Compare commits
6 Commits
renovate/l
...
renovate/c
| Author | SHA1 | Date | |
|---|---|---|---|
| 20f4c2eba8 | |||
| 1b73fda11f | |||
| 96ddfa6ec5 | |||
| 6c0b1c9281 | |||
| 4f2934411b | |||
| 54dbe0c667 |
54
.gitea/workflows/ci.yml
Normal file
54
.gitea/workflows/ci.yml
Normal file
@@ -0,0 +1,54 @@
|
||||
name: CI
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
|
||||
jobs:
|
||||
terraform-validate:
|
||||
name: Terraform fmt + validate
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: hashicorp/setup-terraform@v3
|
||||
|
||||
- name: fmt check — 1-nixos-node
|
||||
run: terraform fmt -check -recursive
|
||||
working-directory: 1-nixos-node
|
||||
|
||||
- name: fmt check — 2-nomad-config
|
||||
run: terraform fmt -check -recursive
|
||||
working-directory: 2-nomad-config
|
||||
|
||||
- name: validate — 2-nomad-config (no backend)
|
||||
run: |
|
||||
terraform init -backend=false
|
||||
terraform validate
|
||||
working-directory: 2-nomad-config
|
||||
|
||||
nomad-validate:
|
||||
name: Nomad job spec validate
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Install Nomad CLI
|
||||
run: |
|
||||
curl -fsSL https://apt.releases.hashicorp.com/gpg | gpg --dearmor -o /usr/share/keyrings/hashicorp.gpg
|
||||
. /etc/os-release
|
||||
echo "deb [signed-by=/usr/share/keyrings/hashicorp.gpg] https://apt.releases.hashicorp.com ${VERSION_CODENAME} main" | tee /etc/apt/sources.list.d/hashicorp.list
|
||||
apt-get update && apt-get install -y nomad
|
||||
|
||||
- name: Validate all job specs
|
||||
env:
|
||||
NOMAD_ADDR: http://jaglan-beta-m20.lan:4646
|
||||
run: |
|
||||
find 2-nomad-config -name '*.nomad.hcl' | while read f; do
|
||||
echo "==> $f"
|
||||
nomad job validate "$f"
|
||||
done
|
||||
@@ -64,6 +64,7 @@
|
||||
cni_path = "$${pkgs.cni-plugins}/bin";
|
||||
};
|
||||
plugin.docker.config.allow_privileged = true;
|
||||
plugin.docker.config.volumes.enabled = true;
|
||||
};
|
||||
extraPackages = with pkgs; [
|
||||
cni-plugins
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
29
2-nomad-config/.terraform.lock.hcl
generated
29
2-nomad-config/.terraform.lock.hcl
generated
@@ -17,18 +17,25 @@ provider "registry.terraform.io/carlpett/sops" {
|
||||
}
|
||||
|
||||
provider "registry.terraform.io/cloudflare/cloudflare" {
|
||||
version = "5.5.0"
|
||||
constraints = "~> 5.0"
|
||||
version = "5.18.0"
|
||||
constraints = ">= 5.0.0"
|
||||
hashes = [
|
||||
"h1:wZhU174xytOMZ1t6uDUQiLtR/XKpi2RH9OzMz0XqP9Q=",
|
||||
"zh:178f29dee2edac39252780819f34004b1841770c61ee7fb5a625afaece6495cd",
|
||||
"zh:6faf26203167ae20ca5c8ece4a8bb1c4187137505058fb7b1a4bd5095823e648",
|
||||
"zh:97c91a95819336b8c41618919786ddd2dca643d28219d52af1d80b88018c6eec",
|
||||
"zh:bbc53670fc2613e3fe81b5bf7b8674c5ad083a206fa8af34f0f055a8d06b2d01",
|
||||
"zh:d305bcb01249ada21b80e5038e371f6ca0a60d95d7052df82456e4c4963f3bfc",
|
||||
"zh:e2f9db57ead7100676b790a3e4567d88443fae0e19127e66b3505210de93e4b5",
