Number = IntegerConstraint(8) # 2**(8*8) == 16EiB ~= 18e18 ~= 18 exabytes
Offset = Number
ReadSize = int # the 'int' constraint is 2**31 == 2Gib -- large files are processed in not-so-large increments
-WriteEnablerSecret = Hash # used to protect mutable bucket modifications
-LeaseRenewSecret = Hash # used to protect bucket lease renewal requests
-LeaseCancelSecret = Hash # used to protect bucket lease cancellation requests
-
-class RIStubClient(RemoteInterface):
- """Each client publishes a service announcement for a dummy object called
- the StubClient. This object doesn't actually offer any services, but the
- announcement helps the Introducer keep track of which clients are
- subscribed (so the grid admin can keep track of things like the size of
- the grid and the client versions in use. This is the (empty)
- RemoteInterface for the StubClient."""
+WriteEnablerSecret = Hash # used to protect mutable share modifications
+LeaseRenewSecret = Hash # used to protect lease renewal requests
+LeaseCancelSecret = Hash # was used to protect lease cancellation requests
+
class RIBucketWriter(RemoteInterface):
""" Objects of this kind live on the server side. """
"""
return None
+
class RIBucketReader(RemoteInterface):
def read(offset=Offset, length=ReadSize):
return ShareData
failures. I will record their concern so that my operator can
manually inspect the shares in question. I return None.
- This is a wrapper around RIStorageServer.advise_corrupt_share(),
- which is tied to a specific share, and therefore does not need the
+ This is a wrapper around RIStorageServer.advise_corrupt_share()
+ that is tied to a specific share, and therefore does not need the
extra share-identifying arguments. Please see that method for full
documentation.
"""
+
TestVector = ListOf(TupleOf(Offset, ReadSize, str, str))
# elements are (offset, length, operator, specimen)
# operator is one of "lt, le, eq, ne, ge, gt"
ReadData = ListOf(ShareData)
# returns data[offset:offset+length] for each element of TestVector
+
class RIStorageServer(RemoteInterface):
__remote_name__ = "RIStorageServer.tahoe.allmydata.com"
This secret is generated by the client and
stored for later comparison by the server. Each
server is given a different secret.
- @param cancel_secret: Like renew_secret, but protects bucket decref.
+ @param cancel_secret: This no longer allows lease cancellation, but
+ must still be a unique value identifying the
+ lease. XXX stop relying on it to be unique.
@param canary: If the canary is lost before close(), the bucket is
deleted.
@return: tuple of (alreadygot, allocated), where alreadygot is what we
For mutable shares, if the given renew_secret does not match an
existing lease, IndexError will be raised with a note listing the
server-nodeids on the existing leases, so leases on migrated shares
- can be renewed or cancelled. For immutable shares, IndexError
- (without the note) will be raised.
+ can be renewed. For immutable shares, IndexError (without the note)
+ will be raised.
"""
return Any()
tw_vectors=TestAndWriteVectorsForShares,
r_vector=ReadVector,
):
- """General-purpose test-and-set operation for mutable slots. Perform
- a bunch of comparisons against the existing shares. If they all pass,
- then apply a bunch of write vectors to those shares. Then use the
- read vectors to extract data from all the shares and return the data.
+ """
+ General-purpose test-read-and-set operation for mutable slots:
+ (1) For submitted shnums, compare the test vectors against extant
+ shares, or against an empty share for shnums that do not exist.
+ (2) Use the read vectors to extract "old data" from extant shares.
+ (3) If all tests in (1) passed, then apply the write vectors
+ (possibly creating new shares).
+ (4) Return whether the tests passed, and the "old data", which does
+ not include any modifications made by the writes.
+
+ The operation does not interleave with other operations on the same
+ shareset.
This method is, um, large. The goal is to allow clients to update all
the shares associated with a mutable file in a single round trip.
This secret is generated by the client and
stored for later comparison by the server. Each
server is given a different secret.
- @param cancel_secret: Like renew_secret, but protects bucket decref.
+ @param cancel_secret: This no longer allows lease cancellation, but
+ must still be a unique value identifying the
+ lease. XXX stop relying on it to be unique.
The 'secrets' argument is a tuple of (write_enabler, renew_secret,
cancel_secret). The first is required to perform any write. The
Each share can have a separate test vector (i.e. a list of
comparisons to perform). If all vectors for all shares pass, then all
writes for all shares are recorded. Each comparison is a 4-tuple of
- (offset, length, operator, specimen), which effectively does a bool(
- (read(offset, length)) OPERATOR specimen ) and only performs the
- write if all these evaluate to True. Basic test-and-set uses 'eq'.
+ (offset, length, operator, specimen), which effectively does a
+ bool( (read(offset, length)) OPERATOR specimen ) and only performs
+ the write if all these evaluate to True. Basic test-and-set uses 'eq'.
Write-if-newer uses a seqnum and (offset, length, 'lt', specimen).
Write-if-same-or-newer uses 'le'.
The write vector will be applied to the given share, expanding it if
necessary. A write vector applied to a share number that did not
- exist previously will cause that share to be created.
+ exist previously will cause that share to be created. Write vectors
+ must not overlap (if they do, this will either cause an error or
+ apply them in an unspecified order). Duplicate write vectors, with
+ the same offset and data, are currently tolerated but are not
+ desirable.
