2013-11-26 04:36:44 +04:00
|
|
|
# remotefilelogserver.py - server logic for a remotefilelog server
|
|
|
|
#
|
|
|
|
# Copyright 2013 Facebook, Inc.
|
|
|
|
#
|
|
|
|
# This software may be used and distributed according to the terms of the
|
|
|
|
# GNU General Public License version 2 or any later version.
|
|
|
|
|
2015-01-15 00:14:35 +03:00
|
|
|
from mercurial import wireproto, changegroup, match, util, changelog, context
|
2015-09-03 05:04:33 +03:00
|
|
|
from mercurial import exchange, sshserver, store
|
2013-11-26 04:36:44 +04:00
|
|
|
from mercurial.extensions import wrapfunction
|
2015-06-30 18:04:47 +03:00
|
|
|
from mercurial.hgweb import protocol as httpprotocol
|
2013-11-26 04:36:44 +04:00
|
|
|
from mercurial.node import bin, hex, nullid, nullrev
|
|
|
|
from mercurial.i18n import _
|
|
|
|
import shallowrepo
|
|
|
|
import stat, os, lz4, time
|
|
|
|
|
|
|
|
def setupserver(ui, repo):
|
|
|
|
"""Sets up a normal Mercurial repo so it can serve files to shallow repos.
|
|
|
|
"""
|
|
|
|
onetimesetup(ui)
|
|
|
|
|
|
|
|
# don't send files to shallow clients during pulls
|
|
|
|
def generatefiles(orig, self, changedfiles, linknodes, commonrevs, source):
|
|
|
|
caps = self._bundlecaps or []
|
|
|
|
if shallowrepo.requirement in caps:
|
|
|
|
# only send files that don't match the specified patterns
|
|
|
|
includepattern = None
|
|
|
|
excludepattern = None
|
|
|
|
for cap in (self._bundlecaps or []):
|
|
|
|
if cap.startswith("includepattern="):
|
|
|
|
includepattern = cap[len("includepattern="):].split('\0')
|
|
|
|
elif cap.startswith("excludepattern="):
|
|
|
|
excludepattern = cap[len("excludepattern="):].split('\0')
|
|
|
|
|
|
|
|
m = match.always(repo.root, '')
|
|
|
|
if includepattern or excludepattern:
|
|
|
|
m = match.match(repo.root, '', None,
|
|
|
|
includepattern, excludepattern)
|
|
|
|
|
|
|
|
changedfiles = list([f for f in changedfiles if not m(f)])
|
|
|
|
return orig(self, changedfiles, linknodes, commonrevs, source)
|
|
|
|
|
2014-09-12 01:39:14 +04:00
|
|
|
wrapfunction(changegroup.cg1packer, 'generatefiles', generatefiles)
|
2013-11-26 04:36:44 +04:00
|
|
|
|
|
|
|
onetime = False
|
|
|
|
def onetimesetup(ui):
|
2015-06-30 17:12:38 +03:00
|
|
|
"""Configures the wireprotocol for both clients and servers.