|
||||
"zh:eb8cef2e6cbf05237b8a2f229314ae12c792ed5f8f60fe180102bdf17dc30841",
|
||||
"zh:f51a5bb0130d2f42772988ee56723f176aa230701184a0f5598dbb1c7b4c3906",
|
||||
"h1:2FKT5YVLuHLmv7BnFxDC3UtipD3hSSrb0iJ9Ei2C/ks=",
|
||||
"h1:6FoKYTGqaCvKctMEm1Y1c06mmY3I04jhCBRXEYe6mcQ=",
|
||||
"h1:AhWro37kF118sAjRjIZ27CuV6kFpg1d+XYDo/7diyjU=",
|
||||
"h1:B9eoAx4QKNVuKHDahNl8JzuSLCCeIGAJiS0MckJu5wQ=",
|
||||
"h1:KfnaaT3RFoyWvPHsNVmsrCV7QEAGPLGNyHWT9IY+bxY=",
|
||||
"h1:SPFFA6LxyFkjpEnpWbyQVyVJVXxzP8RLpehfUMRXDp4=",
|
||||
"h1:VMUOof+Cf2h4asIe2lin7Fvf15mGWQ9mQYiuGhYM1aw=",
|
||||
"h1:ny17Q/ce8iuHxppA/yIuRpCkVDtqhE+LDynWtv9/qwI=",
|
||||
"zh:47e7bdfd8eddd2685f383269c0b6936ef62edd6d8383c8d7757b0cce0a689737",
|
||||
"zh:aa23eb6aa128667883cabc449ceca4072d0181f574cd727e08ebd6d69a4bfd48",
|
||||
"zh:c3da673e05d3bd933c82e2b6ba0f85aa23c5e24fadd3932f7c066314feeb65a3",
|
||||
"zh:c59f07c017fc78b79e80554a0737c9db2a2e681c3e46ff637942d28d1f1a3924",
|
||||
"zh:d559074612835a37fa684d8d7d0cf68911487b71f4067acc59069cb00bb8baf0",
|
||||
"zh:e12290a4eda757c183a4258230245dd170f0def389c37eb771db144ce3b382dd",
|
||||
"zh:ed47e484432ba1bbbb4802061f395ebd253ae8e20be9b72552d3d830fd2ca268",
|
||||
"zh:f35e08d468408697b3e7c4a7f548b874141ac8f8d395ab8edded322201cc7047",
|
||||
"zh:f809ab383cca0a5f83072981c64208cbd7fa67e986a86ee02dd2c82333221e32",
|
||||
]
|
||||
}
|
||||
|
||||
@@ -6,7 +6,7 @@ terraform {
|
||||
}
|
||||
cloudflare = {
|
||||
source = "cloudflare/cloudflare"
|
||||
version = "~> 5"
|
||||
version = ">= 5"
|
||||
}
|
||||
postgresql = {
|
||||
source = "cyrilgdn/postgresql"
|
||||
|
||||
66
2-nomad-config/act-runner.nomad.hcl
Normal file
66
2-nomad-config/act-runner.nomad.hcl
Normal file
@@ -0,0 +1,66 @@
|
||||
job "act-runner" {
|
||||
group "act-runner" {
|
||||
network {
|
||||
mode = "bridge"
|
||||
}
|
||||
|
||||
# Consul Connect upstream to Gitea so the runner can register and receive jobs
|
||||
service {
|
||||
name = "act-runner"
|
||||
connect {
|
||||
sidecar_service {
|
||||
proxy {
|
||||
upstreams {
|
||||
destination_name = "code-connect"
|
||||
local_bind_port = 3000
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
task "act-runner" {
|
||||
driver = "docker"
|
||||
|
||||
config {
|
||||
image = "gitea/act_runner:latest"
|
||||
volumes = ["/var/run/docker.sock:/var/run/docker.sock"]
|
||||
}
|
||||
|
||||
env = {
|
||||
GITEA_INSTANCE_URL = "https://gitea-1ef0bea6b75a4fd3e9393a9f7f7e4b02.othrayte.one"
|
||||
CONFIG_FILE = "/secrets/runner-config.yml"
|
||||
}
|
||||
|
||||
# Required SOPS key:
|
||||
# act-runner.registration_token — runner registration token from Gitea
|
||||
# Admin → Settings → Actions → Runners → Create new runner
|
||||
template {
|
||||
data = <<EOF
|
||||
GITEA_RUNNER_REGISTRATION_TOKEN={{ with nomadVar "nomad/jobs/act-runner" }}{{ .registration_token }}{{ end }}
|
||||
EOF
|
||||
destination = "secrets/runner.env"
