def scan_prev(self, ctx, prev_num):
"""
"""
ctx.total_nodes += 1
if prev_num is None:
cndb = self.backup.get_completed_nodes_db()
path_digest = Digest.dataDigest(self.path().encode('utf8'))
if cndb.has_key(path_digest):
prev_data_is = StringIO.StringIO(cndb[path_digest])
prev_digest = prev_data_is.read(Digest.dataDigestSize())
prev_level = IntegerEncodings.binary_read_int_varlen(prev_data_is)
prev_type = IntegerEncodings.binary_read_int_varlen(prev_data_is)
#print "prev_stat_data->", base64.b64encode(prev_data_is.read())
prev_stat = unserialize_stats(prev_data_is)
else:
ctx.changed_nodes += 1
return False
else:
prev_type, prev_stat, prev_digest, prev_level = prev_num
changed = False
if prev_type != self.get_type():
logging.info("node type differs in the db")
changed = True
#elif (stat.S_IFMT(self.stats[stat.ST_MODE]) !=
#stat.S_IFMT(prev_stat[stat.ST_MODE])):
#print " Node type differs in the fs"
#changed = True
elif prev_stat is None:
logging.info("Base stat not defined")
changed = True
elif self.stats[stat.ST_INO] != prev_stat[stat.ST_INO]:
logging.info("Inode of %s differs: was %d, now %d" %
(self.path(), prev_stat[stat.ST_INO], self.stats[stat.ST_INO]))
changed = True
elif self.stats[stat.ST_MTIME] != prev_stat[stat.ST_MTIME]:
logging.info("Mtime of %s differs: %d != %d" %
(self.path(), self.stats[stat.ST_MTIME], prev_stat[stat.ST_MTIME]))
changed = True
elif time.time() - self.stats[stat.ST_MTIME] <= 1.0:
# The time from the last change is less than the resolution
# of time() functions
logging.info("File %s too recent %d : %d" %
(self.path(), prev_stat[stat.ST_MTIME], time.time()))
changed = True
else:
#
# OK, the prev node seems to be the same as this one.
# Reuse it.
#
self.stats = prev_stat
self.digest = prev_digest
self.level = prev_level
return True
#print "changed node", self.path()
ctx.changed_nodes += 1
return False
def scan_hlink(self, ctx):
if os.name == 'nt':
# Inode numbers not reported, so we canot detect hard links.
return False
if self.stats[stat.ST_NLINK] == 1:
logging.debug("File %s has NLINK=1, can't be hard link", self.path())
return False
inode_num = self.stats[stat.ST_INO]
if ctx.inodes_db.has_key(inode_num):
self.digest = ctx.inodes_db[inode_num][:Digest.dataDigestSize()]
level_str = ctx.inodes_db[inode_num][Digest.dataDigestSize():]
self.level = IntegerEncodings.binary_decode_int_varlen(level_str)
return True
return False
def restore(self, ctx):
"""
Recreate the data from the information stored in the
backup
"""
logging.info("Restoring " + self.path())
#
# Check if the file has already been processed
# during this pass
#
if self.restore_hlink(ctx):
return
#
# No, this file is new. Create it.
#
packer = PackerStream.PackerIStream(self.backup, self.digest,
self.level)
file = open(self.path(), "wb")
for data in FileIO.read_blocks(packer, Digest.dataDigestSize()):
#print "File", self.path(), "reading digest",
# base64.b64encode(digest)
file.write(data)
file.close()
self.restore_stats()
def scan(self, ctx, prev_num):
self.compute_stats()
#
# Check if we have encountered this file during this scan already
#
ctx.num_visited_files_reporter.increment(1)
ctx.current_scanned_file_reporter.set(self.path())
if self.scan_hlink(ctx):
logging.info("File %s: HLINK" % self.path())
return
#
# Check if the file is the same as in one of the upper levels
#
if self.scan_prev(ctx, prev_num):
logging.debug("File %s: PREV" % self.path())
ctx.num_prev_files_reporter.increment(1)
return
# --- File not yet in database, process it
file_size = 0
packer = PackerStream.PackerOStream(self.backup, Container.CODE_DATA)
handle = open(self.path(), "rb")
for data in FileIO.read_blocks(handle, self.backup.get_block_size()):
packer.write(data)
file_size += len(data)
ctx.num_total_blocks_reporter.increment(1)
ctx.size_total_blocks_reporter.increment(len(data))
ctx.update_scan_status()
handle.close()
self.digest = packer.get_digest()
self.level = packer.get_level()
self.update_hlink(ctx)
logging.info("Scanned file %s size:%d new_blocks:%d new_blocks_size:%d" %
(self.path(), file_size, packer.get_num_new_blocks(),
packer.get_size_new_blocks()))
ctx.num_scanned_files_reporter.increment(1)
if packer.get_num_new_blocks() != 0:
