contrib/bdiff-torture.py

clone: properly exclude rev-branch-cache from post clone cache warming

When adding "CACHE_REV_BRANCH" to "CACHES_ALL" in e51161b12c7e, I did not
expected it to impact the clone steps. However the "CACHES_POST_CLONE" set is
created rather creatively. (we should fix that, but not on stable)

The benchmark caught a quite significant slowdown one hardlink and ssh-stream
clones. Such slow down can be reduced to around ~5% by fully warming the cache
before the clone. However keeping this expensive step away from the clone
operation fully fix the slowdown and preserve the initial intend.


Example slowdow for hardlink clone

### benchmark.name                               = hg.command.clone
  # bin-env-vars.hg.flavor                       = default
  # bin-env-vars.hg.py-re2-module                = default
  # benchmark.variants.explicit-rev              = none
  # benchmark.variants.issue6528                 = default
  # benchmark.variants.protocol                  = local-hardlink
  # benchmark.variants.pulled-delta-reuse-policy = default
  # benchmark.variants.resource-usage            = default
  # benchmark.variants.validate                  = default
 ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog
6.8.2:  19.799752
6.9rc0: 29.017493  (+46.55%, +9.22)
after:  19.929341

 ## data-env-vars.name = mercurial-public-2018-08-01-zstd-sparse-revlog
6.8.2:  0.468020
6.9rc0: 1.701294 (+263.51%, +1.23)
after:  0.471934

 ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
6.8.2:  2.397564
6.9rc0: 5.666641 (+137.41%, +3.28)
after:  2.428085

# Randomized torture test generation for bdiff

import random
import sys

from mercurial import (
    mdiff,
    pycompat,
)


def reducetest(a, b):
    tries = 0
    reductions = 0
    print("reducing...")
    while tries < 1000:
        a2 = (
            "\n".join(l for l in a.splitlines() if random.randint(0, 100) > 0)
            + "\n"
        )
        b2 = (
            "\n".join(l for l in b.splitlines() if random.randint(0, 100) > 0)
            + "\n"
        )
        if a2 == a and b2 == b:
            continue
        if a2 == b2:
            continue
        tries += 1

        try:
            test1(a, b)
        except Exception:
            reductions += 1
            tries = 0
            a = a2
            b = b2

    print("reduced:", reductions, len(a) + len(b), repr(a), repr(b))
    try:
        test1(a, b)
    except Exception as inst:
        print("failed:", inst)

    sys.exit(0)


def test1(a, b):
    d = mdiff.textdiff(a, b)
    if not d:
        raise ValueError("empty")
    c = mdiff.patches(a, [d])
    if c != b:
        raise ValueError("bad")


def testwrap(a, b):
    try:
        test1(a, b)
        return
    except Exception as inst:
        print("exception:", inst)
    reducetest(a, b)


def test(a, b):
    testwrap(a, b)
    testwrap(b, a)


def rndtest(size, noise):
    a = []
    src = "                aaaaaaaabbbbccd"
    for x in pycompat.xrange(size):
        a.append(src[random.randint(0, len(src) - 1)])

    while True:
        b = [c for c in a if random.randint(0, 99) > noise]
        b2 = []
        for c in b:
            b2.append(c)
            while random.randint(0, 99) < noise:
                b2.append(src[random.randint(0, len(src) - 1)])
        if b2 != a:
            break

    a = "\n".join(a) + "\n"
    b = "\n".join(b2) + "\n"

    test(a, b)


maxvol = 10000
startsize = 2
while True:
    size = startsize
    count = 0
    while size < maxvol:
        print(size)
        volume = 0
        while volume < maxvol:
            rndtest(size, 2)
            volume += size
            count += 2
        size *= 2
    maxvol *= 4
    startsize *= 4