view hgext/relink.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping The performance and memory benefit is much greater if we don't have to copy all the data in memory for each information. So we introduce an option (on by default) to read the data using mmap. This changeset is the last one definition the API for index support nodemap data. (they have to be able to use the mmaping). Below are some benchmark comparing the best we currently have in 5.3 with the final step of this series (using the persistent nodemap implementation in Rust). The benchmark run `hg perfindex` with various revset and the following variants: Before: * do not use the persistent nodemap * use the CPython implementation of the index for nodemap * use mmapping of the changelog index After: * use the MixedIndex Rust code, with the NodeTree object for nodemap access (still in review) * use the persistent nodemap data from disk * access the persistent nodemap data through mmap * use mmapping of the changelog index The persistent nodemap greatly speed up most operation on very large repositories. Some of the previously very fast lookup end up a bit slower because the persistent nodemap has to be setup. However the absolute slowdown is very small and won't matters in the big picture. Here are some numbers (in seconds) for the reference copy of mozilla-try: Revset Before After abs-change speedup -10000: 0.004622 0.005532 0.000910 × 0.83 -10: 0.000050 0.000132 0.000082 × 0.37 tip 0.000052 0.000085 0.000033 × 0.61 0 + (-10000:) 0.028222 0.005337 -0.022885 × 5.29 0 0.023521 0.000084 -0.023437 × 280.01 (-10000:) + 0 0.235539 0.005308 -0.230231 × 44.37 (-10:) + :9 0.232883 0.000180 -0.232703 ×1293.79 (-10000:) + (:99) 0.238735 0.005358 -0.233377 × 44.55 :99 + (-10000:) 0.317942 0.005593 -0.312349 × 56.84 :9 + (-10:) 0.313372 0.000179 -0.313193 ×1750.68 :9 0.316450 0.000143 -0.316307 ×2212.93 On smaller repositories, the cost of nodemap related operation is not as big, so the win is much more modest. Yet it helps shaving a handful of millisecond here and there. Here are some numbers (in seconds) for the reference copy of mercurial: Revset Before After abs-change speedup -10: 0.000065 0.000097 0.000032 × 0.67 tip 0.000063 0.000078 0.000015 × 0.80 0 0.000561 0.000079 -0.000482 × 7.10 -10000: 0.004609 0.003648 -0.000961 × 1.26 0 + (-10000:) 0.005023 0.003715 -0.001307 × 1.35 (-10:) + :9 0.002187 0.000108 -0.002079 ×20.25 (-10000:) + 0 0.006252 0.003716 -0.002536 × 1.68 (-10000:) + (:99) 0.006367 0.003707 -0.002660 × 1.71 :9 + (-10:) 0.003846 0.000110 -0.003736 ×34.96 :9 0.003854 0.000099 -0.003755 ×38.92 :99 + (-10000:) 0.007644 0.003778 -0.003866 × 2.02 Differential Revision: https://phab.mercurial-scm.org/D7894
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 11 Feb 2020 11:18:52 +0100
parents eef9a2d67051
children b5e7cdb93abc
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 __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))
    )