File: streamclone.py

package info (click to toggle)
mercurial 4.0-1%2Bdeb9u1
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 32,100 kB
  • ctags: 13,376
  • sloc: python: 94,424; ansic: 8,392; tcl: 3,715; lisp: 1,448; sh: 999; makefile: 375; xml: 35
file content (398 lines) | stat: -rw-r--r-- 14,439 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
# streamclone.py - producing and consuming streaming repository data
#
# Copyright 2015 Gregory Szorc <gregory.szorc@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import struct
import time

from .i18n import _
from . import (
    branchmap,
    error,
    store,
    util,
)

def canperformstreamclone(pullop, bailifbundle2supported=False):
    """Whether it is possible to perform a streaming clone as part of pull.

    ``bailifbundle2supported`` will cause the function to return False if
    bundle2 stream clones are supported. It should only be called by the
    legacy stream clone code path.

    Returns a tuple of (supported, requirements). ``supported`` is True if
    streaming clone is supported and False otherwise. ``requirements`` is
    a set of repo requirements from the remote, or ``None`` if stream clone
    isn't supported.
    """
    repo = pullop.repo
    remote = pullop.remote

    bundle2supported = False
    if pullop.canusebundle2:
        if 'v1' in pullop.remotebundle2caps.get('stream', []):
            bundle2supported = True
        # else
            # Server doesn't support bundle2 stream clone or doesn't support
            # the versions we support. Fall back and possibly allow legacy.

    # Ensures legacy code path uses available bundle2.
    if bailifbundle2supported and bundle2supported:
        return False, None
    # Ensures bundle2 doesn't try to do a stream clone if it isn't supported.
    #elif not bailifbundle2supported and not bundle2supported:
    #    return False, None

    # Streaming clone only works on empty repositories.
    if len(repo):
        return False, None

    # Streaming clone only works if all data is being requested.
    if pullop.heads:
        return False, None

    streamrequested = pullop.streamclonerequested

    # If we don't have a preference, let the server decide for us. This
    # likely only comes into play in LANs.
    if streamrequested is None:
        # The server can advertise whether to prefer streaming clone.
        streamrequested = remote.capable('stream-preferred')

    if not streamrequested:
        return False, None

    # In order for stream clone to work, the client has to support all the
    # requirements advertised by the server.
    #
    # The server advertises its requirements via the "stream" and "streamreqs"
    # capability. "stream" (a value-less capability) is advertised if and only
    # if the only requirement is "revlogv1." Else, the "streamreqs" capability
    # is advertised and contains a comma-delimited list of requirements.
    requirements = set()
    if remote.capable('stream'):
        requirements.add('revlogv1')
    else:
        streamreqs = remote.capable('streamreqs')
        # This is weird and shouldn't happen with modern servers.
        if not streamreqs:
            return False, None

        streamreqs = set(streamreqs.split(','))
        # Server requires something we don't support. Bail.
        if streamreqs - repo.supportedformats:
            return False, None
        requirements = streamreqs

    return True, requirements

def maybeperformlegacystreamclone(pullop):
    """Possibly perform a legacy stream clone operation.

    Legacy stream clones are performed as part of pull but before all other
    operations.

    A legacy stream clone will not be performed if a bundle2 stream clone is
    supported.
    """
    supported, requirements = canperformstreamclone(pullop)

    if not supported:
        return

    repo = pullop.repo
    remote = pullop.remote

    # Save remote branchmap. We will use it later to speed up branchcache
    # creation.
    rbranchmap = None
    if remote.capable('branchmap'):
        rbranchmap = remote.branchmap()

    repo.ui.status(_('streaming all changes\n'))

    fp = remote.stream_out()
    l = fp.readline()
    try:
        resp = int(l)
    except ValueError:
        raise error.ResponseError(
            _('unexpected response from remote server:'), l)
    if resp == 1:
        raise error.Abort(_('operation forbidden by server'))
    elif resp == 2:
        raise error.Abort(_('locking the remote repository failed'))
    elif resp != 0:
        raise error.Abort(_('the server sent an unknown error code'))

    l = fp.readline()
    try:
        filecount, bytecount = map(int, l.split(' ', 1))
    except (ValueError, TypeError):
        raise error.ResponseError(
            _('unexpected response from remote server:'), l)

    with repo.lock():
        consumev1(repo, fp, filecount, bytecount)

