hgext/narrow/narrowrevlog.py

narrow: when writing treemanifests, skip inspecting directories outside narrow

This provides significant speed benefits when narrow and treemanifests are in
use, see the timing numbers below. Note that like previously, differences of <5%
are considered noise.

The below timing numbers are in the same style as previously (example:
ee7ee0c516ca). 'before' is 9db85644, and does not include that example commit's
improvements.

    diff --git:
    repo  | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
    ------+---+---+------------------------+-----------------------+------------
    m-u   |   |   | 1.327 s +-  0.051 s    | 1.296 s +-  0.009 s   |  97.7%
    m-u   |   | x | 1.310 s +-  0.020 s    | 1.295 s +-  0.015 s   |  98.9%
    m-u   | x |   | 1.295 s +-  0.018 s    | 1.296 s +-  0.007 s   | 100.1%
    m-u   | x | x | 83.5 ms +-   0.8 ms    | 84.1 ms +-   0.8 ms   | 100.7%
    l-d-r |   |   | 205.1 ms +-   3.5 ms   | 205.0 ms +-   3.8 ms  | 100.0%
    l-d-r |   | x | 194.2 ms +-   5.6 ms   | 192.3 ms +-   4.3 ms  |  99.0%
    l-d-r | x |   | 99.1 ms +-   2.2 ms    | 97.8 ms +-   0.9 ms   |  98.7%
    l-d-r | x | x | 66.2 ms +-   1.0 ms    | 67.2 ms +-   2.7 ms   | 101.5%

    diff -c . --git:
    repo  | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
    ------+---+---+------------------------+-----------------------+------------
    m-u   |   |   | 233.9 ms +-   1.9 ms   | 235.6 ms +-   5.1 ms  | 100.7%
    m-u   |   | x | 151.4 ms +-   1.2 ms   | 152.2 ms +-   2.0 ms  | 100.5%
    m-u   | x |   | 234.8 ms +-   2.7 ms   | 235.0 ms +-   2.7 ms  | 100.1%
    m-u   | x | x | 127.8 ms +-   2.1 ms   | 126.0 ms +-   1.1 ms  |  98.6%
    l-d-r |   |   | 82.5 ms +-   1.6 ms    | 82.3 ms +-   2.0 ms   |  99.8%
    l-d-r |   | x | 3.742 s +-  0.017 s    | 3.819 s +-  0.208 s   | 102.1%
    l-d-r | x |   | 84.4 ms +-   1.5 ms    | 83.2 ms +-   1.0 ms   |  98.6%
    l-d-r | x | x | 751.2 ms +-   5.0 ms   | 755.8 ms +-  12.9 ms  | 100.6%

    rebase -r . --keep -d .^^:
    repo  | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
    ------+---+---+------------------------+-----------------------+------------
    m-u   |   |   | 5.519 s +-  0.038 s    | 5.526 s +-  0.057 s   | 100.1%
    m-u   |   | x | 5.588 s +-  0.048 s    | 5.607 s +-  0.061 s   | 100.3%
    m-u   | x |   | 5.520 s +-  0.044 s    | 5.546 s +-  0.059 s   | 100.5%
    m-u   | x | x | 586.6 ms +-  12.8 ms   | 554.9 ms +-  21.2 ms  |  94.6% <--
    l-d-r |   |   | 629.8 ms +-   5.5 ms   | 627.4 ms +-   6.6 ms  |  99.6%
    l-d-r |   | x | 6.165 s +-  0.058 s    | 6.255 s +-  0.303 s   | 101.5%
    l-d-r | x |   | 270.2 ms +-   2.3 ms   | 271.4 ms +-   2.7 ms  | 100.4%
    l-d-r | x | x | 4.700 s +-  0.025 s    | 1.651 s +-  0.016 s   |  35.1% <--

    status --change . --copies:
    repo  | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
    ------+---+---+------------------------+-----------------------+------------
    m-u   |   |   | 215.4 ms +-   2.3 ms   | 216.5 ms +-   4.2 ms  | 100.5%
    m-u   |   | x | 132.9 ms +-   1.2 ms   | 132.0 ms +-   1.4 ms  |  99.3%
    m-u   | x |   | 217.0 ms +-   1.9 ms   | 215.4 ms +-   1.9 ms  |  99.3%
    m-u   | x | x | 108.6 ms +-   1.0 ms   | 108.2 ms +-   1.5 ms  |  99.6%
    l-d-r |   |   | 80.0 ms +-   1.3 ms    | 80.5 ms +-   1.1 ms   | 100.6%
    l-d-r |   | x | 3.916 s +-  0.187 s    | 3.966 s +-  0.236 s   | 101.3%
    l-d-r | x |   | 84.4 ms +-   3.1 ms    | 83.9 ms +-   1.1 ms   |  99.4%
    l-d-r | x | x | 758.0 ms +-   8.2 ms   | 753.5 ms +-   5.0 ms  |  99.4%

