matrix.yaml') as f:
|
||||
s = yaml.safe_load(f.read())
|
||||
print(s['data']['signing.key'])
|
||||
" 2>/dev/null)
|
||||
|
||||
OLD_MACAROON=$(python3 -c "
|
||||
import yaml, sys
|
||||
with open('${BACKUP_DIR}/secret-chat-matrix.yaml') as f:
|
||||
s = yaml.safe_load(f.read())
|
||||
print(s['data']['macaroon_secret_key'])
|
||||
" 2>/dev/null)
|
||||
|
||||
OLD_REGISTRATION=$(python3 -c "
|
||||
import yaml, sys
|
||||
with open('${BACKUP_DIR}/secret-chat-matrix.yaml') as f:
|
||||
s = yaml.safe_load(f.read())
|
||||
print(s['data']['registration_shared_secret'])
|
||||
" 2>/dev/null)
|
||||
|
||||
OLD_MAS_ENCRYPTION=$(python3 -c "
|
||||
import yaml, sys
|
||||
with open('${BACKUP_DIR}/secret-mas.yaml') as f:
|
||||
s = yaml.safe_load(f.read())
|
||||
print(s['data']['encryption-key'])
|
||||
" 2>/dev/null)
|
||||
|
||||
OLD_MAS_RSA=$(python3 -c "
|
||||
import yaml, sys
|
||||
with open('${BACKUP_DIR}/secret-mas.yaml') as f:
|
||||
s = yaml.safe_load(f.read())
|
||||
print(s['data']['signing-key.pem'])
|
||||
" 2>/dev/null)
|
||||
|
||||
OLD_MAS_SHARED=$(python3 -c "
|
||||
import yaml, sys
|
||||
with open('${BACKUP_DIR}/secret-mas.yaml') as f:
|
||||
s = yaml.safe_load(f.read())
|
||||
print(s['data']['shared-secret'])
|
||||
" 2>/dev/null)
|
||||
|
||||
OLD_SYNAPSE_PG_PW=$(python3 -c "
|
||||
import yaml, sys
|
||||
with open('${BACKUP_DIR}/secret-chat-postgresql.yaml') as f:
|
||||
s = yaml.safe_load(f.read())
|
||||
print(s['data']['password'])
|
||||
" 2>/dev/null)
|
||||
|
||||
OLD_MAS_DB_PW=$(python3 -c "
|
||||
import yaml, sys
|
||||
with open('${BACKUP_DIR}/secret-mas.yaml') as f:
|
||||
s = yaml.safe_load(f.read())
|
||||
print(s['data']['mas-db-password'])
|
||||
" 2>/dev/null)
|
||||
|
||||
# Build the new secret
|
||||
log "Applying generated secret with migrated keys..."
|
||||
|
||||
PYTHON_BODY=$(cat <<'PYEOF'
|
||||
import yaml, sys, base64
|
||||
|
||||
# Read existing secret structure from stdin (if any)
|
||||
existing = {}
|
||||
try:
|
||||
existing = yaml.safe_load(sys.stdin)
|
||||
except:
|
||||
pass
|
||||
|
||||
data = existing.get('data', {}) if existing else {}
|
||||
|
||||
# Overwrite with old keys (these are base64 encoded already)
|
||||
data['SYNAPSE_SIGNING_KEY'] = sys.argv[1] if sys.argv[1] else data.get('SYNAPSE_SIGNING_KEY','')
|
||||
data['SYNAPSE_MACAROON'] = sys.argv[2] if sys.argv[2] else data.get('SYNAPSE_MACAROON','')
|
||||
data['SYNAPSE_REGISTRATION_SHARED_SECRET'] = sys.argv[3] if sys.argv[3] else data.get('SYNAPSE_REGISTRATION_SHARED_SECRET','')
|
||||
data['MAS_ENCRYPTION_SECRET'] = sys.argv[4] if sys.argv[4] else data.get('MAS_ENCRYPTION_SECRET','')
|
||||
data['MAS_RSA_PRIVATE_KEY'] = sys.argv[5] if sys.argv[5] else data.get('MAS_RSA_PRIVATE_KEY','')
|
||||
|
||||
data['MAS_SYNAPSE_SHARED_SECRET'] = sys.argv[6] if sys.argv[6] else data.get('MAS_SYNAPSE_SHARED_SECRET','')
|
||||
