lfs: deduplicate oids in the transfer

Apparently, we can't rely on the server to deduplicate for us.

Sadly, the pointer object isn't hashable, so it can't be reduced by converting
it to a set.  In order to be hashable, it needs to be immutable.  I had a bunch
of code to change it to composition and forward the readonly dict methods to a
member dict.  But the pointer is updated via __setitem__() when creating the
pointer file.  So it didn't see worth adding all of that code to the class.

hgext/lfs/blobstore.py

@@ -1,474 +1,481 b''
 # blobstore.py - local and remote (speaking Git-LFS protocol) blob storages
 #
 # Copyright 2017 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.
 
 from __future__ import absolute_import
 
 import hashlib
 import json
 import os
 import re
 import socket
 
 from mercurial.i18n import _
 
 from mercurial import (
     error,
     pathutil,
     url as urlmod,
     util,
     vfs as vfsmod,
     worker,
 )
 
 from ..largefiles import lfutil
 
 # 64 bytes for SHA256
 _lfsre = re.compile(r'\A[a-f0-9]{64}\Z')
 
 class lfsvfs(vfsmod.vfs):
     def join(self, path):
         """split the path at first two characters, like: XX/XXXXX..."""
         if not _lfsre.match(path):
             raise error.ProgrammingError('unexpected lfs path: %s' % path)
         return super(lfsvfs, self).join(path[0:2], path[2:])
 
     def walk(self, path=None, onerror=None):
         """Yield (dirpath, [], oids) tuple for blobs under path
 
         Oids only exist in the root of this vfs, so dirpath is always ''.
         """
         root = os.path.normpath(self.base)
         # when dirpath == root, dirpath[prefixlen:] becomes empty
         # because len(dirpath) < prefixlen.
         prefixlen = len(pathutil.normasprefix(root))
         oids = []
 
         for dirpath, dirs, files in os.walk(self.reljoin(self.base, path or ''),
                                             onerror=onerror):
             dirpath = dirpath[prefixlen:]
 
             # Silently skip unexpected files and directories
             if len(dirpath) == 2:
                 oids.extend([dirpath + f for f in files
                              if _lfsre.match(dirpath + f)])
 
         yield ('', [], oids)
 
 class filewithprogress(object):
     """a file-like object that supports __len__ and read.
 
     Useful to provide progress information for how many bytes are read.
     """
 
     def __init__(self, fp, callback):
         self._fp = fp
         self._callback = callback # func(readsize)
         fp.seek(0, os.SEEK_END)
         self._len = fp.tell()
         fp.seek(0)
 
     def __len__(self):
         return self._len
 
     def read(self, size):
         if self._fp is None:
             return b''
         data = self._fp.read(size)
         if data:
             if self._callback:
                 self._callback(len(data))
         else:
             self._fp.close()
             self._fp = None
         return data
 
 class local(object):
     """Local blobstore for large file contents.
 
     This blobstore is used both as a cache and as a staging area for large blobs
     to be uploaded to the remote blobstore.
     """
 
     def __init__(self, repo):
         fullpath = repo.svfs.join('lfs/objects')
         self.vfs = lfsvfs(fullpath)
         usercache = lfutil._usercachedir(repo.ui, 'lfs')
         self.cachevfs = lfsvfs(usercache)
         self.ui = repo.ui
 
     def open(self, oid):
         """Open a read-only file descriptor to the named blob, in either the
         usercache or the local store."""
         # The usercache is the most likely place to hold the file.  Commit will
         # write to both it and the local store, as will anything that downloads
         # the blobs.  However, things like clone without an update won't
         # populate the local store.  For an init + push of a local clone,
         # the usercache is the only place it _could_ be.  If not present, the
         # missing file msg here will indicate the local repo, not the usercache.
         if self.cachevfs.exists(oid):
             return self.cachevfs(oid, 'rb')
 
         return self.vfs(oid, 'rb')
 
     def download(self, oid, src):
         """Read the blob from the remote source in chunks, verify the content,
         and write to this local blobstore."""
         sha256 = hashlib.sha256()
 
         with self.vfs(oid, 'wb', atomictemp=True) as fp:
             for chunk in util.filechunkiter(src, size=1048576):
                 fp.write(chunk)
                 sha256.update(chunk)
 
             realoid = sha256.hexdigest()
             if realoid != oid:
                 raise error.Abort(_('corrupt remote lfs object: %s') % oid)
 
