homelab/hosts/jupiter/configuration.nix

{ config, pkgs, lib, ... }:

# ZimaBlade NAS host: hardware + disk + the services it runs.
{
  imports = [
    ./hardware-configuration.nix
    ./disk-config.nix          # disko: OS-disk partitions + filesystems
    ./secrets.nix              # sops-nix: samba password, tailscale key, ...
    ../../common.nix              # shared base: user / ssh / nix / firewall
    ../../services/network/samba.nix
    ../../services/network/avahi.nix
    ../../services/media/audiobookshelf.nix
    ../../services/containers.nix
    ../../services/network/caddy.nix
    ../../services/vpn/tailscale.nix
    ../../services/media/jellyfin.nix
    ../../services/media/sabnzbd.nix
    ../../services/media/prowlarr.nix
    ../../services/media/sonarr.nix
    ../../services/media/radarr.nix
    ../../services/media/clonarr.nix
    ../../services/media/seerr.nix
    ../../services/media/immich.nix
    ../../services/dev/gitea.nix
  ];

  # sabnzbd's unrar dependency is unfree; scope the allowance to just that
  # package rather than blanket-allowing unfree across the host.
  nixpkgs.config.allowUnfreePredicate = pkg: builtins.elem (lib.getName pkg) [ "unrar" ];

  # ---- Host identity ----
  networking.hostName = "jupiter";
  networking.networkmanager.enable = true;
  users.users.darman.extraGroups = [ "docker" ];   # merges with common.nix

  # ---- Boot ----
  # systemd-boot for UEFI. If ZimaBlade boots legacy/BIOS, switch to grub.
  boot.loader.systemd-boot.enable = true;
  boot.loader.efi.canTouchEfiVariables = true;
  # common.nix's cap of 5 comes from this box's own 34-generation incident,
  # but at ~5G free on a 29G eMMC even 5 is too many — override down to 2.
  boot.loader.systemd-boot.configurationLimit = lib.mkForce 2;

  # A `switch` pins the old generation as a GC root until the box reboots onto
  # the new one (booted-system vs current-system) — common.nix's nix.gc is
  # weekly, far too slow to catch that on a 29G eMMC. 2026-08-19: one switch
  # alone took 14G -> 19G used; only reboot (releases the old root) + this GC
  # brought it back to 14G. Run a full collect right after every boot instead
  # of waiting on the weekly timer.
  systemd.services.gc-on-boot = {
    description = "Full nix-collect-garbage on every boot";
    wantedBy = [ "multi-user.target" ];
    serviceConfig = {
      Type = "oneshot";
      ExecStart = "${pkgs.nix}/bin/nix-collect-garbage -d";
    };
  };

  # Root lives on the ZimaBlade eMMC (mmcblk0). nixos-generate-config runs in
  # the RAM installer and does NOT detect these, so pin them here (merged with
  # hardware-configuration.nix) or stage-1 can't mount root and the box panics.
  boot.initrd.availableKernelModules = [ "mmc_block" "sdhci_pci" "sdhci_acpi" ];

  # Warm reboot hangs at firmware reset on this board (cold power-cycle works).
  # Force the PCI-chipset reset method. If a warm `reboot` still hangs, try the
  # next value: acpi -> bios -> cold -> efi.
  boot.kernelParams = [ "reboot=pci" ];

