#!/usr/bin/env bash
#
# JbTecWiz Support Centre -- generated fix script
#
# Fault : A cloned machine will not boot -- device names and UUIDs have changed
# Fix   : Reference filesystems by UUID rather than device name
# Source: https://jbtecwiz.com/support/lnx-sto-uuid-fstab
#
# Run as     : Emergency shell or rescue media
# Expect     : 30 minutes
# Risk       : medium
# Reversible : yes
#
# WHEN THIS IS THE RIGHT FIX
#   A device name has changed.
#
# HOW TO UNDO IT
#   Restore /etc/fstab.bak.
#
# Walks the fix one step at a time and asks before each. Steps with no
# command are yours to do -- it prints those and waits. DRYRUN=1 prints
# without executing; UNATTENDED=1 does not ask.
#
# --------------------------------------------------------------------
# NO WARRANTY - USE AT YOUR OWN RISK
#
# This script is provided by JbTecWiz as-is and with no warranty of any
# kind, express or implied. You run it entirely at your own risk.
#
# JbTecWiz accepts no liability for any loss or damage arising from its
# use, including but not limited to data loss, downtime, or configuration
# changes that turn out to be wrong for your system.
#
# You are responsible for reading this script before running it, for
# satisfying yourself that it suits the machine in front of you, and for
# having a working backup first. Some steps cannot be undone.
# --------------------------------------------------------------------

set -uo pipefail
DRYRUN="${DRYRUN:-0}"
UNATTENDED="${UNATTENDED:-0}"
failed=0

rule() { printf "\n%s\n" "$(printf '-%.0s' $(seq 1 70))"; if [ $# -gt 0 ]; then echo "$1"; fi; }
prose() { echo "$1" | fold -s -w 74 | sed "s/^/  /"; }

# Returns 0 when the caller should run the command, 1 when it should not.
# A manual step always returns 1 -- there is nothing for the caller to run.
step() {  # step <n> <do> <why> <manual|cmd> [command lines...]
  local n="$1" dotext="$2" why="$3" mode="$4"; shift 4
  rule "  Step $n of 5"
  prose "$dotext"
  if [ -n "$why" ]; then echo; prose "$why"; fi
  if [ "$mode" = "manual" ]; then
    echo; echo "  -> Do this yourself, then press Enter to carry on."
    if [ "$UNATTENDED" = "0" ] && [ "$DRYRUN" = "0" ]; then read -r _; fi
    return 1
  fi
  echo; printf "    %s\n" "$@"; echo
  if [ "$DRYRUN" = "1" ]; then echo "  (dry run -- not executed)"; return 1; fi
  if [ "$UNATTENDED" = "0" ]; then
    read -r -p "  Run this step? [Y]es / [S]kip / [Q]uit " a
    case "$a" in
      [Qq]*) echo "  Stopped at your request."; exit 0 ;;
      [Ss]*) echo "  Skipped."; return 1 ;;
    esac
  fi
  return 0
}

rule
echo "  A cloned machine will not boot -- device names and UUIDs have changed"
echo "  Reference filesystems by UUID rather than device name"
echo
echo "  Risk: medium   Reversible   30 minutes"
echo
prose 'No warranty. Use at your own risk - JbTecWiz accepts no liability. Read it before you run it, and have a backup.'
rule
echo
if [ "$UNATTENDED" = "0" ] && [ "$DRYRUN" = "0" ]; then
  read -r -p "  Ready? [y/N] " go
  case "$go" in [Yy]*) ;; *) echo "  Nothing was changed."; exit 0;; esac
fi

if step 1 'At the emergency prompt, sign in as root and remount the root filesystem writable.' '' cmd 'mount -o remount,rw /'; then
  mount -o remount,rw /
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 1 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 2 'List every filesystem with its UUID.' '' cmd 'blkid' 'lsblk -o NAME,SIZE,FSTYPE,UUID,MOUNTPOINT'; then
  blkid
  lsblk -o NAME,SIZE,FSTYPE,UUID,MOUNTPOINT
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 2 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 3 'Replace device names in fstab with UUIDs.' 'A UUID follows the filesystem wherever it is attached. Device names follow detection order, which changes when a disk is added, a controller is changed, or a machine is virtualised.' cmd 'cp /etc/fstab /etc/fstab.bak' 'blkid -s UUID -o value /dev/sdb1'; then
  cp /etc/fstab /etc/fstab.bak
  blkid -s UUID -o value /dev/sdb1
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 3 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 4 'Add nofail to any non-essential mount so a missing device does not stop the boot.' 'Without nofail, systemd waits the full device timeout and then drops to emergency mode because a data volume is absent. That turns a missing backup disk into a machine that will not boot.' cmd 'sed -i '\''s|\(/mnt/data.*defaults\)|\1,nofail,x-systemd.device-timeout=10|'\'' /etc/fstab'; then
  sed -i 's|\(/mnt/data.*defaults\)|\1,nofail,x-systemd.device-timeout=10|' /etc/fstab
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 4 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 5 'Validate before rebooting.' '' cmd 'systemctl daemon-reload' 'mount -a' 'findmnt --verify'; then
  systemctl daemon-reload
  mount -a
  findmnt --verify
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 5 failed. The rest of the fix may depend on it." >&2
  fi
fi

rule "  Confirm it worked"
prose 'mount -a completes silently and the machine boots unattended.'
if [ "$DRYRUN" = "0" ]; then
  findmnt --verify; systemctl --failed
fi

rule
if [ "$failed" -gt 0 ]; then
  echo "  Finished with $failed failed step(s)."
  echo "  Read the full write-up at https://jbtecwiz.com/support/lnx-sto-uuid-fstab"
else
  echo "  Finished."
fi
echo
prose 'To undo: Restore /etc/fstab.bak.'
rule