view contrib/bdiff-torture.py @ 39270:37e56607cbb9

lfs: add a progress bar when searching for blobs to upload

The search itself can take an extreme amount of time if there are a lot of
revisions involved.  I've got a local repo that took 6 minutes to push 1850
commits, and 60% of that time was spent here (there are ~70K files):

     \ 58.1%  wrapper.py:     extractpointers      line 297:  pointers = extractpointers(...
       | 57.7%  wrapper.py:     pointersfromctx    line 352:  for p in pointersfromctx(ct...
       | 57.4%  wrapper.py:     pointerfromctx     line 397:  p = pointerfromctx(ctx, f, ...
         \ 38.7%  context.py:     __contains__     line 368:  if f not in ctx:
           | 38.7%  util.py:        __get__        line 82:  return key in self._manifest
           | 38.7%  context.py:     _manifest      line 1416:  result = self.func(obj)
           | 38.7%  manifest.py:    read           line 472:  return self._manifestctx.re...
             \ 25.6%  revlog.py:      revision     line 1562:  text = rl.revision(self._node)
               \ 12.8%  revlog.py:      _chunks    line 2217:  bins = self._chunks(chain, ...
                 | 12.0%  revlog.py:      decompressline 2112:  ladd(decomp(buffer(data, ch...
               \  7.8%  revlog.py:      checkhash  line 2232:  self.checkhash(text, node, ...
                 |  7.8%  revlog.py:      hash     line 2315:  if node != self.hash(text, ...
                 |  7.8%  revlog.py:      hash     line 2242:  return hash(text, p1, p2)
             \ 12.0%  manifest.py:    __init__     line 1565:  self._data = manifestdict(t...
         \ 16.8%  context.py:     filenode         line 378:  if not _islfs(fctx.filelog(...
           | 15.7%  util.py:        __get__        line 706:  return self._filelog
           | 14.8%  context.py:     _filelog       line 1416:  result = self.func(obj)
           | 14.8%  localrepo.py:   file           line 629:  return self._repo.file(self...
           | 14.8%  filelog.py:     __init__       line 1134:  return filelog.filelog(self...
           | 14.5%  revlog.py:      __init__       line 24:  censorable=True)

# Randomized torture test generation for bdiff

from __future__ import absolute_import, print_function
import random
import sys

from mercurial import (
    mdiff,
)

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 = 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:
        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