1
# Copyright (C) 2006 Canonical Ltd
3
# This program is free software; you can redistribute it and/or modify
4
# it under the terms of the GNU General Public License as published by
5
# the Free Software Foundation; either version 2 of the License, or
6
# (at your option) any later version.
8
# This program is distributed in the hope that it will be useful,
9
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
# GNU General Public License for more details.
13
# You should have received a copy of the GNU General Public License
14
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
17
"""On-disk mutex protecting a resource
19
bzr on-disk objects are locked by the existence of a directory with a
20
particular name within the control directory. We use this rather than OS
21
internal locks (such as flock etc) because they can be seen across all
22
transports, including http.
24
Objects can be read if there is only physical read access; therefore
25
readers can never be required to create a lock, though they will
26
check whether a writer is using the lock. Writers can't detect
27
whether anyone else is reading from the resource as they write.
28
This works because of ordering constraints that make sure readers
29
see a consistent view of existing data.
31
Waiting for a lock must be done by polling; this can be aborted after
34
Locks must always be explicitly released, typically from a try/finally
35
block -- they are not released from a finalizer or when Python
38
Locks may fail to be released if the process is abruptly terminated
39
(machine stop, SIGKILL) or if a remote transport becomes permanently
40
disconnected. There is therefore a method to break an existing lock.
41
This should rarely be used, and generally only with user approval.
42
Locks contain some information on when the lock was taken and by who
43
which may guide in deciding whether it can safely be broken. (This is
44
similar to the messages displayed by emacs and vim.) Note that if the
45
lock holder is still alive they will get no notification that the lock
46
has been broken and will continue their work -- so it is important to be
47
sure they are actually dead.
49
A lock is represented on disk by a directory of a particular name,
50
containing an information file. Taking a lock is done by renaming a
51
temporary directory into place. We use temporary directories because
52
for all known transports and filesystems we believe that exactly one
53
attempt to claim the lock will succeed and the others will fail. (Files
54
won't do because some filesystems or transports only have
55
rename-and-overwrite, making it hard to tell who won.)
57
The desired characteristics are:
59
* Locks are not reentrant. (That is, a client that tries to take a
60
lock it already holds may deadlock or fail.)
61
* Stale locks can be guessed at by a heuristic
62
* Lost locks can be broken by any client
63
* Failed lock operations leave little or no mess
64
* Deadlocks are avoided by having a timeout always in use, clients
65
desiring indefinite waits can retry or set a silly big timeout.
67
Storage formats use the locks, and also need to consider concurrency
68
issues underneath the lock. A format may choose not to use a lock
69
at all for some operations.
71
LockDirs always operate over a Transport. The transport may be readonly, in
72
which case the lock can be queried but not acquired.
74
Locks are identified by a path name, relative to a base transport.
76
Calling code will typically want to make sure there is exactly one LockDir
77
object per actual lock on disk. This module does nothing to prevent aliasing
78
and deadlocks will likely occur if the locks are aliased.
80
In the future we may add a "freshen" method which can be called
81
by a lock holder to check that their lock has not been broken, and to
82
update the timestamp within it.
86
>>> from bzrlib.transport.memory import MemoryTransport
87
>>> # typically will be obtained from a BzrDir, Branch, etc
88
>>> t = MemoryTransport()
89
>>> l = LockDir(t, 'sample-lock')
92
>>> # do something here
99
from StringIO import StringIO
102
from bzrlib.errors import (
114
from bzrlib.trace import mutter
115
from bzrlib.transport import Transport
116
from bzrlib.osutils import rand_chars
117
from bzrlib.rio import read_stanza, Stanza
119
# XXX: At the moment there is no consideration of thread safety on LockDir
120
# objects. This should perhaps be updated - e.g. if two threads try to take a
121
# lock at the same time they should *both* get it. But then that's unlikely
124
# TODO: Perhaps store some kind of note like the bzr command line in the lock
127
# TODO: Some kind of callback run while polling a lock to show progress
130
# TODO: Make sure to pass the right file and directory mode bits to all
131
# files/dirs created.
133
_DEFAULT_TIMEOUT_SECONDS = 300
134
_DEFAULT_POLL_SECONDS = 0.5
136
class LockDir(object):
137
"""Write-lock guarding access to data."""