|
2013-11-26 04:36:44 +04:00
|
|
|
"""
|
|
|
|
global onetime
|
|
|
|
if onetime:
|
|
|
|
return
|
|
|
|
onetime = True
|
|
|
|
|
|
|
|
# support file content requests
|
|
|
|
wireproto.commands['getfiles'] = (getfiles, '')
|
2015-07-01 00:32:31 +03:00
|
|
|
wireproto.commands['getfile'] = (getfile, 'file node')
|
2013-11-26 04:36:44 +04:00
|
|
|
|
|
|
|
class streamstate(object):
|
|
|
|
match = None
|
|
|
|
shallowremote = False
|
|
|
|
state = streamstate()
|
|
|
|
|
|
|
|
def stream_out_shallow(repo, proto, other):
|
|
|
|
includepattern = None
|
|
|
|
excludepattern = None
|
|
|
|
raw = other.get('includepattern')
|
|
|
|
if raw:
|
|
|
|
includepattern = raw.split('\0')
|
|
|
|
raw = other.get('excludepattern')
|
|
|
|
if raw:
|
|
|
|
excludepattern = raw.split('\0')
|
|
|
|
|
|
|
|
oldshallow = state.shallowremote
|
|
|
|
oldmatch = state.match
|
|
|
|
try:
|
|
|
|
state.shallowremote = True
|
|
|
|
state.match = match.always(repo.root, '')
|
|
|
|
if includepattern or excludepattern:
|
|
|
|
state.match = match.match(repo.root, '', None,
|
|
|
|
includepattern, excludepattern)
|
2015-05-28 03:29:34 +03:00
|
|
|
streamres = wireproto.stream(repo, proto)
|
|
|
|
|
|
|
|
# Force the first value to execute, so the file list is computed
|
|
|
|
# within the try/finally scope
|
|
|
|
first = streamres.gen.next()
|
|
|
|
second = streamres.gen.next()
|
|
|
|
def gen():
|
|
|
|
yield first
|
|
|
|
yield second
|
|
|
|
for value in streamres.gen:
|
|
|
|
yield value
|
|
|
|
return wireproto.streamres(gen())
|
2013-11-26 04:36:44 +04:00
|
|
|
finally:
|
|
|
|
state.shallowremote = oldshallow
|
|
|
|
state.match = oldmatch
|
|
|
|
|
|
|
|
wireproto.commands['stream_out_shallow'] = (stream_out_shallow, '*')
|
|
|
|
|
|
|
|
# don't clone filelogs to shallow clients
|
|
|
|
def _walkstreamfiles(orig, repo):
|
|
|
|
if state.shallowremote:
|
|
|
|
# if we are shallow ourselves, stream our local commits
|
|
|
|
if shallowrepo.requirement in repo.requirements:
|
|
|
|
striplen = len(repo.store.path) + 1
|
|
|
|
readdir = repo.store.rawvfs.readdir
|
|
|
|
visit = [os.path.join(repo.store.path, 'data')]
|
|
|
|
while visit:
|
|
|
|
p = visit.pop()
|
|
|
|
for f, kind, st in readdir(p, stat=True):
|
|
|
|
fp = p + '/' + f
|
|
|
|
if kind == stat.S_IFREG:
|
|
|
|
if not fp.endswith('.i') and not fp.endswith('.d'):
|
|
|
|
n = util.pconvert(fp[striplen:])
|
|
|
|
yield (store.decodedir(n), n, st.st_size)
|
|
|
|
if kind == stat.S_IFDIR:
|
|
|
|
visit.append(fp)
|
|
|
|
|
|
|
|
# Return .d and .i files that do not match the shallow pattern
|
2015-09-05 22:24:04 +03:00
|
|
|
match = state.match
|
|
|
|
if match and not match.always():
|
|
|
|
for (u, e, s) in repo.store.datafiles():
|
|
|
|
f = u[5:-2] # trim data/... and .i/.d
|
|
|
|
if not state.match(f):
|
|
|
|
yield (u, e, s)
|
2013-11-26 04:36:44 +04:00
|
|
|
|
|
|
|
for x in repo.store.topfiles():
|
|
|
|
yield x
|
|
|
|
elif shallowrepo.requirement in repo.requirements:
|
|
|
|
# don't allow cloning from a shallow repo to a full repo
|
|
|
|
# since it would require fetching every version of every
|
|
|
|
# file in order to create the revlogs.
|
|
|
|
raise util.Abort(_("Cannot clone from a shallow repo "
|
|
|
|
+ "to a full repo."))
