Files
ubuntu-post-install/extras/backup_kopia.sh
T
Claude 862ecf10e9 feat: backup test script, ntfy notifications, and error categorization
extras/test_backup.sh — new unified test script (Kopia + Borg):
  • Stops container, moves live data aside, restores latest backup,
    compares restored vs live with diff -rq (content, not timestamps),
    moves live data back and restarts container
  • PASS = restore succeeded; diff output is informational (files changed
    since last backup are normal)
  • FAIL = restore command failed or target empty after restore
  • --list flag, CLI service arg, interactive picker
  • Handles both full-service dirs and sub-path sources (gaming-backup)
  • Cleanup trap always restores live data even on error
  • Sends ntfy notification on pass and fail

extras/backup_kopia.sh, backup_borg.sh, backup_gaming.sh:
  • ntfy_send() + categorize_error() helpers added
  • Each snapshot/archive failure captures stderr and categorizes:
    disk full, remote unreachable, repository not found, wrong passphrase,
    permission denied, unknown error
  • Single ntfy notification at end: success (low priority) or failure
    (urgent) with per-service failure reasons listed
  • backup_borg.sh: changed 2>&1 | pipe to 2>"$_ERR" | so stdout logs
    cleanly and stderr is captured for error categorization

services/backup.sh, borg-backup.sh, gaming-backup.sh:
  • New ntfy prompt section in installer (URL + optional token)
  • NTFY_URL / NTFY_TOKEN written to backup.conf
  • test_backup.sh copied from extras/ into service dir
  • Summary updated to show test_backup.sh commands and ntfy URL

https://claude.ai/code/session_019XgsQ13XKm4Zj3cNsDNwHj
2026-06-04 20:03:30 +00:00

