hgext/relink.py

copies: iterate over children directly (instead of parents)

Before this change we would gather all parent → child edges and iterate on
all parent, gathering copy information for children and aggregating them from
there.

They are not strict requirement for edges to be processed in that specific
order. We could also simply iterate over all "children" revision and aggregate
data from both parents at the same time. This patch does that.

It make various things simpler:

 * since both parents are processed at the same time, we no longer need to
   cache data for merge (see next changeset for details),

 * we no longer need nested loop to process data,

 * we no longer need to store partial merge data for a rev from distinct loop
   interaction to another when processing merges,

 * we no longer need to build a full parent -> children mapping (we only rely on
   a simpler "parent -> number of children" map (for memory efficiency),

 * the data access pattern is now simpler (from lower revisions to higher
   revisions) and entirely predicable. That predictability open the way to
   prefetching and parallel processing.

So that new iterations order requires simpler code and open the way to
interesting optimisation.

The effect on performance is quite good. In the worse case, we don't see any
significant negative impact. And in the best case, the reduction of roundtrip
to Python provide us with a significant speed. Some example below:

Repo            Case                                  Source-Rev   Dest-Rev      # of revisions  old time    new time      Difference    Factor    time per rev
---------------------------------------------------------------------------------------------------------------------------------------------------------------
mozilla-try     x00000_revs_x00000_added_0_copies     dc8a3ca7010e d16fde900c9c :  34414 revs,   0.962867 s,   0.502584 s,  -0.460283 s, × 0.5220,    14 µs/rev
mozilla-try     x0000_revs_xx000_added_x_copies       156f6e2674f2 4d0f2c178e66 :   8598 revs,   0.110717 s,   0.076323 s,  -0.034394 s, × 0.6894,     8 µs/rev