|
||||
env = true
|
||||
}
|
||||
|
||||
# Limit which images/labels the runner will accept so it doesn't pick up
|
||||
# unrelated workloads if more runners are added later.
|
||||
template {
|
||||
data = <<EOF
|
||||
runner:
|
||||
labels:
|
||||
- "ubuntu-latest:docker://node:20-bookworm"
|
||||
- "ubuntu-22.04:docker://node:20-bookworm"
|
||||
- "ubuntu-24.04:docker://node:20-bookworm"
|
||||
EOF
|
||||
destination = "secrets/runner-config.yml"
|
||||
}
|
||||
|
||||
resources {
|
||||
cpu = 200
|
||||
memory = 256
|
||||
memory_max = 1024
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
10
2-nomad-config/act-runner.tf
Normal file
10
2-nomad-config/act-runner.tf
Normal file
@@ -0,0 +1,10 @@
|
||||
resource "nomad_job" "act_runner" {
|
||||
jobspec = file("act-runner.nomad.hcl")
|
||||
}
|
||||
|
||||
resource "nomad_variable" "act_runner" {
|
||||
path = "nomad/jobs/act-runner"
|
||||
items = {
|
||||
registration_token = data.sops_file.secrets.data["act-runner.registration_token"]
|
||||
}
|
||||
}
|
||||
@@ -27,6 +27,8 @@ job "gitea" {
|
||||
tags = [
|
||||
"traefik.enable=true",
|
||||
"traefik.http.routers.gitea.middlewares=auth@file",
|
||||
# Token subdomain — no auth middleware — used by act_runner step containers for git checkout
|
||||
"traefik.http.routers.gitea-token.rule=Host(`gitea-1ef0bea6b75a4fd3e9393a9f7f7e4b02.othrayte.one`)",
|
||||
]
|
||||
|
||||
check {
|
||||
|
||||
@@ -12,7 +12,7 @@ terraform {
|
||||
}
|
||||
cloudflare = {
|
||||
source = "cloudflare/cloudflare"
|
||||
version = "~> 5"
|
||||
version = ">= 5"
|
||||
}
|
||||
postgresql = {
|
||||
source = "cyrilgdn/postgresql"