139
__INFO_NAME = '/info'
141
def __init__(self, transport, path, file_modebits=0644, dir_modebits=0755):
142
"""Create a new LockDir object.
144
The LockDir is initially unlocked - this just creates the object.
146
:param transport: Transport which will contain the lock
148
:param path: Path to the lock within the base directory of the
151
assert isinstance(transport, Transport), \
152
("not a transport: %r" % transport)
153
self.transport = transport
155
self._lock_held = False
156
self._fake_read_lock = False
157
self._held_dir = path + '/held'
158
self._held_info_path = self._held_dir + self.__INFO_NAME
159
self._file_modebits = file_modebits
160
self._dir_modebits = dir_modebits
161
self.nonce = rand_chars(20)
164
return '%s(%s%s)' % (self.__class__.__name__,
168
is_held = property(lambda self: self._lock_held)
170
def create(self, mode=None):
171
"""Create the on-disk lock.
173
This is typically only called when the object/directory containing the
174
directory is first created. The lock is not held when it's created.
176
if self.transport.is_readonly():
177
raise UnlockableTransport(self.transport)
178
self.transport.mkdir(self.path, mode=mode)
180
def attempt_lock(self):
181
"""Take the lock; fail if it's already held.
183
If you wish to block until the lock can be obtained, call wait_lock()
186
if self._fake_read_lock:
187
raise LockContention(self)
188
if self.transport.is_readonly():
189
raise UnlockableTransport(self.transport)
191
tmpname = '%s/pending.%s.tmp' % (self.path, rand_chars(20))
193
self.transport.mkdir(tmpname)
195
# This may raise a FileExists exception
196
# which is okay, it will be caught later and determined
197
# to be a LockContention.
198
self.create(mode=self._dir_modebits)
200
# After creating the lock directory, try again
201
self.transport.mkdir(tmpname)
203
info_bytes = self._prepare_info()
204
# We use put_file_non_atomic because we just created a new unique
205
# directory so we don't have to worry about files existing there.
206
# We'll rename the whole directory into place to get atomic
208
self.transport.put_bytes_non_atomic(tmpname + self.__INFO_NAME,
211
self.transport.rename(tmpname, self._held_dir)
212
self._lock_held = True
214
except (PathError, DirectoryNotEmpty, FileExists, ResourceBusy), e:
215
mutter("contention on %r: %s", self, e)
216
raise LockContention(self)
219
"""Release a held lock
221
if self._fake_read_lock:
222
self._fake_read_lock = False
224
if not self._lock_held:
225
raise LockNotHeld(self)
226
# rename before deleting, because we can't atomically remove the whole
228
tmpname = '%s/releasing.%s.tmp' % (self.path, rand_chars(20))
229
# gotta own it to unlock
231
self.transport.rename(self._held_dir, tmpname)
232
self._lock_held = False
233
self.transport.delete(tmpname + self.__INFO_NAME)
234
self.transport.rmdir(tmpname)
236
def break_lock(self):
237
"""Break a lock not held by this instance of LockDir.
239
This is a UI centric function: it uses the bzrlib.ui.ui_factory to
240
prompt for input if a lock is detected and there is any doubt about
241
it possibly being still active.
243
self._check_not_locked()
244
holder_info = self.peek()
245
if holder_info is not None:
246
if bzrlib.ui.ui_factory.get_boolean(
247
"Break lock %s held by %s@%s [process #%s]" % (
250
holder_info["hostname"],
251
holder_info["pid"])):
252
self.force_break(holder_info)
254
def force_break(self, dead_holder_info):
255
"""Release a lock held by another process.
257
WARNING: This should only be used when the other process is dead; if
258
it still thinks it has the lock there will be two concurrent writers.
259
In general the user's approval should be sought for lock breaks.
261
dead_holder_info must be the result of a previous LockDir.peek() call;
262
this is used to check that it's still held by the same process that
263
the user decided was dead. If this is not the current holder,
264
LockBreakMismatch is raised.
266
After the lock is broken it will not be held by any process.
