Merge pull request 'fix(gc-hosts): use pct/qm list output directly as hostnames' (#106) from worktree-crispy-churning-kernighan into main

Reviewed-on: #106

scripts/gc-hosts.sh

@@ -23,7 +23,6 @@
 set -euo pipefail
 cd "$(dirname "$0")/.."
 source scripts/env.sh 2>/dev/null || true
-source scripts/lib/nix-eval.sh 2>/dev/null || true
 
 # ── config ────────────────────────────────────────────────────────────────────
 
@@ -75,21 +74,11 @@ _add_host "pve1" "${PVE1_SSH_USER}@${PVE1_HOST}" "nix"
 # create-proxmox-resource.sh names every guest after its NixOS hostname:
 #   pct create ... --hostname <nixos-hostname>  (LXC)
 #   qm  create ... --name    <nixos-hostname>   (VM)
-# So pct/qm list output already contains the NixOS hostname directly.
+# So pct list / qm list output already contains the NixOS hostname directly —
-# We validate against the flake to filter out non-NixOS guests on pve1
+# no flake eval or name translation needed.
-# (e.g. FreeIPA, Proxmox Backup Server) that share the same Proxmox node.
 echo "Discovering running guests on ${PVE1_HOST}..."
 
-# Eval the flake once to get the set of hostnames that are actually NixOS.
+# SSH_QUERY_OPTS (no BatchMode) so sudo can prompt if wayne's sudo needs a password.
-# Values are NixOS hostnames (e.g. "docker"); keys are flake targets ("lxc-docker").
-nixos_hostnames=""
-nixos_hostnames="$(
-  nix eval --json "${NIX_EVAL_FLAGS[@]}" .#nixosConfigurations \
-    --apply 'cfgs: builtins.attrValues (builtins.mapAttrs (_: cfg: cfg.config.networking.hostName) cfgs)' \
-    2>/dev/null | jq -r '.[]' | sort -u
-)" || { echo "  warning: flake eval failed — non-NixOS guests will not be filtered" >&2; }
-
-# SSH_QUERY_OPTS (no BatchMode) so sudo can prompt if needed for pct/qm.
 if ssh "${SSH_QUERY_OPTS[@]}" "${PVE1_SSH_USER}@${PVE1_HOST}" "true" 2>/dev/null; then
   running_guests="$(
     ssh "${SSH_QUERY_OPTS[@]}" "${PVE1_SSH_USER}@${PVE1_HOST}" bash -s <<'DISCOVER'
@@ -102,10 +91,6 @@ DISCOVER
     [[ -z "$hostname" ]] && continue
     # Exclude nix-cache.
     case "$hostname" in *nix-cache*) continue ;; esac
-    # Skip if not a flake-managed NixOS host (filters non-NixOS pve1 guests).
-    if [[ -n "$nixos_hostnames" ]] && ! grep -qxF "$hostname" <<< "$nixos_hostnames"; then
-      continue
-    fi
     # Skip if already in the list (e.g. a proxmox-gui guest whose hostname is nixos).
     if [[ -n "${_SEEN_HOSTNAMES[$hostname]+_}" ]]; then continue; fi
 

scripts/ha/resize-data-disk.sh

@@ -30,6 +30,8 @@ DATA_DISK_SLOT="${DATA_DISK_SLOT:-scsi1}"   # Proxmox disk name (scsi1 = data di
 HA_USER="${HA_USER:-nixos}"
 PVE_HOST="${PVE_HOST:-${PVE1_HOST}}"
 PVE_SSH_USER="${PVE_SSH_USER:-${PROXMOX_SSH_USER}}"
+PVE_SUDO=""
+[[ "$PVE_SSH_USER" != "root" ]] && PVE_SUDO="sudo"
 # By-id symlink for the data disk; basename resolves to the raw block device.
 # matches variables.nix's haServerDrbdDisk.
 DATA_DISK_BYID="${DATA_DISK_BYID:-scsi-0QEMU_QEMU_HARDDISK_drive-${DATA_DISK_SLOT}}"
@@ -140,7 +142,7 @@ fi
 echo ""
 echo "Looking up VM IDs on ${PVE_HOST}..."
 