        # new requirements = old non-format requirements +
        #                    new format-related remote requirements
        # requirements from the streamed-in repository
        repo.requirements = requirements | (
                repo.requirements - repo.supportedformats)
        repo._applyopenerreqs()
        repo._writerequirements()

        if rbranchmap:
            branchmap.replacecache(repo, rbranchmap)

        repo.invalidate()

def allowservergeneration(ui):
    """Whether streaming clones are allowed from the server."""
    return ui.configbool('server', 'uncompressed', True, untrusted=True)

# This is it's own function so extensions can override it.
def _walkstreamfiles(repo):
    return repo.store.walk()

def generatev1(repo):
    """Emit content for version 1 of a streaming clone.

    This returns a 3-tuple of (file count, byte size, data iterator).

    The data iterator consists of N entries for each file being transferred.
    Each file entry starts as a line with the file name and integer size
    delimited by a null byte.

    The raw file data follows. Following the raw file data is the next file
    entry, or EOF.

    When used on the wire protocol, an additional line indicating protocol
    success will be prepended to the stream. This function is not responsible
    for adding it.

    This function will obtain a repository lock to ensure a consistent view of
    the store is captured. It therefore may raise LockError.
    """
    entries = []
    total_bytes = 0
    # Get consistent snapshot of repo, lock during scan.
    with repo.lock():
        repo.ui.debug('scanning\n')
        for name, ename, size in _walkstreamfiles(repo):
            if size:
                entries.append((name, size))
                total_bytes += size

    repo.ui.debug('%d files, %d bytes to transfer\n' %
                  (len(entries), total_bytes))

    svfs = repo.svfs
    oldaudit = svfs.mustaudit
    debugflag = repo.ui.debugflag
    svfs.mustaudit = False

    def emitrevlogdata():
        try:
            for name, size in entries:
                if debugflag:
                    repo.ui.debug('sending %s (%d bytes)\n' % (name, size))
                # partially encode name over the wire for backwards compat
                yield '%s\0%d\n' % (store.encodedir(name), size)
                if size <= 65536:
                    with svfs(name, 'rb') as fp:
                        yield fp.read(size)
                else:
                    for chunk in util.filechunkiter(svfs(name), limit=size):
                        yield chunk
        finally:
            svfs.mustaudit = oldaudit

    return len(entries), total_bytes, emitrevlogdata()

def generatev1wireproto(repo):
    """Emit content for version 1 of streaming clone suitable for the wire.

    This is the data output from ``generatev1()`` with a header line
    indicating file count and byte size.
    """
    filecount, bytecount, it = generatev1(repo)
    yield '%d %d\n' % (filecount, bytecount)
    for chunk in it:
        yield chunk

def generatebundlev1(repo, compression='UN'):
    """Emit content for version 1 of a stream clone bundle.

    The first 4 bytes of the output ("HGS1") denote this as stream clone
    bundle version 1.

    The next 2 bytes indicate the compression type. Only "UN" is currently
    supported.

    The next 16 bytes are two 64-bit big endian unsigned integers indicating
    file count and byte count, respectively.

    The next 2 bytes is a 16-bit big endian unsigned short declaring the length
    of the requirements string, including a trailing \0. The following N bytes
    are the requirements string, which is ASCII containing a comma-delimited
    list of repo requirements that are needed to support the data.

    The remaining content is the output of ``generatev1()`` (which may be
    compressed in the future).

    Returns a tuple of (requirements, data generator).
    """
    if compression != 'UN':
        raise ValueError('we do not support the compression argument yet')

    requirements = repo.requirements & repo.supportedformats
    requires = ','.join(sorted(requirements))

    def gen():
        yield 'HGS1'
        yield compression

        filecount, bytecount, it = generatev1(repo)
        repo.ui.status(_('writing %d bytes for %d files\n') %
                         (bytecount, filecount))

        yield struct.pack('>QQ', filecount, bytecount)
        yield struct.pack('>H', len(requires) + 1)
        yield requires + '\0'

        # This is where we'll add compression in the future.
        assert compression == 'UN'

        seen = 0
        repo.ui.progress(_('bundle'), 0, total=bytecount, unit=_('bytes'))

        for chunk in it:
            seen += len(chunk)
            repo.ui.progress(_('bundle'), seen, total=bytecount,
                             unit=_('bytes'))
            yield chunk

        repo.ui.progress(_('bundle'), None)

    return requirements, gen()

def consumev1(repo, fp, filecount, bytecount):
    """Apply the contents from version 1 of a streaming clone file handle.

