Phase 1 — fix stale state after strong migration (Phase 1+2, 2026-07-05)
- README: corrected IPs (jellyfin 206→246, arriman 132→245, etc.),
added missing containers (128 trmnl, 129 house, 133 seanime, 134 romm,
124 authentik), updated last-refreshed date, added strong host context
- containers/101-jellyfin.md: IP 206→246, host hubris→strong, mount
/mnt/library→/mnt/media_local, GPU 760M→680M+RX7600, privilege→priv
- containers/118-elementsynapse.md: IP 239→242, added Host: strong
- containers/122-arriman.md: IP 132→245, mount→/mnt/media_local, added Host
- containers/129-house.md: IP 212→244, added Host: strong
- containers/130-grimmory.md: IP 213→247, mount→/mnt/media_local, added Host
- containers/121-caddy.md: fixed site list (books→grimmory, removed auth→VPS,
added house, roms, teddy, trmnl)
- hosts/strong.md: updated At-a-glance to reflect 7 LXCs hosted
- containers/123-claudio-bot.md, 127-mule-photos-new.md: archived to
containers/archive/ (were destroyed LXCs with living pages)
- inventory.yaml: verified correct — no changes needed
Phase 2 — structural cleanup
- infrastructure/index.md: one-page overview of all cross-cutting systems
- runbooks/: moved runbook-budget-from-csv.md and runbook-dpkg-interrupted.md
from operations/ with YAML frontmatter added
- plans/done/: moved 4 completed plans out of active view; updated index
- vms/index.md: added VM index page
Phase 3 — navigation & discoverability
- GLOSSARY.md: term definitions (Authentik, Caddy, LXC, VAAPI, etc.)
- README: added table of contents, links to glossary + infrastructure index
- investigations/: archived 2 resolved cases (crash-loop, authentik-migration)
to investigations/archive/; updated index with active vs archived sections
Phase 4 — ongoing discipline
- CONTRIBUTING.md: documented same-session update rule with explicit checklist
- README: replaced full LXC table with summary + link to containers/index.md
(single source of truth; de-duplication)
5.0 KiB
2026-06-01 — Slate AX → SODOLA Migration
Status: Done — 2026-06-02
Hardware: SODOLA 5-Port 2.5Gbit Managed Switch replacing GL.iNet Slate AX
Router: Fritz!Box 7590
Goal
Remove the Slate AX sub-router. It adds double-NAT, double port-forward complexity, and a second DHCP/gateway hop. Replace with the SODOLA switch so Proxmox and homelab devices attach directly to the Fritz!Box—without changing any of their IPs.
Current topology
ISP
└── Fritz!Box 7590 (192.168.178.1)
└── GL.iNet Slate AX WAN: 192.168.178.x LAN: 192.168.8.1 [NAT]
├── hubris (Proxmox) 192.168.8.77
├── + all 16 LXCs on vmbr0 bridged to the same subnet
└── other homelab devices
Target topology
ISP
└── Fritz!Box 7590
├── VLAN 1 192.168.178.0/24 (main LAN — laptops, phones)
└── VLAN 10 192.168.8.0/24 gateway 192.168.8.1 (homelab, no NAT)
│
└── SODOLA 5-Port 2.5Gbit
├── Port 1 uplink → Fritz!Box LAN port
├── Port 2 hubris (Proxmox) 192.168.8.77
├── Port 3 [homelab device]
├── Port 4 [homelab device]
└── Port 5 spare
Fritz!Box takes over 192.168.8.1 — the same gateway IP the Slate AX used. No static IPs or gateway entries change on any LXC or VM.
See network architecture for the permanent topology reference.
Pre-flight checklist
- Note Slate AX gateway IP on the homelab subnet (expected
192.168.8.1) - Note Slate AX upstream DNS setting (what it forwards to)
- List all port forwards currently on the Slate AX → move these to Fritz!Box
- List all port forwards on Fritz!Box that point at the Slate AX WAN IP → collapse these into direct homelab-IP rules
- Confirm Fritz!OS version supports "second IP network" (Fritz!OS 7.x required)
- SSH into hubris: verify
grep gateway /etc/network/interfaces→192.168.8.1 - SODOLA web UI accessible and ports configurable before physical move
Fritz!Box configuration
Path: Home Network → Network → Network Settings → IPv4 Addresses → Add IP network
| Field | Value |
|---|---|
| IP address | 192.168.8.1 |
| Subnet mask | 255.255.255.0 |
| DHCP range | 192.168.8.100 – 192.168.8.240 |
| Assign to | LAN port that connects to SODOLA |
| Network isolation | Enabled (blocks main LAN from initiating into homelab) |
| DNS for DHCP clients | 192.168.8.2 (Technitium on CT 107) |
After creating the network, move any port forwards from the Slate AX into Fritz!Box → Internet → Permits (target IPs are now directly reachable on 192.168.8.x).
SODOLA configuration
All ports in VLAN 10, untagged (simple access-port setup):
| Port | PVID | Role |
|---|---|---|
| 1 | 10 | Uplink → Fritz!Box |
| 2 | 10 | hubris (Proxmox) |
| 3 | 10 | homelab device |
| 4 | 10 | homelab device |
| 5 | 10 | spare |
Proxmox / LXC changes
If the Slate AX gateway was 192.168.8.1: no changes needed. Fritz!Box takes the same IP.
If Slate AX used a different gateway (e.g. .254), update:
# on hubris
nano /etc/network/interfaces # change gateway line
ifreload -a
# for each LXC with a static gateway
pct config <id> # check net0: line for gw=
pct set <id> --net0 name=eth0,bridge=vmbr0,ip=<ip>/24,gw=192.168.8.1
DNS after migration
Technitium (CT 107) at 192.168.8.2 continues to serve split-horizon DNS for hubris.network. The Fritz!Box DHCP server for VLAN 10 hands out 192.168.8.2 as the DNS server. This fixes the "update router DHCP DNS from dead .180 → .2" outstanding item in dns.md.
Cutover procedure
- Configure Fritz!Box second IP network (VLAN 10 /
192.168.8.1) — verify DHCP works via a test laptop on the target port. - Configure SODOLA port VLAN assignments.
- Connect SODOLA port 1 → Fritz!Box target LAN port.
- Move hubris ethernet → SODOLA port 2. Proxmox should stay reachable immediately (same gateway IP).
- Move remaining homelab devices to SODOLA ports 3–5.
- Decommission Slate AX.
Verification
# internet from Proxmox
ssh proxmox "ping -c3 1.1.1.1"
# Fritz!Box main LAN reachable (routing between VLANs works)
ssh proxmox "ping -c3 192.168.178.1"
# split-horizon DNS via Technitium still resolves
ssh proxmox "dig @192.168.8.2 +short git.hubris.network"
# expected: 192.168.8.175
# Caddy reverse proxy responds
curl -sk https://git.hubris.network | head -5
# Authentik on VPS still reachable
curl -sk https://auth.hubris.network/if/flow/default-authentication-flow/ | head -5
Post-migration
- Update network.md topology to reflect new state.
- Add changelog entries to hosts/hubris.md and any affected container pages.
- Update status in plans/index.md to
Done. - If anything went sideways, open an investigation in
investigations/.