view hgext/relink.py @ 33649:377e8ddaebef stable

pathauditor: disable cache of audited paths by default (issue5628)

The initial attempt was to discard cache when appropriate, but it appears
to be error prone. We had to carefully inspect all places where audit() is
called e.g. without actually updating filesystem, before removing files and
directories, etc.

So, this patch disables the cache of audited paths by default, and enables
it only for the following cases:

 - short-lived auditor objects
 - repo.vfs, repo.svfs, and repo.cachevfs, which are managed directories
   and considered sort of append-only (a file/directory would never be
   replaced with a symlink)

There would be more cacheable vfs objects (e.g. mq.queue.opener), but I
decided not to inspect all of them in this patch. We can make them cached
later.

Benchmark result:

- using old clone of http://selenic.com/repo/linux-2.6/ (38319 files)
- on tmpfs
- run HGRCPATH=/dev/null hg up -q --time tip && hg up -q null
- try 4 times and take the last three results

original:
real 7.480 secs (user 1.140+22.760 sys 0.150+1.690)
real 8.010 secs (user 1.070+22.280 sys 0.170+2.120)
real 7.470 secs (user 1.120+22.390 sys 0.120+1.910)

clearcache (the other series):
real 7.680 secs (user 1.120+23.420 sys 0.140+1.970)
real 7.670 secs (user 1.110+23.620 sys 0.130+1.810)
real 7.740 secs (user 1.090+23.510 sys 0.160+1.940)

enable cache only for vfs and svfs (this series):
real 8.730 secs (user 1.500+25.190 sys 0.260+2.260)
real 8.750 secs (user 1.490+25.170 sys 0.250+2.340)
real 9.010 secs (user 1.680+25.340 sys 0.280+2.540)

remove cache function at all (for reference):
real 9.620 secs (user 1.440+27.120 sys 0.250+2.980)
real 9.420 secs (user 1.400+26.940 sys 0.320+3.130)
real 9.760 secs (user 1.530+27.270 sys 0.250+2.970)

# 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 (
    error,
    hg,
    registrar,
    util,
)

cmdtable = {}
command = registrar.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)))