         # XXX: should we verify the content of the cache, and hardlink back to
         # the local store on success, but truncate, write and link on failure?
         if not self.cachevfs.exists(oid):
             self.ui.note(_('lfs: adding %s to the usercache\n') % oid)
             lfutil.link(self.vfs.join(oid), self.cachevfs.join(oid))
 
     def write(self, oid, data):
         """Write blob to local blobstore.
 
         This should only be called from the filelog during a commit or similar.
         As such, there is no need to verify the data.  Imports from a remote
         store must use ``download()`` instead."""
         with self.vfs(oid, 'wb', atomictemp=True) as fp:
             fp.write(data)
 
         # XXX: should we verify the content of the cache, and hardlink back to
         # the local store on success, but truncate, write and link on failure?
         if not self.cachevfs.exists(oid):
             self.ui.note(_('lfs: adding %s to the usercache\n') % oid)
             lfutil.link(self.vfs.join(oid), self.cachevfs.join(oid))
 
     def read(self, oid, verify=True):
         """Read blob from local blobstore."""
         if not self.vfs.exists(oid):
             blob = self._read(self.cachevfs, oid, verify)
 
             # Even if revlog will verify the content, it needs to be verified
             # now before making the hardlink to avoid propagating corrupt blobs.
             # Don't abort if corruption is detected, because `hg verify` will
             # give more useful info about the corruption- simply don't add the
             # hardlink.
             if verify or hashlib.sha256(blob).hexdigest() == oid:
                 self.ui.note(_('lfs: found %s in the usercache\n') % oid)
                 lfutil.link(self.cachevfs.join(oid), self.vfs.join(oid))
         else:
             self.ui.note(_('lfs: found %s in the local lfs store\n') % oid)
             blob = self._read(self.vfs, oid, verify)
         return blob
 
     def _read(self, vfs, oid, verify):
         """Read blob (after verifying) from the given store"""
         blob = vfs.read(oid)
         if verify:
             _verify(oid, blob)
         return blob
 
     def has(self, oid):
         """Returns True if the local blobstore contains the requested blob,
         False otherwise."""
         return self.cachevfs.exists(oid) or self.vfs.exists(oid)
 
 class _gitlfsremote(object):
 
     def __init__(self, repo, url):
         ui = repo.ui
         self.ui = ui
         baseurl, authinfo = url.authinfo()
         self.baseurl = baseurl.rstrip('/')
         useragent = repo.ui.config('experimental', 'lfs.user-agent')
         if not useragent:
             useragent = 'git-lfs/2.3.4 (Mercurial %s)' % util.version()
         self.urlopener = urlmod.opener(ui, authinfo, useragent)
         self.retry = ui.configint('lfs', 'retry')
 
     def writebatch(self, pointers, fromstore):
         """Batch upload from local to remote blobstore."""
-        self._batch(pointers, fromstore, 'upload')
+        self._batch(_deduplicate(pointers), fromstore, 'upload')
 
     def readbatch(self, pointers, tostore):
         """Batch download from remote to local blostore."""
-        self._batch(pointers, tostore, 'download')
+        self._batch(_deduplicate(pointers), tostore, 'download')
 
     def _batchrequest(self, pointers, action):
         """Get metadata about objects pointed by pointers for given action
 
