view hgext/relink.py @ 31793:69d8fcf20014

help: document bundle specifications

I softly formalized the concept of a "bundle specification" a while
ago when I was working on clone bundles and stream clone bundles and
wanted a more robust way to define what exactly is in a bundle file.

The concept has existed for a while. Since it is part of the clone
bundles feature and exposed to the user via the "-t" argument to
`hg bundle`, it is something we need to support for the long haul.

After the 4.1 release, I heard a few people comment that they didn't
realize you could generate zstd bundles with `hg bundle`. I'm
partially to blame for not documenting it in bundle's docstring.

Additionally, I added a hacky, experimental feature for controlling
the compression level of bundles in 76104a4899ad. As the commit
message says, I went with a quick and dirty solution out of time
constraints. Furthermore, I wanted to eventually store this
configuration in the "bundlespec" so it could be made more flexible.

Given:

a) bundlespecs are here to stay
b) we don't have great documentation over what they are, despite being
   a user-facing feature
c) the list of available compression engines and their behavior isn't
   exposed
d) we need an extensible place to modify behavior of compression
   engines

I want to move forward with formalizing bundlespecs as a user-facing
feature. This commit does that by introducing a "bundlespec" help
page. Leaning on the just-added compression engine documentation
and API, the topic also conveniently lists available compression
engines and details about them. This makes features like zstd
bundle compression more discoverable. e.g. you can now
`hg help -k zstd` and it lists the "bundlespec" topic.

# Mercurial extension to provide 'hg relink' command
#
# Copyright (C) 2007 Brendan Cully <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

"""recreates hardlinks between repository clones"""
from __future__ import absolute_import

import os
import stat

from mercurial.i18n import _
from mercurial import (
    cmdutil,
    error,
    hg,
    util,
)

cmdtable = {}
command = cmdutil.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = 'ships-with-hg-core'

@command('relink', [], _('[ORIGIN]'))
def relink(ui, repo, origin=None, **opts):
    """recreate hardlinks between two repositories

    When repositories are cloned locally, their data files will be
    hardlinked so that they only use the space of a single repository.

    Unfortunately, subsequent pulls into either repository will break
    hardlinks for any files touched by the new changesets, even if
    both repositories end up pulling the same changes.

    Similarly, passing --rev to "hg clone" will fail to use any
    hardlinks, falling back to a complete copy of the source
    repository.

    This command lets you recreate those hardlinks and reclaim that
    wasted space.

    This repository will be relinked to share space with ORIGIN, which
    must be on the same local disk. If ORIGIN is omitted, looks for
    "default-relink", then "default", in [paths].

    Do not attempt any read operations on this repository while the
    command is running. (Both repositories will be locked against
    writes.)
    """
    if (not util.safehasattr(util, 'samefile') or
        not util.safehasattr(util, 'samedevice')):
        raise error.Abort(_('hardlinks are not supported on this system'))
    src = hg.repository(repo.baseui, ui.expandpath(origin or 'default-relink',
                                          origin or 'default'))
    ui.status(_('relinking %s to %s\n') % (src.store.path, repo.store.path))
    if repo.root == src.root:
        ui.status(_('there is nothing to relink\n'))
        return

    if not util.samedevice(src.store.path, repo.store.path):
        # No point in continuing
        raise error.Abort(_('source and destination are on different devices'))

    locallock = repo.lock()
    try:
        remotelock = src.lock()
        try:
            candidates = sorted(collect(src, ui))
            targets = prune(candidates, src.store.path, repo.store.path, ui)
            do_relink(src.store.path, repo.store.path, targets, ui)
        finally:
            remotelock.release()
    finally:
        locallock.release()

def collect(src, ui):
    seplen = len(os.path.sep)
    candidates = []
    live = len(src['tip'].manifest())
    # Your average repository has some files which were deleted before
    # the tip revision. We account for that by assuming that there are
    # 3 tracked files for every 2 live files as of the tip version of
    # the repository.
    #
    # mozilla-central as of 2010-06-10 had a ratio of just over 7:5.
    total = live * 3 // 2
    src = src.store.path
    pos = 0
    ui.status(_("tip has %d files, estimated total number of files: %d\n")
              % (live, total))
    for dirpath, dirnames, filenames in os.walk(src):
        dirnames.sort()
        relpath = dirpath[len(src) + seplen:]
        for filename in sorted(filenames):
            if filename[-2:] not in ('.d', '.i'):
                continue
            st = os.stat(os.path.join(dirpath, filename))
            if not stat.S_ISREG(st.st_mode):
                continue
            pos += 1
            candidates.append((os.path.join(relpath, filename), st))
            ui.progress(_('collecting'), pos, filename, _('files'), total)

    ui.progress(_('collecting'), None)
    ui.status(_('collected %d candidate storage files\n') % len(candidates))
    return candidates

def prune(candidates, src, dst, ui):
    def linkfilter(src, dst, st):
        try:
            ts = os.stat(dst)
        except OSError:
            # Destination doesn't have this file?
            return False
        if util.samefile(src, dst):
            return False
        if not util.samedevice(src, dst):
            # No point in continuing
            raise error.Abort(
                _('source and destination are on different devices'))
        if st.st_size != ts.st_size:
            return False
        return st

    targets = []
    total = len(candidates)
    pos = 0
    for fn, st in candidates:
        pos += 1
        srcpath = os.path.join(src, fn)
        tgt = os.path.join(dst, fn)
        ts = linkfilter(srcpath, tgt, st)
        if not ts:
            ui.debug('not linkable: %s\n' % fn)
            continue
        targets.append((fn, ts.st_size))
        ui.progress(_('pruning'), pos, fn, _('files'), total)

    ui.progress(_('pruning'), None)
    ui.status(_('pruned down to %d probably relinkable files\n') % len(targets))
    return targets

def do_relink(src, dst, files, ui):
    def relinkfile(src, dst):
        bak = dst + '.bak'
        os.rename(dst, bak)
        try:
            util.oslink(src, dst)
        except OSError:
            os.rename(bak, dst)
            raise
        os.remove(bak)

    CHUNKLEN = 65536
    relinked = 0
    savedbytes = 0

    pos = 0
    total = len(files)
    for f, sz in files:
        pos += 1
        source = os.path.join(src, f)
        tgt = os.path.join(dst, f)
        # Binary mode, so that read() works correctly, especially on Windows
        sfp = file(source, 'rb')
        dfp = file(tgt, 'rb')
        sin = sfp.read(CHUNKLEN)
        while sin:
            din = dfp.read(CHUNKLEN)
            if sin != din:
                break
            sin = sfp.read(CHUNKLEN)
        sfp.close()
        dfp.close()
        if sin:
            ui.debug('not linkable: %s\n' % f)
            continue
        try:
            relinkfile(source, tgt)
            ui.progress(_('relinking'), pos, f, _('files'), total)
            relinked += 1
            savedbytes += sz
        except OSError as inst:
            ui.warn('%s: %s\n' % (tgt, str(inst)))

    ui.progress(_('relinking'), None)

    ui.status(_('relinked %d files (%s reclaimed)\n') %
              (relinked, util.bytecount(savedbytes)))