Files
apex.ermnvldmr.com/actions/backup/run.py
T

124 lines
6.4 KiB
Python

# actions/backup/run.py
"""Label-driven restic backup via resticontainer (git.ermnvldmr.com/deytenit/resticontainer).
Runs the resticontainer core service one-shot: init-if-needed -> backup (discovers
`restic.*`-labelled services, runs their pre-hooks/stops, snapshots the union of the
resolved host paths in a single restic run) -> forget --prune -> Telegram. Every
non-`backup` subcommand passes straight through to restic, so init/snapshots/forget
behave exactly as before."""
import json
import os
from pathlib import Path
import time
from engine.descriptor import Meta, Arg
METADATA = Meta(summary="Run the resticontainer label-driven backup (init-if-needed, backup, forget --prune).",
args=[Arg("telegram_bot_url", "Telegram Bot URL for notifications")])
TITLE = "Restic Host Backup"
def write_backup_status(path, state, timestamp):
path = Path(path)
previous = json.loads(path.read_text()) if path.exists() else {}
status = {"state": state, "updated_at": timestamp,
"last_success": timestamp if state == "success" else previous.get("last_success", 0)}
path.parent.mkdir(parents=True, exist_ok=True)
temporary = path.with_name(path.name + f".{os.getpid()}.tmp")
temporary.write_text(json.dumps(status) + "\n")
temporary.chmod(0o644)
temporary.replace(path)
def restore_containers(ctx, container_ids):
"""Recover previously running backup targets, retrying namespace dependents."""
pending = list(container_ids)
if not pending:
return
for _ in range(len(pending) + 1):
cp = ctx.sys.run(["docker", "inspect", *pending], capture=True)
stopped = [c["Id"] for c in json.loads(cp.stdout) if not c["State"]["Running"]]
if not stopped:
return
progress = False
for container_id in stopped:
cp = ctx.sys.run(["docker", "start", container_id], check=False, capture=True)
progress = progress or cp.returncode == 0
if not progress:
raise RuntimeError("Backup left containers stopped: " + ", ".join(stopped))
pending = stopped
raise RuntimeError("Backup containers did not stay running: " + ", ".join(pending))
def run(ctx, args):
log, node, url = ctx.log, ctx.node.name, args.telegram_bot_url
core = ctx.paths.core
host = ctx.node.host # restic --host: the node's public host name (APEX_NODE_HOST)
tag = "biweekly" # restic --tag: snapshot cadence (this cron fires on the 5th & 20th)
if not os.path.isfile(os.path.join(core, "docker-compose.yml")):
log.error(f"Core compose not found in {core}"); raise SystemExit(1)
env = dict(os.environ, COMPOSE_PROFILES="manual")
env.update({k: v for k, v in ctx.vars().items() if k.startswith("APEX_")}) # tier paths, identity
envfiles = []
for ef in (".env", "apex.env"): # secrets (.env) + committed scalars (apex.env)
if os.path.isfile(os.path.join(core, ef)):
envfiles += ["--env-file", ef]
def restic(*cmd, check=True, capture=False):
return ctx.sys.run(["docker", "compose", *envfiles, "--profile", "manual",
"run", "--rm", "-T", "resticontainer", *cmd],
cwd=core, env=env, check=check, capture=capture)
def host_snapshot_ids():
"""This host's snapshot IDs, or None if it can't be determined (never fail on this)."""
cp = restic("snapshots", "--host", host, "--json", check=False, capture=True)
if cp.returncode != 0:
return None
try:
return {s.get("id") for s in json.loads(cp.stdout or "[]")}
except (ValueError, TypeError):
return None
status_path = Path("/var/lib/apex/backup-status.json")
write_backup_status(status_path, "running", time.time())
try:
log.info("Checking restic repository availability...")
if restic("snapshots", check=False).returncode == 0:
log.info("Restic repository reachable.")
elif restic("init", check=False).returncode != 0:
ctx.notify.error(TITLE, url, "restic init failed"); raise SystemExit(1)
before = host_snapshot_ids()
log.info("Backing up `restic.*`-labelled services (resticontainer discovers paths)...")
targets = ctx.sys.run(["docker", "ps", "-q", "--no-trunc",
"--filter", "label=restic.enable=true",
"--filter", "label=restic.backup.stop=true"], capture=True).stdout.split()
try:
result = restic("backup", "--host", host, "--tag", tag, "--compression", "max",
check=False)
finally:
# Resticontainer may start a network-namespace dependent before its owner.
restore_containers(ctx, targets)
if result.returncode != 0:
ctx.notify.error(TITLE, url, "restic backup failed"); raise SystemExit(1)
# Guard: the label-driven backup is a silent no-op if no service carries the
# `restic.enable` label (resticontainer finds zero paths and skips restic).
# Prove a fresh snapshot for this host actually landed before we prune/notify.
after = host_snapshot_ids()
if before is not None and after is not None and not (after - before):
log.error("No new snapshot produced — refusing to report success.")
ctx.notify.error(TITLE, url,
"backup produced no new snapshot (no restic.* labels discovered?)")
raise SystemExit(1)
log.info("Applying retention (forget --prune)...")
if restic("forget", "--prune", "--host", host, "--tag", tag,
"--keep-daily", "7", "--keep-weekly", "4",
"--keep-monthly", "12", check=False).returncode != 0:
ctx.notify.error(TITLE, url, "restic forget/prune failed"); raise SystemExit(1)
log.success("Restic backup completed.")
if not ctx.notify.success(TITLE, url, f"Restic backup + retention succeeded for {node}"):
raise SystemExit(1) # bash exited 1 when the success telegram failed to send
write_backup_status(status_path, "success", time.time())
except SystemExit:
write_backup_status(status_path, "failed", time.time())
raise
except Exception as e:
write_backup_status(status_path, "failed", time.time())
log.error(f"{type(e).__name__}: {e}")
ctx.notify.error(TITLE, url, f"backup failed: {e}")
raise SystemExit(1) from e