|
||||
|
||||
@@ -46,14 +46,8 @@ job "ntfy" {
|
||||
# Bcrypt hashes are not secrets and are hardcoded below (same as /etc/shadow — safe to commit).
|
||||
# Generate with: docker run --rm -it binwiederhier/ntfy user hash
|
||||
# or: echo "mypassword" | docker run --rm -i binwiederhier/ntfy user hash
|
||||
# For the diun account the plaintext is irrelevant (token-only auth); use a random password:
|
||||
# openssl rand -base64 32 | docker run --rm -i binwiederhier/ntfy user hash
|
||||
#
|
||||
# Required SOPS keys:
|
||||
# ntfy.database_pw — postgres password for the ntfy role
|
||||
# diun.ntfy_token — access token for Diun (actual secret — grants write access)
|
||||
# Must start with "tk_" and be exactly 32 chars total.
|
||||
# Generate: tok=$(openssl rand -hex 15); echo "tk_${tok:0:29}"
|
||||
task "ntfy" {
|
||||
driver = "docker"
|
||||
|
||||
@@ -80,11 +74,6 @@ behind-proxy: true
|
||||
enable-login: true
|
||||
auth-users:
|
||||
- "admin:$2a$10$rLp4qagJnsA8Es5hQlISH.WrlzwMrXE2MBaEgz7zdd2lkAVu30lMy:admin"
|
||||
- "diun:$2y$10$4wi1VG.Vp5p3Q2OEIXaTSOmwZm.G9dpNca9BqQRMdGGnk2yQqK3Gq:user"
|
||||
auth-tokens:
|
||||
- "diun:{{with nomadVar "nomad/jobs/ntfy"}}{{.diun_token}}{{end}}:Diun"
|
||||
auth-access:
|
||||
- "diun:diun:write-only"
|
||||
EOF
|
||||
destination = "local/server.yml"
|
||||
}
|
||||
|
||||
@@ -6,7 +6,6 @@ resource "nomad_variable" "ntfy" {
|
||||
path = "nomad/jobs/ntfy"
|
||||
items = {
|
||||
database_pw = data.sops_file.secrets.data["ntfy.database_pw"]
|
||||
diun_token = data.sops_file.secrets.data["diun.ntfy_token"]
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -46,9 +46,12 @@ job "renovate" {
|
||||
# renovate.gitea_token — PAT for the renovate bot account in Gitea
|
||||
# Create a dedicated 'renovate' user in Gitea with these token scopes:
|
||||
# repo (read+write), user (read), issue (read+write), organization (read)
|
||||
# renovate.github_token — read-only GitHub PAT (any account) for
|
||||
# fetching changelogs and avoiding github.com API rate limits
|
||||
template {
|
||||
data = <<EOF
|
||||
RENOVATE_TOKEN={{ with nomadVar "nomad/jobs/renovate" }}{{ .gitea_token }}{{ end }}
|
||||
RENOVATE_GITHUB_COM_TOKEN={{ with nomadVar "nomad/jobs/renovate" }}{{ .github_token }}{{ end }}
|
||||
EOF
|
||||
destination = "secrets/renovate.env"
|
||||
env = true
|
||||
|
||||
@@ -6,5 +6,6 @@ resource "nomad_variable" "renovate" {
|
||||
path = "nomad/jobs/renovate"
|
||||
items = {
|
||||
gitea_token = data.sops_file.secrets.data["renovate.gitea_token"]
|
||||
github_token = data.sops_file.secrets.data["renovate.github_token"]
|
||||
}
|
||||
}
|
||||
|
||||
@@ -53,7 +53,11 @@
|
||||
"database_pw": "ENC[AES256_GCM,data:79c2KFs3tcbet1dSGnkSDlAeKLCZrh4aMYLXTROM8w==,iv:eZ4limyjl++nsvHUzPKy82hfLZEOc+XQYpO6Czo/8os=,tag:iX9SiEACQ5IM8f1jhZh5Qw==,type:str]"
|
||||
},
|
||||
"renovate": {
|
||||
"gitea_token": "ENC[AES256_GCM,data:/J3CDMgWZLe20oQ+ENKBMi8fs/+jgsARV7xihMq0OLmRk8C8ae/IXg==,iv:e7WYOanSOCZ/LhN6SKrH0VrR3xLPTTppOKpGpSl+oAc=,tag:XBAilRdK3jL7WtM+92Fsmg==,type:str]"
|
||||
"gitea_token": "ENC[AES256_GCM,data:/J3CDMgWZLe20oQ+ENKBMi8fs/+jgsARV7xihMq0OLmRk8C8ae/IXg==,iv:e7WYOanSOCZ/LhN6SKrH0VrR3xLPTTppOKpGpSl+oAc=,tag:XBAilRdK3jL7WtM+92Fsmg==,type:str]",
|
||||
