view hgext/churn.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 9f70512ae2cf
children 0d119802242b
line wrap: on
line source

# churn.py - create a graph of revisions count grouped by template
#
# Copyright 2006 Josef "Jeff" Sipek <jeffpc@josefsipek.net>
# Copyright 2008 Alexander Solovyov <piranha@piranha.org.ua>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''command to display statistics about repository history'''

from __future__ import absolute_import, division

import datetime
import os
import time

from mercurial.i18n import _
from mercurial.pycompat import open
from mercurial import (
    cmdutil,
    encoding,
    logcmdutil,
    patch,
    pycompat,
    registrar,
    scmutil,
)
from mercurial.utils import dateutil

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'


def changedlines(ui, repo, ctx1, ctx2, fns):
    added, removed = 0, 0
    fmatch = scmutil.matchfiles(repo, fns)
    diff = b''.join(patch.diff(repo, ctx1.node(), ctx2.node(), fmatch))
    for l in diff.split(b'\n'):
        if l.startswith(b"+") and not l.startswith(b"+++ "):
            added += 1
        elif l.startswith(b"-") and not l.startswith(b"--- "):
            removed += 1
    return (added, removed)


def countrate(ui, repo, amap, *pats, **opts):
    """Calculate stats"""
    opts = pycompat.byteskwargs(opts)
    if opts.get(b'dateformat'):

        def getkey(ctx):
            t, tz = ctx.date()
            date = datetime.datetime(*time.gmtime(float(t) - tz)[:6])
            return encoding.strtolocal(
                date.strftime(encoding.strfromlocal(opts[b'dateformat']))
            )

    else:
        tmpl = opts.get(b'oldtemplate') or opts.get(b'template')
        tmpl = logcmdutil.maketemplater(ui, repo, tmpl)

        def getkey(ctx):
            ui.pushbuffer()
            tmpl.show(ctx)
            return ui.popbuffer()

    progress = ui.makeprogress(
        _(b'analyzing'), unit=_(b'revisions'), total=len(repo)
    )
    rate = {}
    df = False
    if opts.get(b'date'):
        df = dateutil.matchdate(opts[b'date'])

    m = scmutil.match(repo[None], pats, opts)

    def prep(ctx, fns):
        rev = ctx.rev()
        if df and not df(ctx.date()[0]):  # doesn't match date format
            return

        key = getkey(ctx).strip()
        key = amap.get(key, key)  # alias remap
        if opts.get(b'changesets'):
            rate[key] = (rate.get(key, (0,))[0] + 1, 0)
        else:
            parents = ctx.parents()
            if len(parents) > 1:
                ui.note(_(b'revision %d is a merge, ignoring...\n') % (rev,))
                return

            ctx1 = parents[0]
            lines = changedlines(ui, repo, ctx1, ctx, fns)
            rate[key] = [r + l for r, l in zip(rate.get(key, (0, 0)), lines)]

        progress.increment()

    for ctx in cmdutil.walkchangerevs(repo, m, opts, prep):
        continue

    progress.complete()

    return rate


@command(
    b'churn',
    [
        (
            b'r',
            b'rev',
            [],
            _(b'count rate for the specified revision or revset'),
            _(b'REV'),
        ),
        (
            b'd',
            b'date',
            b'',
            _(b'count rate for revisions matching date spec'),
            _(b'DATE'),
        ),
        (
            b't',
            b'oldtemplate',
            b'',
            _(b'template to group changesets (DEPRECATED)'),
            _(b'TEMPLATE'),
        ),
        (
            b'T',
            b'template',
            b'{author|email}',
            _(b'template to group changesets'),
            _(b'TEMPLATE'),
        ),
        (
            b'f',
            b'dateformat',
            b'',
            _(b'strftime-compatible format for grouping by date'),
            _(b'FORMAT'),
        ),
        (b'c', b'changesets', False, _(b'count rate by number of changesets')),
        (b's', b'sort', False, _(b'sort by key (default: sort by count)')),
        (b'', b'diffstat', False, _(b'display added/removed lines separately')),
        (b'', b'aliases', b'', _(b'file with email aliases'), _(b'FILE')),
    ]
    + cmdutil.walkopts,
    _(b"hg churn [-d DATE] [-r REV] [--aliases FILE] [FILE]"),
    helpcategory=command.CATEGORY_MAINTENANCE,
    inferrepo=True,
)
def churn(ui, repo, *pats, **opts):
    '''histogram of changes to the repository

    This command will display a histogram representing the number
    of changed lines or revisions, grouped according to the given
    template. The default template will group changes by author.
    The --dateformat option may be used to group the results by
    date instead.

    Statistics are based on the number of changed lines, or
    alternatively the number of matching revisions if the
    --changesets option is specified.

    Examples::

      # display count of changed lines for every committer
      hg churn -T "{author|email}"

      # display daily activity graph
      hg churn -f "%H" -s -c

      # display activity of developers by month
      hg churn -f "%Y-%m" -s -c

      # display count of lines changed in every year
      hg churn -f "%Y" -s

    It is possible to map alternate email addresses to a main address
    by providing a file using the following format::

      <alias email> = <actual email>

    Such a file may be specified with the --aliases option, otherwise
    a .hgchurn file will be looked for in the working directory root.
    Aliases will be split from the rightmost "=".
    '''

    def pad(s, l):
        return s + b" " * (l - encoding.colwidth(s))

    amap = {}
    aliases = opts.get('aliases')
    if not aliases and os.path.exists(repo.wjoin(b'.hgchurn')):
        aliases = repo.wjoin(b'.hgchurn')
    if aliases:
        for l in open(aliases, b"rb"):
            try:
                alias, actual = l.rsplit(b'=' in l and b'=' or None, 1)
                amap[alias.strip()] = actual.strip()
            except ValueError:
                l = l.strip()
                if l:
                    ui.warn(_(b"skipping malformed alias: %s\n") % l)
                continue

    rate = list(countrate(ui, repo, amap, *pats, **opts).items())
    if not rate:
        return

    if opts.get('sort'):
        rate.sort()
    else:
        rate.sort(key=lambda x: (-sum(x[1]), x))

    # Be careful not to have a zero maxcount (issue833)
    maxcount = float(max(sum(v) for k, v in rate)) or 1.0
    maxname = max(len(k) for k, v in rate)

    ttywidth = ui.termwidth()
    ui.debug(b"assuming %i character terminal\n" % ttywidth)
    width = ttywidth - maxname - 2 - 2 - 2

    if opts.get('diffstat'):
        width -= 15

        def format(name, diffstat):
            added, removed = diffstat
            return b"%s %15s %s%s\n" % (
                pad(name, maxname),
                b'+%d/-%d' % (added, removed),
                ui.label(b'+' * charnum(added), b'diffstat.inserted'),
                ui.label(b'-' * charnum(removed), b'diffstat.deleted'),
            )

    else:
        width -= 6

        def format(name, count):
            return b"%s %6d %s\n" % (
                pad(name, maxname),
                sum(count),
                b'*' * charnum(sum(count)),
            )

    def charnum(count):
        return int(count * width // maxcount)

    for name, count in rate:
        ui.write(format(name, count))