view tests/test-pathencode.py @ 49777:e1953a34c110

bundle: emit full snapshot as is, without doing a redelta With the new `forced` delta-reused policy, it become important to be able to send full snapshot where full snapshot are needed. Otherwise, the fallback delta will simply be used on the client sideā€¦ creating monstrous delta chain, since revision that are meant as a reset of delta-chain chain becoming too complex are simply adding a new full delta-tree on the leaf of another one. In the `non-forced` cases, client process full snapshot from the bundle differently from deltas, so client will still try to convert the full snapshot into a delta if possible. So this will no lead to pathological storage explosion. I have considered making this configurable, but the impact seems limited enough that it does not seems to be worth it. Especially with the current sparse-revlog format that use "delta-tree" with multiple level snapshots, full snapshot are much less frequent and not that different from other intermediate snapshot that we are already sending over the wire anyway. CPU wise, this will help the bundling side a little as it will not need to reconstruct revisions and compute deltas. The unbundling side might save a tiny amount of CPU as it won't need to reconstruct the delta-base to reconstruct the revision full text. This only slightly visible in some of the benchmarks. And have no real impact on most of them. ### data-env-vars.name = pypy-2018-08-01-zstd-sparse-revlog # benchmark.name = perf-bundle # benchmark.variants.revs = last-40000 before: 11.467186 seconds just-emit-full: 11.190576 seconds (-2.41%) with-pull-force: 11.041091 seconds (-3.72%) # benchmark.name = perf-unbundle # benchmark.variants.revs = last-40000 before: 16.744862 just-emit-full:: 16.561036 seconds (-1.10%) with-pull-force: 16.389344 seconds (-2.12%) # benchmark.name = pull # benchmark.variants.revs = last-40000 before: 26.870569 just-emit-full: 26.391188 seconds (-1.78%) with-pull-force: 25.633184 seconds (-4.60%) Space wise (so network-wise) the impact is fairly small. When taking compression into account. Below are tests the size of `hg bundle --all` for a handful of benchmark repositories (with bzip, zstd compression and without it) This show a small increase in the bundle size, but nothing really significant except maybe for mozilla-try (+12%) that nobody really pulls large chunk of anyway. Mozilla-try is also the repository that benefit the most for not having to recompute deltas client size. ### mercurial: bzip-before: 26 406 342 bytes bzip-after: 26 691 543 bytes +1.08% zstd-before: 27 918 645 bytes zstd-after: 28 075 896 bytes +0.56% none-before: 98 675 601 bytes none-after: 100 411 237 bytes +1.76% ### pypy bzip-before: 201 295 752 bytes bzip-after: 209 780 282 bytes +4.21% zstd-before: 202 974 795 bytes zstd-after: 205 165 780 bytes +1.08% none-before: 871 070 261 bytes none-after: 993 595 057 bytes +14.07% ### netbeans bzip-before: 601 314 330 bytes bzip-after: 614 246 241 bytes +2.15% zstd-before: 604 745 136 bytes zstd-after: 615 497 705 bytes +1.78% none-before: 3 338 238 571 bytes none-after: 3 439 422 535 bytes +3.03% ### mozilla-central bzip-before: 1 493 006 921 bytes bzip-after: 1 549 650 570 bytes +3.79% zstd-before: 1 481 910 102 bytes zstd-after: 1 513 052 415 bytes +2.10% none-before: 6 535 929 910 bytes none-after: 7 010 191 342 bytes +7.26% ### mozilla-try bzip-before: 6 583 425 999 bytes bzip-after: 7 423 536 928 bytes +12.76% zstd-before: 6 021 009 212 bytes zstd-after: 6 674 922 420 bytes +10.86% none-before: 22 954 739 558 bytes none-after: 26 013 854 771 bytes +13.32%
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Wed, 07 Dec 2022 20:12:23 +0100
parents 56f98406831b
children
line wrap: on
line source

# This is a randomized test that generates different pathnames every
# time it is invoked, and tests the encoding of those pathnames.
#
# It uses a simple probabilistic model to generate valid pathnames
# that have proven likely to expose bugs and divergent behavior in
# different encoding implementations.


import binascii
import collections
import itertools
import math
import os
import random
import sys
import time
from mercurial import (
    pycompat,
    store,
)

validchars = set(map(pycompat.bytechr, range(0, 256)))
alphanum = range(ord('A'), ord('Z'))

for c in (b'\0', b'/'):
    validchars.remove(c)

winreserved = (
    b'aux con prn nul'.split()
    + [b'com%d' % i for i in range(1, 10)]
    + [b'lpt%d' % i for i in range(1, 10)]
)


def casecombinations(names):
    '''Build all case-diddled combinations of names.'''

    combos = set()

    for r in names:
        for i in range(len(r) + 1):
            for c in itertools.combinations(range(len(r)), i):
                d = r
                for j in c:
                    d = b''.join((d[:j], d[j : j + 1].upper(), d[j + 1 :]))
                combos.add(d)
    return sorted(combos)


def buildprobtable(fp, cmd='hg manifest tip'):
    """Construct and print a table of probabilities for path name
    components.  The numbers are percentages."""

    counts = collections.defaultdict(lambda: 0)
    for line in os.popen(cmd).read().splitlines():
        if line[-2:] in ('.i', '.d'):
            line = line[:-2]
        if line.startswith('data/'):
            line = line[5:]
        for c in line:
            counts[c] += 1
    for c in '\r/\n':
        counts.pop(c, None)
    t = sum(counts.values()) / 100.0
    fp.write('probtable = (')
    for i, (k, v) in enumerate(
        sorted(counts.items(), key=lambda x: x[1], reverse=True)
    ):
        if (i % 5) == 0:
            fp.write('\n    ')
        vt = v / t
        if vt < 0.0005:
            break
        fp.write('(%r, %.03f), ' % (k, vt))
    fp.write('\n    )\n')