         Return decoded JSON object like {'objects': [{'oid': '', 'size': 1}]}
         See https://github.com/git-lfs/git-lfs/blob/master/docs/api/batch.md
         """
         objects = [{'oid': p.oid(), 'size': p.size()} for p in pointers]
         requestdata = json.dumps({
             'objects': objects,
             'operation': action,
         })
         batchreq = util.urlreq.request('%s/objects/batch' % self.baseurl,
                                        data=requestdata)
         batchreq.add_header('Accept', 'application/vnd.git-lfs+json')
         batchreq.add_header('Content-Type', 'application/vnd.git-lfs+json')
         try:
             rawjson = self.urlopener.open(batchreq).read()
         except util.urlerr.httperror as ex:
             raise LfsRemoteError(_('LFS HTTP error: %s (action=%s)')
                                  % (ex, action))
         try:
             response = json.loads(rawjson)
         except ValueError:
             raise LfsRemoteError(_('LFS server returns invalid JSON: %s')
                                  % rawjson)
         return response
 
     def _checkforservererror(self, pointers, responses, action):
         """Scans errors from objects
 
         Raises LfsRemoteError if any objects have an error"""
         for response in responses:
             # The server should return 404 when objects cannot be found. Some
             # server implementation (ex. lfs-test-server)  does not set "error"
             # but just removes "download" from "actions". Treat that case
             # as the same as 404 error.
             notfound = (response.get('error', {}).get('code') == 404
                         or (action == 'download'
                             and action not in response.get('actions', [])))
             if notfound:
                 ptrmap = {p.oid(): p for p in pointers}
                 p = ptrmap.get(response['oid'], None)
                 if p:
                     filename = getattr(p, 'filename', 'unknown')
                     raise LfsRemoteError(
                         _(('LFS server error. Remote object '
                           'for "%s" not found: %r')) % (filename, response))
                 else:
                     raise LfsRemoteError(
                         _('LFS server error. Unsolicited response for oid %s')
                         % response['oid'])
             if 'error' in response:
                 raise LfsRemoteError(_('LFS server error: %r') % response)
 
     def _extractobjects(self, response, pointers, action):
         """extract objects from response of the batch API
 
         response: parsed JSON object returned by batch API
         return response['objects'] filtered by action
         raise if any object has an error
         """
         # Scan errors from objects - fail early
         objects = response.get('objects', [])
         self._checkforservererror(pointers, objects, action)
 
         # Filter objects with given action. Practically, this skips uploading
         # objects which exist in the server.
         filteredobjects = [o for o in objects if action in o.get('actions', [])]
 
         return filteredobjects
 
     def _basictransfer(self, obj, action, localstore):
         """Download or upload a single object using basic transfer protocol
 
         obj: dict, an object description returned by batch API
         action: string, one of ['upload', 'download']
         localstore: blobstore.local
 
         See https://github.com/git-lfs/git-lfs/blob/master/docs/api/\
         basic-transfers.md
         """
         oid = str(obj['oid'])
 
         href = str(obj['actions'][action].get('href'))
         headers = obj['actions'][action].get('header', {}).items()
 
         request = util.urlreq.request(href)
         if action == 'upload':
             # If uploading blobs, read data from local blobstore.
             with localstore.open(oid) as fp:
                 _verifyfile(oid, fp)
             request.data = filewithprogress(localstore.open(oid), None)
             request.get_method = lambda: 'PUT'
 
         for k, v in headers:
             request.add_header(k, v)
 
         response = b''
         try:
             req = self.urlopener.open(request)
             if action == 'download':
                 # If downloading blobs, store downloaded data to local blobstore
                 localstore.download(oid, req)
             else:
                 while True:
                     data = req.read(1048576)
                     if not data:
                         break
                     response += data
                 if response:
                     self.ui.debug('lfs %s response: %s' % (action, response))
         except util.urlerr.httperror as ex:
             if self.ui.debugflag:
                 self.ui.debug('%s: %s\n' % (oid, ex.read()))
             raise LfsRemoteError(_('HTTP error: %s (oid=%s, action=%s)')
                                  % (ex, oid, action))
 
     def _batch(self, pointers, localstore, action):
         if action not in ['upload', 'download']:
             raise error.ProgrammingError('invalid Git-LFS action: %s' % action)
 
