Files
vh efddb4e511 feat(scriberr): stand up transcription on ana-ml2, pinned to GPU1
Scriberr transcribes audio and video locally with WhisperX and
speaker diarization, and it lands on ana-ml2 rather than ana-docker
because the work is GPU-shaped: ana-docker offers eight cores already
shared with fifty containers and thirty-seven gigabytes of disk,
against ninety-six cores, terabytes on /tank and idle capacity on
GPU1. The reservation names device 1 explicitly, since GPU0 is fully
committed to the gen seat, and the container is confirmed to see that
card alone.

The image is built from source, which is not a preference. These are
Blackwell cards at sm_120; the published CUDA image covers Pascal
through Ada only, and the blackwell image the upstream README
documents has never been published at all. The path upstream actually
ships for sm_120 is Dockerfile.cuda.12.9, carrying CUDA 12.9 and cu128
torch, so that is what gets built. The compose header says so, because
the obvious cleanup is to swap in the published image and that would
silently drop the deployment to CPU.

Two configuration details are load-bearing and documented where
someone would go to change them. The application runs as uid 10001
rather than the usual 1000: that Dockerfile moves its user aside for
Ubuntu 24.04's own uid-1000 account and chowns /app accordingly, while
the entrypoint's remapping covers only the data directories, so at
1000 the process cannot open its database and restarts forever behind
a SQLite error that reads as though the machine were out of memory.
Secure cookies stay off while the service is reached over plain HTTP,
or sessions are dropped by the browser and login appears to loop for
no visible reason.

Storage is bind-mounted onto /tank because model weights run to
several gigabytes and the root pool on that host is nearly full.

Also adds the scriberr service alias to internal DNS, following the
existing alias convention so consumers name the service rather than
the box.
2026-08-23 19:28:33 -07:00

