contrib/bdiff-torture.py

match: making visitdir() deal with non-recursive entries

Primarily as an optimization to avoid recursing into directories that will
never have a match inside, this classifies each matcher pattern's root as
recursive or non-recursive (erring on the side of keeping it recursive,
which may lead to wasteful directory or manifest walks that yield no matches).

I measured the performance of "rootfilesin" in two repos:
- The Firefox repo with tree manifests, with
  "hg files -r . -I rootfilesin:browser".
  The browser directory contains about 3K files across 249 subdirectories.
- A specific Google-internal directory which contains 75K files across 19K
  subdirectories, with "hg files -r . -I rootfilesin:REDACTED".

I tested with both cold and warm disk caches. Cold cache was produced by
running "sync; echo 3 > /proc/sys/vm/drop_caches". Warm cache was produced
by re-running the same command a few times.

These were the results:

               Cold cache           Warm cache
             Before   After      Before   After
firefox      0m5.1s   0m2.18s   0m0.22s  0m0.14s
google3 dir  2m3.9s   0m1.57s   0m8.12s  0m0.16s

Certain extensions, notably narrowhg, can depend on this for correctness
(not trying to recurse into directories for which it has no information).

# Randomized torture test generation for bdiff

from __future__ import absolute_import, print_function
import random
import sys

from mercurial import (
    bdiff,
    mpatch,
)

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 as inst:
            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 = bdiff.bdiff(a, b)
    if not d:
        raise ValueError("empty")
    c = mpatch.patches(a, [d])
    if c != b:
        raise ValueError("bad")

def testwrap(a, b):
    try:
        test1(a, b)
        return
    except Exception as inst:
        pass
    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 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