data['POSTGRES_SYNAPSE_PASSWORD'] = sys.argv[7] if sys.argv[7] else data.get('POSTGRES_SYNAPSE_PASSWORD','')
|
||||
data['POSTGRES_MATRIX_AUTHENTICATION_SERVICE_PASSWORD'] = sys.argv[8] if sys.argv[8] else data.get('POSTGRES_MATRIX_AUTHENTICATION_SERVICE_PASSWORD','')
|
||||
|
||||
# Preserve existing non-migrated keys if provided
|
||||
if sys.argv[9]: data['MAS_ECDSA_PRIME256V1_PRIVATE_KEY'] = sys.argv[9]
|
||||
if sys.argv[10]: data['ELEMENT_CALL_LIVEKIT_SECRET'] = sys.argv[10]
|
||||
if sys.argv[11]: data['HOOKSHOT_REGISTRATION'] = sys.argv[11]
|
||||
if sys.argv[12]: data['HOOKSHOT_RSA_PASSKEY'] = sys.argv[12]
|
||||
if sys.argv[13]: data['SYNAPSE_EXTRA'] = sys.argv[13]
|
||||
if sys.argv[14]: data['POSTGRES_ADMIN_PASSWORD'] = sys.argv[14]
|
||||
|
||||
secret = {
|
||||
'apiVersion': 'v1',
|
||||
'kind': 'Secret',
|
||||
'metadata': {
|
||||
'name': f'{sys.argv[15]}-generated',
|
||||
'namespace': sys.argv[16],
|
||||
},
|
||||
'type': 'Opaque',
|
||||
'data': data,
|
||||
}
|
||||
|
||||
yaml.dump(secret, sys.stdout, default_flow_style=False)
|
||||
PYEOF
|
||||
)
|
||||
|
||||
# Get existing secret for merge
|
||||
${K} -n "${NS}" get secret "${NS}-generated" -o yaml 2>/dev/null | \
|
||||
python3 -c "${PYTHON_BODY}" \
|
||||
"${OLD_SIGNING_KEY}" "${OLD_MACAROON}" "${OLD_REGISTRATION}" \
|
||||
"${OLD_MAS_ENCRYPTION}" "${OLD_MAS_RSA}" "${OLD_MAS_SHARED}" \
|
||||
"${OLD_SYNAPSE_PG_PW}" "${OLD_MAS_DB_PW}" \
|
||||
"${EXISTING_KEY_ECDSA}" "${EXISTING_KEY_LIVEKIT}" "${EXISTING_KEY_HOOKSHOT_REG}" \
|
||||
"${EXISTING_KEY_HOOKSHOT_PASS}" "${EXISTING_KEY_SYNAPSE_EXTRA}" "${EXISTING_KEY_PG_ADMIN}" \
|
||||
"${NS}" "${NS}" | \
|
||||
${K} replace --force -f - 2>/dev/null || \
|
||||
${K} create -f - 2>/dev/null
|
||||
|
||||
log "Generated secret applied with migrated keys from old chart."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 5: Scale Synapse to 1
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 5: Starting Synapse ==="
|
||||
|
||||
${K} -n "${NS}" scale sts -l "app.kubernetes.io/component=matrix-server" --replicas=1 2>/dev/null || \
|
||||
${K} -n "${NS}" scale sts "${NS}-synapse-main" --replicas=1 2>/dev/null || \
|
||||
${K} -n "${NS}" scale deploy chat-matrix --replicas=1 2>/dev/null
|
||||
|
||||
log "Waiting for Synapse..."
|
||||
${K} -n "${NS}" wait --for=condition=ready pod -l "app.kubernetes.io/component=matrix-server" --timeout=300s 2>/dev/null || warn "Synapse not ready yet."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 6: Restore media files
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 6: Restoring media files ==="
|
||||
|
||||
if [ -f "${BACKUP_DIR}/synapse-media.tar.gz" ]; then
|
||||
SYNAPSE_POD=$( ${K} -n "${NS}" get pods -l "app.kubernetes.io/component=matrix-server" -o jsonpath='{.items[?(@.status.phase=="Running")].metadata.name}' 2>/dev/null)
|
||||
if [ -z "${SYNAPSE_POD}" ]; then
|
||||
warn "No running Synapse pod for media restore."