In Tahoe-LAFS v1.8.3 or later (except 1.9.0a1), if you send a write
vector whose offset is beyond the end of the current data, the space
than the size of the data after applying all write vectors.
The read vector is used to extract data from all known shares,
- *before* any writes have been applied. The same vector is used for
- all shares. This captures the state that was tested by the test
- vector.
+ *before* any writes have been applied. The same read vector is used
+ for all shares. This captures the state that was tested by the test
+ vector, for extant shares.
This method returns two values: a boolean and a dict. The boolean is
True if the write vectors were applied, False if not. The dict is
Note that the nodeid here is encoded using the same base32 encoding
used by Foolscap and allmydata.util.idlib.nodeid_b2a().
-
"""
return TupleOf(bool, DictOf(int, ReadData))
(binary) storage index string, and 'shnum' is the integer share
number. 'reason' is a human-readable explanation of the problem,
probably including some expected hash values and the computed ones
- which did not match. Corruption advisories for mutable shares should
+ that did not match. Corruption advisories for mutable shares should
include a hash of the public key (the same value that appears in the
mutable-file verify-cap), since the current share format does not
store that on disk.
"""
+
class IStorageBucketWriter(Interface):
"""
Objects of this kind live on the client side.
"""
- def put_block(segmentnum=int, data=ShareData):
- """@param data: For most segments, this data will be 'blocksize'
- bytes in length. The last segment might be shorter.
- @return: a Deferred that fires (with None) when the operation completes
- """
-
- def put_plaintext_hashes(hashes=ListOf(Hash)):
+ def put_block(segmentnum, data):
"""
+ @param segmentnum=int
+ @param data=ShareData: For most segments, this data will be 'blocksize'
+ bytes in length. The last segment might be shorter.
@return: a Deferred that fires (with None) when the operation completes
"""
- def put_crypttext_hashes(hashes=ListOf(Hash)):
+ def put_crypttext_hashes(hashes):
"""
+ @param hashes=ListOf(Hash)
@return: a Deferred that fires (with None) when the operation completes
"""
- def put_block_hashes(blockhashes=ListOf(Hash)):
+ def put_block_hashes(blockhashes):
"""
+ @param blockhashes=ListOf(Hash)
@return: a Deferred that fires (with None) when the operation completes
"""
- def put_share_hashes(sharehashes=ListOf(TupleOf(int, Hash))):
+ def put_share_hashes(sharehashes):
"""
+ @param sharehashes=ListOf(TupleOf(int, Hash))
@return: a Deferred that fires (with None) when the operation completes
"""
- def put_uri_extension(data=URIExtensionData):
+ def put_uri_extension(data):
"""This block of data contains integrity-checking information (hashes
of plaintext, crypttext, and shares), as well as encoding parameters
that are necessary to recover the data. This is a serialized dict
assert re.match(r'^[a-zA-Z_\-]+$', k)
write(k + ':' + netstring(dict[k]))
+ @param data=URIExtensionData
@return: a Deferred that fires (with None) when the operation completes
"""
@return: a Deferred that fires (with None) when the operation completes
"""
-class IStorageBucketReader(Interface):
- def get_block_data(blocknum=int, blocksize=int, size=int):
+class IStorageBucketReader(Interface):
+ def get_block_data(blocknum, blocksize, size):
"""Most blocks will be the same size. The last block might be shorter
than the others.
+ @param blocknum=int
+ @param blocksize=int
+ @param size=int
@return: ShareData
"""
@return: ListOf(Hash)
"""
- def get_block_hashes(at_least_these=SetOf(int)):
+ def get_block_hashes(at_least_these=()):
"""
+ @param at_least_these=SetOf(int)
@return: ListOf(Hash)
"""
- def get_share_hashes(at_least_these=SetOf(int)):
+ def get_share_hashes():
"""
@return: ListOf(TupleOf(int, Hash))
"""
@return: URIExtensionData
"""
+
class IStorageBroker(Interface):
def get_servers_for_psi(peer_selection_index):
"""
public attributes::
service_name: the type of service provided, like 'storage'
- announcement_time: when we first heard about this service
last_connect_time: when we last established a connection
last_loss_time: when we last lost a connection
remote_host: the IAddress, if connected, otherwise None
This method is intended for monitoring interfaces, such as a web page
- which describes connecting and connected peers.
+ that describes connecting and connected peers.
"""
def get_all_peerids():
"""
+class IDisplayableServer(Interface):
+ def get_nickname():
+ pass
+
+ def get_name():
+ pass
+
+ def get_longname():
+ pass
+
+
+class IServer(IDisplayableServer):
+ """I live in the client, and represent a single server."""
+ def start_connecting(tub, trigger_cb):
+ pass
+
+ def get_rref():
+ """Once a server is connected, I return a RemoteReference.
+ Before a server is connected for the first time, I return None.
+
+ Note that the rref I return will start producing DeadReferenceErrors
+ once the connection is lost.
+ """
+
+
class IMutableSlotWriter(Interface):
"""
The interface for a writer around a mutable slot on a remote server.
"""
- def set_checkstring(checkstring, *args):
+ def set_checkstring(seqnum_or_checkstring, root_hash=None, salt=None):
"""
Set the checkstring that I will pass to the remote server when
writing.
Add the encrypted private key to the share.
"""
- def put_blockhashes(blockhashes=list):
+ def put_blockhashes(blockhashes):
"""
+ @param blockhashes=list
Add the block hash tree to the share.
