deytenit
6aaef35780
Adversarial parity review of every ported action against its bash source confirmed 17 real behavioral drifts (of 22 claimed); all fixed here: - tiers/chown: defaults were compositions/apex/tierN (one level too deep); now the tier roots. shared/ base reset is non-recursive again. - compose: --dry-run was swallowed by argparse.REMAINDER; now stripped. - host.write_file: rendered files land 0644 (tempfile's 0600 made fresh systemd units/crowdsec configs owner-only). - systemd.deploy_units: top-level non-hidden files only. - ufw: missing docker/host config dir exits 66; missing /etc/ufw target aborts; empty rules dir warns; dotfile .rules excluded. - sync/packages: Telegram error-trap parity and failed notify exits 1. Same notify-failure exit for backup/run and sync/repository. repository regains the node-dir guard. - tiers/useradd: no more secret-bearing .env.bak per run. - tiers/link: EOF on confirm prompt declines and continues. - extract-traefik-certs: sudo mkdir inside the notify envelope. - generate-happ-subscriptions: realpath parent-exists guards + docker check. - configure/crowdsec: bouncer install goes through install_packages. - lint-docker-compose: malformed/unreadable anchor-IP inputs are lint errors. - core compose: APEX_RESTIC_REPOSITORY now ?error; RESTIC_COMPRESSION per-node via APEX_RESTIC_COMPRESSION (default auto). - sys.service_exists line-anchored; tpl docstring corrected.
51 lines
2.7 KiB
Python
51 lines
2.7 KiB
Python
# actions/backup/run.py
|
|
"""Port of sync/tiers restic-backup (SP4: behavior-identical). Runs the restic core
|
|
service one-shot: init-if-needed -> backup tiers -> forget --prune -> Telegram."""
|
|
import os
|
|
from engine.descriptor import Meta, Arg
|
|
|
|
METADATA = Meta(summary="Run restic backup of the backed-up tiers (init-if-needed, backup, forget --prune).",
|
|
args=[Arg("telegram_bot_url", "Telegram Bot URL for notifications")])
|
|
TITLE = "Restic Host Backup"
|
|
|
|
def run(ctx, args):
|
|
log, node, url = ctx.log, ctx.node.name, args.telegram_bot_url
|
|
core = ctx.paths.core
|
|
tag = f"com-ermnvldmr-root-{node}" # KEPT unchanged for backup continuity (SP4/Decision D)
|
|
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):
|
|
return ctx.sys.run(["docker", "compose", *envfiles, "--profile", "manual",
|
|
"run", "--rm", "restic", *cmd], cwd=core, env=env, check=check)
|
|
|
|
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", node); raise SystemExit(1)
|
|
log.info("Backing up /data/@tier1 and /data/@tier2 ...")
|
|
if restic("backup", "/data/@tier1", "/data/@tier2", "--host", node, "--tag", tag,
|
|
"--compression", "auto", check=False).returncode != 0:
|
|
ctx.notify.error(TITLE, url, "restic backup failed", node); raise SystemExit(1)
|
|
log.info("Applying retention (forget --prune)...")
|
|
if restic("forget", "--prune", "--keep-daily", "7", "--keep-weekly", "4",
|
|
"--keep-monthly", "12", check=False).returncode != 0:
|
|
ctx.notify.error(TITLE, url, "restic forget/prune failed", node); raise SystemExit(1)
|
|
log.success("Restic backup completed.")
|
|
if not ctx.notify.success(TITLE, url, f"Restic backup + retention succeeded for {node}", node):
|
|
raise SystemExit(1) # bash exited 1 when the success telegram failed to send
|
|
except SystemExit:
|
|
raise
|
|
except Exception as e:
|
|
log.error(f"{type(e).__name__}: {e}")
|
|
ctx.notify.error(TITLE, url, f"backup failed: {e}", node)
|
|
raise SystemExit(1)
|