def sync(self):
"""Initializes cache by fetching and reading all archive indicies
"""
def add(id, size, csize):
try:
count, size, csize = self.chunks[id]
self.chunks[id] = count + 1, size, csize
except KeyError:
self.chunks[id] = 1, size, csize
self.begin_txn()
print('Initializing cache...')
self.chunks.clear()
unpacker = msgpack.Unpacker()
repository = cache_if_remote(self.repository)
for name, info in self.manifest.archives.items():
archive_id = info[b'id']
cdata = repository.get(archive_id)
data = self.key.decrypt(archive_id, cdata)
add(archive_id, len(data), len(cdata))
archive = msgpack.unpackb(data)
if archive[b'version'] != 1:
raise Exception('Unknown archive metadata version')
decode_dict(archive, (b'name',))
print('Analyzing archive:', archive[b'name'])
for key, chunk in zip(archive[b'items'], repository.get_many(archive[b'items'])):
data = self.key.decrypt(key, chunk)
add(key, len(data), len(chunk))
unpacker.feed(data)
for item in unpacker:
if b'chunks' in item:
for chunk_id, size, csize in item[b'chunks']:
add(chunk_id, size, csize)
def __init__(self, key, repository, manifest, archive):
super(AtticOperations, self).__init__()
self._inode_count = 0
self.key = key
self.repository = cache_if_remote(repository)
self.items = {}
self.parent = {}
self.contents = defaultdict(dict)
self.default_dir = {
b'mode': 0o40755,
b'mtime': int(time.time() * 1e9),
b'uid': os.getuid(),
b'gid': os.getgid()
}
self.pending_archives = {}
self.cache = ItemCache()
if archive:
self.process_archive(archive)
else:
# Create root inode
self.parent[1] = self.allocate_inode()
self.items[1] = self.default_dir
for archive_name in manifest.archives:
# Create archive placeholder inode
archive_inode = self.allocate_inode()
self.items[archive_inode] = self.default_dir
self.parent[archive_inode] = 1
self.contents[1][os.fsencode(archive_name)] = archive_inode
self.pending_archives[archive_inode] = Archive(
repository, key, manifest, archive_name)
def sync(self):
"""Initializes cache by fetching and reading all archive indicies
"""
def add(id, size, csize):
try:
count, size, csize = self.chunks[id]
self.chunks[id] = count + 1, size, csize
except KeyError:
self.chunks[id] = 1, size, csize
self.begin_txn()
print('Initializing cache...')
self.chunks.clear()
unpacker = msgpack.Unpacker()
repository = cache_if_remote(self.repository)
for name, info in self.manifest.archives.items():
archive_id = info[b'id']
cdata = repository.get(archive_id)
data = self.key.decrypt(archive_id, cdata)
add(archive_id, len(data), len(cdata))
archive = msgpack.unpackb(data)
if archive[b'version'] != 1:
raise Exception('Unknown archive metadata version')
decode_dict(archive, (b'name', ))
print('Analyzing archive:', archive[b'name'])
for key, chunk in zip(archive[b'items'],
repository.get_many(archive[b'items'])):
data = self.key.decrypt(key, chunk)
add(key, len(data), len(chunk))
unpacker.feed(data)
for item in unpacker:
if b'chunks' in item:
for chunk_id, size, csize in item[b'chunks']:
add(chunk_id, size, csize)
def __init__(self, key, repository, manifest, archive):
super(FuseOperations, self).__init__()
self._inode_count = 0
self.key = key
self.repository = cache_if_remote(repository)
self.items = {}
self.parent = {}
self.contents = defaultdict(dict)
self.default_dir = {b'mode': 0o40755, b'mtime': int(time.time() * 1e9), b'uid': os.getuid(), b'gid': os.getgid()}
self.pending_archives = {}
self.accounted_chunks = {}
self.cache = ItemCache()
if archive:
self.process_archive(archive)
else:
# Create root inode
self.parent[1] = self.allocate_inode()
self.items[1] = self.default_dir
for archive_name in manifest.archives:
# Create archive placeholder inode
archive_inode = self.allocate_inode()
self.items[archive_inode] = self.default_dir
self.parent[archive_inode] = 1
self.contents[1][os.fsencode(archive_name)] = archive_inode
self.pending_archives[archive_inode] = Archive(repository, key, manifest, archive_name)
def rebuild_refcounts(self, last=None):
"""Rebuild object reference counts by walking the metadata
Missing and/or incorrect data is repaired when detected
"""
# Exclude the manifest from chunks
del self.chunks[Manifest.MANIFEST_ID]
def mark_as_possibly_superseded(id_):
if self.chunks.get(id_, (0,))[0] == 0:
self.possibly_superseded.add(id_)
def add_callback(chunk):
id_ = self.key.id_hash(chunk)
cdata = self.key.encrypt(chunk)
add_reference(id_, len(chunk), len(cdata), cdata)
return id_
def add_reference(id_, size, csize, cdata=None):
try:
count, _, _ = self.chunks[id_]
self.chunks[id_] = count + 1, size, csize
except KeyError:
assert cdata is not None
self.chunks[id_] = 1, size, csize
if self.repair:
self.repository.put(id_, cdata)
def verify_file_chunks(item):
"""Verifies that all file chunks are present
Missing file chunks will be replaced with new chunks of the same
length containing all zeros.