         response = self._batchrequest(pointers, action)
         objects = self._extractobjects(response, pointers, action)
         total = sum(x.get('size', 0) for x in objects)
         sizes = {}
         for obj in objects:
             sizes[obj.get('oid')] = obj.get('size', 0)
         topic = {'upload': _('lfs uploading'),
                  'download': _('lfs downloading')}[action]
         if len(objects) > 1:
             self.ui.note(_('lfs: need to transfer %d objects (%s)\n')
                          % (len(objects), util.bytecount(total)))
         self.ui.progress(topic, 0, total=total)
         def transfer(chunk):
             for obj in chunk:
                 objsize = obj.get('size', 0)
                 if self.ui.verbose:
                     if action == 'download':
                         msg = _('lfs: downloading %s (%s)\n')
                     elif action == 'upload':
                         msg = _('lfs: uploading %s (%s)\n')
                     self.ui.note(msg % (obj.get('oid'),
                                  util.bytecount(objsize)))
                 retry = self.retry
                 while True:
                     try:
                         self._basictransfer(obj, action, localstore)
                         yield 1, obj.get('oid')
                         break
                     except socket.error as ex:
                         if retry > 0:
                             self.ui.note(
                                 _('lfs: failed: %r (remaining retry %d)\n')
                                 % (ex, retry))
                             retry -= 1
                             continue
                         raise
 
         # Until https multiplexing gets sorted out
         if self.ui.configbool('experimental', 'lfs.worker-enable'):
             oids = worker.worker(self.ui, 0.1, transfer, (),
                                  sorted(objects, key=lambda o: o.get('oid')))
         else:
             oids = transfer(sorted(objects, key=lambda o: o.get('oid')))
 
         processed = 0
         blobs = 0
         for _one, oid in oids:
             processed += sizes[oid]
             blobs += 1
             self.ui.progress(topic, processed, total=total)
             self.ui.note(_('lfs: processed: %s\n') % oid)
         self.ui.progress(topic, pos=None, total=total)
 
         if blobs > 0:
             if action == 'upload':
                 self.ui.status(_('lfs: uploaded %d files (%s)\n')
                                % (blobs, util.bytecount(processed)))
             # TODO: coalesce the download requests, and comment this in
             #elif action == 'download':
             #    self.ui.status(_('lfs: downloaded %d files (%s)\n')
             #                   % (blobs, util.bytecount(processed)))
 
     def __del__(self):
         # copied from mercurial/httppeer.py
         urlopener = getattr(self, 'urlopener', None)
         if urlopener:
             for h in urlopener.handlers:
                 h.close()
                 getattr(h, "close_all", lambda : None)()
 
 class _dummyremote(object):
     """Dummy store storing blobs to temp directory."""
 
     def __init__(self, repo, url):
         fullpath = repo.vfs.join('lfs', url.path)
         self.vfs = lfsvfs(fullpath)
 
     def writebatch(self, pointers, fromstore):
-        for p in pointers:
+        for p in _deduplicate(pointers):
             content = fromstore.read(p.oid(), verify=True)
             with self.vfs(p.oid(), 'wb', atomictemp=True) as fp:
                 fp.write(content)
 
     def readbatch(self, pointers, tostore):
-        for p in pointers:
+        for p in _deduplicate(pointers):
             with self.vfs(p.oid(), 'rb') as fp:
                 tostore.download(p.oid(), fp)
 
 class _nullremote(object):
     """Null store storing blobs to /dev/null."""
 
     def __init__(self, repo, url):
         pass
 
     def writebatch(self, pointers, fromstore):
         pass
 
     def readbatch(self, pointers, tostore):
         pass
 
 class _promptremote(object):
     """Prompt user to set lfs.url when accessed."""
 
     def __init__(self, repo, url):
         pass
 
     def writebatch(self, pointers, fromstore, ui=None):
         self._prompt()
 
     def readbatch(self, pointers, tostore, ui=None):
         self._prompt()
 
     def _prompt(self):
         raise error.Abort(_('lfs.url needs to be configured'))
 
