Files
ComfyAssets-ComfyUI_PromptM…/py/api/restore_plans.py
T
Vito Sansevero 5ce3349d64 fix(backup): final review round for the restore and backup routes
- I1: once the stage's copy replaced the library the restore succeeded:
  pruning, reopening self.db, dropping old previews and closing the old
  object only log, so the job finishes and the legacy /restore answers 200
  instead of "the library was not changed". The generation is always bumped.
- M1: a backup download holds its guarded slot only while the snapshot is
  written; the stream runs outside it, so a stalled download blocks nothing.
- M2: a restore preview leases only its read of the live library, not the
  upload or the staging; a restore whose drain still times out keeps the
  reviewed stage under its token.
- M3: the reviewed-preview store changes only on the event loop; stage
  folders are removed in the executor.
- M4: a document whose body inflates completely while only its recorded
  hash or only its length disagrees is re-keyed (or merged into the
  document holding that text) instead of dropped.
- M5: a backup download is refused only when the snapshot is not SQLite or
  fails integrity_check; a semantic check failure still downloads, logged,
  sent as X-PromptManager-Verify and recorded as not verified.
- M6: a refused, failed or cancelled preview removes its stage, also when
  the cancel lands while a worker still stages; a timer removes expired
  stages without another request.
- M7, N1: repair reads rows one at a time and counts distinct images.
- N3: the live fingerprint never commits a transaction it did not open.
2026-10-25 08:11:27 -07:00

140 lines
4.9 KiB
Python

"""Reviewed restores: staged uploads held under single-use tokens (#249 S8).
A restore preview stages the upload (``database/restore_stage.py``) and
keeps it here under a ``secrets.token_urlsafe(32)`` token with the live
library's fingerprint and the database identity it was reviewed against.
``take`` hands the stage to the restore job exactly once; a second apply of
the token names that job (``PlanUsed``). An expired, discarded or unknown
token raises ``PlanExpired``; its stage folder is removed. A restart forgets
every token (the startup sweep removes the folders).
At most ``max_stages`` stages are held. Bytes are bounded by free disk space
(the upload is refused when the disk has no room, and held stages use that
disk), not by a fixed budget. A stage being applied belongs to its job and is
never evicted or counted.
The store is only read and changed on the event loop (it has no lock). Its
entries own stage folders, whose removal is blocking: every method that
drops an entry returns it (or keeps it in ``take_doomed``), and the caller
removes the folder in the executor (``HeldRestore.staged.discard``).
"""
import secrets
import time
from dataclasses import dataclass
from typing import Any, Callable, Dict, List, Optional
from .maintenance_plans import PlanExpired, PlanUsed
STAGE_TTL_SECONDS = 900
MAX_STAGES = 2
_USED_KEPT = 32 # applied tokens remembered for plan-used answers
class TooManyStages(Exception):
"""Every stage slot is held by a reviewed restore."""
@dataclass
class HeldRestore:
staged: Any # database.restore_stage.StagedRestore
fingerprint: str
db_identity: Any
live: Dict[str, int]
expires_at: float
class RestorePlanStore:
def __init__(
self,
clock: Optional[Callable[[], float]] = None,
ttl: float = STAGE_TTL_SECONDS,
max_stages: int = MAX_STAGES,
):
self._ttl = ttl
self._max = max_stages
self._clock = clock or time.time
self._held: Dict[str, HeldRestore] = {}
self._used: Dict[str, str] = {}
self._doomed: List[HeldRestore] = []
@property
def ttl(self) -> float:
return self._ttl
def now(self) -> float:
return self._clock()
def __len__(self):
return len(self._held)
def full(self) -> bool:
return len(self._held) >= self._max
def issue(self, staged, fingerprint, db_identity, live) -> str:
"""Hold ``staged`` and return its token; TooManyStages when full."""
if self.full():
raise TooManyStages()
token = secrets.token_urlsafe(32)
self._held[token] = HeldRestore(
staged=staged,
fingerprint=fingerprint,
db_identity=db_identity,
live=dict(live),
expires_at=self._clock() + self._ttl,
)
return token
def peek(self, token) -> HeldRestore:
if token in self._used:
raise PlanUsed(self._used[token])
held = self._held.get(token)
if held is None:
raise PlanExpired()
if held.expires_at <= self._clock():
self._doomed.append(self._held.pop(token))
raise PlanExpired()
return held
def take(self, token, job_id) -> HeldRestore:
"""Hand the held stage to the job applying it (single use)."""
held = self.peek(token)
del self._held[token]
self._used[token] = job_id
while len(self._used) > _USED_KEPT:
self._used.pop(next(iter(self._used)))
return held
def give_back(self, token, held) -> None:
"""Hold a taken stage again under its token (its job did not apply it)."""
self._used.pop(token, None)
self._held[token] = held
def entry(self, token) -> Optional[HeldRestore]:
"""The held entry, expired or not (for the response that issued it)."""
return self._held.get(token)
def pop(self, token) -> Optional[HeldRestore]:
"""Drop the token; its entry (to discard) or None when it was not held."""
return self._held.pop(token, None)
def pop_expired(self) -> List[HeldRestore]:
"""Drop every expired entry; them, with any ``peek`` found expired."""
now = self._clock()
expired = [t for t, held in self._held.items() if held.expires_at <= now]
return [self._held.pop(token) for token in expired] + self.take_doomed()
def pop_all(self) -> List[HeldRestore]:
"""Drop every entry (the library was replaced); them, to discard."""
held = list(self._held.values()) + self.take_doomed()
self._held.clear()
return held
def take_doomed(self) -> List[HeldRestore]:
doomed, self._doomed = self._doomed, []
return doomed
def next_expiry(self) -> Optional[float]:
"""When the soonest held entry expires (clock time), or None."""
return min((held.expires_at for held in self._held.values()), default=None)