267
It is possible that another process may sneak in and take the
268
lock before the breaking process acquires it.
270
if not isinstance(dead_holder_info, dict):
271
raise ValueError("dead_holder_info: %r" % dead_holder_info)
272
self._check_not_locked()
273
current_info = self.peek()
274
if current_info is None:
275
# must have been recently released
277
if current_info != dead_holder_info:
278
raise LockBreakMismatch(self, current_info, dead_holder_info)
279
tmpname = '%s/broken.%s.tmp' % (self.path, rand_chars(20))
280
self.transport.rename(self._held_dir, tmpname)
281
# check that we actually broke the right lock, not someone else;
282
# there's a small race window between checking it and doing the
284
broken_info_path = tmpname + self.__INFO_NAME
285
broken_info = self._read_info_file(broken_info_path)
286
if broken_info != dead_holder_info:
287
raise LockBreakMismatch(self, broken_info, dead_holder_info)
288
self.transport.delete(broken_info_path)
289
self.transport.rmdir(tmpname)
291
def _check_not_locked(self):
292
"""If the lock is held by this instance, raise an error."""
294
raise AssertionError("can't break own lock: %r" % self)
297
"""Make sure that the lock is still held by this locker.
299
This should only fail if the lock was broken by user intervention,
300
or if the lock has been affected by a bug.
302
If the lock is not thought to be held, raises LockNotHeld. If
303
the lock is thought to be held but has been broken, raises
306
if not self._lock_held:
307
raise LockNotHeld(self)
310
# no lock there anymore!
311
raise LockBroken(self)
312
if info.get('nonce') != self.nonce:
313
# there is a lock, but not ours
314
raise LockBroken(self)
316
def _read_info_file(self, path):
317
"""Read one given info file.
319
peek() reads the info file of the lock holder, if any.
321
return self._parse_info(self.transport.get(path))
324
"""Check if the lock is held by anyone.
326
If it is held, this returns the lock info structure as a rio Stanza,
327
which contains some information about the current lock holder.
328
Otherwise returns None.
331
info = self._read_info_file(self._held_info_path)
332
assert isinstance(info, dict), \
333
"bad parse result %r" % info
335
except NoSuchFile, e:
338
def _prepare_info(self):
339
"""Write information about a pending lock to a temporary file.
342
# XXX: is creating this here inefficient?
343
config = bzrlib.config.GlobalConfig()
344
s = Stanza(hostname=socket.gethostname(),
345
pid=str(os.getpid()),
346
start_time=str(int(time.time())),
348
user=config.user_email(),
352
def _parse_info(self, info_file):
353
return read_stanza(info_file.readlines()).as_dict()
355
def wait_lock(self, timeout=_DEFAULT_TIMEOUT_SECONDS,
356
poll=_DEFAULT_POLL_SECONDS):
357
"""Wait a certain period for a lock.
359
If the lock can be acquired within the bounded time, it
360
is taken and this returns. Otherwise, LockContention
361
is raised. Either way, this function should return within
362
approximately `timeout` seconds. (It may be a bit more if
363
a transport operation takes a long time to complete.)
365
# XXX: the transport interface doesn't let us guard
366
# against operations there taking a long time.
367
deadline = time.time() + timeout
372
except LockContention:
374
if time.time() + poll < deadline:
377
raise LockContention(self)
379
def lock_write(self):
380
"""Wait for and acquire the lock."""
384
"""Compatibility-mode shared lock.
386
LockDir doesn't support shared read-only locks, so this
387
just pretends that the lock is taken but really does nothing.
389
# At the moment Branches are commonly locked for read, but
390
# we can't rely on that remotely. Once this is cleaned up,
391
# reenable this warning to prevent it coming back in
393
## warn("LockDir.lock_read falls back to write lock")
394
if self._lock_held or self._fake_read_lock:
395
raise LockContention(self)
396
self._fake_read_lock = True
398
def wait(self, timeout=20, poll=0.5):
399
"""Wait a certain period for a lock to be released."""
400
# XXX: the transport interface doesn't let us guard
401
# against operations there taking a long time.
402
deadline = time.time() + timeout
406
if time.time() + poll < deadline:
409
raise LockContention(self)