prosolis
8410b6315b
Deploy plumbing so Petal can run on the public VPS behind the Traefik already on that box, with vLLM reached over headscale. - Dockerfile: node build -> go build -> alpine runtime. CGO stays off (modernc SQLite is pure Go), so the runtime layer exists only for ffmpeg (read-aloud transcodes Piper's WAV) and tzdata (the companion's bedtime nag and night mode read the local clock). Runs as uid 10001 with /data as the single writable mount. - docker-compose.yml: Traefik labels following this host's convention (external `traefik` network, `web-secure` entrypoint, `default` cert resolver). Petal publishes no host port. ./data is a bind mount, not a named volume, so the nightly backup and a restore are reachable from the host. - Piper runs as two sibling containers rather than host systemd units. The plan assumed Piper was already installed on the VPS; it is not, the host has no lingering user session to keep user units alive, and containers keep the TTS ports on an internal network unreachable from anywhere but Petal. One image, voice chosen per service, model cached in a shared volume -- so the pt-PT voice is a new service, not a new image. - db.Backup + a `-backup` flag: VACUUM INTO, not a file copy. Petal runs in WAL mode, so the newest committed pages may live in petal.db-wal; copying the three files separately can capture a torn mid-checkpoint state. VACUUM INTO reads one coherent snapshot without taking a write lock, and emits a single file with no -wal/-shm companions. Refuses an existing destination so a failed run can't destroy the last good backup. - deploy/backup-petal.sh: nightly snapshot, compress, push to millenia over headscale with a post-transfer size check, prune both sides. - deploy/petal.env.example: LLM_TIMEOUT raised 30s -> 90s for the WAN+VPN round trip, since the voice and collocation passes send a whole document and the timeout is a hard deadline on Complete.
82 lines
3.2 KiB
Bash
Executable File
82 lines
3.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Nightly off-VPS backup of Petal's database.
|
|
#
|
|
# ./backup-petal.sh # snapshot, compress, push off-box, prune
|
|
# ./backup-petal.sh --local-only # snapshot + prune, skip the remote push
|
|
#
|
|
# Run it from cron on the VPS (see deploy/README.md). The snapshot itself goes
|
|
# through `petal -backup`, which uses SQLite's VACUUM INTO: one coherent file
|
|
# including anything still in the WAL, taken without a write lock, so it is
|
|
# safe against the live running app. That is why this script never touches
|
|
# petal.db / -wal / -shm directly — copying those three separately can capture
|
|
# a torn mid-checkpoint state.
|
|
#
|
|
# Everything below is overridable from the environment.
|
|
set -euo pipefail
|
|
|
|
# Stack directory (holds docker-compose.yml and ./data).
|
|
STACK_DIR="${STACK_DIR:-$HOME/petal}"
|
|
# Where snapshots land on the VPS before being pushed off-box. Inside ./data so
|
|
# the container can write it through the existing bind mount.
|
|
LOCAL_DIR="${LOCAL_DIR:-$STACK_DIR/data/backups}"
|
|
# Off-VPS destination: millenia over headscale. Empty disables the push.
|
|
REMOTE_HOST="${REMOTE_HOST:-100.64.0.2}"
|
|
REMOTE_USER="${REMOTE_USER:-}"
|
|
REMOTE_DIR="${REMOTE_DIR:-petal-backups}"
|
|
# Retention, in days, on each side.
|
|
KEEP_LOCAL_DAYS="${KEEP_LOCAL_DAYS:-7}"
|
|
KEEP_REMOTE_DAYS="${KEEP_REMOTE_DAYS:-30}"
|
|
|
|
local_only=0
|
|
[ "${1:-}" = "--local-only" ] && local_only=1
|
|
|
|
stamp="$(date -u +%Y%m%dT%H%M%SZ)"
|
|
name="petal-${stamp}.db"
|
|
|
|
cd "$STACK_DIR"
|
|
|
|
echo ">> snapshotting to data/backups/${name}"
|
|
# The container writes to its own /data mount; ./data/backups is the same
|
|
# directory seen from the host.
|
|
docker compose exec -T petal /app/petal -backup "/data/backups/${name}"
|
|
|
|
snapshot="${LOCAL_DIR}/${name}"
|
|
[ -s "$snapshot" ] || { echo "snapshot missing or empty: $snapshot" >&2; exit 1; }
|
|
|
|
echo ">> compressing"
|
|
gzip -9 "$snapshot"
|
|
archive="${snapshot}.gz"
|
|
echo " $(du -h "$archive" | cut -f1) ${archive}"
|
|
|
|
if [ "$local_only" -eq 0 ] && [ -n "$REMOTE_HOST" ]; then
|
|
target="${REMOTE_HOST}"
|
|
[ -n "$REMOTE_USER" ] && target="${REMOTE_USER}@${REMOTE_HOST}"
|
|
|
|
echo ">> pushing to ${target}:${REMOTE_DIR}/"
|
|
ssh -o BatchMode=yes "$target" "mkdir -p '${REMOTE_DIR}'"
|
|
scp -q -o BatchMode=yes "$archive" "${target}:${REMOTE_DIR}/"
|
|
|
|
# Verify by size rather than trusting scp's exit code alone — a truncated
|
|
# transfer that still exits 0 would leave a backup that only looks fine.
|
|
local_size="$(stat -c%s "$archive")"
|
|
remote_size="$(ssh -o BatchMode=yes "$target" "stat -c%s '${REMOTE_DIR}/$(basename "$archive")'")"
|
|
if [ "$local_size" != "$remote_size" ]; then
|
|
echo "size mismatch after transfer: local ${local_size}, remote ${remote_size}" >&2
|
|
exit 1
|
|
fi
|
|
echo " verified ${remote_size} bytes"
|
|
|
|
echo ">> pruning remote copies older than ${KEEP_REMOTE_DAYS} days"
|
|
ssh -o BatchMode=yes "$target" \
|
|
"find '${REMOTE_DIR}' -name 'petal-*.db.gz' -type f -mtime +${KEEP_REMOTE_DAYS} -delete"
|
|
elif [ "$local_only" -eq 1 ]; then
|
|
echo ">> --local-only: skipping the remote push"
|
|
else
|
|
echo ">> REMOTE_HOST is empty: skipping the remote push" >&2
|
|
fi
|
|
|
|
echo ">> pruning local copies older than ${KEEP_LOCAL_DAYS} days"
|
|
find "$LOCAL_DIR" -name 'petal-*.db.gz' -type f -mtime "+${KEEP_LOCAL_DAYS}" -delete
|
|
|
|
echo ">> done"
|