view contrib/bdiff-torture.py @ 34065:c6c8a52e28c9

revset: optimize "draft() & ::x" pattern

The `draft() & ::x` type query could be common for selecting one or more
draft feature branches being worked on.

Before this patch, `::x` may travel through the changelog DAG for a long
distance until it gets a smaller revision number than `min(draft())`. It
could be very slow on long changelog with distant (in terms of revision
numbers) drafts.

This patch adds a fast path for this situation, and will stop traveling the
changelog DAG once `::x` hits a non-draft revision.

The fast path also works for `secret()` and `not public()`.

To measure the performance difference, I used drawdag to create a repo that
emulates distant drafts:

          DRAFT4
           |
          DRAFT3 # draft
          /
  PUBLIC9999 # public
      |
  PUBLIC9998
      |
      .   DRAFT2
      .    |
      .   DRAFT1 # draft
      |   /
  PUBLIC0001 # public

And measured the performance using the repo:

  (BEFORE)
  $ hg perfrevset 'draft() & ::(DRAFT2+DRAFT4)'
  ! wall 0.017132 comb 0.010000 user 0.010000 sys 0.000000 (best of 156)
  $ hg perfrevset 'draft() & ::(all())'
  ! wall 0.024221 comb 0.030000 user 0.030000 sys 0.000000 (best of 113)
  (AFTER)
  $ hg perfrevset 'draft() & ::(DRAFT2+DRAFT4)'
  ! wall 0.000243 comb 0.000000 user 0.000000 sys 0.000000 (best of 9303)
  $ hg perfrevset 'draft() & ::(all())'
  ! wall 0.004319 comb 0.000000 user 0.000000 sys 0.000000 (best of 655)

Differential Revision: https://phab.mercurial-scm.org/D441

# 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