# full comparison between the previous changeset and this one

Repo            Case                                  Source-Rev   Dest-Rev      # of revisions  old time    new time      Difference    Factor    time per rev
---------------------------------------------------------------------------------------------------------------------------------------------------------------
mercurial       x_revs_x_added_0_copies               ad6b123de1c7 39cfcef4f463 :      1 revs,   0.000048 s,   0.000041 s,  -0.000007 s, × 0.8542,    41 µs/rev
mercurial       x_revs_x_added_x_copies               2b1c78674230 0c1d10351869 :      6 revs,   0.000153 s,   0.000102 s,  -0.000051 s, × 0.6667,    17 µs/rev
mercurial       x000_revs_x000_added_x_copies         81f8ff2a9bf2 dd3267698d84 :   1032 revs,   0.004209 s,   0.004254 s,  +0.000045 s, × 1.0107,     4 µs/rev
pypy            x_revs_x_added_0_copies               aed021ee8ae8 099ed31b181b :      9 revs,   0.000203 s,   0.000282 s,  +0.000079 s, × 1.3892,    31 µs/rev
pypy            x_revs_x000_added_0_copies            4aa4e1f8e19a 359343b9ac0e :      1 revs,   0.000059 s,   0.000048 s,  -0.000011 s, × 0.8136,    48 µs/rev
pypy            x_revs_x_added_x_copies               ac52eb7bbbb0 72e022663155 :      7 revs,   0.000194 s,   0.000211 s,  +0.000017 s, × 1.0876,    30 µs/rev
pypy            x_revs_x00_added_x_copies             c3b14617fbd7 ace7255d9a26 :      1 revs,   0.000380 s,   0.000375 s,  -0.000005 s, × 0.9868,   375 µs/rev
pypy            x_revs_x000_added_x000_copies         df6f7a526b60 a83dc6a2d56f :      6 revs,   0.010588 s,   0.010574 s,  -0.000014 s, × 0.9987,  1762 µs/rev
pypy            x000_revs_xx00_added_0_copies         89a76aede314 2f22446ff07e :   4785 revs,   0.048961 s,   0.049974 s,  +0.001013 s, × 1.0207,    10 µs/rev
pypy            x000_revs_x000_added_x_copies         8a3b5bfd266e 2c68e87c3efe :   6780 revs,   0.083612 s,   0.084300 s,  +0.000688 s, × 1.0082,    12 µs/rev
pypy            x000_revs_x000_added_x000_copies      89a76aede314 7b3dda341c84 :   5441 revs,   0.058579 s,   0.060128 s,  +0.001549 s, × 1.0264,    11 µs/rev
pypy            x0000_revs_x_added_0_copies           d1defd0dc478 c9cb1334cc78 :  43645 revs,   0.736783 s,   0.686542 s,  -0.050241 s, × 0.9318,    15 µs/rev
pypy            x0000_revs_xx000_added_0_copies       bf2c629d0071 4ffed77c095c :      2 revs,   0.022050 s,   0.009277 s,  -0.012773 s, × 0.4207,  4638 µs/rev
pypy            x0000_revs_xx000_added_x000_copies    08ea3258278e d9fa043f30c0 :  11316 revs,   0.120800 s,   0.114733 s,  -0.006067 s, × 0.9498,    10 µs/rev
netbeans        x_revs_x_added_0_copies               fb0955ffcbcd a01e9239f9e7 :      2 revs,   0.000140 s,   0.000081 s,  -0.000059 s, × 0.5786,    40 µs/rev
netbeans        x_revs_x000_added_0_copies            6f360122949f 20eb231cc7d0 :      2 revs,   0.000114 s,   0.000107 s,  -0.000007 s, × 0.9386,    53 µs/rev
netbeans        x_revs_x_added_x_copies               1ada3faf6fb6 5a39d12eecf4 :      3 revs,   0.000224 s,   0.000173 s,  -0.000051 s, × 0.7723,    57 µs/rev
netbeans        x_revs_x00_added_x_copies             35be93ba1e2c 9eec5e90c05f :      9 revs,   0.000723 s,   0.000698 s,  -0.000025 s, × 0.9654,    77 µs/rev
netbeans        x000_revs_xx00_added_0_copies         eac3045b4fdd 51d4ae7f1290 :   1421 revs,   0.009665 s,   0.009248 s,  -0.000417 s, × 0.9569,     6 µs/rev
netbeans        x000_revs_x000_added_x_copies         e2063d266acd 6081d72689dc :   1533 revs,   0.014820 s,   0.015446 s,  +0.000626 s, × 1.0422,    10 µs/rev
netbeans        x000_revs_x000_added_x000_copies      ff453e9fee32 411350406ec2 :   5750 revs,   0.076049 s,   0.074373 s,  -0.001676 s, × 0.9780,    12 µs/rev
netbeans        x0000_revs_xx000_added_x000_copies    588c2d1ced70 1aad62e59ddd :  66949 revs,   0.683603 s,   0.639870 s,  -0.043733 s, × 0.9360,     9 µs/rev
mozilla-central x_revs_x_added_0_copies               3697f962bb7b 7015fcdd43a2 :      2 revs,   0.000161 s,   0.000088 s,  -0.000073 s, × 0.5466,    44 µs/rev
mozilla-central x_revs_x000_added_0_copies            dd390860c6c9 40d0c5bed75d :      8 revs,   0.000234 s,   0.000199 s,  -0.000035 s, × 0.8504,    24 µs/rev
mozilla-central x_revs_x_added_x_copies               8d198483ae3b 14207ffc2b2f :      9 revs,   0.000247 s,   0.000171 s,  -0.000076 s, × 0.6923,    19 µs/rev
mozilla-central x_revs_x00_added_x_copies             98cbc58cc6bc 446a150332c3 :      7 revs,   0.000630 s,   0.000592 s,  -0.000038 s, × 0.9397,    84 µs/rev
mozilla-central x_revs_x000_added_x000_copies         3c684b4b8f68 0a5e72d1b479 :      3 revs,   0.003286 s,   0.003151 s,  -0.000135 s, × 0.9589,  1050 µs/rev