  # ---- GPU (jellyfin hardware transcoding) ----
  # Apollo Lake N3450 / HD Graphics 500 (Gen9, pci 8086:5A85). The i915 KERNEL
  # driver binds on its own — /dev/dri/{card1,renderD128} exist without this —
  # but the libva USERSPACE driver only ships when hardware.graphics is on, and
  # nothing else here pulled it in. Without it VAAPI init fails with "unknown
  # libva error" and jellyfin-ffmpeg exits 251 on EVERY transcode, which the
  # client shows as generic playback failure: the server log only says "FFmpeg
  # exited with code 251", never that a driver is missing. Verified on the box:
  # the same h264_vaapi encode goes 251 -> 0 once iHD is on LIBVA_DRIVERS_PATH.
  #
  # iHD (intel-media-driver) is the right one for Gen9; i965 is for Gen8 and
  # older. Note the render node is 0666 but card1 is 0660 root:video, so the
  # group membership in services/media/jellyfin.nix matters for the card node.
  hardware.graphics = {
    enable = true;
    extraPackages = [ pkgs.intel-media-driver ];
  };
  # ⚠️ This buys VAAPI only — jellyfin must be set to VAAPI, NOT QSV, in its
  # web UI (Dashboard -> Playback -> Transcoding). QSV needs an MFX runtime on
  # top of the libva driver: ffmpeg's `-init_hw_device qsv=qs@va` dies with
  # "Error creating a MFX session: -9" -> exit 171, the SECOND failure hiding
  # behind the first (fixing the missing driver only moved 251 -> 171).
  # There is no good way to provide it here: vpl-gpu-rt is Gen12+, and the
  # Gen9 runtime `intel-media-sdk` is marked INSECURE in nixpkgs (EOL, 5 CVEs
  # incl. local privilege escalation) — not worth it when VAAPI does the same
  # job on this chip at ~3.5x realtime for 1080p->720p.
  #
  # Also: 4K HDR (the 2160p HEVC/DV remuxes) can NOT be tone-mapped here.
  # tonemap_opencl needs OpenCL, which has no platform on this box, and
  # tonemap_vaapi is Gen11+ — both fail. Only a plain scale_vaapi=format=nv12
  # succeeds, which drops HDR without tone-mapping (washed-out picture).
  # Those files need to direct-play, or be kept as 1080p SDR versions.

  # ---- NAS data array ----
  # Existing ext4 on the mdadm RAID0 over sda+sdb (md0, 29.1T).
  # Mounted, NOT formatted; kept out of disko so it is never wiped.
  # ⚠️ RAID0 = no redundancy: either 16TB disk failing loses ALL data.
  boot.swraid.enable = true;  # assemble the mdadm array at boot
  # Silences "mdmon service will crash" eval warning. RAID0 here uses native
  # superblocks so mdmon (external-metadata arrays only) never actually runs,
  # but the module warns unconditionally without SOME MAILADDR/PROGRAM set.
  boot.swraid.mdadmConf = "MAILADDR root";
  fileSystems."/mnt/data" = {
    # fs UUID (stable) — the array may enumerate as /dev/md127, so avoid /dev/md0.
    device = "/dev/disk/by-uuid/dadbff6f-652e-49b2-bfed-eb1308ab8b78";
    fsType = "ext4";
    options = [ "nofail" ];  # don't block boot if the array is degraded/absent
  };

  # `nofail` above is necessary but NOT sufficient — any mount layered on the
  # array (prowlarr/seerr binds) is RequiredBy local-fs.target and will fail it
  # regardless, and emergency mode on this box is a dead end: root is locked, so
  # sulogin drops you at a prompt you cannot answer, with no ssh. 2026-08-06: a
  # drive that failed to enumerate after the rack move did exactly this —
  # "Timed out waiting for device /dev/disk/by-uuid/dadbff6f-…" -> Dependency
  # failed for Local File Systems -> Reached target Emergency Mode, twice.
  # Boot as far as possible instead and leave the failed units to be read over
  # ssh. The array-backed services carry RequiresMountsFor=/mnt/data so they
  # still refuse to start rather than writing to the eMMC.
  systemd.enableEmergencyMode = false;

  # ---- Heavy state moved off the eMMC ----
  # A deploy holds TWO full closures (~9G each) on a 29G disk at once, so the
  # OS disk has no room for state that grows on its own. 2026-08-09: it hit 0
  # bytes free with both gen 39 and gen 40 resident, and postgres died on
  # "No space left on device" — note ext4 reserves 5% for root, so non-root
  # services see zero while df still shows ~300M free.
  #
  # Paths live under /mnt/data/AppData like every other service's state. Both
  # settings below are jupiter-only on purpose: services/containers.nix stays
  # engine- and host-agnostic (mercury runs pihole on podman with no array).