"github_token": "ENC[AES256_GCM,data:omZpdsTV1aFgQ9PjIApITEyIRKk6Z8QyvD2Kp5tJnBWzFCm4v2lRAg==,iv:cKL7z+CSChzF9eZEcske2lbmx9KV6CrWw0tn7rmP/10=,tag:gon3Sc1d3ntNSbWwenHuOw==,type:str]"
|
||||
},
|
||||
"act-runner": {
|
||||
"registration_token": "ENC[AES256_GCM,data:RnDvcNh69lLlL/ms+sMPKhhc+ECtc5hUHSkAQZv8e77iTD/QPd356Q==,iv:sl2Aua8rTe6cKYQAUC7O4UyHajGy1LgG/ZNLTVP4SyE=,tag:JjdaQqZ4PaWjfoiVmBl6lQ==,type:str]"
|
||||
},
|
||||
"sops": {
|
||||
"age": [
|
||||
@@ -62,8 +66,8 @@
|
||||
"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSByUWM4ZDVVbGFrUGdMRHBX\nUFBmU3Nlc0RBSzhFK0tHNHpkQXUvUVdiZUZJCmpRN1lFdENpWW0rcThjVlVQNUl6\nWnlLU0RnQ3FZby81Ly8xTFBrek9nMncKLS0tIFQ4UTRNOC9CRmx4OFJWem1wckZz\nUDFTSzdWZldFK3FqcTNWTWRyNDhHQ2MKS811mR5xn7qiC/aVgPFYJ5c6Q3zxRfcr\nHcvxUvB01vNJKZpRg92vvKPkV6lQO3DXCT98OdfwiymlEOvYxg71Pg==\n-----END AGE ENCRYPTED FILE-----\n"
|
||||
}
|
||||
],
|
||||
"lastmodified": "2026-04-18T06:07:22Z",
|
||||
"mac": "ENC[AES256_GCM,data:4UJMEZNS8HXtn1vIJ+qCkBJL5oh3Jp7wbaGm5hMiSNPseNq3smTYmMgh+TNK4t/K7yxfukTuhEFTUsnMfi7rIxTrbCpcTdnqJSYm/iflkdA57Tx+mHpY9iG7wtRmObow18Ea0rj6foMu+1V8pVFomzhc/ipafinTCuqodKW1a2Y=,iv:Gu/Lh8mir36ltN++qJg122ry+eJA0GKSrfijulYM7q4=,tag:5tjBzrCZcQUvc76No+E9Ow==,type:str]",
|
||||
"lastmodified": "2026-04-18T07:41:42Z",
|
||||
"mac": "ENC[AES256_GCM,data:+HhhsiZXok4BZI05tG3p9veZaj51kELSQlWFYMSInv7bGfEadmOrJqCxaGrFcNkMmgVPx80jWQFrILfVLW5MUvEsHAhD4Vza2TSWeUq1HuL9DbMxsK2G9Y1fbthd12r/++dDcXxVnTUf/rCD70in/+g/zRObocAnUcFEcIqx1JE=,iv:pS+aj+47J4bYZYGlMVniQVTlLt4jtCLUT7oROJLUkZo=,tag:+lznxDhs2C3bcz5quxfHjA==,type:str]",
|
||||
"encrypted_regex": "^(.*)$",
|
||||
"version": "3.10.2"
|
||||
}
|
||||
|
||||
305
cicd-plan.md
Normal file
305
cicd-plan.md
Normal file
@@ -0,0 +1,305 @@
|
||||
# CI/CD Plan
|
||||
|
||||
## Overview
|
||||
|
||||
Three distinct problems, tackled in phases:
|
||||
|
||||
1. **Does the config parse/validate without errors?** (static, no credentials)
|
||||
2. **Does the new Docker image actually exist and start?** (pre-merge, needs Docker)
|
||||
3. **Does the running service stay healthy through a deployment?** (post-merge, needs Nomad canary)
|
||||
|
||||
The goal is: Renovate opens a PR → CI runs checks → you review → merge → canary starts automatically → you promote (or it auto-reverts).
|
||||
|
||||
---
|
||||
|
||||
## Phase 1 — Static Validation (proves the runner works)
|
||||
|
||||
No secrets needed. Runs on every PR.
|
||||
|
||||
### Infrastructure required
|
||||
|
||||
- `act_runner` Nomad job (see below) with a Gitea runner token
|
||||
- `.gitea/workflows/ci.yml` in this repo
|
||||
|
||||
### Checks
|
||||
|
||||
| Check | Command | Notes |
|
||||
| --------------------- | ----------------------------------------------------- | ------------------------------------------------------------------- |
|
||||
| HCL formatting | `terraform fmt -check -recursive` | Fails on whitespace/style drift |
|
||||
| Terraform syntax | `terraform init -backend=false && terraform validate` | Catches wrong resource types, missing required args, bad references |
|
||||
| Nomad job spec syntax | `nomad job validate <file>` | Catches Nomad-specific issues; needs `NOMAD_ADDR` + read token |
|
||||
|
||||
`terraform validate -backend=false` is the most valuable: it catches ~90% of real mistakes with zero secret exposure. The Nomad validate step requires a low-privilege read token — worth adding once the runner is trusted.
