#!/usr/bin/env bash
#
# JbTecWiz Support Centre -- generated fix script
#
# Fault : "Read-only file system" -- the filesystem remounted itself read-only
# Fix   : Check and repair the filesystem
# Source: https://jbtecwiz.com/support/lnx-readonly-fs
#
# Run as     : Single-user mode or a live USB
# Expect     : 1 hour
# Risk       : high
# Reversible : NO -- read the undo note below
#
# WHEN THIS IS THE RIGHT FIX
#   The hardware is sound. Never run a repair on a mounted filesystem --
#   it corrupts what it is trying to fix.
#
# HOW TO UNDO IT
#   None. fsck changes are permanent -- which is why the image in the
#   previous fix matters.
#
# 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 $n of 7"
  prose "$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 "  "Read-only file system" -- the filesystem remounted itself read-only"
echo "  Check and repair the filesystem"
echo
echo "  Risk: high   NOT REVERSIBLE   1 hour"
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 'Confirm what is mounted and how.' '' cmd 'mount | grep '\'' / '\''' 'findmnt -no OPTIONS /'; then
  mount | grep ' / '
  findmnt -no OPTIONS /
  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 'For a non-root filesystem, unmount it and check.' '' cmd 'sudo umount /dev/sdb1' 'sudo fsck -f /dev/sdb1'; then
  sudo umount /dev/sdb1
  sudo fsck -f /dev/sdb1
  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 'For the root filesystem, schedule a check at the next boot instead of trying to do it live.' 'Running fsck against a mounted root filesystem is the single fastest way to turn a recoverable problem into an unrecoverable one.' cmd 'sudo touch /forcefsck' 'sudo reboot'; then
  sudo touch /forcefsck
  sudo reboot
  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 'Alternatively boot a live USB and check it from there.' '' cmd 'sudo fsck -y /dev/sda2'; then
  sudo fsck -y /dev/sda2
  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 'XFS uses a different tool and will not repair a mounted or dirty log.' '' cmd 'sudo xfs_repair /dev/sda2'; then
  sudo xfs_repair /dev/sda2
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 5 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 6 'If XFS refuses because the log is dirty, mount and unmount it once to replay the log before repairing.' 'xfs_repair -L discards the log and loses whatever was in it. Replaying it properly first is almost always possible and always preferable.' cmd 'sudo mount /dev/sda2 /mnt && sudo umount /mnt' 'sudo xfs_repair /dev/sda2'; then
  sudo mount /dev/sda2 /mnt && sudo umount /mnt
  sudo xfs_repair /dev/sda2
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 6 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 7 'Remount read-write once clean.' '' cmd 'sudo mount -o remount,rw /'; then
  sudo mount -o remount,rw /
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 7 failed. The rest of the fix may depend on it." >&2
  fi
fi

rule "  Confirm it worked"
prose 'The filesystem mounts read-write and stays that way under load.'
if [ "$DRYRUN" = "0" ]; then
  findmnt -no OPTIONS / && touch /root/.wtest && rm /root/.wtest && echo OK
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-readonly-fs"
else
  echo "  Finished."
fi
echo
prose 'To undo: None. fsck changes are permanent -- which is why the image in the previous fix matters.'
rule