 _storemap = {
     'https': _gitlfsremote,
     'http': _gitlfsremote,
     'file': _dummyremote,
     'null': _nullremote,
     None: _promptremote,
 }
 
+def _deduplicate(pointers):
+    """Remove any duplicate oids that exist in the list"""
+    reduced = util.sortdict()
+    for p in pointers:
+        reduced[p.oid()] = p
+    return reduced.values()
+
 def _verify(oid, content):
     realoid = hashlib.sha256(content).hexdigest()
     if realoid != oid:
         raise error.Abort(_('detected corrupt lfs object: %s') % oid,
                           hint=_('run hg verify'))
 
 def _verifyfile(oid, fp):
     sha256 = hashlib.sha256()
     while True:
         data = fp.read(1024 * 1024)
         if not data:
             break
         sha256.update(data)
     realoid = sha256.hexdigest()
     if realoid != oid:
         raise error.Abort(_('detected corrupt lfs object: %s') % oid,
                           hint=_('run hg verify'))
 
 def remote(repo):
     """remotestore factory. return a store in _storemap depending on config"""
     url = util.url(repo.ui.config('lfs', 'url') or '')
     scheme = url.scheme
     if scheme not in _storemap:
         raise error.Abort(_('lfs: unknown url scheme: %s') % scheme)
     return _storemap[scheme](repo, url)
 
 class LfsRemoteError(error.RevlogError):
     pass

tests/test-lfs-test-server.t

@@ -1,279 +1,273 b''
 #require lfs-test-server
 
   $ LFS_LISTEN="tcp://:$HGPORT"
   $ LFS_HOST="localhost:$HGPORT"
   $ LFS_PUBLIC=1
   $ export LFS_LISTEN LFS_HOST LFS_PUBLIC
 #if no-windows
   $ lfs-test-server &> lfs-server.log &
   $ echo $! >> $DAEMON_PIDS
 #else
   $ cat >> $TESTTMP/spawn.py <<EOF
   > import os
   > import subprocess
   > import sys
   > 
   > for path in os.environ["PATH"].split(os.pathsep):
   >     exe = os.path.join(path, 'lfs-test-server.exe')
   >     if os.path.exists(exe):
   >         with open('lfs-server.log', 'wb') as out:
   >             p = subprocess.Popen(exe, stdout=out, stderr=out)
   >             sys.stdout.write('%s\n' % p.pid)
   >             sys.exit(0)
   > sys.exit(1)
   > EOF
   $ $PYTHON $TESTTMP/spawn.py >> $DAEMON_PIDS
 #endif
 
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > lfs=
   > [lfs]
   > url=http://foo:bar@$LFS_HOST/
   > track=all()
   > EOF
 
   $ hg init repo1
   $ cd repo1
   $ echo THIS-IS-LFS > a
   $ hg commit -m a -A a
 
 A push can be serviced directly from the usercache if it isn't in the local
 store.
 
   $ hg init ../repo2
   $ mv .hg/store/lfs .hg/store/lfs_
   $ hg push ../repo2 -v
   pushing to ../repo2
   searching for changes
   lfs: uploading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
   lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
   lfs: uploaded 1 files (12 bytes)
   1 changesets found
   uncompressed size of bundle content:
        * (changelog) (glob)
        * (manifests) (glob)
        *  a (glob)
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 1 changes to 1 files
   calling hook pretxnchangegroup.lfs: hgext.lfs.checkrequireslfs
   $ mv .hg/store/lfs_ .hg/store/lfs
 
 Clear the cache to force a download
   $ rm -rf `hg config lfs.usercache`
   $ cd ../repo2
   $ hg update tip -v
   resolving manifests
   lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
   lfs: adding 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b to the usercache
   lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
   getting a
   lfs: found 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b in the local lfs store
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 When the server has some blobs already
 
