Backup hardening, UPS monitoring, Nextcloud cron, image bumps #10

Merged
bastian merged 6 commits from backup-hardening into master 2026-07-30 13:05:20 -04:00
2 changed files with 36 additions and 14 deletions
Showing only changes of commit 6e99794d0f - Show all commits
@@ -40,11 +40,17 @@ log "status=start"
# $MYSQL_ROOT_PASSWORD and $MYSQL_DATABASE are expanded by the shell INSIDE # $MYSQL_ROOT_PASSWORD and $MYSQL_DATABASE are expanded by the shell INSIDE
# the database container, which already carries them in its environment. # the database container, which already carries them in its environment.
# #
# Flags are deliberately minimal. --events and --routines were both tried and # --routines and --events initially aborted the dump here: mysql.proc read as
# both abort the dump on these instances: the event scheduler is disabled # corrupted (error 1728) and the event scheduler reported disabled (1577),
# (error 1577) and mysql.proc reads as corrupted (error 1728, an artefact of # both artefacts of an image bump without mariadb-upgrade. `mariadb-upgrade
# an image bump without mariadb-upgrade). Nextcloud uses neither events nor # --force` has since been run against both instances and repaired the system
# stored routines, so dropping them loses nothing. # tables, so the full flag set works and is kept for completeness.
#
# Note that upgrade still exits non-zero on these containers: it cannot
# install the `sys` schema because the datadir root (/var/lib/mysql) is owned
# by daemon rather than mysql, so mysqld may not create new top-level
# databases. `sys` is purely diagnostic and unused by Nextcloud, so this is
# cosmetic -- but it does mean creating a NEW database would fail too.
pexec() { pexec() {
sudo -H -u {{ podman_user }} bash -c \ sudo -H -u {{ podman_user }} bash -c \
'cd; d=/run/user/$(id -u); [ -d "$d" ] && export XDG_RUNTIME_DIR="$d" 'cd; d=/run/user/$(id -u); [ -d "$d" ] && export XDG_RUNTIME_DIR="$d"
@@ -59,7 +65,7 @@ log "dumping {{ db_container }}"
set +e set +e
pexec exec {{ db_container }} sh -c ' pexec exec {{ db_container }} sh -c '
exec env MYSQL_PWD="$MYSQL_ROOT_PASSWORD" mariadb-dump -u root \ exec env MYSQL_PWD="$MYSQL_ROOT_PASSWORD" mariadb-dump -u root \
--single-transaction --quick --triggers \ --single-transaction --quick --routines --events --triggers \
--no-tablespaces --default-character-set=utf8mb4 "$MYSQL_DATABASE" --no-tablespaces --default-character-set=utf8mb4 "$MYSQL_DATABASE"
' | gzip -6 > "$tmp" ' | gzip -6 > "$tmp"
dump_rc=${PIPESTATUS[0]} dump_rc=${PIPESTATUS[0]}
@@ -16,21 +16,37 @@ HOST="$(hostname -f 2>/dev/null || hostname)"
result="$(systemctl show -p Result --value "$UNIT" 2>/dev/null)" result="$(systemctl show -p Result --value "$UNIT" 2>/dev/null)"
code="$(systemctl show -p ExecMainStatus --value "$UNIT" 2>/dev/null)" code="$(systemctl show -p ExecMainStatus --value "$UNIT" 2>/dev/null)"
# One machine-parseable line for Graylog, then the context. # Only claim a failure when the unit actually reports one. Starting this
logger -t "$TAG" -p daemon.err -- \ # handler by hand (or any other spurious trigger) would otherwise mail out a
"status=failed unit=$UNIT result=${result:-unknown} exit=${code:-unknown}" # subject line saying FAILED about a run that succeeded. Keeping status=failed
# exact also stops such triggers matching the Graylog alert rule.
if [ "${result:-success}" = "success" ]; then
state=spurious
prio=daemon.warning
headline="$(printf 'Nextcloud backup alert handler was invoked on %s, but %s reports SUCCESS.\nThis is not a backup failure -- most likely the handler was started manually.' "$HOST" "$UNIT")"
subject="[$HOST] Nextcloud backup alert (spurious, unit OK): $UNIT"
else
state=failed
prio=daemon.err
headline="Nextcloud backup FAILED on $HOST"
subject="[$HOST] Nextcloud backup FAILED: $UNIT"
fi
body="$(printf 'Nextcloud backup FAILED on %s\n\nunit: %s\nresult: %s\nexit: %s\n\n--- last 40 journal lines ---\n' \ # One machine-parseable line for Graylog, then the context.
"$HOST" "$UNIT" "${result:-unknown}" "${code:-unknown}") logger -t "$TAG" -p "$prio" -- \
"status=$state unit=$UNIT result=${result:-unknown} exit=${code:-unknown}"
body="$(printf '%s\n\nunit: %s\nresult: %s\nexit: %s\n\n--- last 40 journal lines ---\n' \
"$headline" "$UNIT" "${result:-unknown}" "${code:-unknown}")
$(journalctl -u "$UNIT" -n 40 --no-pager -o cat 2>/dev/null)" $(journalctl -u "$UNIT" -n 40 --no-pager -o cat 2>/dev/null)"
echo "$body" | logger -t "$TAG" -p daemon.err echo "$body" | logger -t "$TAG" -p "$prio"
# Mail is best-effort: if the MTA is not configured the journald record above # Mail is best-effort: if the MTA is not configured the journald record above
# is still the authoritative signal, so never fail the handler on this. # is still the authoritative signal, so never fail the handler on this.
if command -v sendmail >/dev/null 2>&1; then if command -v sendmail >/dev/null 2>&1; then
printf 'To: %s\nSubject: [%s] Nextcloud backup FAILED: %s\nContent-Type: text/plain; charset=UTF-8\n\n%s\n' \ printf 'To: %s\nSubject: %s\nContent-Type: text/plain; charset=UTF-8\n\n%s\n' \
"$TO" "$HOST" "$UNIT" "$body" | sendmail -t \ "$TO" "$subject" "$body" | sendmail -t \
&& logger -t "$TAG" -p daemon.info -- "alert_mail=sent to=$TO" \ && logger -t "$TAG" -p daemon.info -- "alert_mail=sent to=$TO" \
|| logger -t "$TAG" -p daemon.err -- "alert_mail=failed to=$TO" || logger -t "$TAG" -p daemon.err -- "alert_mail=failed to=$TO"
else else