ansible-roles/autosysadmin-agent/files/upstream/repair/repair_disk

#!/bin/bash

: "${AUTOSYSADMIN_LIB:=/usr/local/lib/autosysadmin}"
source "${AUTOSYSADMIN_LIB}/common.sh" || exit 1
source "${AUTOSYSADMIN_LIB}/repair.sh" || exit 1

pre_repair


# We always keep some reserved blocks to avoid missing some logs
# https://gitea.evolix.org/evolix/autosysadmin/issues/22
RESERVED_BLOCKS_MIN=1

get_mountpoints() {
    # the $(...) get the check_disk1 command
    # the cut command selects the critical part of the check_disk1 output
    # the grep command extracts the mountpoints and available disk space
    # the last cut command selects the mountpoints
    check_disk1_command=$(grep check_disk1 /etc/nagios/nrpe.d/evolix.cfg | cut -d'=' -f2-)
    
    ${check_disk1_command} -e | cut -d'|' -f1 | grep --extended-regexp --only-matching '/[[:graph:]]* [0-9]+ [A-Z][A-Z]' | cut -d' ' -f1
}

is_reserved_blocks_nominal() {
    partition=${1}

    fs_type="$(findmnt -n --output=fstype "${partition}")"
    if [ "${fs_type}" = "ext4" ]; then
        device="$(findmnt -n --output=source "${partition}")"
        reserved_block_count="$(tune2fs -l "${device}" | grep 'Reserved block count' | awk -F':' '{ gsub (" ", "", $0); print $2}')"
        block_count="$(tune2fs -l "${device}" | grep 'Block count' | awk -F':' '{ gsub (" ", "", $0); print $2}')"
        percentage=$(awk "BEGIN { pc=100*${reserved_block_count}/${block_count}; i=int(pc); print (pc-i<0.5)?i:i+1 }")

        log_run "Reserved blocks for ${partition} is currently at ${percentage}%"
        if [ "${percentage}" -gt "${RESERVED_BLOCKS_MIN}" ]; then
            log_run "Allowing tune2fs action to reduce the number of reserved blocks"
            return 0
        else
            log_run "Reserved blocks already at or bellow ${RESERVED_BLOCKS_MIN}%, no automatic action possible"
            return 1
        fi
    else
        log_run "Filesystem for ${partition} (${fs_type}) is incompatible with reserved block reduction."
        return 1
    fi
}

reduce_reserved_blocks() {
    partition=${1}

    device=$(findmnt -n --output=source "${partition}")
    tune2fs -m "${RESERVED_BLOCKS_MIN}" "${device}"
    log_action "Reserved blocks for ${partition} changed to ${RESERVED_BLOCKS_MIN} percent"
}

is_tmp_to_delete() {
    size="$(find /var/log/ -type f -ctime +1 -exec du {} \+ | awk '{s+=$1}END{print s / 1024}')"
    if [ -n "${size}" ]; then
        return 0
    else
        return 1
    fi
}

is_log_to_delete() {
    size="$(find /var/log/ -type f -mtime +365 -exec du {} \+ | awk '{s+=$1}END{print s / 1024}')"
    if [ -n "${size}" ]; then
        return 0
    else
        return 1
    fi
}

clean_apt_cache() {
    for container in $(lxc-ls -1); do
        if [ -e "$(lxc-config lxc.lxcpath)/${container}/rootfs/var/cache" ]; then
            lxc-attach --name "${container}" -- apt-get clean
            log_action "Clean apt cache in LXC container ${container}";
        fi
    done

    # NOTE: "head -n 1" might be superfluous, but let's be sure to have only the first returned value
    biggest_subdir=$(du --summarize --one-file-system "/var/*" | sort --numeric-sort --reverse | sed 's/^[0-9]\+[[:space:]]\+//;q' | head -n 1)
    case "${biggest_subdir}" in
        '/var/cache')
            apt-get clean
            log_action 'Clean apt cache'
        ;;
    esac
}

clean_amavis_virusmails() {
    if du --inodes /var/lib/* | sort --numeric-sort | tail -n 3 | grep --quiet 'virusmails$'; then
        find /var/lib/amavis/virusmails/ -type f -atime +30 -delete
        log_action 'Clean amavis infected mails'
    fi
}

critical_mountpoints=$(get_mountpoints)

if [ -z "${critical_mountpoints}" ]; then
    log_abort_and_quit "No partition is in critical state, nothing left to do."
else
    for mountpoint in ${critical_mountpoints}; do
        case "${mountpoint}" in
        /var)
            #if is_log_to_delete
            #then
            #    find /var/log/ -type f -mtime +365 -delete
            #    log_action "$size Mo of disk space freed in /var"
            #fi
            if is_reserved_blocks_nominal /var; then
                reduce_reserved_blocks /var
                clean_apt_cache
                clean_amavis_virusmails
            fi
            ;;
        /tmp)
            #if is_tmp_to_delete
            #then
            #    find /tmp/ -type f -ctime +1 -delete
            #    log_action "$size Mo of disk space freed in /tmp"
            #fi
            if is_reserved_blocks_nominal /tmp; then
                reduce_reserved_blocks /tmp
            fi
            ;;
        /home)
            if is_reserved_blocks_nominal /home; then
                reduce_reserved_blocks /home
            fi
            ;;
        /srv)
            if is_reserved_blocks_nominal /srv; then
                reduce_reserved_blocks /srv
            fi
            ;;
        /filer)
            if is_reserved_blocks_nominal /filer; then
                reduce_reserved_blocks /filer
            fi
            ;;
        /)
            if is_reserved_blocks_nominal /; then
                reduce_reserved_blocks /
                # Suggest remove old kernel ?
            fi
            ;;
        *)
            # unknown
            log_run 'Unknown partition (or weird case) or nothing to do'
            ;;
        esac
    done
fi

post_repair