view contrib/genosxversion.py @ 42121:6578654916ae

branchcache: lazily validate nodes from the branchmap

On my personal hg-repository with 365 entries in .hg/cache/branch2, following
are the numbers for perfbranchmapload.

Before this patch:

! wall 0.000866 comb 0.000000 user 0.000000 sys 0.000000 (best of 2680)
! wall 0.001525 comb 0.000000 user 0.000000 sys 0.000000 (max of 2680)
! wall 0.001107 comb 0.001097 user 0.001086 sys 0.000011 (avg of 2680)
! wall 0.001104 comb 0.000000 user 0.000000 sys 0.000000 (median of 2680)

With this patch:

! wall 0.000530 comb 0.000000 user 0.000000 sys 0.000000 (best of 4240)
! wall 0.001078 comb 0.000000 user 0.000000 sys 0.000000 (max of 4240)
! wall 0.000696 comb 0.000693 user 0.000677 sys 0.000017 (avg of 4240)
! wall 0.000690 comb 0.000000 user 0.000000 sys 0.000000 (median of 4240)

On our internal repository with ~20k entries in branchcache, I see improvement
from 0.125 sec to 0.066 sec which is 47% speed up.

The above are the numbers of perfbranchmapload which shows how much time we
saved by not validating the nodes. But we need to validate some nodes. Following
are timings of some mercurial operations which have speed up because of this
lazy validation of nodes:

No-op `hg update` on our internal repository (Avg on 4 runs):

Before: 0.540 secs
After: 0.430 secs

Setting a branch name which already exists without --force (Avg of 4 runs):

Before: 0.510 secs
After: 0.250 secs

I ran the ASV performance suite and was unable to see any improvements except
there was improvement of perfdirstatewrite() on netbeans which I think was not
related.

I looked into the commit code, the command which I am trying to speedup, it
looks like it uses revbranchcache to update the branchcache.

Differential Revision: https://phab.mercurial-scm.org/D6208

#!/usr/bin/env python2
from __future__ import absolute_import, print_function

import argparse
import json
import os
import subprocess
import sys

# Always load hg libraries from the hg we can find on $PATH.
hglib = json.loads(subprocess.check_output(
    ['hg', 'debuginstall', '-Tjson']))[0]['hgmodules']
sys.path.insert(0, os.path.dirname(hglib))

from mercurial import util

ap = argparse.ArgumentParser()
ap.add_argument('--paranoid',
                action='store_true',
                help=("Be paranoid about how version numbers compare and "
                      "produce something that's more likely to sort "
                      "reasonably."))
ap.add_argument('--selftest', action='store_true', help='Run self-tests.')
ap.add_argument('versionfile', help='Path to a valid mercurial __version__.py')

def paranoidver(ver):
    """Given an hg version produce something that distutils can sort.

    Some Mac package management systems use distutils code in order to
    figure out upgrades, which makes life difficult. The test case is
    a reduced version of code in the Munki tool used by some large
    organizations to centrally manage OS X packages, which is what
    inspired this kludge.

    >>> paranoidver('3.4')
    '3.4.0'
    >>> paranoidver('3.4.2')
    '3.4.2'
    >>> paranoidver('3.0-rc+10')
    '2.9.9999-rc+10'
    >>> paranoidver('4.2+483-5d44d7d4076e')
    '4.2.0+483-5d44d7d4076e'
    >>> paranoidver('4.2.1+598-48d1e1214d8c')
    '4.2.1+598-48d1e1214d8c'
    >>> paranoidver('4.3-rc')
    '4.2.9999-rc'
    >>> paranoidver('4.3')
    '4.3.0'
    >>> from distutils import version
    >>> class LossyPaddedVersion(version.LooseVersion):
    ...     '''Subclass version.LooseVersion to compare things like
    ...     "10.6" and "10.6.0" as equal'''
    ...     def __init__(self, s):
    ...             self.parse(s)
    ...
    ...     def _pad(self, version_list, max_length):
    ...         'Pad a version list by adding extra 0 components to the end'
    ...         # copy the version_list so we don't modify it
    ...         cmp_list = list(version_list)
    ...         while len(cmp_list) < max_length:
    ...             cmp_list.append(0)
    ...         return cmp_list
    ...
    ...     def __cmp__(self, other):
    ...         if isinstance(other, str):
    ...             other = MunkiLooseVersion(other)
    ...         max_length = max(len(self.version), len(other.version))
    ...         self_cmp_version = self._pad(self.version, max_length)
    ...         other_cmp_version = self._pad(other.version, max_length)
    ...         return cmp(self_cmp_version, other_cmp_version)
    >>> def testver(older, newer):
    ...   o = LossyPaddedVersion(paranoidver(older))
    ...   n = LossyPaddedVersion(paranoidver(newer))
    ...   return o < n
    >>> testver('3.4', '3.5')
    True
    >>> testver('3.4.0', '3.5-rc')
    True
    >>> testver('3.4-rc', '3.5')
    True
    >>> testver('3.4-rc+10-deadbeef', '3.5')
    True
    >>> testver('3.4.2', '3.5-rc')
    True
    >>> testver('3.4.2', '3.5-rc+10-deadbeef')
    True
    >>> testver('4.2+483-5d44d7d4076e', '4.2.1+598-48d1e1214d8c')
    True
    >>> testver('4.3-rc', '4.3')
    True
    >>> testver('4.3', '4.3-rc')
    False
    """
    major, minor, micro, extra = util.versiontuple(ver, n=4)
    if micro is None:
        micro = 0
    if extra:
        if extra.startswith('rc'):
            if minor == 0:
                major -= 1
                minor = 9
            else:
                minor -= 1
            micro = 9999
            extra = '-' + extra
        else:
            extra = '+' + extra
    else:
        extra = ''
    return '%d.%d.%d%s' % (major, minor, micro, extra)

def main(argv):
    opts = ap.parse_args(argv[1:])
    if opts.selftest:
        import doctest
        doctest.testmod()
        return
    with open(opts.versionfile) as f:
        for l in f:
            if l.startswith('version = b'):
                # version number is entire line minus the quotes
                ver = l[len('version = b') + 1:-2]
                break
    if opts.paranoid:
        print(paranoidver(ver))
    else:
        print(ver)

if __name__ == '__main__':
    main(sys.argv)