bisect: avoid copying ancestor list for non-merge commits During a bisection, hg needs to compute a list of all ancestors for every candidate commit. This is accomplished via a bottom-up traversal of the set of candidates, during which each revision's ancestor list is populated using the ancestor list of its parent(s). Previously, this involved copying the entire list, which could be very long in if the bisection range was large. To help improve this, we can observe that each candidate commit is visited exactly once, at which point its ancestor list is copied into its children's lists and then dropped. In the case of non-merge commits, a commit's ancestor list consists exactly of its parent's list plus itself. This means that we can trivially reuse the parent's existing list for one of its non-merge children, which avoids copying entirely if that commit is the parent's only child. This makes bisections over linear ranges of commits much faster. During some informal testing in the large publicly-available `mozilla-central` repository, this noticeably sped up bisections over large ranges of history: Setup: $ cd mozilla-central $ hg bisect --reset $ hg bisect --good 0 $ hg log -r tip -T '{rev}\n' 628417 Test: $ time hg bisect --bad tip --noupdate Before: real 3m35.927s user 3m35.553s sys 0m0.319s After: real 1m41.142s user 1m40.810s sys 0m0.285s

     1

import os

     2

from mercurial.hgweb import hgwebdir_mod

     3

     4

hgwebdir = hgwebdir_mod.hgwebdir

     5

     6

os.mkdir(b'webdir')

     7

os.chdir(b'webdir')

     8

     9

webdir = os.path.realpath(b'.')

    10

    11

    12

def trivial_response(req, res):

    13

    return []

    14

    15

    16

def make_hgwebdir(gc_rate=None):

    17

    config = os.path.join(webdir, b'hgwebdir.conf')

    18

    with open(config, 'wb') as configfile:

    19

        configfile.write(b'[experimental]\n')

    20

        if gc_rate is not None:

    21

            configfile.write(b'web.full-garbage-collection-rate=%d\n' % gc_rate)

    22

    hg_wd = hgwebdir(config)

    23

    hg_wd._runwsgi = trivial_response

    24

    return hg_wd

    25

    26

    27

def process_requests(webdir_instance, number):

    28

    # we don't care for now about passing realistic arguments

    29

    for _ in range(number):

    30

        for chunk in webdir_instance.run_wsgi(None, None):

    31

            pass

    32

    33

    34

without_gc = make_hgwebdir(gc_rate=0)

    35

process_requests(without_gc, 5)

    36

assert without_gc.requests_count == 5

    37

assert without_gc.gc_full_collections_done == 0

    38

    39

with_gc = make_hgwebdir(gc_rate=2)

    40

process_requests(with_gc, 5)

    41

assert with_gc.requests_count == 5

    42

assert with_gc.gc_full_collections_done == 2

    43

    44

with_systematic_gc = make_hgwebdir()  # default value of the setting

    45

process_requests(with_systematic_gc, 3)

    46

assert with_systematic_gc.requests_count == 3

    47

assert with_systematic_gc.gc_full_collections_done == 3