fix(ha): resolve data disk device via by-id symlink even in dry-run

The by-id lookup is read-only so it's safe to run in dry-run mode.
Previously it was gated behind `if ! $DRY_RUN`, which always triggered
the sdb fallback warning in dry-run — making it look like the device
path wasn't reliable when the symlink actually exists on both servers.

Now the lookup always runs and the script errors out with a clear message
if the by-id symlink is genuinely missing, instead of silently falling
back to a guessed /dev/sd* name.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

scripts/gc-hosts.sh

@@ -0,0 +1,227 @@
+#!/usr/bin/env bash
+# gc-hosts.sh — Run nix-collect-garbage -d on all live NixOS hosts.
+#
+# The host list is rebuilt on every run:
+#   1. This workstation (nixos) — always first
+#   2. pve1 — always second (non-NixOS Proxmox node with Nix installed)
+#   3. Every NixOS guest currently running on pve1 (discovered via pct/qm list)
+#
+# nix-cache is excluded: gc-ing the shared binary cache evicts store paths
+# that other hosts depend on for substitution.
+#
+# NixOS hosts: tries "sudo -n nix-collect-garbage -d" first (works when
+# wheelNeedsPassword = false, e.g. the HA cluster).  Falls back to user-level
+# "nix-collect-garbage -d" if sudo needs a password — still collects
+# unreferenced store paths and old nixos-user profile generations, but leaves
+# old system generations in place.
+# pve1: runs "nix-collect-garbage -d" as the login user (no system generations
+# on a non-NixOS host).
+#
+# Usage (from repo root):
+#   bash scripts/gc-hosts.sh [--dry-run]
+
+set -euo pipefail
+cd "$(dirname "$0")/.."
+source scripts/env.sh 2>/dev/null || true
+source scripts/lib/nix-eval.sh 2>/dev/null || true
+
+# ── config ────────────────────────────────────────────────────────────────────
+
+: "${MAX_JOBS:=8}"
+: "${NIXOS_USER:=nixos}"
+: "${PVE1_SSH_USER:=${PROXMOX_SSH_USER:-wayne}}"
+SSH_OPTS=(-o StrictHostKeyChecking=no -o BatchMode=yes -o ConnectTimeout=10)
+
+DRY_RUN=0
+for arg in "$@"; do
+  case "$arg" in
+    --dry-run) DRY_RUN=1 ;;
+    *) echo "Unknown option: $arg" >&2; exit 1 ;;
+  esac
+done
+
+# ── build the host list ───────────────────────────────────────────────────────
+
+# ORDERED_HOSTS: names in display/execution order.
+# HOST_TARGET[name]: SSH target string (user@host).
+# HOST_TYPE[name]: "nixos" (try sudo gc, fallback user) | "nix" (user gc only).
+declare -a  ORDERED_HOSTS=()
+declare -A  HOST_TARGET=()
+declare -A  HOST_TYPE=()
+declare -A  _SEEN_HOSTNAMES=()   # dedup tracker
+
+_add_host() {
+  local name="$1" target="$2" type="$3"
+  if [[ -n "${_SEEN_HOSTNAMES[$name]+_}" ]]; then return; fi
+  _SEEN_HOSTNAMES[$name]=1
+  ORDERED_HOSTS+=("$name")
+  HOST_TARGET[$name]="$target"
+  HOST_TYPE[$name]="$type"
+}
+
+# 1. Workstation (hard-wired first)
+_add_host "nixos" "${NIXOS_USER}@nixos" "nixos"
+
+# 2. pve1 (hard-wired second; non-NixOS, no system generations)
+_add_host "pve1" "${PVE1_SSH_USER}@${PVE1_HOST}" "nix"
+
+# 3. Dynamically discover running NixOS guests on pve1
+echo "Discovering running guests on ${PVE1_HOST}..."
+
+# Evaluate the full flake hostname map in one shot.
+hostname_map="{}"
+if ! hostname_map="$(
+  nix eval --json "${NIX_EVAL_FLAGS[@]}" .#nixosConfigurations \
+    --apply 'cfgs: builtins.mapAttrs (_: cfg: cfg.config.networking.hostName) cfgs' \
+    2>/dev/null
+)"; then
+  echo "  warning: flake eval failed — skipping dynamic host discovery" >&2
+fi
+
+# Get names of all currently running guests from pve1.
+if ssh "${SSH_OPTS[@]}" "${PVE1_SSH_USER}@${PVE1_HOST}" "true" 2>/dev/null; then
+  running_guests="$(
+    ssh "${SSH_OPTS[@]}" "${PVE1_SSH_USER}@${PVE1_HOST}" bash <<'REMOTE'
+      { sudo pct list 2>/dev/null | awk 'NR>1 && $2=="running" { print $NF }';
+        sudo qm  list 2>/dev/null | awk 'NR>1 && $3=="running" { print $2  }'; } | sort -u
+REMOTE
+  )" || running_guests=""
+
+  while IFS= read -r guest; do
+    [[ -z "$guest" ]] && continue
+
+    # Resolve flake target name → NixOS hostname.
+    hostname="$(printf '%s' "$hostname_map" \
+      | jq -r --arg g "$guest" '.[$g] // empty' 2>/dev/null || true)"
