feat: migrate all managed LXC provisioning to OpenTofu (blue-green)
Blue-green: a new container is created beside the old one, data is copied, the
IP is moved onto it, and the old container is kept stopped as rollback for at
least a week. Keeping the IP means only the VMID changes, and its consumers
(backup jobs, backup audit) already derive it from the registry.
Batch 1 (2026-09-02): emergency-bot 148->151, docker-test 145->152,
gitea 141->153, vaultwarden 140->154, monitoring 146->155, gyro 150->156,
grimmory 149->157.
Batch 2 (2026-09-03): adguard 144->158, mihomo 143->159, ovpn-mini 132->160.
All migratable LXC are now provisioner: tofu. hermes-ai (frozen) and pbs stay.
- tofu/services.tf + tofu/svc-*.tf: one resource per service, reproducing the
pct-config etalon. /dev/fuse -> features.fuse; /dev/net/tun ->
device_passthrough (first live use on mihomo and ovpn-mini); gitea bind mount
-> datastore volume (data finally reaches PBS); console { type = "shell" }
declared explicitly (provider tracks cmode there).
- services.yml: vmid + provisioner: tofu for every migrated service; features
strings and device notes updated to the tofu representation; also drops the
memoir-bot entry and adds homelab_reverse_proxy_image/_unit.
- pve-*.yml: configuration play target is `{{ pve_config_target | default(...) }}`
so it can run against <name>-new on a temp address (a bare --limit zeroes the
play instead of retargeting it). Container-creation plays are gated behind
`provisioner != 'tofu'` / `pve_provisioning_enabled` (meta: end_play), so a
stray run cannot pct start a stopped OLD VMID on a live IP. Override for
intentional legacy rollback: -e pve_<svc>_legacy_provisioning_enabled=true.
- ssh_config: drop memoir-bot; ovpn-mini gets ProxyJump none (a jump via ru-vps
would route through the very tunnel ovpn-mini terminates).
- gyro.yml / uptime-kuma.yml: same pve_config_target override.
- roles/uptime_kuma: only freeze homelab-monitoring when the unit actually
exists (a fresh blue-green container never had it).
- offsite-restic-yadisk.yml: the gitea restic profile now runs inside the LXC
(hosts: gitea), since the bind-mount host path is gone after the volume move;
lost+found excluded (unreadable in an unprivileged LXC, restic exit 3).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012uoq5AVK8mkBgg83Mq6o5V
This commit is contained in:
