revset: stop serializing node when using "%ln" Turning hundred of thousand of node from node to hex and back can be slow… what about we stop doing it? In many case were we are using node id we should be using revision id. However this is not a good reason to have a stupidly slow implementation of "%ln". This caught my attention again because the phase discovery during push make an extensive use of "%ln" or huge set. In absolute, that phase discovery probably should use "%ld" and need to improves its algorithmic complexity, but improving "%ln" seems simple and long overdue. This greatly speeds up `hg push` on repository with many drafts. Here are some relevant poulpe benchmarks: ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # benchmark.name = hg.command.push # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.reuse-external-delta-parent = default ## benchmark.variants.revs = any-1-extra-rev before: 44.235070 after: 20.416329 (-53.85%, -23.82) ## benchmark.variants.revs = any-100-extra-rev before: 49.234697 after: 26.519829 (-46.14%, -22.71) ### benchmark.name = hg.command.bundle # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.revs = all # benchmark.variants.type = none-streamv2 ## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog before: 10.138396 after: 7.750458 (-23.55%, -2.39) ## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog before: 1.263859 after: 0.700229 (-44.60%, -0.56) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog before: 399.484481 after: 346.5089 (-13.26%, -52.98) ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog before: 4.540080 after: 3.401700 (-25.07%, -1.14) ## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog before: 2.975765 after: 1.870798 (-37.13%, -1.10)

     1

#!/usr/bin/env python3

     2

     3

# Filter output by pyflakes to control which warnings we check

     4

     5

     6

import re

     7

import sys

     8

     9

lines = []

    10

for line in sys.stdin:

    11

    # We blacklist tests that are too noisy for us

    12

    pats = [

    13

        r"undefined name 'WindowsError'",

    14

        r"redefinition of unused '[^']+' from line",

    15

        # for cffi, allow re-exports from pure.*

    16

        r"cffi/[^:]*:.*\bimport \*' used",

    17

        r"cffi/[^:]*:.*\*' imported but unused",

    18

    ]

    19

    20

    keep = True

    21

    for pat in pats:

    22

        if re.search(pat, line):

    23

            keep = False

    24

            break  # pattern matches

    25

    if keep:

    26

        fn = line.split(':', 1)[0]

    27

        with open(fn, 'rb') as f:

    28

            data = f.read()

    29

        if b'no-' b'check-code' in data:

    30

            continue

    31

        lines.append(line)

    32

    33

for line in lines:

    34

    sys.stdout.write(line)

    35

print()