#!/usr/bin/env bash
#
# JbTecWiz Support Centre -- generated fix script
#
# Fault : mdadm array degraded, or missing after a reboot
# Fix   : Reassemble an array that did not come up
# Source: https://jbtecwiz.com/support/lnx-sto-mdadm
#
# Run as     : Root shell
# Expect     : 40 minutes
# Risk       : high
# Reversible : yes
#
# WHEN THIS IS THE RIGHT FIX
#   The array is inactive or missing after a reboot.
#
# HOW TO UNDO IT
#   Superblocks are unchanged by assembly. --force can commit a stale
#   member, so examine first.
#
# 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

if [ "$(id -u)" -ne 0 ]; then
  echo "  This fix is documented as needing root. Re-run with sudo." >&2
  exit 3
fi

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 "  mdadm array degraded, or missing after a reboot"
echo "  Reassemble an array that did not come up"
echo
echo "  Risk: high   Reversible   40 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 'Look for the members and their superblocks.' 'The Events counter is the key number. Members with matching counts can be assembled cleanly; a member several hundred behind was out of the array and must be re-added rather than assembled, or it will corrupt the data.' cmd 'sudo mdadm --examine /dev/sd[a-d]1 | grep -E '\''Device Role|Array UUID|Events|State'\'''; then
  sudo mdadm --examine /dev/sd[a-d]1 | grep -E 'Device Role|Array UUID|Events|State'
  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 'Assemble by UUID, which is stable across device name changes.' '' cmd 'sudo mdadm --assemble --scan' 'sudo mdadm --assemble /dev/md0 --uuid=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx'; then
  sudo mdadm --assemble --scan
  sudo mdadm --assemble /dev/md0 --uuid=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
  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 'If it will not assemble because a member is behind, force it only after understanding which member and by how much.' '' cmd 'sudo mdadm --assemble --force /dev/md0 /dev/sda1 /dev/sdb1'; then
  sudo mdadm --assemble --force /dev/md0 /dev/sda1 /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 'Once running, write the configuration and rebuild the initramfs -- this is the step whose absence causes the array to vanish at every boot.' 'The array is assembled from the initramfs before the root filesystem is available, so a configuration written only to /etc is not read at the time it is needed.' cmd 'sudo mdadm --detail --scan | sudo tee -a /etc/mdadm/mdadm.conf' 'sudo update-initramfs -u'; then
  sudo mdadm --detail --scan | sudo tee -a /etc/mdadm/mdadm.conf
  sudo update-initramfs -u
  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 'Check fstab uses UUIDs rather than /dev/md0, which can change number.' '' cmd 'sudo blkid /dev/md0' 'grep md /etc/fstab'; then
  sudo blkid /dev/md0
  grep md /etc/fstab
  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 'The array assembles automatically after a reboot and the filesystem mounts.'
if [ "$DRYRUN" = "0" ]; then
  sudo reboot
  cat /proc/mdstat
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-mdadm"
else
  echo "  Finished."
fi
echo
prose 'To undo: Superblocks are unchanged by assembly. --force can commit a stale member, so examine first.'
rule