|
||||
else
|
||||
log "Copying media to Synapse pod: ${SYNAPSE_POD}"
|
||||
${K} cp "${BACKUP_DIR}/synapse-media.tar.gz" "${NS}/${SYNAPSE_POD}:/tmp/synapse-media.tar.gz"
|
||||
${K} exec -n "${NS}" "${SYNAPSE_POD}" -- tar xzf /tmp/synapse-media.tar.gz -C /media/
|
||||
${K} exec -n "${NS}" "${SYNAPSE_POD}" -- rm /tmp/synapse-media.tar.gz
|
||||
log "Media files restored."
|
||||
fi
|
||||
else
|
||||
warn "synapse-media.tar.gz not found in backup."
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Step 7: Scale MAS to 1
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Step 7: Starting MAS ==="
|
||||
|
||||
${K} -n "${NS}" scale deploy -l "app.kubernetes.io/component=matrix-authentication" --replicas=1 2>/dev/null || \
|
||||
${K} -n "${NS}" scale deploy "${NS}-matrix-authentication-service" --replicas=1 2>/dev/null || \
|
||||
${K} -n "${NS}" scale deploy mas --replicas=1 2>/dev/null
|
||||
|
||||
log "Waiting for MAS..."
|
||||
${K} -n "${NS}" wait --for=condition=ready pod -l "app.kubernetes.io/component=matrix-authentication" --timeout=120s 2>/dev/null || warn "MAS not ready yet."
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Summary
|
||||
# -------------------------------------------------------------------
|
||||
cat <<SUMMARY
|
||||
|
||||
${GREEN}========================================${NC}
|
||||
${GREEN} Restore Complete: ${NS}${NC}
|
||||
${GREEN}========================================${NC}
|
||||
|
||||
Verification:
|
||||
1. Check Synapse logs: ${K} logs -n ${NS} -l "app.kubernetes.io/component=matrix-server" --tail=20
|
||||
2. Test login: https://chat.${NAME}.tech
|
||||
3. Federation tester: https://federationtester.matrix.org/?server_name=${NAME}.tech
|
||||
|
||||
SUMMARY
|
||||
124
scripts/setup-pg-creds.sh
Executable file
124
scripts/setup-pg-creds.sh
Executable file
@@ -0,0 +1,124 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
# ================================================================
|
||||
# Setup PG credentials for an ESS Matrix instance
|
||||
# ================================================================
|
||||
# Generates random passwords, updates CNPG roles, applies a
|
||||
# Kubernetes Secret in the instance namespace, and updates the
|
||||
# matching pg-secret.yaml file in the repo.
|
||||
#
|
||||
# Usage: ./setup-pg-creds.sh <homeserver-name>
|
||||
# Example: ./setup-pg-creds.sh mrt0rtikize
|
||||
# ================================================================
|
||||
|
||||
readonly YC_KUBECONFIG="${KUBECONFIG:-/home/mrt0rtikize/infra/yandex-prod/kubeconfig}"
|
||||
readonly K="${KUBECTL:-kubectl} --kubeconfig ${YC_KUBECONFIG}"
|
||||
readonly REPO_DIR="$(dirname "$(realpath "$0")")/.."
|
||||
|
||||
readonly CNPG_NS="cnpg"
|
||||
readonly CNPG_POD="shared-pg-1"
|
||||
|
||||
# Colors
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
NC='\033[0m'
|
||||
log() { echo -e "${GREEN}[$(date +%H:%M:%S)]${NC} $*"; }
|
||||
err() { echo -e "${RED}[$(date +%H:%M:%S)] ERROR:${NC} $*"; }
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Parse argument
|
||||
# -------------------------------------------------------------------
|
||||
NAME="${1:?Usage: $0 <homeserver-name>}"
|
||||
NS="matrix-${NAME}"
|
||||
DB_SYNAPSE="synapse_${NAME}"
|
||||
DB_MAS="mas_${NAME}"
|
||||
USER_SYNAPSE="synapse_${NAME}"
|
||||
USER_MAS="mas_${NAME}"
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Prerequisites
|
||||
# -------------------------------------------------------------------
|
||||
log "=== Setting up PG credentials for ${NAME} ==="
|
||||
|
||||
if ! ${K} get ns "${NS}" >/dev/null 2>&1; then
|
||||
err "Namespace ${NS} not found. Deploy the ESS app first."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if ! ${K} -n "${CNPG_NS}" get pod "${CNPG_POD}" >/dev/null 2>&1; then
|
||||
err "CNPG pod ${CNPG_POD} not found."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Generate passwords
|
||||
# -------------------------------------------------------------------
|
||||
log "Generating passwords..."