  # podman: CI images dominate and keep growing — the gitea runner's
  # act-latest is 1.7G, and the act-22.04 label in services/dev/gitea.nix
  # pulls another ~1.7G the first time a job requests it.
  # runroot stays on /run: it is per-boot tmpfs state, not a growing store.
  virtualisation.containers.storage.settings.storage = {
    driver = "overlay";
    graphroot = "/mnt/data/AppData/containers/storage";
    runroot = "/run/containers/storage";
  };

  # immich's postgres cluster. Version component mirrors the upstream default
  # (`/var/lib/postgresql/${psqlSchema}`) so a major bump gets its own dir
  # instead of silently reusing the old cluster's files.
  # ⚠️ This puts the DB in the SAME failure domain as the photos it indexes:
  # /mnt/data is RAID0, so either 16TB disk now loses both, where before an
  # eMMC failure and an array failure each took only one. Chosen deliberately
  # — the two are useless apart — but neither is backed up.
  services.postgresql.dataDir =
    "/mnt/data/AppData/postgresql/${config.services.postgresql.package.psqlSchema}";

  # /mnt/data/AppData is drwx--x--- darman:users, so postgres needs group
  # "users" just to TRAVERSE into its own dataDir — exactly the reason immich
  # has the same line. The cluster dir itself keeps the mode it was initdb'd
  # with (0750 postgres:postgres) — postgres only accepts 0700, or 0750 when
  # the cluster was created with group access, and refuses to start otherwise.
  users.users.postgres.extraGroups = [ "users" ];

  # Neither path is under /var/lib, so no module creates it: the postgresql
  # module's own tmpfiles entry only adjusts a dataDir that already exists,
  # the same way immich's mediaLocation rule does.
  systemd.tmpfiles.rules = [
    "d /mnt/data/AppData/postgresql 0750 postgres postgres -"
    "d /mnt/data/AppData/containers 0700 root root -"
  ];

  # graphroot is not a systemd path dependency the way dataDir is, so nothing
  # derives a mount ordering from it. Without these, podman would recreate an
  # empty store on the eMMC under the mountpoint when the array is late or
  # absent, and the runner would re-pull every image into it.
  # (podman-clonarr already carries this from services/media/clonarr.nix.)
  systemd.services.podman.unitConfig.RequiresMountsFor = [ "/mnt/data" ];
  systemd.services.gitea-runner-jupiter.unitConfig.RequiresMountsFor = [ "/mnt/data" ];

  # ---- Caddy vhosts (LAN) ----
  # Reached via pihole local-DNS names -> jupiter IP.
  services.caddy.virtualHosts = {
    "http://audiobookshelf.jupiter.sol".extraConfig = "reverse_proxy localhost:8000";
    "http://jellyfin.jupiter.sol".extraConfig = "reverse_proxy localhost:8096";
    "http://sabnzbd.jupiter.sol".extraConfig = "reverse_proxy localhost:8085";
    "http://prowlarr.jupiter.sol".extraConfig = "reverse_proxy localhost:9696";
    "http://sonarr.jupiter.sol".extraConfig = "reverse_proxy localhost:8989";
    "http://radarr.jupiter.sol".extraConfig = "reverse_proxy localhost:7878";
    "http://clonarr.jupiter.sol".extraConfig = "reverse_proxy localhost:6060";
    "http://seerr.jupiter.sol".extraConfig = "reverse_proxy localhost:5055";
    "http://gitea.jupiter.sol".extraConfig = "reverse_proxy localhost:3000";
    # Immich uploads are large: raise the body limit off caddy's default and
    # give slow phone uploads room before the proxy gives up.
    "http://immich.jupiter.sol".extraConfig = ''
      request_body {
        max_size 50GB
      }
      reverse_proxy localhost:2283
    '';
  };

  system.stateVersion = "26.05";
}