#!/usr/bin/env bash
#
# JbTecWiz Support Centre -- generated fix script
#
# Fault : LVM volume group not found at boot
# Fix   : Activate the group and repair the initramfs
# Source: https://jbtecwiz.com/support/lnx-lvm-missing
#
# Run as     : Emergency shell or live USB
# Expect     : 40 minutes
# Risk       : medium
# Reversible : yes
#
# WHEN THIS IS THE RIGHT FIX
#   All the physical volumes are present but the group is not active.
#
# HOW TO UNDO IT
#   The initramfs rebuild keeps previous kernels' images -- select an
#   older kernel from GRUB if needed.
#
# 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 "  LVM volume group not found at boot"
echo "  Activate the group and repair the initramfs"
echo
echo "  Risk: medium   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 'Scan for physical volumes, volume groups and logical volumes in that order.' '' cmd 'pvscan' 'vgscan' 'lvscan'; then
  pvscan
  vgscan
  lvscan
  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 'Activate everything.' '' cmd 'vgchange -ay'; then
  vgchange -ay
  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 activates, you are booted -- but it will happen again. Continue.' '' cmd 'lsblk -f' 'mount -a'; then
  lsblk -f
  mount -a
  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 'Check lvm.conf is not filtering the device out.' 'A filter added for a SAN or a multipath setup that rejects everything not explicitly listed will silently exclude a newly added disk.' cmd 'grep -E '\''^\s*(filter|global_filter)'\'' /etc/lvm/lvm.conf'; then
  grep -E '^\s*(filter|global_filter)' /etc/lvm/lvm.conf
  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 'Rebuild the initramfs so LVM is available at boot. Debian-family:' '' cmd 'sudo update-initramfs -u -k all'; then
  sudo update-initramfs -u -k all
  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 'RHEL-family:' '' cmd 'sudo dracut -f --regenerate-all'; then
  sudo dracut -f --regenerate-all
  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 'Confirm the volumes are set to activate automatically.' '' cmd 'sudo lvchange -ay --setactivationskip n /dev/vg0/root' 'sudo lvs -o lv_name,vg_name,lv_attr'; then
  sudo lvchange -ay --setactivationskip n /dev/vg0/root
  sudo lvs -o lv_name,vg_name,lv_attr
  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 machine boots unattended and all volumes are mounted.'
if [ "$DRYRUN" = "0" ]; then
  sudo lvs && findmnt --verify
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-lvm-missing"
else
  echo "  Finished."
fi
echo
prose 'To undo: The initramfs rebuild keeps previous kernels'\'' images -- select an older kernel from GRUB if needed.'
rule