|
||||
|
||||
### Workflow sketch
|
||||
|
||||
```yaml
|
||||
# .gitea/workflows/ci.yml
|
||||
on: [pull_request]
|
||||
|
||||
jobs:
|
||||
validate:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: hashicorp/setup-terraform@v3
|
||||
|
||||
- name: fmt check
|
||||
run: terraform fmt -check -recursive
|
||||
working-directory: 2-nomad-config
|
||||
|
||||
- name: init + validate (no backend)
|
||||
run: |
|
||||
terraform init -backend=false
|
||||
terraform validate
|
||||
working-directory: 2-nomad-config
|
||||
|
||||
- name: fmt check (nixos-node)
|
||||
run: terraform fmt -check -recursive
|
||||
working-directory: 1-nixos-node
|
||||
|
||||
nomad-validate:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Install Nomad CLI
|
||||
run: |
|
||||
curl -fsSL https://apt.releases.hashicorp.com/gpg | sudo gpg --dearmor -o /usr/share/keyrings/hashicorp.gpg
|
||||
echo "deb [signed-by=/usr/share/keyrings/hashicorp.gpg] https://apt.releases.hashicorp.com $(lsb_release -cs) main" | sudo tee /etc/apt/sources.list.d/hashicorp.list
|
||||
sudo apt-get update && sudo apt-get install -y nomad
|
||||
- name: validate all job specs
|
||||
env:
|
||||
NOMAD_ADDR: ${{ secrets.NOMAD_ADDR }}
|
||||
NOMAD_TOKEN: ${{ secrets.NOMAD_TOKEN }} # read-only policy sufficient
|
||||
run: |
|
||||
find 2-nomad-config -name '*.nomad.hcl' | while read f; do
|
||||
echo "==> $f"
|
||||
nomad job validate "$f"
|
||||
done
|
||||
```
|
||||
|
||||
### act_runner Nomad job
|
||||
|
||||
```hcl
|
||||
# act-runner.nomad.hcl
|
||||
job "act-runner" {
|
||||
group "act-runner" {
|
||||
network {
|
||||
mode = "bridge"
|
||||
}
|
||||
|
||||
# Connect upstream to Gitea
|
||||
service {
|
||||
name = "act-runner"
|
||||
connect {
|
||||
sidecar_service {
|
||||
proxy {
|
||||
upstreams {
|
||||
destination_name = "code-connect"
|
||||
local_bind_port = 3000
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
task "act-runner" {
|
||||
driver = "docker"
|
||||
|
||||
config {
|
||||
image = "gitea/act_runner:latest"
|
||||
volumes = ["/var/run/docker.sock:/var/run/docker.sock"]
|
||||
}
|
||||
|
||||
env = {
|
||||
GITEA_INSTANCE_URL = "http://localhost:3000"
|
||||
}
|
||||
|
||||
template {
|
||||
data = <<EOF
|
||||
GITEA_RUNNER_REGISTRATION_TOKEN={{ with nomadVar "nomad/jobs/act-runner" }}{{ .registration_token }}{{ end }}
|
||||
EOF
|
||||
destination = "secrets/runner.env"
|
||||
env = true
|
||||
}
|
||||
|
||||
resources {
|
||||
cpu = 200
|
||||
memory = 256
|
||||
memory_max = 512
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Security note**: mounting `/var/run/docker.sock` gives the runner root-equivalent access to the host. Acceptable for a home server. Alternative: use `docker:dind` sidecar or Nomad's `exec` driver — more complex, lower risk.
|
||||
|
||||
---
|
||||
|
||||
## Phase 2 — Docker Image Validation (pre-merge)
|
||||
|
||||
Runs on PRs that touch `.nomad.hcl` files. Catches: tag typos, deleted images, registry outages.
|
||||
|
||||
Requires the `act_runner` to have Docker access (same socket mount as above).
|
||||
|
||||
```yaml
|
||||
image-pull:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Pull changed images
|
||||
run: |
|
||||
# Extract image tags added or changed vs main
|
||||
git fetch origin main
|
||||
git diff origin/main...HEAD -- '*.nomad.hcl' \
|
||||
| grep '^\+\s*image\s*=' \
|
||||
| grep -oP '"[^"]+:[^"]+"' \
|
||||
| tr -d '"' \
|
||||
| sort -u \
|
||||
| while read image; do
|
||||
echo "==> Pulling $image"
|
||||
docker pull "$image"
|
||||
done
|
||||
```
|
||||
|
||||
This intentionally only tests _changed_ images — no value in pulling everything on every PR.