"""
- def put_sharehashes(sharehashes=dict):
+ def put_sharehashes(sharehashes):
"""
+ @param sharehashes=dict
Add the share hash chain to the share.
"""
# TODO: rename to get_read_cap()
def get_readonly():
- """Return another IURI instance, which represents a read-only form of
+ """Return another IURI instance that represents a read-only form of
this one. If is_readonly() is True, this returns self."""
def get_verify_cap():
"""Return a string of printable ASCII characters, suitable for
passing into init_from_string."""
+
class IVerifierURI(Interface, IURI):
def init_from_string(uri):
"""Accept a string (as created by my to_string() method) and populate
"""Return a string of printable ASCII characters, suitable for
passing into init_from_string."""
+
class IDirnodeURI(Interface):
- """I am a URI which represents a dirnode."""
+ """I am a URI that represents a dirnode."""
+
class IFileURI(Interface):
- """I am a URI which represents a filenode."""
+ """I am a URI that represents a filenode."""
def get_size():
"""Return the length (in bytes) of the file that I represent."""
+
class IImmutableFileURI(IFileURI):
pass
class IMutableFileURI(Interface):
- """I am a URI which represents a mutable filenode."""
- def get_extension_params():
- """Return the extension parameters in the URI"""
-
- def set_extension_params():
- """Set the extension parameters that should be in the URI"""
+ pass
class IDirectoryURI(Interface):
pass
class IReadonlyDirectoryURI(Interface):
pass
+
class CapConstraintError(Exception):
"""A constraint on a cap was violated."""
the last byte has been given to it, or because the consumer threw an
exception during write(), possibly because it no longer wants to
receive data). The portion downloaded will start at 'offset' and
- contain 'size' bytes (or the remainder of the file if size==None).
+ contain 'size' bytes (or the remainder of the file if size==None). It
+ is an error to read beyond the end of the file: callers must use
+ get_size() and clip any non-default offset= and size= parameters. It
+ is permissible to read zero bytes.
The consumer will be used in non-streaming mode: an IPullProducer
will be attached to it.
writer-visible data using this writekey.
"""
- # TODO: Can this be overwrite instead of replace?
- def replace(new_contents):
+ def overwrite(new_contents):
"""Replace the contents of the mutable file, provided that no other
node has published (or is attempting to publish, concurrently) a
newer version of the file than this one.
data this node represents.
"""
+
class IFileNode(IFilesystemNode):
- """I am a node which represents a file: a sequence of bytes. I am not a
+ """I am a node that represents a file: a sequence of bytes. I am not a
container, like IDirectoryNode."""
def get_best_readable_version():
"""Return a Deferred that fires with an IReadable for the 'best'
multiple versions of a file present in the grid, some of which might be
unrecoverable (i.e. have fewer than 'k' shares). These versions are
loosely ordered: each has a sequence number and a hash, and any version
- with seqnum=N was uploaded by a node which has seen at least one version
+ with seqnum=N was uploaded by a node that has seen at least one version
with seqnum=N-1.
The 'servermap' (an instance of IMutableFileServerMap) is used to
as a guide to where the shares are located.
I return a Deferred that fires with the requested contents, or
- errbacks with UnrecoverableFileError. Note that a servermap which was
+ errbacks with UnrecoverableFileError. Note that a servermap that was
updated with MODE_ANYTHING or MODE_READ may not know about shares for
all versions (those modes stop querying servers as soon as they can
fulfil their goals), so you may want to use MODE_CHECK (which checks
def get_version():
"""Returns the mutable file protocol version."""
+
class NotEnoughSharesError(Exception):
"""Download was unable to get enough shares"""
"""Upload was unable to satisfy 'servers_of_happiness'"""
class UnableToFetchCriticalDownloadDataError(Exception):
- """I was unable to fetch some piece of critical data which is supposed to
+ """I was unable to fetch some piece of critical data that is supposed to
be identically present in all shares."""
class NoServersError(Exception):
exists, and overwrite= was set to False."""
class NoSuchChildError(Exception):
- """A directory node was asked to fetch a child which does not exist."""
+ """A directory node was asked to fetch a child that does not exist."""
+ def __str__(self):
+ # avoid UnicodeEncodeErrors when converting to str
+ return self.__repr__()
class ChildOfWrongTypeError(Exception):
"""An operation was attempted on a child of the wrong type (file or directory)."""
+
class IDirectoryNode(IFilesystemNode):
"""I represent a filesystem node that is a container, with a
name-to-child mapping, holding the tahoe equivalent of a directory. All
is a file, or if must_be_file is True and the child is a directory,
I raise ChildOfWrongTypeError."""
- def create_subdirectory(name, initial_children={}, overwrite=True, metadata=None):
+ def create_subdirectory(name, initial_children={}, overwrite=True,
+ mutable=True, mutable_version=None, metadata=None):
"""I create and attach a directory at the given name. The new
directory can be empty, or it can be populated with children
according to 'initial_children', which takes a dictionary in the same
takes several minutes of 100% CPU for ~1700 directories).
"""
+
class ICodecEncoder(Interface):
def set_params(data_size, required_shares, max_shares):
"""Set up the parameters of this encoder.
if you initially thought you were going to use 10 peers, started
encoding, and then two of the peers dropped out: you could use
desired_share_ids= to skip the work (both memory and CPU) of
- producing shares for the peers which are no longer available.