Dmitry
co-authored by
Claude Sonnet 5
Claude Sonnet 5
parent
e349f19e68
commit
a3fe8031fe
@@ -0,0 +1,127 @@
|
||||
# ============================================================================
|
||||
# Сервис №8 по плану (docs/ai/migration-tofu.md, раздел 5): adguard.
|
||||
# DNS-фильтр всей LAN. Жёсткое окно простоя только между шагами 4.5.14 и
|
||||
# 4.5.17 (два контейнера на 192.168.1.28 одновременно невозможны).
|
||||
#
|
||||
# OLD vmid 144, узел mini-pc, боевой адрес 192.168.1.28.
|
||||
# Эталон снят 2026-09-02: ssh mini-pc sudo pct config 144 (дословно совпадает
|
||||
# с /etc/pve/lxc/144.conf):
|
||||
#
|
||||
# arch: amd64
|
||||
# cmode: shell
|
||||
# cores: 1
|
||||
# features: nesting=1,keyctl=1
|
||||
# hostname: adguard
|
||||
# memory: 512
|
||||
# nameserver: 1.1.1.1
|
||||
# net0: name=eth0,bridge=vmbr0,firewall=1,gw=192.168.1.1,ip=192.168.1.28/24,type=veth
|
||||
# onboot: 1
|
||||
# ostype: debian
|
||||
# rootfs: local-lvm:vm-144-disk-0,size=8G
|
||||
# startup: order=40
|
||||
# swap: 512
|
||||
# unprivileged: 1
|
||||
# lxc.cgroup2.devices.allow: c 10:229 rwm
|
||||
# lxc.mount.entry: /dev/fuse dev/fuse none bind,create=file
|
||||
#
|
||||
# vm_id 158 — новый VMID для blue-green переезда (назначен, не менять).
|
||||
# TMPIP 192.168.1.17 используется только на шаге 4.3 (проверка перед cutover).
|
||||
# После шага 4.5.15 адрес меняется на боевой 192.168.1.28, OLD (144)
|
||||
# останавливается и остаётся откатом минимум неделю.
|
||||
#
|
||||
# --- /dev/fuse: features.fuse, а не device_passthrough ----------------------
|
||||
# Эталонные lxc.cgroup2.devices.allow + lxc.mount.entry для /dev/fuse — ручной
|
||||
# обход (lineinfile по /etc/pve/lxc/144.conf в pve-adguard.yml), потому что
|
||||
# Proxmox API сырые lxc.* ключи не принимает. Заменяется штатным флагом PVE
|
||||
# features.fuse, проверенным на пилоте VMID 199 и на сервисах 2-7. Следствие:
|
||||
# pct config нового контейнера покажет features: fuse=1,keyctl=1,nesting=1 —
|
||||
# текстуально иначе, чем эталон, при том же эффекте. См. tofu/README.md.
|
||||
#
|
||||
# --- Данные ----------------------------------------------------------------
|
||||
# /opt/adguard/{conf,work} (~313 МБ, почти всё — work/: журнал запросов,
|
||||
# статистика, кэш фильтров). conf/AdGuardHome.yaml несёт весь конфиг, включая
|
||||
# хэш пароля админа, DNS rewrites, upstream и клиентов. Переносится целиком
|
||||
# на шаге 4.4; Ansible этим каталогом не управляет.
|
||||
# ============================================================================
|
||||
|
||||
resource "proxmox_virtual_environment_container" "adguard" {
|
||||
node_name = "mini-pc"
|
||||
vm_id = 158
|
||||
unprivileged = true
|
||||
start_on_boot = true
|
||||
started = true
|
||||
tags = ["tofu"]
|
||||
|
||||
initialization {
|
||||
hostname = "adguard"
|
||||
|
||||
ip_config {
|
||||
ipv4 {
|
||||
address = "192.168.1.28/24"
|
||||
gateway = "192.168.1.1"
|
||||
}
|
||||
}
|
||||
|
||||
dns {
|
||||
servers = ["1.1.1.1"]
|
||||
}
|
||||
|
||||
user_account {
|
||||
keys = [trimspace(file(pathexpand("~/.ssh/id_ed25519_homelab.pub")))]
|
||||
}
|
||||
}
|
||||
|
||||
operating_system {
|
||||
template_file_id = "local:vztmpl/debian-13-standard_13.1-2_amd64.tar.zst"
|
||||
type = "debian"
|
||||
}
|
||||
|
||||
cpu {
|
||||
cores = 1
|
||||
}
|
||||
|
||||
memory {
|
||||
dedicated = 512
|
||||
swap = 512
|
||||
}
|
||||
|
||||
disk {
|
||||
datastore_id = "local-lvm"
|
||||
size = 8
|
||||
}
|
||||
|
||||
# Эталон: features: nesting=1,keyctl=1 плюс проброс /dev/fuse через сырые
|
||||
# lxc.* строки. fuse=1 — штатная замена этого обхода (см. комментарий выше).
|
||||
features {
|
||||
nesting = true
|
||||
keyctl = true
|
||||
fuse = true
|
||||
}
|
||||
|
||||
# roles/pve_lxc всем контейнерам ставит cmode=shell (pve_lxc_cmode), провайдер
|
||||
# это отслеживает через блок console.type — без него на следующем apply
|
||||
# откатит на дефолт Proxmox tty. Обнаружено 2026-09-02 на emergency-bot,
|
||||
# см. tofu/README.md.
|
||||
console {
|
||||
type = "shell"
|
||||
}
|
||||
|
||||
network_interface {
|
||||
name = "eth0"
|
||||
bridge = "vmbr0"
|
||||
firewall = true
|
||||
}
|
||||
|
||||
startup {
|
||||
order = 40
|
||||
}
|
||||
}
|
||||
|
||||
output "adguard" {
|
||||
description = "Что проверять на узле после apply"
|
||||
value = {
|
||||
vmid = proxmox_virtual_environment_container.adguard.vm_id
|
||||
node = proxmox_virtual_environment_container.adguard.node_name
|
||||
verify = "ssh mini-pc sudo pct config ${proxmox_virtual_environment_container.adguard.vm_id}"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user