|
|
|
|
else:
|
|
|
|
for x in orig(repo):
|
|
|
|
yield x
|
|
|
|
|
2015-05-28 03:29:34 +03:00
|
|
|
# This function moved in Mercurial 3.5
|
|
|
|
if util.safehasattr(wireproto, '_walkstreamfiles'):
|
|
|
|
wrapfunction(wireproto, '_walkstreamfiles', _walkstreamfiles)
|
|
|
|
else:
|
|
|
|
wrapfunction(exchange, '_walkstreamfiles', _walkstreamfiles)
|
2013-11-26 04:36:44 +04:00
|
|
|
|
|
|
|
# We no longer use getbundle_shallow commands, but we must still
|
|
|
|
# support it for migration purposes
|
|
|
|
def getbundleshallow(repo, proto, others):
|
|
|
|
bundlecaps = others.get('bundlecaps', '')
|
|
|
|
bundlecaps = set(bundlecaps.split(','))
|
|
|
|
bundlecaps.add('remotefilelog')
|
|
|
|
others['bundlecaps'] = ','.join(bundlecaps)
|
|
|
|
|
|
|
|
return wireproto.commands["getbundle"][0](repo, proto, others)
|
|
|
|
|
|
|
|
wireproto.commands["getbundle_shallow"] = (getbundleshallow, '*')
|
|
|
|
|
|
|
|
# expose remotefilelog capabilities
|
2015-06-30 00:35:32 +03:00
|
|
|
def _capabilities(orig, repo, proto):
|
2013-11-26 04:36:44 +04:00
|
|
|
caps = orig(repo, proto)
|
2015-06-30 00:36:25 +03:00
|
|
|
if ((shallowrepo.requirement in repo.requirements or
|
2015-07-01 00:32:31 +03:00
|
|
|
ui.configbool('remotefilelog', 'server'))):
|
|
|
|
if isinstance(proto, sshserver.sshserver):
|
|
|
|
# legacy getfiles method which only works over ssh
|
|
|
|
caps.append(shallowrepo.requirement)
|
|
|
|
caps.append("getfile")
|
2013-11-26 04:36:44 +04:00
|
|
|
return caps
|
2015-06-30 00:35:32 +03:00
|
|
|
wrapfunction(wireproto, '_capabilities', _capabilities)
|
2013-11-26 04:36:44 +04:00
|
|
|
|
2015-05-23 07:32:12 +03:00
|
|
|
def _adjustlinkrev(orig, self, path, filelog, fnode, *args, **kwargs):
|
|
|
|
# When generating file blobs, taking the real path is too slow on large
|
|
|
|
# repos, so force it to just return the linkrev directly.
|
|
|
|
repo = self._repo
|
|
|
|
if util.safehasattr(repo, 'forcelinkrev') and repo.forcelinkrev:
|
|
|
|
return filelog.linkrev(filelog.rev(fnode))
|
|
|
|
return orig(self, path, filelog, fnode, *args, **kwargs)
|
|
|
|
|
|
|
|
wrapfunction(context.basefilectx, '_adjustlinkrev', _adjustlinkrev)
|
2015-01-15 00:14:35 +03:00
|
|
|
|
2015-06-30 18:04:47 +03:00
|
|
|
def _iscmd(orig, cmd):
|
|
|
|
if cmd == 'getfiles':
|
|
|
|
return False
|
|
|
|
return orig(cmd)
|
|
|
|
|
|
|
|
wrapfunction(httpprotocol, 'iscmd', _iscmd)
|
|
|
|
|
2015-06-30 22:02:07 +03:00
|
|
|
def _loadfileblob(repo, cachepath, path, node):
|
|
|
|
filecachepath = os.path.join(cachepath, path, hex(node))
|
|
|
|
if not os.path.exists(filecachepath):
|
|
|
|
filectx = repo.filectx(path, fileid=node)
|
|
|
|
if filectx.node() == nullid:
|
|
|
|
repo.changelog = changelog.changelog(repo.svfs)
|
|
|
|
filectx = repo.filectx(path, fileid=node)
|
|
|
|
|
|
|
|
text = createfileblob(filectx)
|
|
|
|
text = lz4.compressHC(text)
|
|
|
|
|
2015-06-30 23:58:15 +03:00
|
|
|
# everything should be user & group read/writable
|
|
|
|
oldumask = os.umask(0o002)
|
2015-06-30 22:02:07 +03:00
|
|
|
try:
|
2015-06-30 23:58:15 +03:00
|
|
|
dirname = os.path.dirname(filecachepath)
|
|
|
|
if not os.path.exists(dirname):
|
|
|
|
os.makedirs(dirname)
|
2015-09-28 20:31:38 +03:00
|
|
|
f = None
|
2015-06-30 23:58:15 +03:00
|
|
|
try:
|
2015-09-28 20:31:38 +03:00
|
|
|
f = util.atomictempfile(filecachepath, "w")
|
|
|
|
f.write(text)
|
|
|
|
except (IOError, OSError):