ctx.num_new_blocks_reporter.increment(packer.get_num_new_blocks())
ctx.size_new_blocks_reporter.increment(packer.get_size_new_blocks())
ctx.num_changed_files_reporter.increment(1)
ctx.changed_files_reporter.append(self.path())
if file_size > 256 * 1024:
logging.debug("File %s is big enough to register in cndb" %
self.path())
cndb = self.backup.get_completed_nodes_db()
assert self.stats is not None
path_digest = Digest.dataDigest(self.path().encode('utf8'))
encoded = (self.digest +
IntegerEncodings.binary_encode_int_varlen(self.level) +
IntegerEncodings.binary_encode_int_varlen(self.get_type()) +
serialize_stats(self.get_stats()))
if not cndb.has_key(path_digest) or cndb[path_digest] != encoded:
cndb[path_digest] = encoded
def write_block(self, data):
digest = Digest.dataDigest(data)
if self.backup.add_block(digest, self.code, data):
self.num_new_blocks += 1
self.size_new_blocks += len(data)
if self.rec_ostream is not None:
self.rec_ostream.write(digest)
else:
self.digests.append(digest)
if (Digest.dataDigestSize() * len(self.digests) >
self.backup.get_block_size()):
self.rec_ostream = PackerOStream(self.backup, self.code_packer,
self.level + 1)
for digest in self.digests:
self.rec_ostream.write(digest)
self.digests = None
def get_digest(self):
self.flush()
if self.rec_ostream is not None:
return self.rec_ostream.get_digest()
digests_str = "".join(self.digests)
digest = Digest.dataDigest(digests_str)
self.backup.add_block(digest, self.code_packer, digests_str)
return digest
def retrieve(self, stream):
"""
Recreate the data from the information stored in the backup into the given
stream
"""
logging.info("Retrieving file " + self.path())
packer = PackerStream.PackerIStream(self.backup, self.digest,
self.level)
for data in FileIO.read_blocks(packer, Digest.dataDigestSize()):
stream.write(data)
def test(self, ctx):
"""
Test that loading the data from the storages is successful
"""
logging.info("Testing " + self.path())
packer = PackerStream.PackerIStream(self.backup, self.digest,
self.level)
for data in FileIO.read_blocks(packer, Digest.dataDigestSize()):
# Do nothing with the data, just make sure it got loaded
pass
def read_directory_entries(self, file):
while True:
node_type = Format.read_int(file)
if node_type is None:
raise StopIteration
node_name = Format.read_string(file)
node_digest = file.read(Digest.dataDigestSize())
node_level = IntegerEncodings.binary_read_int_varlen(file)
node_stat = unserialize_stats(file)
try:
node_name_decoded = unicode(node_name, 'utf8')
yield (node_type, node_name_decoded, node_stat, node_digest, node_level)
except:
logging.info("Encountered bad file name in " + self.path())
def load_epoch_data(self):
# So far, the cache is too resource-intensive.
# Avoid keeping it persistently.
return
if not self.block_longevity_data.has_key("epoch"):
self.epoch = 0
return
self.epoch = int(self.block_longevity_data["epoch"])
longevity_os = StringIO.StringIO(self.block_longevity_data["data"])
while True:
digest = longevity_os.read(Digest.dataDigestSize())
if len(digest) == 0:
break
longevity = IE.binary_read_int_varlen(longevity_os)
epoch = IE.binary_read_int_varlen(longevity_os)
self.block_longevity[digest] = longevity
self.block_epoch[digest] = epoch
def finalize(self, fs_digest, fs_level, fs_stats, num_files):
if self.readonly != False:
raise Exception("Increment already finalized")
self.attributes["fs_digest"] = fs_digest
self.attributes["fs_level"] = str(fs_level)
self.attributes["fs_stats"] = Nodes.serialize_stats(fs_stats)
self.attributes["ftime"] = str(time.time())
self.attributes["num_files"] = str(num_files)
self.readonly = True
#print "Finalizing increment", self.fs_digest
PREFIX = "Increment.%s.%s." % (self.attributes["storage_index"],
self.attributes["index"])
for key, val in self.attributes.iteritems():
self.db[PREFIX + key] = val
message = self.compute_message()
digest = Digest.dataDigest(message)
self.block_database.add_block(
digest, Container.CODE_INCREMENT_DESCRIPTOR, message)
return digest
def scan(self, ctx, prev_num, exclusion_processor):
"""Scan the node, considering data in all the previous increments
"""
logging.debug("Scanning directory " + self.path())
self.compute_stats()
ctx.num_visited_dirs_reporter.increment(1)