   $ hg mv a b
   $ echo ANOTHER-LARGE-FILE > c
   $ echo ANOTHER-LARGE-FILE2 > d
   $ hg commit -m b-and-c -A b c d
   $ hg push ../repo1 -v | grep -v '^  '
   pushing to ../repo1
   searching for changes
   lfs: need to transfer 2 objects (39 bytes)
   lfs: uploading 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 (20 bytes)
   lfs: processed: 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19
   lfs: uploading d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 (19 bytes)
   lfs: processed: d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
   lfs: uploaded 2 files (39 bytes)
   1 changesets found
   uncompressed size of bundle content:
   adding changesets
   adding manifests
   adding file changes
   added 1 changesets with 3 changes to 3 files
 
 Clear the cache to force a download
   $ rm -rf `hg config lfs.usercache`
   $ hg --repo ../repo1 update tip -v
   resolving manifests
   lfs: need to transfer 2 objects (39 bytes)
   lfs: downloading 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 (20 bytes)
   lfs: adding 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 to the usercache
   lfs: processed: 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19
   lfs: downloading d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 (19 bytes)
   lfs: adding d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 to the usercache
   lfs: processed: d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
   getting b
   lfs: found 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b in the local lfs store
   getting c
   lfs: found d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 in the local lfs store
   getting d
   lfs: found 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 in the local lfs store
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 Test a corrupt file download, but clear the cache first to force a download.
 
   $ rm -rf `hg config lfs.usercache`
   $ cp $TESTTMP/lfs-content/d1/1e/1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 blob
   $ echo 'damage' > $TESTTMP/lfs-content/d1/1e/1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
   $ rm ../repo1/.hg/store/lfs/objects/d1/1e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
   $ rm ../repo1/*
 
   $ hg --repo ../repo1 update -C tip -v
   resolving manifests
   lfs: downloading d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 (19 bytes)
   abort: corrupt remote lfs object: d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
   [255]
 
 The corrupted blob is not added to the usercache or local store
 
   $ test -f ../repo1/.hg/store/lfs/objects/d1/1e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
   [1]
   $ test -f `hg config lfs.usercache`/d1/1e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
   [1]
   $ cp blob $TESTTMP/lfs-content/d1/1e/1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
 
 Test a corrupted file upload
 
   $ echo 'another lfs blob' > b
   $ hg ci -m 'another blob'
   $ echo 'damage' > .hg/store/lfs/objects/e6/59058e26b07b39d2a9c7145b3f99b41f797b6621c8076600e9cb7ee88291f0
   $ hg push -v ../repo1
   pushing to ../repo1
   searching for changes
   lfs: uploading e659058e26b07b39d2a9c7145b3f99b41f797b6621c8076600e9cb7ee88291f0 (17 bytes)
   abort: detected corrupt lfs object: e659058e26b07b39d2a9c7145b3f99b41f797b6621c8076600e9cb7ee88291f0
   (run hg verify)
   [255]
 
 Archive will prefetch blobs in a group
 
   $ rm -rf .hg/store/lfs `hg config lfs.usercache`
   $ hg archive -vr 1 ../archive
-  lfs: need to transfer 4 objects (63 bytes)
+  lfs: need to transfer 3 objects (51 bytes)
   lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
   lfs: adding 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b to the usercache
   lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
-  lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
-  lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
   lfs: downloading 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 (20 bytes)
   lfs: adding 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 to the usercache
   lfs: processed: 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19
   lfs: downloading d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 (19 bytes)
   lfs: adding d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 to the usercache
   lfs: processed: d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
   lfs: found 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b in the local lfs store
   lfs: found 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b in the local lfs store
   lfs: found d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 in the local lfs store
   lfs: found 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 in the local lfs store
   $ find ../archive | sort
   ../archive
   ../archive/.hg_archival.txt
   ../archive/a
   ../archive/b
   ../archive/c
   ../archive/d
 