    status --copies:
    repo  | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
    ------+---+---+------------------------+-----------------------+------------
    m-u   |   |   | 1.905 s +-  0.025 s    | 1.910 s +-  0.044 s   | 100.3%
    m-u   |   | x | 1.892 s +-  0.009 s    | 1.895 s +-  0.012 s   | 100.2%
    m-u   | x |   | 1.891 s +-  0.012 s    | 1.902 s +-  0.018 s   | 100.6%
    m-u   | x | x | 93.3 ms +-   0.9 ms    | 93.4 ms +-   0.8 ms   | 100.1%
    l-d-r |   |   | 570.7 ms +-   7.8 ms   | 571.9 ms +-  18.5 ms  | 100.2%
    l-d-r |   | x | 561.5 ms +-   5.2 ms   | 562.9 ms +-   6.1 ms  | 100.2%
    l-d-r | x |   | 171.7 ms +-   2.6 ms   | 171.9 ms +-   1.2 ms  | 100.1%
    l-d-r | x | x | 142.7 ms +-   2.0 ms   | 140.3 ms +-   1.0 ms  |  98.3%

    update $rev^; ~/src/hg/hg{hg}/hg update $rev:
    repo  | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
    ------+---+---+------------------------+-----------------------+------------
    m-u   |   |   | 3.126 s +-  0.016 s    | 3.128 s +-  0.015 s   | 100.1%
    m-u   |   | x | 3.014 s +-  0.068 s    | 3.008 s +-  0.031 s   |  99.8%
    m-u   | x |   | 3.143 s +-  0.037 s    | 3.184 s +-  0.086 s   | 101.3%
    m-u   | x | x | 308.0 ms +-   1.8 ms   | 308.1 ms +-   5.7 ms  | 100.0%
    l-d-r |   |   | 430.8 ms +-   4.5 ms   | 436.4 ms +-   8.7 ms  | 101.3%
    l-d-r |   | x | 9.676 s +-  0.127 s    | 9.945 s +-  0.272 s   | 102.8%
    l-d-r | x |   | 254.2 ms +-   3.3 ms   | 255.7 ms +-   3.1 ms  | 100.6%
    l-d-r | x | x | 1.571 s +-  0.030 s    | 1.555 s +-  0.014 s   |  99.0%

Differential Revision: https://phab.mercurial-scm.org/D4606

# narrowrevlog.py - revlog storing irrelevant nodes as "ellipsis" nodes
#
# Copyright 2017 Google, Inc.
#
# 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

from mercurial import (
   revlog,
   util,
)

def readtransform(self, text):
    return text, False

def writetransform(self, text):
    return text, False

def rawtransform(self, text):
    return False

revlog.addflagprocessor(revlog.REVIDX_ELLIPSIS,
                        (readtransform, writetransform, rawtransform))

def setup():
    # We just wanted to add the flag processor, which is done at module
    # load time.
    pass

def makenarrowfilelog(fl, narrowmatch):
    class narrowfilelog(fl.__class__):
        def renamed(self, node):
            # Renames that come from outside the narrowspec are
            # problematic at least for git-diffs, because we lack the
            # base text for the rename. This logic was introduced in
            # 3cd72b1 of narrowhg (authored by martinvonz, reviewed by
            # adgar), but that revision doesn't have any additional
            # commentary on what problems we can encounter.
            m = super(narrowfilelog, self).renamed(node)
            if m and not narrowmatch(m[0]):
                return None
            return m

        def size(self, rev):
            # We take advantage of the fact that remotefilelog
            # lacks a node() method to just skip the
            # rename-checking logic when on remotefilelog. This
            # might be incorrect on other non-revlog-based storage
            # engines, but for now this seems to be fine.
            #
            # TODO: when remotefilelog is in core, improve this to
            # explicitly look for remotefilelog instead of cheating
            # with a hasattr check.
            if util.safehasattr(self, 'node'):
                node = self.node(rev)
                # Because renamed() is overridden above to
                # sometimes return None even if there is metadata
                # in the revlog, size can be incorrect for
                # copies/renames, so we need to make sure we call
                # the super class's implementation of renamed()
                # for the purpose of size calculation.
                if super(narrowfilelog, self).renamed(node):
                    return len(self.read(node))
            return super(narrowfilelog, self).size(rev)

        def cmp(self, node, text):
            different = super(narrowfilelog, self).cmp(node, text)
            if different:
                # Similar to size() above, if the file was copied from
                # a file outside the narrowspec, the super class's
                # would have returned True because we tricked it into
                # thinking that the file was not renamed.
                if super(narrowfilelog, self).renamed(node):
                    t2 = self.read(node)
                    return t2 != text
            return different

    fl.__class__ = narrowfilelog