#!/bin/bash # Copyright (C) 2018 Oracle. All Rights Reserved. # # Author: Darrick J. Wong <darrick.wong@oracle.com> # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; either version 2 # of the License, or (at your option) any later version. # # This program is distributed in the hope that it would be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write the Free Software Foundation, # Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA. # Automatically check an LVM-managed filesystem online. # We use lvm snapshots to do this, which means that we can only # check filesystems in VGs that have at least 256MB (or so) of # free space. PATH=/usr/local/sbin:/usr/local/bin:/sbin:/bin:/usr/sbin:/usr/bin if (( $EUID != 0 )); then echo "e2scrub must be run as root" exit 1 fi snap_size_mb=256 fstrim=0 reap=0 e2fsck_opts="" conffile="/etc/e2scrub.conf" test -f "${conffile}" && . "${conffile}" print_help() { echo "Usage: $0 [OPTIONS] mountpoint | device" echo echo "mountpoint must be on an LVM-managed block device" echo "-n: Show what commands e2scrub would execute." echo "-r: Remove e2scrub snapshot and exit, do not check anything." echo "-t: Run fstrim if successful." echo "-V: Print version information and exit." } print_version() { echo "e2scrub 1.46.5 (30-Dec-2021)" } exitcode() { ret="$1" # If we're being run as a service, the return code must fit the LSB # init script action error guidelines, which is to say that we # compress all errors to 1 ("generic or unspecified error", LSB 5.0 # section 22.2) and hope the admin will scan the log for what # actually happened. # We have to sleep 2 seconds here because journald uses the pid to # connect our log messages to the systemd service. This is critical # for capturing all the log messages if the scrub fails, because the # fail service uses the service name to gather log messages for the # error report. if [ -n "${SERVICE_MODE}" -a "${ret}" -ne 0 ]; then test "${ret}" -ne 0 && ret=1 sleep 2 fi exit "${ret}" } while getopts "nrtV" opt; do case "${opt}" in "n") DBG="echo Would execute: " ;; "r") reap=1;; "t") fstrim=1;; "V") print_version; exitcode 0;; *) print_help; exitcode 2;; esac done shift "$((OPTIND - 1))" arg="$1" if [ -z "${arg}" ]; then print_help exitcode 1 fi if ! type lsblk >& /dev/null ; then echo "e2scrub: can't find lsblk --- is util-linux installed?" exitcode 1 fi if ! type lvcreate >& /dev/null ; then echo "e2scrub: can't find lvcreate --- is lvm2 installed?" exitcode 1 fi # close file descriptor 3 (from cron) since it causes lvm to kvetch exec 3<&- # Find the device for a given mountpoint dev_from_mount() { local mountpt="$(realpath "$1")" lsblk -o NAME,FSTYPE,MOUNTPOINT -p -P -n 2> /dev/null | while read vars; do eval "${vars}" if [ "${mountpt}" != "${MOUNTPOINT}" ]; then continue fi case "${FSTYPE}" in ext[234]) echo "${NAME}" return 0 ;; esac done return 1 } # Check a device argument dev_from_arg() { local dev="$1" local fstype="$(lsblk -o FSTYPE -n "${dev}" 2> /dev/null)" case "${fstype}" in ext[234]) echo "${dev}" return 0 ;; esac return 1 } mnt_from_dev() { local dev="$1" if [ -n "${dev}" ]; then lsblk -o MOUNTPOINT -n "${dev}" fi } # Construct block device path and mountpoint from argument if [ -b "${arg}" ]; then dev="$(dev_from_arg "${arg}")" mnt="$(mnt_from_dev "${dev}")" else dev="$(dev_from_mount "${arg}")" mnt="${arg}" fi if [ ! -e "${dev}" ]; then echo "${arg}: Not an ext[234] filesystem." print_help exitcode 16 fi # Make sure this is an LVM device we can snapshot lvm_vars="$(lvs --nameprefixes -o name,vgname,lv_role --noheadings "${dev}" 2> /dev/null)" eval "${lvm_vars}" if [ -z "${LVM2_VG_NAME}" ] || [ -z "${LVM2_LV_NAME}" ] || echo "${LVM2_LV_ROLE}" | grep -q "snapshot"; then echo "${arg}: Not connnected to an LVM logical volume." print_help exitcode 16 fi start_time="$(date +'%Y%m%d%H%M%S')" snap="${LVM2_LV_NAME}.e2scrub" snap_dev="/dev/${LVM2_VG_NAME}/${snap}" teardown() { # Remove and wait for removal to succeed. ${DBG} lvremove -f "${LVM2_VG_NAME}/${snap}" while [ -e "${snap_dev}" ] && [ "$?" -eq "5" ]; do sleep 0.5 ${DBG} lvremove -f "${LVM2_VG_NAME}/${snap}" done } check() { # First we recover the journal, then we see if e2fsck tries any # non-optimization repairs. If either of these two returns a # non-zero status (errors fixed or remaining) then this fs is bad. E2FSCK_FIXES_ONLY=1 export E2FSCK_FIXES_ONLY ${DBG} "/sbin/e2fsck" -E journal_only -p ${e2fsck_opts} "${snap_dev}" || return $? ${DBG} "/sbin/e2fsck" -f -y ${e2fsck_opts} "${snap_dev}" } mark_clean() { ${DBG} "/sbin/tune2fs" -C 0 -T "${start_time}" "${dev}" } mark_corrupt() { ${DBG} "/sbin/tune2fs" -E force_fsck "${dev}" } setup() { # Try to remove snapshot for 30s, bail out if we can't remove it. lvremove_deadline="$(( $(date "+%s") + 30))" ${DBG} lvremove -f "${LVM2_VG_NAME}/${snap}" 2>/dev/null while [ -e "${snap_dev}" ] && [ "$?" -eq "5" ] && [ "$(date "+%s")" -lt "${lvremove_deadline}" ]; do sleep 0.5 ${DBG} lvremove -f "${LVM2_VG_NAME}/${snap}" done if [ -e "${snap_dev}" ]; then echo "${arg}: e2scrub snapshot is in use, cannot check!" return 1 fi # Create the snapshot, wait for device to appear. ${DBG} lvcreate -s -L "${snap_size_mb}m" -n "${snap}" "${LVM2_VG_NAME}/${LVM2_LV_NAME}" if [ $? -ne 0 ]; then echo "${arg}: e2scrub snapshot FAILED, will not check!" return 1 fi ${DBG} udevadm settle 2> /dev/null return 0 } if [ "${reap}" -gt 0 ]; then if [ -e "${snap_dev}" ]; then teardown 2> /dev/null fi exit 0 fi if ! setup; then exitcode 8 fi trap "teardown; exit 1" EXIT INT QUIT TERM # Check and react check case "$?" in "0") # Clean check! echo "${arg}: Scrub succeeded." mark_clean teardown trap '' EXIT # Trim the free space, which requires the snapshot be deleted. if [ "${fstrim}" -eq 1 ] && [ -d "${mnt}" ] && type fstrim > /dev/null 2>&1; then echo "${arg}: Trimming free space." fstrim -v "${mnt}" fi ret=0 ;; "8") # Operational error, what now? echo "${arg}: e2fsck operational error." teardown trap '' EXIT ret=8 ;; *) # fsck failed. Check if the snapshot is invalid; if so, make a # note of that at the end of the log. This isn't necessarily a # failure because the mounted fs could have overflowed the # snapshot with regular disk writes /or/ our repair process # could have done it by repairing too much. # # If it's really corrupt we ought to fsck at next boot. is_invalid="$(lvs -o lv_snapshot_invalid --noheadings "${snap_dev}" | awk '{print $1}')" if [ -n "${is_invalid}" ]; then echo "${arg}: Scrub FAILED due to invalid snapshot." ret=8 else echo "${arg}: Scrub FAILED due to corruption! Unmount and run e2fsck -y." mark_corrupt ret=6 fi teardown trap '' EXIT ;; esac exitcode "${ret}"