-QM_LIST=$(pve "qm list 2>/dev/null" || true)
+QM_LIST=$(pve "$PVE_SUDO qm list 2>/dev/null" || true)
 VMID1=$(echo "$QM_LIST" | awk -v name="$NODE1" '$0 ~ name {print $1}' | head -1)
 VMID2=$(echo "$QM_LIST" | awk -v name="$NODE2" '$0 ~ name {print $1}' | head -1)
 
@@ -182,12 +184,12 @@ echo "── Phase 1 — Proxmox disk resize (${DATA_DISK_SLOT} ${SIZE} on both
 
 echo "  ${DRY_PREFIX}qm resize $VMID1 ${DATA_DISK_SLOT} ${SIZE}  ($NODE1 on ${PVE_HOST})"
 if ! $DRY_RUN; then
-  pve "qm resize $VMID1 ${DATA_DISK_SLOT} ${SIZE}"
+  pve "$PVE_SUDO qm resize $VMID1 ${DATA_DISK_SLOT} ${SIZE}"
 fi
 
 echo "  ${DRY_PREFIX}qm resize $VMID2 ${DATA_DISK_SLOT} ${SIZE}  ($NODE2 on ${PVE_HOST})"
 if ! $DRY_RUN; then
-  pve "qm resize $VMID2 ${DATA_DISK_SLOT} ${SIZE}"
+  pve "$PVE_SUDO qm resize $VMID2 ${DATA_DISK_SLOT} ${SIZE}"
 fi
 
 echo "  Phase 1 done."
@@ -202,17 +204,13 @@ rescan_node() {
   local node_name=$1 run_fn=$2
 
   # Resolve block device name from the stable by-id symlink on the guest.
+  # Read-only lookup — safe to run even in dry-run so we show the real device.
   local blk_dev=""
-  if ! $DRY_RUN; then
+  blk_dev=$($run_fn "bash -c 'basename \$(readlink -f /dev/disk/by-id/${DATA_DISK_BYID})'" 2>/dev/null || true)
-    blk_dev=$($run_fn "bash -c 'basename \$(readlink -f /dev/disk/by-id/${DATA_DISK_BYID})'" 2>/dev/null || true)
-  fi
   if [[ -z "$blk_dev" ]]; then
-    # Fall back: scsi1 → index 1 → sdb, scsi2 → sdc, etc.
+    echo "  ERROR: /dev/disk/by-id/${DATA_DISK_BYID} not found on $node_name" >&2
-    local slot_idx
+    echo "         Check DATA_DISK_BYID or DATA_DISK_SLOT configuration." >&2
-    slot_idx=$(echo "$DATA_DISK_SLOT" | grep -oE '[0-9]+$' || echo "1")
+    exit 1
-    blk_dev=$(printf "sd%s" "$(echo "abcdefghij" | cut -c$((slot_idx + 1)))")
-    echo "  WARNING: could not resolve /dev/disk/by-id/${DATA_DISK_BYID} on $node_name;" \
-         "falling back to /dev/${blk_dev}" >&2
   fi
 
   echo "  ${DRY_PREFIX}Rescanning /dev/${blk_dev} on ${node_name}..."

variables.nix

@@ -58,6 +58,7 @@
     "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIBZ9WKKAlP9Z7GQdgaZ1Xgw9C+vja2lqEZO5rJFpVqYN root@ha-server-1"
     "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIEGNKlaaMckd8nLWNGz4B2QokXjnnIvM+rEUv+R6h0sp root@ha-server-2"
     "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIK+XeMco7OxUpjrjZm54HogMs9QB5xlcKmElASRvrmlW root@nixos"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIMseQwPpmaa6cgV5U8KhUsiVSYARG85zGa9rho0LJWks wayne@pve1"
   ];
 
   # Admin SSH public key, authorized on the primary user of every host and