fix(maintenance): restore a backup of any size the disk has room for

The legacy restore refused the maintainer's own 1.6 GB safety backup with
"File too large. Maximum size is 100MB", a fixed cap since #153. Free
disk space now decides: the upload, its staged copy and the swap must fit,
under a 64 GiB ceiling. A request with a Content-Length that does not fit
is refused before anything is written, one without as soon as its running
size does not, with 507 insufficient-space and a message without paths.
The upload still streams and its temp file is removed on every path.
This commit is contained in:
Vito Sansevero
2026-10-24 05:01:14 -07:00
parent 1e2f448646
commit 399c0cb63f
4 changed files with 246 additions and 13 deletions
+41 -12
View File
@@ -1274,7 +1274,11 @@ class AdminRoutesMixin:
async def restore_database(self, request):
"""Restore the prompts database from an uploaded SQLite file.
The upload is streamed to a temp file (capped at restore_max_bytes),
The upload is streamed to a temp file. Free disk space decides how
large it may be (``maintenance.restore_room``), under a 64 GiB ceiling
(``restore_max_bytes``): a request whose Content-Length does not fit
is refused before anything is written, and one without is refused as
soon as its running size does not. The file is
verified with PromptModel.verify_database_file and only then copied
over the live database, which is backed up first. The whole request
holds the registry (records): it is refused while a scan or another
@@ -1287,10 +1291,44 @@ class AdminRoutesMixin:
lambda: self._restore_database(request),
)
def _restore_refusal(self, size, ceiling, room, *, known):
"""``400 too-large`` past the ceiling, else ``507 insufficient-space``."""
from .maintenance import restore_space_message
if size > ceiling:
return web.json_response(
{
"success": False,
"code": "too-large",
"error": (
"File too large. Maximum size is "
f"{ceiling // (1024 * 1024)}MB"
),
},
status=400,
)
return web.json_response(
{
"success": False,
"code": "insufficient-space",
"error": restore_space_message(size, room, known=known),
},
status=507,
)
async def _restore_database(self, request):
max_bytes = getattr(self, "restore_max_bytes", 100 * 1024 * 1024)
from .maintenance import RESTORE_MAX_BYTES, restore_room
ceiling = getattr(self, "restore_max_bytes", RESTORE_MAX_BYTES)
temp_path = None
try:
# Free disk space decides how large a backup may be (#313): the
# upload, its staged copy and the swap must all fit.
room = await self._run_in_executor(restore_room, self.db.model.db_path)
max_bytes = min(ceiling, room)
length = request.content_length
if length is not None and length > max_bytes:
return self._restore_refusal(length, ceiling, room, known=True)
reader = await request.multipart()
field = await reader.next()
@@ -1316,16 +1354,7 @@ class AdminRoutesMixin:
break
size += len(chunk)
if size > max_bytes:
return web.json_response(
{
"success": False,
"error": (
"File too large. Maximum size is "
f"{max_bytes // (1024 * 1024)}MB"
),
},
status=400,
)
return self._restore_refusal(size, ceiling, room, known=False)
out.write(chunk)
if size == 0:
+51
View File
@@ -207,6 +207,57 @@ def disk_plan(db_path, *, backup, vacuum):
return public, short, size
# A restore upload's hard ceiling; below it, free disk space decides.
RESTORE_MAX_BYTES = 64 * 2**30
def size_label(size):
"""``1.6 GB`` or ``120.0 MB``: a backup's size for a message."""
if size >= 2**30:
return f"{size / 2**30:,.1f} GB"
return _megabytes(size)
def restore_room(db_path):
"""The largest restore upload the disks have room for (blocking).
The upload is written to a temp file and staged once more in the
temporary folder (2x), then copied over the live database beside it,
whose current contents are first kept as a safety backup (1x the upload
for the WAL, plus the current database). Needs on one device add up,
each with ``DISK_MARGIN_BYTES``.
"""
db_path = os.path.abspath(db_path)
folder = os.path.dirname(db_path)
current = database_bytes(db_path) if os.path.exists(db_path) else 0
devices = {}
for path, per_upload, fixed in (
(tempfile.gettempdir(), 2, 0),
(folder, 1, current),
):
entry = devices.setdefault(_device(path), {"path": path, "per": 0, "fixed": 0})
entry["per"] += per_upload
entry["fixed"] += fixed
room = min(
(_free_bytes(e["path"]) - e["fixed"] - DISK_MARGIN_BYTES) // e["per"]
for e in devices.values()
)
return max(0, room)
def restore_space_message(size, room, *, known):
"""The truthful refusal of a restore the disks have no room for."""
if known:
return (
f"Not enough free disk space to restore a {size_label(size)} backup; "
f"there is room for about {size_label(room)}. Nothing was changed."
)
return (
"Not enough free disk space to restore this backup: it is larger than "
f"the {size_label(room)} there is room for. Nothing was changed."
)
def short_space_message(short):
"""The truthful refusal for ``disk_plan``'s ``short``."""
place, what, required, free = short