# A table of character frequencies (as percentages), gleaned by
# looking at filelog names from a real-world, very large repo.

probtable = (
    (b't', 9.828),
    (b'e', 9.042),
    (b's', 8.011),
    (b'a', 6.801),
    (b'i', 6.618),
    (b'g', 5.053),
    (b'r', 5.030),
    (b'o', 4.887),
    (b'p', 4.363),
    (b'n', 4.258),
    (b'l', 3.830),
    (b'h', 3.693),
    (b'_', 3.659),
    (b'.', 3.377),
    (b'm', 3.194),
    (b'u', 2.364),
    (b'd', 2.296),
    (b'c', 2.163),
    (b'b', 1.739),
    (b'f', 1.625),
    (b'6', 0.666),
    (b'j', 0.610),
    (b'y', 0.554),
    (b'x', 0.487),
    (b'w', 0.477),
    (b'k', 0.476),
    (b'v', 0.473),
    (b'3', 0.336),
    (b'1', 0.335),
    (b'2', 0.326),
    (b'4', 0.310),
    (b'5', 0.305),
    (b'9', 0.302),
    (b'8', 0.300),
    (b'7', 0.299),
    (b'q', 0.298),
    (b'0', 0.250),
    (b'z', 0.223),
    (b'-', 0.118),
    (b'C', 0.095),
    (b'T', 0.087),
    (b'F', 0.085),
    (b'B', 0.077),
    (b'S', 0.076),
    (b'P', 0.076),
    (b'L', 0.059),
    (b'A', 0.058),
    (b'N', 0.051),
    (b'D', 0.049),
    (b'M', 0.046),
    (b'E', 0.039),
    (b'I', 0.035),
    (b'R', 0.035),
    (b'G', 0.028),
    (b'U', 0.026),
    (b'W', 0.025),
    (b'O', 0.017),
    (b'V', 0.015),
    (b'H', 0.013),
    (b'Q', 0.011),
    (b'J', 0.007),
    (b'K', 0.005),
    (b'+', 0.004),
    (b'X', 0.003),
    (b'Y', 0.001),
)

for c, _ in probtable:
    validchars.remove(c)
validchars = list(validchars)


def pickfrom(rng, table):
    c = 0
    r = rng.random() * sum(i[1] for i in table)
    for i, p in table:
        c += p
        if c >= r:
            return i


reservedcombos = casecombinations(winreserved)

# The first component of a name following a slash.

firsttable = (
    (lambda rng: pickfrom(rng, probtable), 90),
    (lambda rng: rng.choice(validchars), 5),
    (lambda rng: rng.choice(reservedcombos), 5),
)

# Components of a name following the first.

resttable = firsttable[:-1]

# Special suffixes.

internalsuffixcombos = casecombinations(b'.hg .i .d'.split())

# The last component of a path, before a slash or at the end of a name.

lasttable = resttable + (
    (lambda rng: b'', 95),
    (lambda rng: rng.choice(internalsuffixcombos), 5),
)


def makepart(rng, k):
    '''Construct a part of a pathname, without slashes.'''

    p = pickfrom(rng, firsttable)(rng)
    l = len(p)
    ps = [p]
    maxl = rng.randint(1, k)
    while l < maxl:
        p = pickfrom(rng, resttable)(rng)
        l += len(p)
        ps.append(p)
    ps.append(pickfrom(rng, lasttable)(rng))
    return b''.join(ps)


def makepath(rng, j, k):
    '''Construct a complete pathname.'''

    return (
        b'data/'
        + b'/'.join(makepart(rng, k) for _ in range(j))
        + rng.choice([b'.d', b'.i'])
    )


def genpath(rng, count):
    '''Generate random pathnames with gradually increasing lengths.'''

    mink, maxk = 1, 4096

    def steps():
        for i in range(count):
            yield mink + int(round(math.sqrt((maxk - mink) * float(i) / count)))

    for k in steps():
        x = rng.randint(1, k)
        y = rng.randint(1, k)
        yield makepath(rng, x, y)


def runtests(rng, seed, count):
    nerrs = 0
    for p in genpath(rng, count):
        h = store._pathencode(p)  # uses C implementation, if available
        r = store._hybridencode(p, True)  # reference implementation in Python
        if h != r:
            if nerrs == 0:
                print('seed:', hex(seed)[:-1], file=sys.stderr)
            print("\np: '%s'" % p.encode("string_escape"), file=sys.stderr)
            print("h: '%s'" % h.encode("string_escape"), file=sys.stderr)
            print("r: '%s'" % r.encode("string_escape"), file=sys.stderr)
            nerrs += 1
    return nerrs


def main():
    import getopt

    # Empirically observed to take about a second to run
    count = 100
    seed = None
    opts, args = getopt.getopt(
        sys.argv[1:], 'c:s:', ['build', 'count=', 'seed=']
    )
    for o, a in opts:
        if o in ('-c', '--count'):
            count = int(a)
        elif o in ('-s', '--seed'):
            seed = int(a, base=0)  # accepts base 10 or 16 strings
        elif o == '--build':
            buildprobtable(
                sys.stdout,
                'find .hg/store/data -type f && '
                'cat .hg/store/fncache 2>/dev/null',
            )
            sys.exit(0)

    if seed is None:
        try:
            seed = int(binascii.hexlify(os.urandom(16)), 16)
        except AttributeError:
            seed = int(time.time() * 1000)

    rng = random.Random(seed)
    if runtests(rng, seed, count):
        sys.exit(1)


if __name__ == '__main__':
    main()