"""
offset = 0
chunk_list = []
for chunk_id, size, csize in item[b'chunks']:
if chunk_id not in self.chunks:
# If a file chunk is missing, create an all empty replacement chunk
self.report_progress('{}: Missing file chunk detected (Byte {}-{})'.format(item[b'path'].decode('utf-8', 'surrogateescape'), offset, offset + size), error=True)
data = bytes(size)
chunk_id = self.key.id_hash(data)
cdata = self.key.encrypt(data)
csize = len(cdata)
add_reference(chunk_id, size, csize, cdata)
else:
add_reference(chunk_id, size, csize)
chunk_list.append((chunk_id, size, csize))
offset += size
item[b'chunks'] = chunk_list
def robust_iterator(archive):
"""Iterates through all archive items
Missing item chunks will be skipped and the msgpack stream will be restarted
"""
unpacker = RobustUnpacker(lambda item: isinstance(item, dict) and b'path' in item)
_state = 0
def missing_chunk_detector(chunk_id):
nonlocal _state
if _state % 2 != int(chunk_id not in self.chunks):
_state += 1
return _state
for state, items in groupby(archive[b'items'], missing_chunk_detector):
items = list(items)
if state % 2:
self.report_progress('Archive metadata damage detected', error=True)
continue
if state > 0:
unpacker.resync()
for chunk_id, cdata in zip(items, repository.get_many(items)):
unpacker.feed(self.key.decrypt(chunk_id, cdata))
for item in unpacker:
yield item
repository = cache_if_remote(self.repository)
num_archives = len(self.manifest.archives)
archive_items = sorted(self.manifest.archives.items(), reverse=True,
key=lambda name_info: name_info[1][b'time'])
end = None if last is None else min(num_archives, last)
for i, (name, info) in enumerate(archive_items[:end]):
self.report_progress('Analyzing archive {} ({}/{})'.format(name, num_archives - i, num_archives))
archive_id = info[b'id']
if archive_id not in self.chunks:
self.report_progress('Archive metadata block is missing', error=True)
del self.manifest.archives[name]
continue
mark_as_possibly_superseded(archive_id)
cdata = self.repository.get(archive_id)
data = self.key.decrypt(archive_id, cdata)
archive = StableDict(msgpack.unpackb(data))
if archive[b'version'] != 1:
raise Exception('Unknown archive metadata version')
decode_dict(archive, (b'name', b'hostname', b'username', b'time')) # fixme: argv
items_buffer = ChunkBuffer(self.key)
items_buffer.write_chunk = add_callback
for item in robust_iterator(archive):
if b'chunks' in item:
verify_file_chunks(item)
items_buffer.add(item)
items_buffer.flush(flush=True)
for previous_item_id in archive[b'items']:
mark_as_possibly_superseded(previous_item_id)
archive[b'items'] = items_buffer.chunks
data = msgpack.packb(archive, unicode_errors='surrogateescape')
new_archive_id = self.key.id_hash(data)
cdata = self.key.encrypt(data)
add_reference(new_archive_id, len(data), len(cdata), cdata)
info[b'id'] = new_archive_id
def rebuild_refcounts(self):
"""Rebuild object reference counts by walking the metadata
Missing and/or incorrect data is repaired when detected
"""
# Exclude the manifest from chunks
del self.chunks[Manifest.MANIFEST_ID]
def mark_as_possibly_superseded(id_):
if self.chunks.get(id_, (0,))[0] == 0:
self.possibly_superseded.add(id_)
def add_callback(chunk):
id_ = self.key.id_hash(chunk)
cdata = self.key.encrypt(chunk)
add_reference(id_, len(chunk), len(cdata), cdata)
return id_
def add_reference(id_, size, csize, cdata=None):
try:
count, _, _ = self.chunks[id_]
self.chunks[id_] = count + 1, size, csize
except KeyError:
assert cdata is not None
self.chunks[id_] = 1, size, csize
if self.repair:
self.repository.put(id_, cdata)
def verify_file_chunks(item):
"""Verifies that all file chunks are present
Missing file chunks will be replaced with new chunks of the same
length containing all zeros.