|
||||
|
||||
SYNAPSE_PW=$(openssl rand -base64 24 | tr -d '\n')
|
||||
MAS_PW=$(openssl rand -base64 24 | tr -d '\n')
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Update PostgreSQL roles
|
||||
# -------------------------------------------------------------------
|
||||
log "Creating/updating CNPG role: ${USER_SYNAPSE}"
|
||||
${K} exec -n "${CNPG_NS}" "${CNPG_POD}" -- \
|
||||
psql -U postgres -c "DO \$\$ BEGIN IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = '${USER_SYNAPSE}') THEN CREATE ROLE ${USER_SYNAPSE} WITH LOGIN PASSWORD '${SYNAPSE_PW}'; ELSE ALTER ROLE ${USER_SYNAPSE} WITH PASSWORD '${SYNAPSE_PW}'; END IF; END \$\$;"
|
||||
|
||||
log "Creating/updating CNPG role: ${USER_MAS}"
|
||||
${K} exec -n "${CNPG_NS}" "${CNPG_POD}" -- \
|
||||
psql -U postgres -c "DO \$\$ BEGIN IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = '${USER_MAS}') THEN CREATE ROLE ${USER_MAS} WITH LOGIN PASSWORD '${MAS_PW}'; ELSE ALTER ROLE ${USER_MAS} WITH PASSWORD '${MAS_PW}'; END IF; END \$\$;"
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Apply Kubernetes Secret
|
||||
# -------------------------------------------------------------------
|
||||
log "Creating/updating Kubernetes Secret pg-creds in ${NS}..."
|
||||
|
||||
${K} create secret generic pg-creds -n "${NS}" \
|
||||
--from-literal=synapse="${SYNAPSE_PW}" \
|
||||
--from-literal=mas="${MAS_PW}" \
|
||||
--dry-run=client -o yaml | ${K} apply -f -
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Update repo file
|
||||
# -------------------------------------------------------------------
|
||||
SECRET_FILE="${REPO_DIR}/manifests/${NS}/pg-secret.yaml"
|
||||
if [ -f "${SECRET_FILE}" ]; then
|
||||
log "Updating ${SECRET_FILE}..."
|
||||
|
||||
cat > "${SECRET_FILE}" <<EOF
|
||||
apiVersion: v1
|
||||
kind: Secret
|
||||
metadata:
|
||||
name: pg-creds
|
||||
namespace: ${NS}
|
||||
labels:
|
||||
app.kubernetes.io/part-of: matrix-stack
|
||||
type: Opaque
|
||||
stringData:
|
||||
synapse: ${SYNAPSE_PW}
|
||||
mas: ${MAS_PW}
|
||||
EOF
|
||||
log "Repo file updated."
|
||||
else
|
||||
log "File ${SECRET_FILE} does not exist — skipping repo update."
|
||||
log "The Secret is live in the cluster (not in git). Create the file manually."
|
||||
fi
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Restart pods
|
||||
# -------------------------------------------------------------------
|
||||
log "Restarting pods to pick up new credentials..."
|
||||
|
||||
${K} delete pod -n "${NS}" -l "app.kubernetes.io/component=matrix-server" --ignore-not-found 2>/dev/null
|
||||
${K} delete pod -n "${NS}" -l "app.kubernetes.io/component=matrix-authentication" --ignore-not-found 2>/dev/null
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Summary
|
||||
# -------------------------------------------------------------------
|
||||
echo ""
|
||||
echo "Synapse password: ${SYNAPSE_PW}"
|
||||
echo "MAS password: ${MAS_PW}"
|
||||
echo ""
|
||||
echo "Done. Synapse + MAS pods are restarting with new credentials."
|
||||
Reference in New Issue
Block a user