mozilla-central x_revs_x0000_added_x0000_copies       effb563bb7e5 c07a39dc4e80 :      6 revs,   0.062441 s,   0.061612 s,  -0.000829 s, × 0.9867, 10268 µs/rev
mozilla-central x000_revs_xx00_added_0_copies         6100d773079a 04a55431795e :   1593 revs,   0.005423 s,   0.005381 s,  -0.000042 s, × 0.9923,     3 µs/rev
mozilla-central x000_revs_x000_added_x_copies         9f17a6fc04f9 2d37b966abed :     41 revs,   0.005919 s,   0.003742 s,  -0.002177 s, × 0.6322,    91 µs/rev
mozilla-central x000_revs_x000_added_x000_copies      7c97034feb78 4407bd0c6330 :   7839 revs,   0.062597 s,   0.061983 s,  -0.000614 s, × 0.9902,     7 µs/rev
mozilla-central x0000_revs_xx000_added_0_copies       9eec5917337d 67118cc6dcad :    615 revs,   0.043551 s,   0.019861 s,  -0.023690 s, × 0.4560,    32 µs/rev
mozilla-central x0000_revs_xx000_added_x000_copies    f78c615a656c 96a38b690156 :  30263 revs,   0.192475 s,   0.188101 s,  -0.004374 s, × 0.9773,     6 µs/rev
mozilla-central x00000_revs_x0000_added_x0000_copies  6832ae71433c 4c222a1d9a00 : 153721 revs,   1.955575 s,   1.806696 s,  -0.148879 s, × 0.9239,    11 µs/rev
mozilla-central x00000_revs_x00000_added_x000_copies  76caed42cf7c 1daa622bbe42 : 204976 revs,   2.886501 s,   2.682987 s,  -0.203514 s, × 0.9295,    13 µs/rev
mozilla-try     x_revs_x_added_0_copies               aaf6dde0deb8 9790f499805a :      2 revs,   0.001181 s,   0.000852 s,  -0.000329 s, × 0.7214,   426 µs/rev
mozilla-try     x_revs_x000_added_0_copies            d8d0222927b4 5bb8ce8c7450 :      2 revs,   0.001189 s,   0.000859 s,  -0.000330 s, × 0.7225,   429 µs/rev
mozilla-try     x_revs_x_added_x_copies               092fcca11bdb 936255a0384a :      4 revs,   0.000563 s,   0.000150 s,  -0.000413 s, × 0.2664,    37 µs/rev
mozilla-try     x_revs_x00_added_x_copies             b53d2fadbdb5 017afae788ec :      2 revs,   0.001548 s,   0.001158 s,  -0.000390 s, × 0.7481,   579 µs/rev
mozilla-try     x_revs_x000_added_x000_copies         20408ad61ce5 6f0ee96e21ad :      1 revs,   0.027782 s,   0.027240 s,  -0.000542 s, × 0.9805, 27240 µs/rev
mozilla-try     x_revs_x0000_added_x0000_copies       effb563bb7e5 c07a39dc4e80 :      6 revs,   0.062781 s,   0.062824 s,  +0.000043 s, × 1.0007, 10470 µs/rev
mozilla-try     x000_revs_xx00_added_0_copies         6100d773079a 04a55431795e :   1593 revs,   0.005778 s,   0.005463 s,  -0.000315 s, × 0.9455,     3 µs/rev
mozilla-try     x000_revs_x000_added_x_copies         9f17a6fc04f9 2d37b966abed :     41 revs,   0.006192 s,   0.004238 s,  -0.001954 s, × 0.6844,   103 µs/rev
mozilla-try     x000_revs_x000_added_x000_copies      1346fd0130e4 4c65cbdabc1f :   6657 revs,   0.065391 s,   0.064113 s,  -0.001278 s, × 0.9805,     9 µs/rev
mozilla-try     x0000_revs_x_added_0_copies           63519bfd42ee a36a2a865d92 :  40314 revs,   0.317216 s,   0.294063 s,  -0.023153 s, × 0.9270,     7 µs/rev
mozilla-try     x0000_revs_x_added_x_copies           9fe69ff0762d bcabf2a78927 :  38690 revs,   0.303119 s,   0.281493 s,  -0.021626 s, × 0.9287,     7 µs/rev
mozilla-try     x0000_revs_xx000_added_x_copies       156f6e2674f2 4d0f2c178e66 :   8598 revs,   0.110717 s,   0.076323 s,  -0.034394 s, × 0.6894,     8 µs/rev
mozilla-try     x0000_revs_xx000_added_0_copies       9eec5917337d 67118cc6dcad :    615 revs,   0.045739 s,   0.020390 s,  -0.025349 s, × 0.4458,    33 µs/rev
mozilla-try     x0000_revs_xx000_added_x000_copies    89294cd501d9 7ccb2fc7ccb5 :  97052 revs,   3.098021 s,   3.023879 s,  -0.074142 s, × 0.9761,    31 µs/rev
mozilla-try     x0000_revs_x0000_added_x0000_copies   e928c65095ed e951f4ad123a :  52031 revs,   0.771480 s,   0.735549 s,  -0.035931 s, × 0.9534,    14 µs/rev
mozilla-try     x00000_revs_x_added_0_copies          6a320851d377 1ebb79acd503 : 363753 revs,  18.813422 s,  18.568900 s,  -0.244522 s, × 0.9870,    51 µs/rev
mozilla-try     x00000_revs_x00000_added_0_copies     dc8a3ca7010e d16fde900c9c :  34414 revs,   0.962867 s,   0.502584 s,  -0.460283 s, × 0.5220,    14 µs/rev
mozilla-try     x00000_revs_x_added_x_copies          5173c4b6f97c 95d83ee7242d : 362229 revs,  18.684923 s,  18.356645 s,  -0.328278 s, × 0.9824,    50 µs/rev
mozilla-try     x00000_revs_x000_added_x_copies       9126823d0e9c ca82787bb23c : 359344 revs,  18.296305 s,  18.250393 s,  -0.045912 s, × 0.9975,    50 µs/rev
mozilla-try     x00000_revs_x0000_added_x0000_copies  8d3fafa80d4b eb884023b810 : 192665 revs,   3.061887 s,   2.792459 s,  -0.269428 s, × 0.9120,    14 µs/rev
mozilla-try     x00000_revs_x00000_added_x0000_copies 1b661134e2ca 1ae03d022d6d : 228985 revs, 103.869641 s, 107.697264 s,  +3.827623 s, × 1.0369,   470 µs/rev
mozilla-try     x00000_revs_x00000_added_x000_copies  9b2a99adc05e 8e29777b48e6 : 382065 revs,  64.262957 s,  63.961040 s,  -0.301917 s, × 0.9953,   167 µs/rev