#
# Process data from previous increments.
#
ctx.total_nodes += 1
# prev data indexed by file, for directory scan
prev_name_data = {}
subdirs = []
#
# Fetch prev information of this node
#
# Find the digest of prev node if it exists
prev_digest = None
if prev_num is not None:
prev_type, prev_stat, prev_digest, prev_level = prev_num
if prev_type != NODE_TYPE_DIR:
prev_digest = None
else:
cndb = self.backup.get_completed_nodes_db()
path_digest = Digest.dataDigest(self.path().encode('utf8'))
if cndb.has_key(path_digest):
prev_data_is = StringIO.StringIO(cndb[path_digest])
prev_digest = prev_data_is.read(Digest.dataDigestSize())
prev_level = IntegerEncodings.binary_read_int_varlen(prev_data_is)
prev_type = IntegerEncodings.binary_read_int_varlen(prev_data_is)
#print "prev_stat_data->", base64.b64encode(prev_data_is.read())
prev_stat = unserialize_stats(prev_data_is)
if prev_type != self.get_type():
logging.debug("Node from cndb is not a directory!")
prev_digest = None
# Load the data of the prev node
if prev_digest is not None:
dir_stream = PackerStream.PackerIStream(self.backup, prev_digest,
prev_level)
for node_type, node_name, node_stat, node_digest, node_level in\
self.read_directory_entries(dir_stream):
if node_type == NODE_TYPE_DIR:
subdirs.append(node_name)
prev_name_data[node_name] = ((node_type, node_stat,
node_digest, node_level))
#
# Scan the directory
#
exclusion_processor.filter_files()
# Initialize scanning data
self.children = []
num_children = len(exclusion_processor.get_included_files() +
exclusion_processor.get_included_dirs())
processed_children = 0.0
# Scan the files in the directory
for name in exclusion_processor.get_included_files():
path = os.path.join(self.path(), name)
file_mode = os.lstat(path)[stat.ST_MODE]
if prev_name_data.has_key(name):
cur_prev = prev_name_data[name]
else:
cur_prev = None
try:
if stat.S_ISLNK(file_mode):
node = Symlink(self.backup, self, name)
node.scan(ctx, cur_prev)
self.children.append(node)
elif stat.S_ISREG(file_mode):
node = File(self.backup, self, name)
node.scan(ctx, cur_prev)
self.children.append(node)
else:
ctx.unrecognized_files_reporter.append(path)
logging.info("Ignoring unrecognized file type " + path)
except OSError:
logging.info("OSError accessing " + path)
ctx.oserror_files_reporter.append(path)
# traceback.print_exc()
except IOError, (errno, strerror):
logging.info("IOError %s accessing '%s' %s" % (errno, strerror, path))
ctx.ioerror_files_reporter.append(path)
# traceback.print_exc()
finally:
ctx.num_scanned_dirs_reporter.increment(1)
if num_new_blocks != 0:
ctx.num_new_blocks_reporter.increment(num_new_blocks)
ctx.size_new_blocks_reporter.increment(size_new_blocks)
ctx.num_changed_dirs_reporter.increment(1)
ctx.changed_dirs_reporter.append(self.path())
self.children = None
#
# Update the current dir in completed_nodes_db
#
cndb = self.backup.get_completed_nodes_db()
for subdir in subdirs:
subdir_path = os.path.join(self.path(), subdir)
subdir_path_digest = Digest.dataDigest(subdir_path.encode('utf8'))
if cndb.has_key(subdir_path_digest):
del cndb[subdir_path_digest]
if self.stats is not None:
# Stats are empty for the root node, but we don't want to store
# it in the cndb, because at this point we're already done with the
# increment anyway
digest = Digest.dataDigest(self.path().encode('utf8'))
encoded = (self.digest +
IntegerEncodings.binary_encode_int_varlen(self.level) +
IntegerEncodings.binary_encode_int_varlen(self.get_type()) +
serialize_stats(self.get_stats()))
if not cndb.has_key(digest) or cndb[digest] != encoded:
cndb[digest] = encoded
def next(self):
digest = self.block_istream.read(Digest.dataDigestSize())
if len(digest) == 0:
raise StopIteration
return digest
def read_block(self):
digest = self.digest_stream.read(Digest.dataDigestSize())
if len(digest) == 0:
return ""
return self.backup.load_block(digest)