+    [[ -z "$hostname" ]] && continue
+
+    # Exclude nix-cache and any target whose hostname is already in our list.
+    case "$hostname" in nix-cache) continue ;; esac
+    if [[ -n "${_SEEN_HOSTNAMES[$hostname]+_}" ]]; then continue; fi
+
+    echo "  + $guest → $hostname"
+    _add_host "$hostname" "${NIXOS_USER}@${hostname}" "nixos"
+  done <<< "$running_guests"
+else
+  echo "  warning: ${PVE1_HOST} unreachable — skipping dynamic host discovery" >&2
+fi
+
+echo ""
+echo "Hosts: ${ORDERED_HOSTS[*]}"
+echo ""
+
+# ── dry-run ───────────────────────────────────────────────────────────────────
+
+if [[ "$DRY_RUN" -eq 1 ]]; then
+  echo "[dry-run] commands that would run:"
+  for host in "${ORDERED_HOSTS[@]}"; do
+    target="${HOST_TARGET[$host]}"
+    type="${HOST_TYPE[$host]}"
+    if [[ "$type" == "nixos" ]]; then
+      echo "  ssh ${SSH_OPTS[*]} $target 'sudo -n nix-collect-garbage -d'"
+      echo "  # fallback: ssh ... $target 'nix-collect-garbage -d'"
+    else
+      echo "  ssh ${SSH_OPTS[*]} $target '. /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh && nix-collect-garbage -d'"
+    fi
+  done
+  exit 0
+fi
+
+# ── gc worker ─────────────────────────────────────────────────────────────────
+
+gc_one() {
+  local host="$1" target="${HOST_TARGET[$1]}" type="${HOST_TYPE[$1]}" logfile="$2"
+
+  if ! ssh "${SSH_OPTS[@]}" "$target" "true" 2>>"$logfile"; then
+    echo "unreachable"; return
+  fi
+
+  if [[ "$type" == "nixos" ]]; then
+    if ssh "${SSH_OPTS[@]}" "$target" "sudo -n nix-collect-garbage -d" \
+        >>"$logfile" 2>>"$logfile"; then
+      echo "ok(sudo)"; return
+    fi
+    echo "[sudo needs password — falling back to user-level gc]" >>"$logfile"
+    if ssh "${SSH_OPTS[@]}" "$target" "nix-collect-garbage -d" \
+        >>"$logfile" 2>>"$logfile"; then
+      echo "ok(user)"; return
+    fi
+  else
+    # Non-NixOS node: BatchMode SSH doesn't source the Nix daemon profile, so
+    # nix-collect-garbage won't be on PATH unless we source it explicitly.
+    local nix_profile='. /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh 2>/dev/null || true'
+    if ssh "${SSH_OPTS[@]}" "$target" "$nix_profile && nix-collect-garbage -d" \
+        >>"$logfile" 2>>"$logfile"; then
+      echo "ok"; return
+    fi
+  fi
+
+  echo "failed:$?"
+}
+
+# ── parallel execution ────────────────────────────────────────────────────────
+
+echo "Running gc on ${#ORDERED_HOSTS[@]} hosts (up to ${MAX_JOBS} parallel)..."
+echo ""
+
+TMPDIR_GC="$(mktemp -d)"
+trap 'rm -rf "$TMPDIR_GC"' EXIT
+
+declare -A LOGS=()
+job_count=0
+
+for host in "${ORDERED_HOSTS[@]}"; do
+  logfile="${TMPDIR_GC}/${host}.log"
+  resultfile="${TMPDIR_GC}/${host}.result"
+  LOGS[$host]="$logfile"
+  : > "$logfile"
+
+  ( result="$(gc_one "$host" "$logfile")"; echo "$result" > "$resultfile" ) &
+
+  (( job_count++ )) || true
+  if [[ "$job_count" -ge "$MAX_JOBS" ]]; then
+    wait -n 2>/dev/null || wait
+    (( job_count-- )) || true
+  fi
+done
+
+wait
+
+# ── summary ───────────────────────────────────────────────────────────────────
+
+echo "Results:"
+echo "──────────────────────────────"
+
+ok_hosts=()
+warn_hosts=()
+fail_hosts=()
+
+for host in "${ORDERED_HOSTS[@]}"; do
+  result="$(cat "${TMPDIR_GC}/${host}.result" 2>/dev/null || echo "failed:missing")"
+  case "$result" in
+    ok|"ok(sudo)"|"ok(user)")
+      printf "  %-22s  %s\n" "$host" "$result"
+      ok_hosts+=("$host") ;;
+    unreachable)
+      printf "  %-22s  UNREACHABLE\n" "$host"
+      warn_hosts+=("$host") ;;
+    *)
+      printf "  %-22s  FAILED (%s)\n" "$host" "$result"
+      fail_hosts+=("$host") ;;
+  esac
+done
+
+echo ""
+echo "  ${#ok_hosts[@]} succeeded, ${#warn_hosts[@]} unreachable, ${#fail_hosts[@]} failed"
+
+for host in "${warn_hosts[@]+"${warn_hosts[@]}"}" "${fail_hosts[@]+"${fail_hosts[@]}"}"; do
+  logfile="${LOGS[$host]}"
+  if [[ -s "$logfile" ]]; then
+    echo ""
+    echo "── $host ──"
+    cat "$logfile"
+  fi
+done
+
+echo ""
+[[ "${#fail_hosts[@]}" -eq 0 ]]

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)
-  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}..."