+ producing shares for the peers that are no longer available.
"""
if you initially thought you were going to use 10 peers, started
encoding, and then two of the peers dropped out: you could use
desired_share_ids= to skip the work (both memory and CPU) of
- producing shares for the peers which are no longer available.
+ producing shares for the peers that are no longer available.
For each call, encode() will return a Deferred that fires with two
lists, one containing shares and the other containing the shareids.
required to be of the same length. The i'th element of their_shareids
is required to be the shareid of the i'th buffer in some_shares.
- This returns a Deferred which fires with a sequence of buffers. This
+ This returns a Deferred that fires with a sequence of buffers. This
sequence will contain all of the segments of the original data, in
order. The sum of the lengths of all of the buffers will be the
'data_size' value passed into the original ICodecEncode.set_params()
call.
"""
+
class IEncoder(Interface):
"""I take an object that provides IEncryptedUploadable, which provides
encrypted data, and a list of shareholders. I then encode, hash, and
"""Specify the number of bytes that will be encoded. This must be
peformed before get_serialized_params() can be called.
"""
- def set_params(params):
- """Override the default encoding parameters. 'params' is a tuple of
- (k,d,n), where 'k' is the number of required shares, 'd' is the
- servers_of_happiness, and 'n' is the total number of shares that will
- be created.
-
- Encoding parameters can be set in three ways. 1: The Encoder class
- provides defaults (3/7/10). 2: the Encoder can be constructed with
- an 'options' dictionary, in which the
- needed_and_happy_and_total_shares' key can be a (k,d,n) tuple. 3:
- set_params((k,d,n)) can be called.
-
- If you intend to use set_params(), you must call it before
- get_share_size or get_param are called.
- """
def set_encrypted_uploadable(u):
"""Provide a source of encrypted upload data. 'u' must implement
sufficient to construct the read cap.
"""
+
class IDecoder(Interface):
"""I take a list of shareholders and some setup information, then
download, validate, decode, and decrypt data from them, writing the
complete.
"""
+
class IDownloadTarget(Interface):
# Note that if the IDownloadTarget is also an IConsumer, the downloader
# will register itself as a producer. This allows the target to invoke
def write(data):
"""Output some data to the target."""
+
def close():
"""Inform the target that there is no more data to be written."""
+
def fail(why):
"""fail() is called to indicate that the download has failed. 'why'
is a Failure object indicating what went wrong. No further methods
will be invoked on the IDownloadTarget after fail()."""
+
def register_canceller(cb):
"""The CiphertextDownloader uses this to register a no-argument function
that the target can call to cancel the download. Once this canceller
is invoked, no further calls to write() or close() will be made."""
+
def finish():
"""When the CiphertextDownloader is done, this finish() function will be
called. Whatever it returns will be returned to the invoker of
Downloader.download.
"""
+
class IDownloader(Interface):
def download(uri, target):
"""Perform a CHK download, sending the data to the given target.
Returns a Deferred that fires (with the results of target.finish)
when the download is finished, or errbacks if something went wrong."""
+
class IEncryptedUploadable(Interface):
def set_upload_status(upload_status):
"""Provide an IUploadStatus object that should be filled with status
resuming an interrupted upload (where we need to compute the
plaintext hashes, but don't need the redundant encrypted data)."""
- def get_plaintext_hashtree_leaves(first, last, num_segments):
- """OBSOLETE; Get the leaf nodes of a merkle hash tree over the
- plaintext segments, i.e. get the tagged hashes of the given segments.
- The segment size is expected to be generated by the
- IEncryptedUploadable before any plaintext is read or ciphertext
- produced, so that the segment hashes can be generated with only a
- single pass.
-
- This returns a Deferred which fires with a sequence of hashes, using:
-
- tuple(segment_hashes[first:last])
-
- 'num_segments' is used to assert that the number of segments that the
- IEncryptedUploadable handled matches the number of segments that the
- encoder was expecting.
-
- This method must not be called until the final byte has been read
- from read_encrypted(). Once this method is called, read_encrypted()
- can never be called again.
- """
-
- def get_plaintext_hash():
- """OBSOLETE; Get the hash of the whole plaintext.
-
- This returns a Deferred which fires with a tagged SHA-256 hash of the
- whole plaintext, obtained from hashutil.plaintext_hash(data).
- """
-
def close():
"""Just like IUploadable.close()."""
+
class IUploadable(Interface):
def set_upload_status(upload_status):
"""Provide an IUploadStatus object that should be filled with status
be used to encrypt the data. The key will also be hashed to derive
the StorageIndex.
- Uploadables which want to achieve convergence should hash their file
+ Uploadables that want to achieve convergence should hash their file
contents and the serialized_encoding_parameters to form the key
(which of course requires a full pass over the data). Uploadables can
use the upload.ConvergentUploadMixin class to achieve this
automatically.
- Uploadables which do not care about convergence (or do not wish to
+ Uploadables that do not care about convergence (or do not wish to
make multiple passes over the data) can simply return a
strongly-random 16 byte string.
def read(length):
"""Return a Deferred that fires with a list of strings (perhaps with
- only a single element) which, when concatenated together, contain the
+ only a single element) that, when concatenated together, contain the
next 'length' bytes of data. If EOF is near, this may provide fewer
than 'length' bytes. The total number of bytes provided by read()
before it signals EOF must equal the size provided by get_size().
def read(length):
"""
- Returns a list of strings which, when concatenated, are the next
+ Returns a list of strings that, when concatenated, are the next
length bytes of the file, or fewer if there are fewer bytes
between the current location and the end of the file.