|
2015-06-30 23:58:15 +03:00
|
|
|
# Don't abort if the user only has permission to read,
|
|
|
|
# and not write.
|
|
|
|
pass
|
2015-09-28 20:31:38 +03:00
|
|
|
finally:
|
|
|
|
if f:
|
|
|
|
f.close()
|
2015-06-30 23:58:15 +03:00
|
|
|
finally:
|
|
|
|
os.umask(oldumask)
|
2015-06-30 22:02:07 +03:00
|
|
|
else:
|
|
|
|
with open(filecachepath, "r") as f:
|
|
|
|
text = f.read()
|
|
|
|
return text
|
|
|
|
|
2015-07-01 00:32:31 +03:00
|
|
|
def getfile(repo, proto, file, node):
|
2015-08-04 21:59:53 +03:00
|
|
|
"""A server api for requesting a particular version of a file. Can be used
|
|
|
|
in batches to request many files at once. The return protocol is:
|
|
|
|
<errorcode>\0<data/errormsg> where <errorcode> is 0 for success or
|
|
|
|
non-zero for an error.
|
|
|
|
"""
|
2015-07-01 00:32:31 +03:00
|
|
|
if shallowrepo.requirement in repo.requirements:
|
2015-08-04 21:59:53 +03:00
|
|
|
return '1\0' + _('cannot fetch remote files from shallow repo')
|
2015-07-01 00:32:31 +03:00
|
|
|
cachepath = repo.ui.config("remotefilelog", "servercachepath")
|
|
|
|
if not cachepath:
|
|
|
|
cachepath = os.path.join(repo.path, "remotefilelogcache")
|
|
|
|
node = bin(node.strip())
|
|
|
|
if node == nullid:
|
2015-08-04 21:59:53 +03:00
|
|
|
return '0\0'
|
|
|
|
return '0\0' + _loadfileblob(repo, cachepath, file, node)
|
2015-07-01 00:32:31 +03:00
|
|
|
|
2013-11-26 04:36:44 +04:00
|
|
|
def getfiles(repo, proto):
|
|
|
|
"""A server api for requesting particular versions of particular files.
|
|
|
|
"""
|
|
|
|
if shallowrepo.requirement in repo.requirements:
|
|
|
|
raise util.Abort(_('cannot fetch remote files from shallow repo'))
|
2015-06-29 23:34:31 +03:00
|
|
|
if not isinstance(proto, sshserver.sshserver):
|
|
|
|
raise util.Abort(_('cannot fetch remote files over non-ssh protocol'))
|
2013-11-26 04:36:44 +04:00
|
|
|
|
|
|
|
def streamer():
|
|
|
|
fin = proto.fin
|
2015-06-30 17:12:38 +03:00
|
|
|
opener = repo.svfs
|
2013-11-26 04:36:44 +04:00
|
|
|
|
|
|
|
cachepath = repo.ui.config("remotefilelog", "servercachepath")
|
|
|
|
if not cachepath:
|
|
|
|
cachepath = os.path.join(repo.path, "remotefilelogcache")
|
|
|
|
|
2015-06-30 23:58:15 +03:00
|
|
|
while True:
|
|
|
|
request = fin.readline()[:-1]
|
|
|
|
if not request:
|
|
|
|
break
|
2013-11-26 04:36:44 +04:00
|
|
|
|
2015-06-30 23:58:15 +03:00
|
|
|
node = bin(request[:40])
|
|
|
|
if node == nullid:
|
|
|
|
yield '0\n'
|
|
|
|
continue
|
2013-11-26 04:36:44 +04:00
|
|
|
|
2015-06-30 23:58:15 +03:00
|
|
|
path = request[40:]
|
2013-11-26 04:36:44 +04:00
|
|
|
|
2015-06-30 23:58:15 +03:00
|
|
|
text = _loadfileblob(repo, cachepath, path, node)