|
||||
|
||||
---
|
||||
|
||||
## Phase 3 — Nomad Canary Deployments (post-merge gate)
|
||||
|
||||
Makes "merge" mean "start canary" rather than "go live". The old allocation keeps running until you promote.
|
||||
|
||||
### Which jobs get canaries
|
||||
|
||||
Most jobs already have Consul health checks — these can use `health_check = "checks"` for automatic revert gating.
|
||||
|
||||
| Job | Health check | Shared writable volume | Canary safe? |
|
||||
| ---------- | ------------- | ----------------------- | --------------------------------------------------------------------------------- |
|
||||
| ntfy | ✅ `/healthz` | no | ✅ yes |
|
||||
| gitea | ✅ `/` | ✅ `single-node-writer` | ⚠️ volume blocks 2nd alloc from mounting — needs `max_parallel=1` rolling instead |
|
||||
| jellyfin | ✅ | ✅ `single-node-writer` | ⚠️ same — rolling |
|
||||
| immich | ✅ | ✅ `single-node-writer` | ⚠️ same — rolling |
|
||||
| sonarr | ✅ | ✅ `single-node-writer` | ⚠️ same — rolling |
|
||||
| prowlarr | ✅ | ✅ `single-node-writer` | ⚠️ same — rolling |
|
||||
| deluge | ✅ | ✅ `single-node-writer` | ⚠️ same — rolling |
|
||||
| frigate | ✅ | ✅ `single-node-writer` | ⚠️ same — rolling |
|
||||
| glance | ✅ | no | ✅ yes |
|
||||
| transfer | ✅ | ✅ `single-node-writer` | ⚠️ rolling |
|
||||
| openreader | ❌ | ✅ `single-node-writer` | ⚠️ add check first, then rolling |
|
||||
| unifi | ❌ | ✅ `single-node-writer` | ⚠️ add check first, then rolling |
|
||||
| traefik | (ingress) | ✅ | ⚠️ rolling — downtime risk, promote quickly |
|
||||
| authelia | (ingress) | ✅ | ✅ stateless config, canary fine |
|
||||
| renovate | batch job | n/a | n/a — no deployment model |
|
||||
| postgres | (data layer) | ✅ | ❌ never canary — single-writer DB |
|
||||
|
||||
### Canary stanza (stateless jobs with no volume conflict)
|
||||
|
||||
```hcl
|
||||
update {
|
||||
canary = 1
|
||||
auto_promote = false
|
||||
auto_revert = true
|
||||
health_check = "checks"
|
||||
healthy_deadline = "5m"
|
||||
min_healthy_time = "30s"
|
||||
}
|
||||
```
|
||||
|
||||
### Rolling stanza (jobs with single-node-writer volumes)
|
||||
|
||||
```hcl
|
||||
update {
|
||||
max_parallel = 1
|
||||
auto_revert = true
|
||||
health_check = "checks"
|
||||
healthy_deadline = "5m"
|
||||
min_healthy_time = "30s"
|
||||
}
|
||||
```
|
||||
|
||||
Rolling with `max_parallel=1` still gives auto-revert but doesn't attempt to run two allocations simultaneously — the old one stops before the new one mounts the volume.
|
||||
|
||||
---
|
||||
|
||||
## Phase 4 — Automated terraform apply + Deployment Promotion
|
||||
|
||||
Full CD: merge triggers apply, which creates the canary, CI then watches it and promotes or reverts.