"""
the uploadable may be closed.
"""
+
class IUploadResults(Interface):
- """I am returned by upload() methods. I contain a number of public
- attributes which can be read to determine the results of the upload. Some
- of these are functional, some are timing information. All of these may be
- None.
+ """I am returned by immutable upload() methods and contain the results of
+ the upload.
- .file_size : the size of the file, in bytes
- .uri : the CHK read-cap for the file
- .ciphertext_fetched : how many bytes were fetched by the helper
- .sharemap: dict mapping share identifier to set of serverids
- (binary strings). This indicates which servers were given
- which shares. For immutable files, the shareid is an
- integer (the share number, from 0 to N-1). For mutable
- files, it is a string of the form 'seq%d-%s-sh%d',
- containing the sequence number, the roothash, and the
- share number.
- .servermap : dict mapping server peerid to a set of share numbers
- .timings : dict of timing information, mapping name to seconds (float)
- total : total upload time, start to finish
- storage_index : time to compute the storage index
- peer_selection : time to decide which peers will be used
- contacting_helper : initial helper query to upload/no-upload decision
- existence_check : helper pre-upload existence check
- helper_total : initial helper query to helper finished pushing
- cumulative_fetch : helper waiting for ciphertext requests
- total_fetch : helper start to last ciphertext response
- cumulative_encoding : just time spent in zfec
- cumulative_sending : just time spent waiting for storage servers
- hashes_and_close : last segment push to shareholder close
- total_encode_and_push : first encode to shareholder close
+ Note that some of my methods return empty values (0 or an empty dict)
+ when called for non-distributed LIT files."""
+
+ def get_file_size():
+ """Return the file size, in bytes."""
+
+ def get_uri():
+ """Return the (string) URI of the object uploaded, a CHK readcap."""
+
+ def get_ciphertext_fetched():
+ """Return the number of bytes fetched by the helpe for this upload,
+ or 0 if the helper did not need to fetch any bytes (or if there was
+ no helper)."""
+
+ def get_preexisting_shares():
+ """Return the number of shares that were already present in the grid."""
+
+ def get_pushed_shares():
+ """Return the number of shares that were uploaded."""
+
+ def get_sharemap():
+ """Return a dict mapping share identifier to set of IServer
+ instances. This indicates which servers were given which shares. For
+ immutable files, the shareid is an integer (the share number, from 0
+ to N-1). For mutable files, it is a string of the form
+ 'seq%d-%s-sh%d', containing the sequence number, the roothash, and
+ the share number."""
+
+ def get_servermap():
+ """Return dict mapping IServer instance to a set of share numbers."""
+
+ def get_timings():
+ """Return dict of timing information, mapping name to seconds. All
+ times are floats:
+ total : total upload time, start to finish
+ storage_index : time to compute the storage index
+ peer_selection : time to decide which peers will be used
+ contacting_helper : initial helper query to upload/no-upload decision
+ helper_total : initial helper query to helper finished pushing
+ cumulative_fetch : helper waiting for ciphertext requests
+ total_fetch : helper start to last ciphertext response
+ cumulative_encoding : just time spent in zfec
+ cumulative_sending : just time spent waiting for storage servers
+ hashes_and_close : last segment push to shareholder close
+ total_encode_and_push : first encode to shareholder close
+ """
+
+ def get_uri_extension_data():
+ """Return the dict of UEB data created for this file."""
+
+ def get_verifycapstr():
+ """Return the (string) verify-cap URI for the uploaded object."""
- """
class IDownloadResults(Interface):
"""I am created internally by download() methods. I contain a number of
- public attributes which contain details about the download process.::
+ public attributes that contain details about the download process.::
.file_size : the size of the file, in bytes
.servers_used : set of server peerids that were used during download
cumulative_decode : just time spent in zfec
cumulative_decrypt : just time spent in decryption
total : total download time, start to finish
- fetch_per_server : dict of peerid to list of per-segment fetch times
-
+ fetch_per_server : dict of server to list of per-segment fetch times
"""
+
class IUploader(Interface):
def upload(uploadable):
"""Upload the file. 'uploadable' must impement IUploadable. This
- returns a Deferred which fires with an IUploadResults instance, from
+ returns a Deferred that fires with an IUploadResults instance, from
which the URI of the file can be obtained as results.uri ."""
- def upload_ssk(write_capability, new_version, uploadable):
- """TODO: how should this work?"""
class ICheckable(Interface):
def check(monitor, verify=False, add_lease=False):
kind of lease that is obtained (which account number to claim, etc).
TODO: any problems seen during checking will be reported to the
- health-manager.furl, a centralized object which is responsible for
+ health-manager.furl, a centralized object that is responsible for
figuring out why files are unhealthy so corrective action can be
taken.
"""
will be put in the check-and-repair results. The Deferred will not
fire until the repair is complete.
- This returns a Deferred which fires with an instance of
+ This returns a Deferred that fires with an instance of
ICheckAndRepairResults."""
+
class IDeepCheckable(Interface):
def start_deep_check(verify=False, add_lease=False):
"""Check upon the health of me and everything I can reach.
failure.
"""
+
class ICheckResults(Interface):
"""I contain the detailed results of a check/verify operation.