|
2013-11-26 04:36:44 +04:00
|
|
|
|
2015-06-30 23:58:15 +03:00
|
|
|
yield '%d\n%s' % (len(text), text)
|
2013-11-26 04:36:44 +04:00
|
|
|
|
2015-06-30 23:58:15 +03:00
|
|
|
# it would be better to only flush after processing a whole batch
|
|
|
|
# but currently we don't know if there are more requests coming
|
|
|
|
proto.fout.flush()
|
2013-11-26 04:36:44 +04:00
|
|
|
return wireproto.streamres(streamer())
|
|
|
|
|
|
|
|
def createfileblob(filectx):
|
|
|
|
text = filectx.data()
|
2015-01-15 00:14:35 +03:00
|
|
|
repo = filectx._repo
|
2013-11-26 04:36:44 +04:00
|
|
|
|
|
|
|
ancestors = [filectx]
|
2015-01-15 00:14:35 +03:00
|
|
|
|
|
|
|
try:
|
|
|
|
repo.forcelinkrev = True
|
|
|
|
ancestors.extend([f for f in filectx.ancestors()])
|
|
|
|
|
|
|
|
ancestortext = ""
|
|
|
|
for ancestorctx in ancestors:
|
|
|
|
parents = ancestorctx.parents()
|
|
|
|
p1 = nullid
|
|
|
|
p2 = nullid
|
|
|
|
if len(parents) > 0:
|
|
|
|
p1 = parents[0].filenode()
|
|
|
|
if len(parents) > 1:
|
|
|
|
p2 = parents[1].filenode()
|
|
|
|
|
|
|
|
copyname = ""
|
|
|
|
rename = ancestorctx.renamed()
|
|
|
|
if rename:
|
|
|
|
copyname = rename[0]
|
|
|
|
linknode = ancestorctx.node()
|
|
|
|
ancestortext += "%s%s%s%s%s\0" % (
|
|
|
|
ancestorctx.filenode(), p1, p2, linknode,
|
|
|
|
copyname)
|
|
|
|
finally:
|
|
|
|
repo.forcelinkrev = False
|
2013-11-26 04:36:44 +04:00
|
|
|
|
|
|
|
return "%d\0%s%s" % (len(text), text, ancestortext)
|
|
|
|
|
|
|
|
def gcserver(ui, repo):
|
|
|
|
if not repo.ui.configbool("remotefilelog", "server"):
|
|
|
|
return
|
|
|
|
|
|
|
|
neededfiles = set()
|
|
|
|
heads = repo.revs("heads(all())")
|
|
|
|
|
|
|
|
cachepath = repo.join("remotefilelogcache")
|
|
|
|
for head in heads:
|
|
|
|
mf = repo[head].manifest()
|
|
|
|
for filename, filenode in mf.iteritems():
|
|
|
|
filecachepath = os.path.join(cachepath, filename, hex(filenode))
|
|
|
|
neededfiles.add(filecachepath)
|
|
|
|
|
|
|
|
# delete unneeded older files
|
|
|
|
days = repo.ui.configint("remotefilelog", "serverexpiration", 30)
|
|
|
|
expiration = time.time() - (days * 24 * 60 * 60)
|
|
|
|
|
|
|
|
_removing = _("removing old server cache")
|
|
|
|
count = 0
|
|
|
|
ui.progress(_removing, count, unit="files")
|
|
|
|
for root, dirs, files in os.walk(cachepath):
|
|
|
|
for file in files:
|
|
|
|
filepath = os.path.join(root, file)
|
|
|
|
count += 1
|
|
|
|
ui.progress(_removing, count, unit="files")
|
|
|
|
if filepath in neededfiles:
|
|
|
|
continue
|
|
|
|
|
|
|
|
stat = os.stat(filepath)
|
|
|
|
if stat.st_mtime < expiration:
|
|
|
|
os.remove(filepath)
|
|
|
|
|
|
|
|
ui.progress(_removing, None)
|