view hgext/relink.py @ 21424:d13b4ecdb680

test: split test-largefile.t in multiple file The `test-largefiles.t` unified test is significantly longer (about 30%) than any other tests in the mercurial test suite. As a result, its is alway the last test my test runner is waiting for at the end of a run. In practice, this means that `test-largefile.t` is wasting half a minute of my life every times I'm running the mercurial test suites. This probably mean more a few cumulated day by now. I've finally decided to split it up in multiple smaller tests to bring it back in reasonable length. This changeset extracts independent test cases in two files. One dedicated to wire protocole testing, and another one dedicated to all other tests that could be independently extracted. No test case were haltered in the making of this changeset. Various timing available below. All timing have been done on a with 90 jobs on a 64 cores machine. Similar result are shown on firefly (20 jobs on 12 core). General timing of the whole run -------------------------------- We see a 25% real time improvement for no significant cpu time impact. Before split: real 2m1.149s user 58m4.662s sys 11m28.563s After split: real 1m31.977s user 57m45.993s sys 11m33.634s Last test to finish (using run-test.py --time) ---------------------------------------------- test-largefile.t is now finishing at the same time than other slow tests. Before split: Time Test 119.280 test-largefiles.t 93.995 test-mq.t 89.897 test-subrepo.t 86.920 test-glog.t 85.508 test-rename-merge2.t 83.594 test-revset.t 79.824 test-keyword.t 78.077 test-mq-header-date.t After split: Time Test 90.414 test-mq.t 88.594 test-largefiles.t 85.363 test-subrepo.t 81.059 test-glog.t 78.927 test-rename-merge2.t 78.021 test-revset.t 77.777 test-command-template.t Timing of largefile test themself ----------------------------------- Running only tests prefixed with "test-largefiles". No significant change in cumulated time. Before: Time Test 58.673 test-largefiles.t 2.931 test-largefiles-cache.t 0.583 test-largefiles-small-disk.t After: Time Test 31.754 test-largefiles.t 17.460 test-largefiles-misc.t 8.888 test-largefiles-wireproto.t 2.864 test-largefiles-cache.t 0.580 test-largefiles-small-disk.t
author Pierre-Yves David <pierre-yves.david@fb.com>
date Fri, 16 May 2014 13:18:57 -0700
parents da0eb4970913
children 80c5b2666a96
line wrap: on
line source

# Mercurial extension to provide 'hg relink' command
#
# Copyright (C) 2007 Brendan Cully <brendan@kublai.com>
#
# 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 mercurial import cmdutil, hg, util
from mercurial.i18n import _
import os, stat

cmdtable = {}
command = cmdutil.command(cmdtable)
testedwith = 'internal'

@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 util.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 util.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: %s\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 util.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, 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)))