"""
def get_storage_index():
"""Return a string with the (binary) storage index."""
+
def get_storage_index_string():
"""Return a string with the (printable) abbreviated storage index."""
+
def get_uri():
"""Return the (string) URI of the object that was checked."""
not. Unrecoverable files are obviously unhealthy. Non-distributed LIT
files always return True."""
- def needs_rebalancing():
- """Return a boolean, True if the file/dir's reliability could be
- improved by moving shares to new servers. Non-distributed LIT files
- always return False."""
-
-
- def get_data():
- """Return a dictionary that describes the state of the file/dir. LIT
- files always return an empty dictionary. Normal files and directories
- return a dictionary with the following keys (note that these use
- binary strings rather than base32-encoded ones) (also note that for
- mutable files, these counts are for the 'best' version):
-
- count-shares-good: the number of distinct good shares that were found
- count-shares-needed: 'k', the number of shares required for recovery
- count-shares-expected: 'N', the number of total shares generated
- count-good-share-hosts: the number of distinct storage servers with
- good shares. If this number is less than
- count-shares-good, then some shares are
- doubled up, increasing the correlation of
- failures. This indicates that one or more
- shares should be moved to an otherwise unused
- server, if one is available.
- count-corrupt-shares: the number of shares with integrity failures
- list-corrupt-shares: a list of 'share locators', one for each share
- that was found to be corrupt. Each share
- locator is a list of (serverid, storage_index,
- sharenum).
- count-incompatible-shares: the number of shares which are of a share
- format unknown to this checker
- list-incompatible-shares: a list of 'share locators', one for each
- share that was found to be of an unknown
- format. Each share locator is a list of
- (serverid, storage_index, sharenum).
- servers-responding: list of (binary) storage server identifiers,
- one for each server which responded to the share
- query (even if they said they didn't have
- shares, and even if they said they did have
- shares but then didn't send them when asked, or
- dropped the connection, or returned a Failure,
- and even if they said they did have shares and
- sent incorrect ones when asked)
- sharemap: dict mapping share identifier to list of serverids
- (binary strings). This indicates which servers are holding
- which shares. For immutable files, the shareid is an
- integer (the share number, from 0 to N-1). For mutable
- files, it is a string of the form 'seq%d-%s-sh%d',
- containing the sequence number, the roothash, and the
- share number.
-
- The following keys are most relevant for mutable files, but immutable
- files will provide sensible values too::
-
- count-wrong-shares: the number of shares for versions other than the
- 'best' one (which is defined as being the
- recoverable version with the highest sequence
- number, then the highest roothash). These are
- either leftover shares from an older version
- (perhaps on a server that was offline when an
- update occurred), shares from an unrecoverable
- newer version, or shares from an alternate
- current version that results from an
- uncoordinated write collision. For a healthy
- file, this will equal 0.
-
- count-recoverable-versions: the number of recoverable versions of
- the file. For a healthy file, this will
- equal 1.
-
- count-unrecoverable-versions: the number of unrecoverable versions
- of the file. For a healthy file, this
- will be 0.
+ # the following methods all return None for non-distributed LIT files
- """
+ def get_happiness():
+ """Return the happiness count of the file."""
+
+ def get_encoding_needed():
+ """Return 'k', the number of shares required for recovery."""
+
+ def get_encoding_expected():
+ """Return 'N', the number of total shares generated."""
+
+ def get_share_counter_good():
+ """Return the number of distinct good shares that were found. For
+ mutable files, this counts shares for the 'best' version."""
+
+ def get_share_counter_wrong():
+ """For mutable files, return the number of shares for versions other
+ than the 'best' one (which is defined as being the recoverable
+ version with the highest sequence number, then the highest roothash).
+ These are either leftover shares from an older version (perhaps on a
+ server that was offline when an update occurred), shares from an
+ unrecoverable newer version, or shares from an alternate current
+ version that results from an uncoordinated write collision. For a
+ healthy file, this will equal 0. For immutable files, this will
+ always equal 0."""
+
+ def get_corrupt_shares():
+ """Return a list of 'share locators', one for each share that was
+ found to be corrupt (integrity failure). Each share locator is a list
+ of (IServer, storage_index, sharenum)."""
+
+ def get_incompatible_shares():
+ """Return a list of 'share locators', one for each share that was
+ found to be of an unknown format. Each share locator is a list of
+ (IServer, storage_index, sharenum)."""
+
+ def get_servers_responding():
+ """Return a list of IServer objects, one for each server that
+ responded to the share query (even if they said they didn't have
+ shares, and even if they said they did have shares but then didn't
+ send them when asked, or dropped the connection, or returned a
+ Failure, and even if they said they did have shares and sent
+ incorrect ones when asked)"""
+
+ def get_host_counter_good_shares():
+ """Return the number of distinct storage servers with good shares. If
+ this number is less than get_share_counters()[good], then some shares
+ are doubled up, increasing the correlation of failures. This
+ indicates that one or more shares should be moved to an otherwise
+ unused server, if one is available.
+ """
+
+ def get_version_counter_recoverable():
+ """Return the number of recoverable versions of the file. For a
+ healthy file, this will equal 1."""
+
+ def get_version_counter_unrecoverable():
+ """Return the number of unrecoverable versions of the file. For a
+ healthy file, this will be 0."""
+
+ def get_sharemap():
+ """Return a dict mapping share identifier to list of IServer objects.