Differential Revision: https://phab.mercurial-scm.org/D9422

# 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.pycompat import open
from mercurial import (
    error,
    hg,
    registrar,
    util,
)
from mercurial.utils import stringutil

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 = b'ships-with-hg-core'


@command(
    b'relink', [], _(b'[ORIGIN]'), helpcategory=command.CATEGORY_MAINTENANCE
)
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, b'samefile') or not util.safehasattr(
        util, b'samedevice'
    ):
        raise error.Abort(_(b'hardlinks are not supported on this system'))
    src = hg.repository(
        repo.baseui,
        ui.expandpath(origin or b'default-relink', origin or b'default'),
    )
    ui.status(_(b'relinking %s to %s\n') % (src.store.path, repo.store.path))
    if repo.root == src.root:
        ui.status(_(b'there is nothing to relink\n'))
        return

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

    with repo.lock(), src.lock():
        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)


def collect(src, ui):
    seplen = len(os.path.sep)
    candidates = []
    live = len(src[b'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
    progress = ui.makeprogress(_(b'collecting'), unit=_(b'files'), total=total)
    pos = 0
    ui.status(
        _(b"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 (b'.d', b'.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))
            progress.update(pos, item=filename)

    progress.complete()
    ui.status(_(b'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(
                _(b'source and destination are on different devices')
            )
        if st.st_size != ts.st_size:
            return False
        return st

    targets = []
    progress = ui.makeprogress(
        _(b'pruning'), unit=_(b'files'), 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(b'not linkable: %s\n' % fn)
            continue
        targets.append((fn, ts.st_size))
        progress.update(pos, item=fn)

    progress.complete()
    ui.status(
        _(b'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 + b'.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

    progress = ui.makeprogress(
        _(b'relinking'), unit=_(b'files'), total=len(files)
    )
    pos = 0
    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 = open(source, b'rb')
        dfp = open(tgt, b'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(b'not linkable: %s\n' % f)
            continue
        try:
            relinkfile(source, tgt)
            progress.update(pos, item=f)
            relinked += 1
            savedbytes += sz
        except OSError as inst:
            ui.warn(b'%s: %s\n' % (tgt, stringutil.forcebytestr(inst)))

    progress.complete()

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