#!/usr/bin/env bash
#
# JbTecWiz Support Centre -- generated fix script
#
# Fault : /boot is full and updates fail
# Fix   : Clear old kernels on the RHEL family
# Source: https://jbtecwiz.com/support/lnx-sto-boot-full
#
# Run as     : Root shell
# Expect     : 25 minutes
# Risk       : medium
# Reversible : NO -- read the undo note below
#
# WHEN THIS IS THE RIGHT FIX
#   dnf or yum.
#
# HOW TO UNDO IT
#   Reinstall a removed kernel with dnf install kernel-<version>.
#
# 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 "  /boot is full and updates fail"
echo "  Clear old kernels on the RHEL family"
echo
echo "  Risk: medium   NOT REVERSIBLE   25 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 'Check what is installed and what is running.' '' cmd 'uname -r' 'rpm -q kernel' 'df -h /boot'; then
  uname -r
  rpm -q kernel
  df -h /boot
  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 'Remove old kernels, keeping the configured number. dnf refuses to remove the running one, which makes this considerably safer than the apt equivalent.' 'The installonly mechanism is aware of which kernel is booted and will not remove it. This is the supported path and it should be used in preference to removing packages by name.' cmd 'sudo dnf remove --oldinstallonly --setopt installonly_limit=2 kernel'; then
  sudo dnf remove --oldinstallonly --setopt installonly_limit=2 kernel
  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 'Set the retention limit permanently.' '' cmd 'sudo sed -i '\''s/^installonly_limit.*/installonly_limit=2/'\'' /etc/dnf/dnf.conf' 'grep installonly /etc/dnf/dnf.conf'; then
  sudo sed -i 's/^installonly_limit.*/installonly_limit=2/' /etc/dnf/dnf.conf
  grep installonly /etc/dnf/dnf.conf
  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 'Rebuild the boot configuration if entries are stale.' '' cmd 'sudo grub2-mkconfig -o /boot/grub2/grub.cfg' 'sudo grubby --info=ALL | grep ^kernel'; then
  sudo grub2-mkconfig -o /boot/grub2/grub.cfg
  sudo grubby --info=ALL | grep ^kernel
  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 'Complete any interrupted transaction.' '' cmd 'sudo dnf history' 'sudo dnf distro-sync'; then
  sudo dnf history
  sudo dnf distro-sync
  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 '/boot has space and the boot menu lists the expected kernels.'
if [ "$DRYRUN" = "0" ]; then
  df -h /boot; sudo grubby --default-kernel
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-boot-full"
else
  echo "  Finished."
fi
echo
prose 'To undo: Reinstall a removed kernel with dnf install kernel-<version>.'
rule