 Cat will prefetch blobs in a group
 
   $ rm -rf .hg/store/lfs `hg config lfs.usercache`
   $ hg cat -vr 1 a b c
-  lfs: need to transfer 3 objects (43 bytes)
+  lfs: need to transfer 2 objects (31 bytes)
   lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
   lfs: adding 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b to the usercache
   lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
-  lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
-  lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
   lfs: downloading d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 (19 bytes)
   lfs: adding d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 to the usercache
   lfs: processed: d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
   lfs: found 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b in the local lfs store
   THIS-IS-LFS
   lfs: found 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b in the local lfs store
   THIS-IS-LFS
   lfs: found d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 in the local lfs store
   ANOTHER-LARGE-FILE
 
 Revert will prefetch blobs in a group
 
   $ rm -rf .hg/store/lfs
   $ rm -rf `hg config lfs.usercache`
   $ rm *
   $ hg revert --all -r 1 -v
   adding a
   reverting b
   reverting c
   reverting d
-  lfs: need to transfer 4 objects (63 bytes)
+  lfs: need to transfer 3 objects (51 bytes)
   lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
   lfs: adding 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b to the usercache
   lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
-  lfs: downloading 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b (12 bytes)
-  lfs: processed: 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b
   lfs: downloading 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 (20 bytes)
   lfs: adding 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 to the usercache
   lfs: processed: 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19
   lfs: downloading d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 (19 bytes)
   lfs: adding d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 to the usercache
   lfs: processed: d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998
   lfs: found 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b in the local lfs store
   lfs: found d11e1a642b60813aee592094109b406089b8dff4cb157157f753418ec7857998 in the local lfs store
   lfs: found 37a65ab78d5ecda767e8622c248b5dbff1e68b1678ab0e730d5eb8601ec8ad19 in the local lfs store
   lfs: found 31cf46fbc4ecd458a0943c5b4881f1f5a6dd36c53d6167d5b69ac45149b38e5b in the local lfs store
 
 Check error message when the remote missed a blob:
 
   $ echo FFFFF > b
   $ hg commit -m b -A b
   $ echo FFFFF >> b
   $ hg commit -m b b
   $ rm -rf .hg/store/lfs
   $ rm -rf `hg config lfs.usercache`
   $ hg update -C '.^'
   abort: LFS server error. Remote object for "b" not found:(.*)! (re)
   [255]
 
 Check error message when object does not exist:
 
   $ cd $TESTTMP
   $ hg init test && cd test
   $ echo "[extensions]" >> .hg/hgrc
   $ echo "lfs=" >> .hg/hgrc
   $ echo "[lfs]" >> .hg/hgrc
   $ echo "threshold=1" >> .hg/hgrc
   $ echo a > a
   $ hg add a
   $ hg commit -m 'test'
   $ echo aaaaa > a
   $ hg commit -m 'largefile'
   $ hg debugdata .hg/store/data/a.i 1 # verify this is no the file content but includes "oid", the LFS "pointer".
   version https://git-lfs.github.com/spec/v1
   oid sha256:bdc26931acfb734b142a8d675f205becf27560dc461f501822de13274fe6fc8a
   size 6
   x-is-binary 0
   $ cd ..
   $ rm -rf `hg config lfs.usercache`
 
 (Restart the server in a different location so it no longer has the content)
 
   $ $PYTHON $RUNTESTDIR/killdaemons.py $DAEMON_PIDS
   $ rm $DAEMON_PIDS
   $ mkdir $TESTTMP/lfs-server2
   $ cd $TESTTMP/lfs-server2
 #if no-windows
   $ lfs-test-server &> lfs-server.log &
   $ echo $! >> $DAEMON_PIDS
 #else
   $ $PYTHON $TESTTMP/spawn.py >> $DAEMON_PIDS
 #endif
 
   $ cd $TESTTMP
   $ hg clone test test2
   updating to branch default
   abort: LFS server error. Remote object for "a" not found:(.*)! (re)
   [255]
 
   $ $PYTHON $RUNTESTDIR/killdaemons.py $DAEMON_PIDS