+ This indicates which servers are holding which shares. For immutable
+ files, the shareid is an integer (the share number, from 0 to N-1).
+ For mutable files, it is a string of the form 'seq%d-%s-sh%d',
+ containing the sequence number, the roothash, and the share number."""
def get_summary():
"""Return a string with a brief (one-line) summary of the results."""
def get_report():
"""Return a list of strings with more detailed results."""
+
class ICheckAndRepairResults(Interface):
"""I contain the detailed results of a check/verify/repair operation.
def get_storage_index():
"""Return a string with the (binary) storage index."""
+
def get_storage_index_string():
"""Return a string with the (printable) abbreviated storage index."""
+
def get_repair_attempted():
"""Return a boolean, True if a repair was attempted. We might not
attempt to repair the file because it was healthy, or healthy enough
(i.e. some shares were missing but not enough to exceed some
threshold), or because we don't know how to repair this object."""
+
def get_repair_successful():
"""Return a boolean, True if repair was attempted and the file/dir
was fully healthy afterwards. False if no repair was attempted or if
a repair attempt failed."""
+
def get_pre_repair_results():
"""Return an ICheckResults instance that describes the state of the
file/dir before any repair was attempted."""
+
def get_post_repair_results():
"""Return an ICheckResults instance that describes the state of the
file/dir after any repair was attempted. If no repair was attempted,
def get_root_storage_index_string():
"""Return the storage index (abbreviated human-readable string) of
the first object checked."""
+
def get_counters():
"""Return a dictionary with the following keys::
"""
def get_corrupt_shares():
- """Return a set of (serverid, storage_index, sharenum) for all shares
- that were found to be corrupt. Both serverid and storage_index are
- binary.
- """
+ """Return a set of (IServer, storage_index, sharenum) for all shares
+ that were found to be corrupt. storage_index is binary."""
+
def get_all_results():
"""Return a dictionary mapping pathname (a tuple of strings, ready to
be slash-joined) to an ICheckResults instance, one for each object
"""Return a dictionary with the same keys as
IDirectoryNode.deep_stats()."""
+
class IDeepCheckAndRepairResults(Interface):
"""I contain the results of a deep-check-and-repair operation.
def get_root_storage_index_string():
"""Return the storage index (abbreviated human-readable string) of
the first object checked."""
+
def get_counters():
"""Return a dictionary with the following keys::
IDirectoryNode.deep_stats()."""
def get_corrupt_shares():
- """Return a set of (serverid, storage_index, sharenum) for all shares
- that were found to be corrupt before any repair was attempted. Both
- serverid and storage_index are binary.
+ """Return a set of (IServer, storage_index, sharenum) for all shares
+ that were found to be corrupt before any repair was attempted.
+ storage_index is binary.
"""
def get_remaining_corrupt_shares():
- """Return a set of (serverid, storage_index, sharenum) for all shares
- that were found to be corrupt after any repair was completed. Both
- serverid and storage_index are binary. These are shares that need
- manual inspection and probably deletion.
+ """Return a set of (IServer, storage_index, sharenum) for all shares
+ that were found to be corrupt after any repair was completed.
+ storage_index is binary. These are shares that need manual inspection
+ and probably deletion.
"""
def get_all_results():
"""Return a dictionary mapping pathname (a tuple of strings, ready to
return d
"""
+
class IRepairResults(Interface):
"""I contain the results of a repair operation."""
- def get_successful(self):
+ def get_successful():
"""Returns a boolean: True if the repair made the file healthy, False
if not. Repair failure generally indicates a file that has been
damaged beyond repair."""
DirectoryNode.
"""
+
class INodeMaker(Interface):
"""The NodeMaker is used to create IFilesystemNode instances. It can
accept a filecap/dircap string and return the node right away. It can
Tahoe process will typically have a single NodeMaker, but unit tests may
create simplified/mocked forms for testing purposes.
"""
- def create_from_cap(writecap, readcap=None, **kwargs):
+
+ def create_from_cap(writecap, readcap=None, deep_immutable=False, name=u"<unknown name>"):
"""I create an IFilesystemNode from the given writecap/readcap. I can
only provide nodes for existing file/directory objects: use my other
methods to create new objects. I return synchronously."""
def create_mutable_file(contents=None, keysize=None):
- """I create a new mutable file, and return a Deferred which will fire
+ """I create a new mutable file, and return a Deferred that will fire
with the IMutableFileNode instance when it is ready. If contents= is
provided (a bytestring), it will be used as the initial contents of
the new file, otherwise the file will contain zero bytes. keysize= is
usual."""
def create_new_mutable_directory(initial_children={}):
- """I create a new mutable directory, and return a Deferred which will
+ """I create a new mutable directory, and return a Deferred that will
fire with the IDirectoryNode instance when it is ready. If
initial_children= is provided (a dict mapping unicode child name to
(childnode, metadata_dict) tuples), the directory will be populated
with those children, otherwise it will be empty."""
+
class IClientStatus(Interface):
def list_all_uploads():
- """Return a list of uploader objects, one for each upload which
+ """Return a list of uploader objects, one for each upload that
currently has an object available (tracked with weakrefs). This is
intended for debugging purposes."""
+
def list_active_uploads():
"""Return a list of active IUploadStatus objects."""
