Add support for cloning with hardlinks on windows. In order to use hardlinks, the win32file module is needed, and this is present in ActivePython. If it isn't present, or hardlinks are not supported on the underlying filesystem, a regular copy is used. When using hardlinks the biggest benefit is probably the saving in space, but cloning can be much quicker. For example cloning the Xen tree (non trivial) without an update goes from about 95s to 15s. Unix-like platforms should be unaffected, although should be more tolerant on filesystems that don't support hard links. (tweaked by mpm to deal with new copyfiles function) --- hg.orig/mercurial/commands.py 2005-09-13 19:32:53.000000000 -0500 +++ hg/mercurial/commands.py 2005-09-14 12:11:34.000000000 -0500 @@ -620,10 +620,6 @@ def clone(ui, source, dest=None, **opts) if other.dev() != -1: abspath = os.path.abspath(source) - copyfile = (os.stat(dest).st_dev == other.dev() - and getattr(os, 'link', None) or shutil.copy2) - if copyfile is not shutil.copy2: - ui.note("cloning by hardlink\n") # we use a lock here because if we race with commit, we can # end up with extra data in the cloned revlogs that's not @@ -638,7 +634,7 @@ def clone(ui, source, dest=None, **opts) for f in files.split(): src = os.path.join(source, ".hg", f) dst = os.path.join(dest, ".hg", f) - util.copyfiles(src, dst, copyfile) + util.copyfiles(src, dst) repo = hg.repository(ui, dest) Index: hg/mercurial/util.py =================================================================== --- hg.orig/mercurial/util.py 2005-09-08 00:15:25.000000000 -0500 +++ hg/mercurial/util.py 2005-09-14 12:16:49.000000000 -0500 @@ -12,7 +12,7 @@ platform-specific details from the core. import os, errno from demandload import * -demandload(globals(), "re cStringIO") +demandload(globals(), "re cStringIO shutil") def binary(s): """return true if a string is binary data using diff's heuristic""" @@ -217,17 +217,28 @@ def rename(src, dst): os.unlink(dst) os.rename(src, dst) -def copyfiles(src, dst, copyfile): - """Copy a directory tree, files are copied using 'copyfile'.""" +def copyfiles(src, dst, hardlink=None): + """Copy a directory tree using hardlinks if possible""" + + if hardlink is None: + hardlink = (os.stat(src).st_dev == + os.stat(os.path.dirname(dst)).st_dev) if os.path.isdir(src): os.mkdir(dst) for name in os.listdir(src): srcname = os.path.join(src, name) dstname = os.path.join(dst, name) - copyfiles(srcname, dstname, copyfile) + copyfiles(srcname, dstname, hardlink) else: - copyfile(src, dst) + if hardlink: + try: + os_link(src, dst) + except: + hardlink = False + shutil.copy2(src, dst) + else: + shutil.copy2(src, dst) def opener(base): """ @@ -244,13 +255,13 @@ def opener(base): if mode[0] != "r": try: - s = os.stat(f) + nlink = nlinks(f) except OSError: d = os.path.dirname(f) if not os.path.isdir(d): os.makedirs(d) else: - if s.st_nlink > 1: + if nlink > 1: file(f + ".tmp", "wb").write(file(f, "rb").read()) rename(f+".tmp", f) @@ -266,10 +277,41 @@ def _makelock_file(info, pathname): def _readlock_file(pathname): return file(pathname).read() +def nlinks(pathname): + """Return number of hardlinks for the given file.""" + return os.stat(pathname).st_nlink + +if hasattr(os, 'link'): + os_link = os.link +else: + def os_link(src, dst): + raise OSError(0, "Hardlinks not supported") + # Platform specific variants if os.name == 'nt': nulldev = 'NUL:' + try: # ActivePython can create hard links using win32file module + import win32file + + def os_link(src, dst): # NB will only succeed on NTFS + win32file.CreateHardLink(dst, src) + + def nlinks(pathname): + """Return number of hardlinks for the given file.""" + try: + fh = win32file.CreateFile(pathname, + win32file.GENERIC_READ, win32file.FILE_SHARE_READ, + None, win32file.OPEN_EXISTING, 0, None) + res = win32file.GetFileInformationByHandle(fh) + fh.Close() + return res[7] + except: + return os.stat(pathname).st_nlink + + except ImportError: + pass + def is_exec(f, last): return last

                    Mercurial      git                     BK (*)
storage             revlog delta   compressed revisions    SCCS weave
storage naming      by filename    by revision hash        by filename
merge               file DAGs      changeset DAG           file DAGs?
consistency         SHA1           SHA1                    CRC
signable?           yes            yes                     no       

retrieve file tip   O(1)           O(1)                    O(revs)
add rev             O(1)           O(1)                    O(revs)
find prev file rev  O(1)           O(changesets)           O(revs)
annotate file       O(revs)        O(changesets)           O(revs)
find file changeset O(1)           O(changesets)           ?

checkout            O(files)       O(files)                O(revs)?
commit              O(changes)     O(changes)              ?
                    6 patches/s    6 patches/s             slow
diff working dir    O(changes)     O(changes)              ?
                    < 1s           < 1s                    ?
tree diff revs      O(changes)     O(changes)              ?
                    < 1s           < 1s                    ?
hardlink clone      O(files)       O(revisions)            O(files)

find remote csets   O(log new)     rsync: O(revisions)     ?
                                   git-http: O(changesets)
pull remote csets   O(patch)       O(modified files)       O(patch)

repo growth         O(patch)       O(revisions)            O(patch)
 kernel history     300M           3.5G?                   250M?
lines of code       2500           6500 (+ cogito)         ??

* I've never used BK so this is just guesses