167 lines
6.5 KiB
Bash

#!/bin/bash
# extras/backup_kopia.sh — Kopia backup worker for all Docker services.
# Installed to ~/docker/backup/backup_kopia.sh by the backup service installer.
#
# sudo ./backup_kopia.sh run a full backup cycle
# sudo ./backup_kopia.sh snapshots list all snapshots (all repos)
# sudo ./backup_kopia.sh policy show retention policies
#
# Minecraft instances: flush to disk (save-all) then snapshot — no downtime.
# All other services: stop → snapshot → restart for consistency.
# Reads backup.conf from the same directory.
set -uo pipefail
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
CONF="${BACKUP_CONF:-$HERE/backup.conf}"
[ -f "$CONF" ] || { echo "Config not found: $CONF (re-run: sudo setup.sh backup)"; exit 1; }
# shellcheck source=/dev/null
source "$CONF"
ACTUAL_USER="${SUDO_USER:-${USER:-$(id -un)}}"
ACTUAL_HOME="$(getent passwd "$ACTUAL_USER" 2>/dev/null | cut -d: -f6 || echo "/home/$ACTUAL_USER")"
DOCKER_DIR="$ACTUAL_HOME/docker"
HOST="$(hostname -s 2>/dev/null || hostname)"
log() { echo "[$(date '+%F %T')] $*"; }
ntfy_send() {
local title="$1" msg="$2" priority="${3:-default}" tags="${4:-}"
[ -z "${NTFY_URL:-}" ] && return 0
local -a _args=(-fsS -o /dev/null)
_args+=(-H "Title: $title" -H "Priority: $priority")
[ -n "$tags" ] && _args+=(-H "Tags: $tags")
[ -n "${NTFY_TOKEN:-}" ] && _args+=(-H "Authorization: Bearer $NTFY_TOKEN")
curl "${_args[@]}" -d "$msg" "$NTFY_URL" 2>/dev/null || true
}
categorize_error() {
local txt="$1"
if echo "$txt" | grep -qi "no space left\|disk quota exceeded"; then
echo "disk full — backup destination is out of space"
elif echo "$txt" | grep -qi "connection refused\|network unreachable\|no route to host\|ssh.*connect\|timed out\|host unreachable"; then
echo "remote unreachable — check network / destination host"
elif echo "$txt" | grep -qi "repository.*not.*exist\|not a valid kopia\|not connected"; then
echo "repository not found — re-run the backup installer"
elif echo "$txt" | grep -qi "passphrase\|wrong key\|cannot decrypt"; then
echo "wrong passphrase — check backup.conf"
elif echo "$txt" | grep -qi "permission denied\|access denied"; then
echo "permission denied — check file permissions"
else
echo "error — see system logs on $HOST"
fi
}
kp_for() {
local dest="$1"; shift
local cfg_var="DEST_${dest}_CONFIG" pw_var="DEST_${dest}_PASSWORD"
local cfg="${!cfg_var:-}" pw="${!pw_var:-}"
[ -n "$cfg" ] || { log "Unknown destination: $dest"; return 1; }
env KOPIA_PASSWORD="$pw" "$KOPIA" --config-file="$cfg" "$@"
}
dest_for_svc() {
local var="SVC_${1//-/_}"
echo "${!var:-${DEST_DEFAULT:-default}}"
}
is_minecraft() { [ -f "${1}Dockerfile" ] && grep -qs itzg "${1}Dockerfile"; }
case "${1:-run}" in
snapshots)
for dest in ${DEST_NAMES:-default}; do
echo ""; echo "── dest: $dest ──"
kp_for "$dest" snapshot list 2>/dev/null || true
done
exit 0 ;;
policy)
for dest in ${DEST_NAMES:-default}; do
echo ""; echo "── dest: $dest ──"
kp_for "$dest" policy show --global 2>/dev/null || true
done
exit 0 ;;
esac
log "===== Backup starting ====="
rc=0
declare -a FAILED_SVCS=()
_ERR="$(mktemp)"
trap 'rm -f "$_ERR"' EXIT
for svc_dir in "$DOCKER_DIR"/*/; do
[ -f "${svc_dir}docker-compose.yml" ] || continue
svc="$(basename "$svc_dir")"
[[ "$svc" == "backup" || "$svc" == "borg-backup" || "$svc" == "gaming-backup" ]] && continue
dest="$(dest_for_svc "$svc")"
_repo_var="DEST_${dest}_REPO"
[ -n "${!_repo_var:-}" ] || { log "SKIP $svc — dest '$dest' not configured in conf"; continue; }
if is_minecraft "$svc_dir"; then
if docker ps --format '{{.Names}}' 2>/dev/null | grep -qx "$svc"; then
log "Flushing Minecraft world '$svc' (save-all, no downtime)..."
docker exec "$svc" mc-send-to-console save-all flush 2>/dev/null \
|| docker exec "$svc" rcon-cli save-all 2>/dev/null || true
sleep 5
fi
log "Snapshotting $svc (dest: $dest)..."
if kp_for "$dest" snapshot create --description="backup: $svc" "$svc_dir" 2>"$_ERR"; then
log "OK $svc (Minecraft, no downtime)"
else
_reason="$(categorize_error "$(cat "$_ERR")")"
log "WARNING: snapshot failed for $svc$_reason"
FAILED_SVCS+=("$svc: $_reason")
rc=1
fi
else
STOPPED=false
if docker ps --format '{{.Names}}' 2>/dev/null | grep -qx "$svc"; then
log "Stopping $svc..."
docker compose -f "${svc_dir}docker-compose.yml" down 2>/dev/null \
|| docker stop "$svc" 2>/dev/null \
|| log "WARNING: could not stop $svc — snapshotting live (consistency not guaranteed)"
STOPPED=true
fi
log "Snapshotting $svc (dest: $dest)..."
if kp_for "$dest" snapshot create --description="backup: $svc" "$svc_dir" 2>"$_ERR"; then
log "OK $svc"
else
_reason="$(categorize_error "$(cat "$_ERR")")"
log "WARNING: snapshot failed for $svc$_reason"
FAILED_SVCS+=("$svc: $_reason")
rc=1
fi
if [ "$STOPPED" = true ]; then
log "Starting $svc..."
docker compose -f "${svc_dir}docker-compose.yml" up -d 2>/dev/null \
|| log "WARNING: could not restart $svc — run: docker compose -f ${svc_dir}docker-compose.yml up -d"
fi
fi
done
if [ "${REMOTE_TYPE:-none}" != "none" ] && [ -n "${REMOTE_TYPE:-}" ]; then
for dest in ${DEST_NAMES:-default}; do
log "Mirroring '$dest' offsite ($REMOTE_TYPE)..."
# shellcheck disable=SC2086
if ! kp_for "$dest" repository sync-to "$REMOTE_TYPE" $REMOTE_ARGS 2>"$_ERR"; then
_reason="$(categorize_error "$(cat "$_ERR")")"
log "WARNING: mirror failed for '$dest' — $_reason"
FAILED_SVCS+=("mirror[$dest]: $_reason")
rc=1
fi
done
fi
if [ "$rc" -eq 0 ]; then
log "===== Backup complete ====="
ntfy_send "✓ Backup complete" "$HOST: all services backed up successfully" \
"low" "white_check_mark"
else
log "===== Backup finished WITH WARNINGS (see above) ====="
_ntfy_msg="$HOST: backup failures:"
for _s in "${FAILED_SVCS[@]}"; do _ntfy_msg+=$'\n'"• $_s"; done
ntfy_send "✗ Backup FAILED" "$_ntfy_msg" "urgent" "rotating_light"
fi
exit "$rc"