"""
offset = 0
chunk_list = []
for chunk_id, size, csize in item[b'chunks']:
if not chunk_id in self.chunks:
# If a file chunk is missing, create an all empty replacement chunk
self.report_progress('{}: Missing file chunk detected (Byte {}-{})'.format(item[b'path'].decode('utf-8', 'surrogateescape'), offset, offset + size), error=True)
data = bytes(size)
chunk_id = self.key.id_hash(data)
cdata = self.key.encrypt(data)
csize = len(cdata)
add_reference(chunk_id, size, csize, cdata)
else:
add_reference(chunk_id, size, csize)
chunk_list.append((chunk_id, size, csize))
offset += size
item[b'chunks'] = chunk_list
def robust_iterator(archive):
"""Iterates through all archive items
Missing item chunks will be skipped and the msgpack stream will be restarted
"""
unpacker = RobustUnpacker(lambda item: isinstance(item, dict) and b'path' in item)
_state = 0
def missing_chunk_detector(chunk_id):
nonlocal _state
if _state % 2 != int(not chunk_id in self.chunks):
_state += 1
return _state
for state, items in groupby(archive[b'items'], missing_chunk_detector):
items = list(items)
if state % 2:
self.report_progress('Archive metadata damage detected', error=True)
continue
if state > 0:
unpacker.resync()
for chunk_id, cdata in zip(items, repository.get_many(items)):
unpacker.feed(self.key.decrypt(chunk_id, cdata))
for item in unpacker:
yield item
repository = cache_if_remote(self.repository)
num_archives = len(self.manifest.archives)
for i, (name, info) in enumerate(list(self.manifest.archives.items()), 1):
self.report_progress('Analyzing archive {} ({}/{})'.format(name, i, num_archives))
archive_id = info[b'id']
if not archive_id in self.chunks:
self.report_progress('Archive metadata block is missing', error=True)
del self.manifest.archives[name]
continue
mark_as_possibly_superseded(archive_id)
cdata = self.repository.get(archive_id)
data = self.key.decrypt(archive_id, cdata)
archive = StableDict(msgpack.unpackb(data))
if archive[b'version'] != 1:
raise Exception('Unknown archive metadata version')
decode_dict(archive, (b'name', b'hostname', b'username', b'time')) # fixme: argv
items_buffer = ChunkBuffer(self.key)
items_buffer.write_chunk = add_callback
for item in robust_iterator(archive):
if b'chunks' in item:
verify_file_chunks(item)
items_buffer.add(item)
items_buffer.flush(flush=True)
for previous_item_id in archive[b'items']:
mark_as_possibly_superseded(previous_item_id)
archive[b'items'] = items_buffer.chunks
data = msgpack.packb(archive, unicode_errors='surrogateescape')
new_archive_id = self.key.id_hash(data)
cdata = self.key.encrypt(data)
add_reference(new_archive_id, len(data), len(cdata), cdata)
info[b'id'] = new_archive_id