+
def list_recent_uploads():
"""Return a list of IUploadStatus objects for the most recently
started uploads."""
def list_all_downloads():
- """Return a list of downloader objects, one for each download which
+ """Return a list of downloader objects, one for each download that
currently has an object available (tracked with weakrefs). This is
intended for debugging purposes."""
+
def list_active_downloads():
"""Return a list of active IDownloadStatus objects."""
+
def list_recent_downloads():
"""Return a list of IDownloadStatus objects for the most recently
started downloads."""
+
class IUploadStatus(Interface):
def get_started():
"""Return a timestamp (float with seconds since epoch) indicating
when the operation was started."""
+
def get_storage_index():
"""Return a string with the (binary) storage index in use on this
upload. Returns None if the storage index has not yet been
calculated."""
+
def get_size():
"""Return an integer with the number of bytes that will eventually
be uploaded for this file. Returns None if the size is not yet known.
"""
def using_helper():
"""Return True if this upload is using a Helper, False if not."""
+
def get_status():
"""Return a string describing the current state of the upload
process."""
+
def get_progress():
"""Returns a tuple of floats, (chk, ciphertext, encode_and_push),
each from 0.0 to 1.0 . 'chk' describes how much progress has been
process has finished: for helper uploads this is dependent upon the
helper providing progress reports. It might be reasonable to add all
three numbers and report the sum to the user."""
+
def get_active():
"""Return True if the upload is currently active, False if not."""
+
def get_results():
"""Return an instance of UploadResults (which contains timing and
sharemap information). Might return None if the upload is not yet
finished."""
+
def get_counter():
"""Each upload status gets a unique number: this method returns that
number. This provides a handle to this particular upload, so a web
page can generate a suitable hyperlink."""
+
class IDownloadStatus(Interface):
def get_started():
"""Return a timestamp (float with seconds since epoch) indicating
when the operation was started."""
+
def get_storage_index():
"""Return a string with the (binary) storage index in use on this
download. This may be None if there is no storage index (i.e. LIT
files)."""
+
def get_size():
"""Return an integer with the number of bytes that will eventually be
retrieved for this file. Returns None if the size is not yet known.
"""
+
def using_helper():
"""Return True if this download is using a Helper, False if not."""
+
def get_status():
"""Return a string describing the current state of the download
process."""
+
def get_progress():
"""Returns a float (from 0.0 to 1.0) describing the amount of the
download that has completed. This value will remain at 0.0 until the
first byte of plaintext is pushed to the download target."""
+
def get_active():
"""Return True if the download is currently active, False if not."""
+
def get_counter():
"""Each download status gets a unique number: this method returns
that number. This provides a handle to this particular download, so a
web page can generate a suitable hyperlink."""
+
class IServermapUpdaterStatus(Interface):
pass
+
class IPublishStatus(Interface):
pass
+
class IRetrieveStatus(Interface):
pass
+
class NotCapableError(Exception):
"""You have tried to write to a read-only node."""
class BadWriteEnablerError(Exception):
pass
-class RIControlClient(RemoteInterface):
+class RIControlClient(RemoteInterface):
def wait_for_client_connections(num_clients=int):
"""Do not return until we have connections to at least NUM_CLIENTS
storage servers.
"""
- def upload_from_file_to_uri(filename=str,
- convergence=ChoiceOf(None,
- StringConstraint(2**20))):
- """Upload a file to the grid. This accepts a filename (which must be
- absolute) that points to a file on the node's local disk. The node will
- read the contents of this file, upload it to the grid, then return the
- URI at which it was uploaded. If convergence is None then a random
- encryption key will be used, else the plaintext will be hashed, then
- that hash will be mixed together with the "convergence" string to form
- the encryption key.
- """
- return URI
+ # debug stuff
- def download_from_uri_to_file(uri=URI, filename=str):
- """Download a file from the grid, placing it on the node's local disk
- at the given filename (which must be absolute[?]). Returns the
- absolute filename where the file was written."""
+ def upload_random_data_from_file(size=int, convergence=str):
return str
- # debug stuff
+ def download_to_tempfile_and_delete(uri=str):
+ return None
def get_memory_usage():
"""Return a dict describes the amount of memory currently in use. The
return DictOf(str, float)
+
UploadResults = Any() #DictOf(str, str)
+
class RIEncryptedUploadable(RemoteInterface):
__remote_name__ = "RIEncryptedUploadable.tahoe.allmydata.com"
"""
return DictOf(str, DictOf(str, ChoiceOf(float, int, long, None)))
+
class RIStatsGatherer(RemoteInterface):
__remote_name__ = "RIStatsGatherer.tahoe.allmydata.com"
"""
def provide(provider=RIStatsProvider, nickname=str):
"""
- @param provider: a stats collector instance which should be polled
+ @param provider: a stats collector instance that should be polled
periodically by the gatherer to collect stats.
@param nickname: a name useful to identify the provided client
"""
class FileTooLargeError(Exception):
pass
+
class IValidatedThingProxy(Interface):
def start():
- """ Acquire a thing and validate it. Return a deferred which is
+ """ Acquire a thing and validate it. Return a deferred that is
eventually fired with self if the thing is valid or errbacked if it
can't be acquired or validated."""
+
class InsufficientVersionError(Exception):
def __init__(self, needed, got):
self.needed = needed
self.got = got
+
def __repr__(self):
return "InsufficientVersionError(need '%s', got %s)" % (self.needed,
self.got)
projects / tahoe-lafs / tahoe-lafs.git / blobdiff