mercurial/rcutil.py

revlog: add option to mmap revlog index

Following on from Jun Wu's patch last October[1], we have found that using mmap
for the revlog index in repos with large revlogs gives a noticable performance
improvment (~110ms on each hg invocation), particularly for commands that don't
touch the index very much.

This changeset adds this as an option, activated by a new experimental config
option so that it can be enabled on a per-repo basis. The configuration option
specifies an index size threshold at which Mercurial will switch to using mmap
to access the index.

If the configuration option is not specified, the default remains to load the
full file, which seems to be the best option for smaller repos.

Some initial performance numbers for average of 5 invocations of `hg log -l 5`
for different cache states:

| Repo: | HG | FB |
|---|---|---|
| Index size: | 2.3MB | much bigger |
| read (warm): | 237ms | 432ms |
| mmap (warm): | 227ms | 321ms |
|   | (-3%) | (-26%) |
| read (cold): | 397ms | 696ms |
| mmap (cold): | 410ms | 888ms |
|   | (+3%) | (+28%) |

[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2016-October/088737.html

Test Plan:
`hg log --config experimental.mmapindex=true`

Differential Revision: https://phab.mercurial-scm.org/D477

# rcutil.py - utilities about config paths, special config sections etc.
#
#  Copyright Mercurial Contributors
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import os

from . import (
    encoding,
    pycompat,
    util,
)

if pycompat.osname == 'nt':
    from . import scmwindows as scmplatform
else:
    from . import scmposix as scmplatform

fallbackpager = scmplatform.fallbackpager
systemrcpath = scmplatform.systemrcpath
userrcpath = scmplatform.userrcpath

def _expandrcpath(path):
    '''path could be a file or a directory. return a list of file paths'''
    p = util.expandpath(path)
    if os.path.isdir(p):
        join = os.path.join
        return [join(p, f) for f, k in util.listdir(p) if f.endswith('.rc')]
    return [p]

def envrcitems(env=None):
    '''Return [(section, name, value, source)] config items.

    The config items are extracted from environment variables specified by env,
    used to override systemrc, but not userrc.

    If env is not provided, encoding.environ will be used.
    '''
    if env is None:
        env = encoding.environ
    checklist = [
        ('EDITOR', 'ui', 'editor'),
        ('VISUAL', 'ui', 'editor'),
        ('PAGER', 'pager', 'pager'),
    ]
    result = []
    for envname, section, configname in checklist:
        if envname not in env:
            continue
        result.append((section, configname, env[envname], '$%s' % envname))
    return result

def defaultrcpath():
    '''return rc paths in default.d'''
    path = []
    defaultpath = os.path.join(util.datapath, 'default.d')
    if os.path.isdir(defaultpath):
        path = _expandrcpath(defaultpath)
    return path

def rccomponents():
    '''return an ordered [(type, obj)] about where to load configs.

    respect $HGRCPATH. if $HGRCPATH is empty, only .hg/hgrc of current repo is
    used. if $HGRCPATH is not set, the platform default will be used.

    if a directory is provided, *.rc files under it will be used.

    type could be either 'path' or 'items', if type is 'path', obj is a string,
    and is the config file path. if type is 'items', obj is a list of (section,
    name, value, source) that should fill the config directly.
    '''
    envrc = ('items', envrcitems())

    if 'HGRCPATH' in encoding.environ:
        # assume HGRCPATH is all about user configs so environments can be
        # overridden.
        _rccomponents = [envrc]
        for p in encoding.environ['HGRCPATH'].split(pycompat.ospathsep):
            if not p:
                continue
            _rccomponents.extend(('path', p) for p in _expandrcpath(p))
    else:
        normpaths = lambda paths: [('path', os.path.normpath(p)) for p in paths]
        _rccomponents = normpaths(defaultrcpath() + systemrcpath())
        _rccomponents.append(envrc)
        _rccomponents.extend(normpaths(userrcpath()))
    return _rccomponents

def defaultpagerenv():
    '''return a dict of default environment variables and their values,
    intended to be set before starting a pager.
    '''
    return {'LESS': 'FRX', 'LV': '-c'}