view contrib/bdiff-torture.py @ 47346:f27f2afb15da

dirstate-tree: Skip readdir() in `hg status -mard`

When running the status algorithm in a mode where we don’t list unknown
or ignored files, all we care about are files that are listed in the dirstate.
We can there for skip making expensive calls to readdir() to list the contents
of filesystem directories, and instead only run stat() to get the filesystem
state of files listed in the dirstate. (This state may be an error for files
that don’t exist anymore on the filesystem.)

On 16 CPU threads, this reduces the time spent in the `status()` function for
`hg status -mard` on an old snapshot of mozilla-central from ~70ms to ~50ms.

Differential Revision: https://phab.mercurial-scm.org/D10752

# Randomized torture test generation for bdiff

from __future__ import absolute_import, print_function
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