112 lines
6.8 KiB
YAML

# Fleet internal DNS — the source of truth for *.internal names.
#
# THIS FILE IS AUTHORITATIVE. `scripts/dns-sync.sh` reconciles every resolver
# against it: names here are created, names removed here are deleted, and
# names edited here are updated. Do NOT add .internal names in the AdGuard UI
# — the next sync will delete them.
#
# WHAT THE SYNC WILL NOT TOUCH: any rewrite outside the `.internal` zone. The
# ESH resolver carries hand-made `esteban.net` entries that predate this file
# and are deliberately left alone. Authority is scoped to the zone, not to the
# resolver's whole table.
#
# NAMING: <host>.<site>.internal, sites `ana` / `esh` / `nh3` (operator,
# 2026-08-19). `.internal` is ICANN-reserved for exactly this use since 2024,
# which is why it is used here rather than `.local` (reserved for mDNS) or a
# made-up TLD that could later collide with a real one.
#
# EVERY name is published to EVERY resolver, so `ana-docker.ana.internal`
# resolves from ESH and NH3 too. The site label says where a host IS, not
# which resolver knows about it.
#
# ⚠️ THE v6 COLUMN IS EMPTY ON PURPOSE, AND MUST STAY DECLARATIVE.
# No fleet host has a global IPv6 address today (verified 2026-08-19: ESH's
# /56 is live only on esh-cameras, NH3's LANs are back to ipv6_interface_type
# none, the colo has no v6 at all). When v6 lands, do NOT paste in whatever
# `ip -6 addr` happens to show: SLAAC addresses are either EUI-64 (MAC-coupled)
# or privacy-extension (they rotate), and UniFi has no v6 equivalent of a DHCP
# reservation. A v6 address only belongs in this file once it has been pinned
# STATICALLY on the host itself — otherwise the record rots silently and the
# name starts lying, which is worse than having no record.
zone: internal
sites:
ana:
subnet: 10.250.0.0/16
resolver: 10.250.50.70 # ana-docker — AdGuard #3, stood up for this
# ⚠️ NOT 8080. ana-docker already has :8080 and :3000 taken, so this
# AdGuard's API is on 8053. The port lives here rather than in the script
# precisely so the odd one out cannot be forgotten.
api_port: 8053
description: Anaheim colo
esh:
subnet: 10.0.0.0/16
resolver: 10.0.50.45 # esh-docker-vm
api_port: 8080
description: ESH home lab (esteban.net)
nh3:
subnet: 10.100.0.0/16
resolver: 10.100.50.40 # nh3-docker
api_port: 8080
description: NH3 office
hosts:
# ---- ana: Anaheim colo ----
- {name: ana-docker, site: ana, v4: 10.250.50.70, note: general-purpose docker host}
- {name: ana-ml2, site: ana, v4: 10.250.50.54, note: GPU inference, dual RTX PRO 6000}
- {name: ana-nas, site: ana, v4: 10.250.50.50, note: CT109 on pfi-pve — NFS/SMB}
- {name: ana-filebot, site: ana, v4: 10.250.50.53, note: file-task automation}
- {name: ana-wg, site: ana, v4: 10.250.50.252, note: WireGuard host}
- {name: corviduo-dev, site: ana, v4: 10.250.50.152, note: Worldtree-team dev VM (PFI-hosted)}
- {name: pbs-ana, site: ana, v4: 10.250.50.90, note: Proxmox Backup Server — fleet primary}
- {name: pfi-ana-webhost, site: ana, v4: 10.250.50.52, note: web workload}
- {name: pfi-postgres, site: ana, v4: 10.250.50.80, note: shared Postgres}
- {name: pfi-pteradactyl, site: ana, v4: 10.250.50.55, note: game panel}
- {name: pfi-tacticalrmm, site: ana, v4: 10.250.50.57, note: TacticalRMM}
- {name: pfi-pve, site: ana, v4: 10.250.250.31, note: Proxmox hypervisor}
- {name: ana-gw, site: ana, v4: 10.250.0.1, note: FortiGate-80F edge}
- {name: pfi-pve-idrac, site: ana, v4: 10.250.250.30, note: iDRAC — OOB for pfi-pve}
- {name: ana-ml2-bmc, site: ana, v4: 10.250.250.50, note: BMC for ana-ml2}
# SureFire tenant hardware — PFI-managed under the hosting agreement.
- {name: sfsrv-ana, site: ana, v4: 10.250.250.115, note: SureFire tenant hypervisor}
- {name: sf-ana-container, site: ana, v4: 10.250.150.100, note: SureFire tenant container host}
- {name: sf-r630-idrac, site: ana, v4: 10.250.250.110, note: SureFire tenant R630 iDRAC}
# ---- nh3: NH3 office ----
- {name: nh3-docker, site: nh3, v4: 10.100.50.40, note: general-purpose docker host + AdGuard}
- {name: nh3-dev, site: nh3, v4: 10.100.10.50, note: dev box, fleet sidecars, Claude sessions}
- {name: nh3-extdev, site: nh3, v4: 10.100.50.42, note: manager / external-dev box}
- {name: nh3-nas, site: nh3, v4: 10.100.50.50, note: Synology RS2418+}
- {name: nh3-pve, site: nh3, v4: 10.100.250.60, note: Proxmox hypervisor}
- {name: pbs-nh3, site: nh3, v4: 10.100.50.90, note: Proxmox Backup Server — DR mirror}
- {name: nh3-gw, site: nh3, v4: 10.100.0.1, note: UniFi UDM Pro SE — gateway + controller}
# Irvine is not its own zone: irv-ml1 is reachable only through NH3's
# WireGuard tunnel and is numbered out of NH3's 10.100.79.0/24, so it is
# named under nh3. Revisit if Irvine ever becomes a site in its own right.
- {name: irv-ml1, site: nh3, v4: 10.100.79.3, note: GPU host (Irvine, via WG) — 3090 + A6000}
# ---- esh: ESH home lab ----
- {name: esh-docker-vm, site: esh, v4: 10.0.50.45, note: general-purpose docker host + AdGuard}
- {name: esh-nas, site: esh, v4: 10.0.50.50, note: NAS}
- {name: esh-pve, site: esh, v4: 10.0.250.35, note: Proxmox hypervisor}
- {name: esh-pve-nas, site: esh, v4: 10.0.50.55, note: Proxmox hypervisor — storage/media}
- {name: esh-vm-db, site: esh, v4: 10.0.50.60, note: PostgreSQL + MongoDB}
- {name: vm-esh-nas, site: esh, v4: 10.0.50.154, note: NAS-adjacent docker host}
- {name: esh-filebot, site: esh, v4: 10.0.50.70, note: restic / file-sync VM}
- {name: esh-gw, site: esh, v4: 10.0.250.1, note: esh-gw}
- {name: esh-udm, site: esh, v4: 10.0.0.1, note: UniFi UDM Pro Max — gateway + controller}
- {name: plex, site: esh, v4: 10.0.50.56, note: media server}
- {name: jellyfin, site: esh, v4: 10.0.50.57, note: media server}
- {name: brother, site: esh, v4: 10.0.90.125, note: Brother printer}
# Service aliases — a name that points at whatever host currently runs it, so
# consumers reference the SERVICE rather than the box. Changing where something
# runs becomes a one-line edit here instead of a hunt through configs.
aliases:
- {name: searxng, site: ana, target: ana-docker, note: replaces searxng.pfi.local (.local is mDNS-reserved)}
- {name: gateway, site: ana, target: ana-docker, note: LiteLLM gateway :4000}
- {name: booth, site: nh3, target: nh3-dev, note: The Booth :8090}
- {name: homepage, site: esh, target: esh-docker-vm, note: fleet dashboard :5100}
- {name: scriberr, site: ana, target: ana-ml2, note: transcription + diarization :8080 (GPU1)}