|
||||
|
||||
### Flow
|
||||
|
||||
```
|
||||
PR merged to main
|
||||
│
|
||||
▼
|
||||
Gitea Actions (on: push, branches: [main])
|
||||
- terraform init
|
||||
- terraform apply -auto-approve
|
||||
│
|
||||
▼
|
||||
Nomad canary starts (old allocation still live)
|
||||
│
|
||||
▼
|
||||
CI polls `nomad deployment list` for the new deployment ID
|
||||
CI waits for canary allocation to reach "healthy" in Consul
|
||||
│ healthy within deadline
|
||||
▼
|
||||
CI runs: nomad deployment promote <id>
|
||||
│ or unhealthy → nomad deployment fail <id> (auto_revert fires)
|
||||
▼
|
||||
ntfy notification: "deployment promoted" or "deployment reverted"
|
||||
```
|
||||
|
||||
### Secrets required for full CD
|
||||
|
||||
| Secret | Used by | Risk level |
|
||||
| ---------------------- | ----------------------------------- | ---------------------------------- |
|
||||
| `NOMAD_ADDR` | validate + apply + promote | Low (internal LAN addr) |
|
||||
| `NOMAD_TOKEN` | terraform apply (write) + promote | **High** — grants full infra write |
|
||||
| `CLOUDFLARE_API_TOKEN` | terraform apply | **High** — DNS write |
|
||||
| `SOPS_AGE_KEY` | terraform apply (decrypt secrets) | **High** — decrypts all secrets |
|
||||
| `PG_PASSWORD` | terraform apply (postgres provider) | High |
|
||||
|
||||
Full CD requires all of these in Gitea Actions secrets. This is acceptable for a self-hosted, non-public Gitea instance where you control runner access — but it's the trust boundary to be deliberate about. A reasonable middle ground: **Phase 1-3 are fully automated; Phase 4 (apply + promote) runs automatically but requires a manual re-trigger or approval step** (Gitea supports required reviewers on environments).
|
||||
|
||||
### Promote/revert script sketch
|
||||
|
||||
```bash
|
||||
# In CI, after terraform apply completes:
|
||||
DEPLOY_ID=$(nomad deployment list -json | jq -r '[.[] | select(.JobID == "$JOB" and .Status == "running")] | first | .ID')
|
||||
echo "Watching deployment $DEPLOY_ID..."
|
||||
|
||||
for i in $(seq 1 30); do
|
||||
STATUS=$(nomad deployment status -json "$DEPLOY_ID" | jq -r '.Status')
|
||||
HEALTHY=$(nomad deployment status -json "$DEPLOY_ID" | jq -r '.TaskGroups[].HealthyAllocs')
|
||||
echo "[$i] status=$STATUS healthy=$HEALTHY"
|
||||
if [ "$STATUS" = "successful" ]; then exit 0; fi
|
||||
if [ "$STATUS" = "failed" ]; then exit 1; fi
|
||||
# Check if canary is healthy enough to promote
|
||||
CANARY_HEALTHY=$(nomad deployment status -json "$DEPLOY_ID" | jq -r '.TaskGroups[].DesiredCanaries == .TaskGroups[].HealthyAllocs')
|
||||
if [ "$CANARY_HEALTHY" = "true" ]; then
|
||||
nomad deployment promote "$DEPLOY_ID"
|
||||
exit 0
|
||||
fi
|
||||
sleep 10
|
||||
done
|
||||
nomad deployment fail "$DEPLOY_ID"
|
||||
exit 1
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Implementation Order
|
||||
|
||||
- [x] **Phase 1a**: Create `act-runner.nomad.hcl` + Terraform wrapper, register runner token in Gitea, get a hello-world workflow green
|
||||
- [x] **Phase 1b**: Add `terraform fmt` + `terraform validate -backend=false` workflow — no secrets needed
|
||||
- [x] **Phase 1c**: Add Nomad validate step — add `NOMAD_ADDR` + read-only `NOMAD_TOKEN` to Gitea secrets
|
||||
- [ ] **Phase 2**: Add image pull validation step to the workflow
|
||||
- [ ] **Phase 3a**: Add `update` stanzas to ntfy and glance (simplest, no volume conflict)
|
||||
- [ ] **Phase 3b**: Add rolling `update` stanzas to remaining service jobs (jellyfin, sonarr, etc.)
|
||||
- [ ] **Phase 3c**: Add health checks to openreader and unifi before adding update stanzas
|
||||
- [ ] **Phase 4a**: Add on-push workflow that runs `terraform apply -auto-approve` using full credential set
|
||||
- [ ] **Phase 4b**: Add deployment promotion/revert polling script
|
||||
- [ ] **Phase 4c**: Wire ntfy notifications for promote/revert outcomes
|
||||
Reference in New Issue
Block a user