    This takes the output from "streamout" and applies it to the specified
    repository.

    Like "streamout," the status line added by the wire protocol is not handled
    by this function.
    """
    with repo.lock():
        repo.ui.status(_('%d files to transfer, %s of data\n') %
                       (filecount, util.bytecount(bytecount)))
        handled_bytes = 0
        repo.ui.progress(_('clone'), 0, total=bytecount, unit=_('bytes'))
        start = time.time()

        # TODO: get rid of (potential) inconsistency
        #
        # If transaction is started and any @filecache property is
        # changed at this point, it causes inconsistency between
        # in-memory cached property and streamclone-ed file on the
        # disk. Nested transaction prevents transaction scope "clone"
        # below from writing in-memory changes out at the end of it,
        # even though in-memory changes are discarded at the end of it
        # regardless of transaction nesting.
        #
        # But transaction nesting can't be simply prohibited, because
        # nesting occurs also in ordinary case (e.g. enabling
        # clonebundles).

        with repo.transaction('clone'):
            with repo.svfs.backgroundclosing(repo.ui, expectedcount=filecount):
                for i in xrange(filecount):
                    # XXX doesn't support '\n' or '\r' in filenames
                    l = fp.readline()
                    try:
                        name, size = l.split('\0', 1)
                        size = int(size)
                    except (ValueError, TypeError):
                        raise error.ResponseError(
                            _('unexpected response from remote server:'), l)
                    if repo.ui.debugflag:
                        repo.ui.debug('adding %s (%s)\n' %
                                      (name, util.bytecount(size)))
                    # for backwards compat, name was partially encoded
                    path = store.decodedir(name)
                    with repo.svfs(path, 'w', backgroundclose=True) as ofp:
                        for chunk in util.filechunkiter(fp, limit=size):
                            handled_bytes += len(chunk)
                            repo.ui.progress(_('clone'), handled_bytes,
                                             total=bytecount, unit=_('bytes'))
                            ofp.write(chunk)

            # force @filecache properties to be reloaded from
            # streamclone-ed file at next access
            repo.invalidate(clearfilecache=True)

        elapsed = time.time() - start
        if elapsed <= 0:
            elapsed = 0.001
        repo.ui.progress(_('clone'), None)
        repo.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                       (util.bytecount(bytecount), elapsed,
                        util.bytecount(bytecount / elapsed)))

def readbundle1header(fp):
    compression = fp.read(2)
    if compression != 'UN':
        raise error.Abort(_('only uncompressed stream clone bundles are '
            'supported; got %s') % compression)

    filecount, bytecount = struct.unpack('>QQ', fp.read(16))
    requireslen = struct.unpack('>H', fp.read(2))[0]
    requires = fp.read(requireslen)

    if not requires.endswith('\0'):
        raise error.Abort(_('malformed stream clone bundle: '
                            'requirements not properly encoded'))

    requirements = set(requires.rstrip('\0').split(','))

    return filecount, bytecount, requirements

def applybundlev1(repo, fp):
    """Apply the content from a stream clone bundle version 1.

    We assume the 4 byte header has been read and validated and the file handle
    is at the 2 byte compression identifier.
    """
    if len(repo):
        raise error.Abort(_('cannot apply stream clone bundle on non-empty '
                            'repo'))

    filecount, bytecount, requirements = readbundle1header(fp)
    missingreqs = requirements - repo.supportedformats
    if missingreqs:
        raise error.Abort(_('unable to apply stream clone: '
                            'unsupported format: %s') %
                            ', '.join(sorted(missingreqs)))

    consumev1(repo, fp, filecount, bytecount)

class streamcloneapplier(object):
    """Class to manage applying streaming clone bundles.

    We need to wrap ``applybundlev1()`` in a dedicated type to enable bundle
    readers to perform bundle type-specific functionality.
    """
    def __init__(self, fh):
        self._fh = fh

    def apply(self, repo):
        return applybundlev1(repo, self._fh)