view mercurial/pvec.py @ 41276:5affe1583e1d

revset: use changelog's `headrevs` method to compute heads Instead of implementing our own algorithm, we reuse a more generic one. This previous algorithm did not leave much room for laziness so we do not really regress in that regards. A small impact is visible for first/last value in some of the simpler cases. The time needed to compute all values improves overall. Small optimization in the dagop.headrevs function will help to buy this back in the next changesets. There is room to introduce actual laziness in this algorithm, but this is out of scope for this series. This has no visible effect on expensive cases: revset: heads(matching(tip, "author")) plain min max first last reverse rev..rst rev..ast sort sor..rst sor..ast 0) 7.574666 7.545950 7.570743 7.578697 7.525725 7.509929 7.443854 7.488442 7.452880 7.445411 7.689107 1) 7.549390 7.389162 7.529790 7.536297 7.450467 7.555347 7.404586 7.514948 7.542794 7.524787 7.536918 revset: heads(matching(tip, "author")) and -10000:-1 plain min max first last reverse rev..rst rev..ast sort sor..rst sor..ast 0) 7.512533 7.605877 7.382894 7.462109 7.420086 7.575034 7.448452 7.549374 7.457880 7.450308 7.515019 1) 7.548677 7.551832 7.629598 7.494857 7.550554 7.521838 7.451794 error 7.321781 7.546885 7.557523 revset: (-10000:-1) and heads(matching(tip, "author")) plain min max first last reverse rev..rst rev..ast sort sor..rst sor..ast 0) 7.465419 7.570089 7.439594 7.521221 7.498716 7.492922 7.479108 7.552397 7.407888 error 7.468264 1) 7.539866 7.548045 7.491761 7.517170 7.469824 7.501990 7.579102 7.502568 7.578102 7.555754 7.567622 In simpler cases, we see a 10-15% impact when retrieving a single value, the full computation time is equivalent or improved: revset: (-5000:-1000) and heads(-10000:-1) plain min max first last reverse rev..rst rev..ast sort sor..rst sor..ast 0) 0.004244 0.003368 0.003313 0.003367 0.003327 0.004325 0.003401 0.003379 0.004310 0.003359 0.003396 1) 0.003969 93% 0.003862 114% 0.003834 115% 0.003810 113% 0.003822 114% 0.003940 91% 0.003908 114% 0.003814 112% 0.003986 92% 0.003954 117% 0.003816 112% revset: heads(all()) plain min max first last reverse rev..rst rev..ast sort sor..rst sor..ast 0) 0.036503 0.032564 0.030024 0.032378 0.030887 0.036367 0.031713 0.032205 0.036467 0.032286 0.030300 1) 0.036668 0.035347 108% 0.035611 118% 0.035358 109% 0.035726 115% 0.036411 0.035261 111% 0.036096 112% 0.036052 0.035095 108% 0.035792 118% revset: heads(-10000:-1) plain min max first last reverse rev..rst rev..ast sort sor..rst sor..ast 0) 0.003936 0.003218 0.003227 0.003302 0.003328 0.003848 0.003305 0.003252 0.003839 0.003306 0.003279 1) 0.003870 0.003785 117% 0.003821 118% 0.003780 114% 0.003769 113% 0.003776 0.003792 114% 0.003805 117% 0.003810 0.003798 114% 0.003840 117%
author Boris Feld <boris.feld@octobus.net>
date Mon, 14 Jan 2019 17:10:51 +0100
parents e7aa113b14f7
children 2372284d9457
line wrap: on
line source

# pvec.py - probabilistic vector clocks for Mercurial
#
# Copyright 2012 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''
A "pvec" is a changeset property based on the theory of vector clocks
that can be compared to discover relatedness without consulting a
graph. This can be useful for tasks like determining how a
disconnected patch relates to a repository.

Currently a pvec consist of 448 bits, of which 24 are 'depth' and the
remainder are a bit vector. It is represented as a 70-character base85
string.

Construction:

- a root changeset has a depth of 0 and a bit vector based on its hash
- a normal commit has a changeset where depth is increased by one and
  one bit vector bit is flipped based on its hash
- a merge changeset pvec is constructed by copying changes from one pvec into
  the other to balance its depth

Properties:

- for linear changes, difference in depth is always <= hamming distance
- otherwise, changes are probably divergent
- when hamming distance is < 200, we can reliably detect when pvecs are near

Issues:

- hamming distance ceases to work over distances of ~ 200
- detecting divergence is less accurate when the common ancestor is very close
  to either revision or total distance is high
- this could probably be improved by modeling the relation between
  delta and hdist

Uses:

- a patch pvec can be used to locate the nearest available common ancestor for
  resolving conflicts
- ordering of patches can be established without a DAG
- two head pvecs can be compared to determine whether push/pull/merge is needed
  and approximately how many changesets are involved
- can be used to find a heuristic divergence measure between changesets on
  different branches
'''

from __future__ import absolute_import

from .node import nullrev
from . import (
    pycompat,
    util,
)

_size = 448 # 70 chars b85-encoded
_bytes = _size / 8
_depthbits = 24
_depthbytes = _depthbits / 8
_vecbytes = _bytes - _depthbytes
_vecbits = _vecbytes * 8
_radius = (_vecbits - 30) / 2 # high probability vectors are related

def _bin(bs):
    '''convert a bytestring to a long'''
    v = 0
    for b in bs:
        v = v * 256 + ord(b)
    return v

def _str(v, l):
    bs = ""
    for p in pycompat.xrange(l):
        bs = chr(v & 255) + bs
        v >>= 8
    return bs

def _split(b):
    '''depth and bitvec'''
    return _bin(b[:_depthbytes]), _bin(b[_depthbytes:])

def _join(depth, bitvec):
    return _str(depth, _depthbytes) + _str(bitvec, _vecbytes)

def _hweight(x):
    c = 0
    while x:
        if x & 1:
            c += 1
        x >>= 1
    return c
_htab = [_hweight(x) for x in pycompat.xrange(256)]

def _hamming(a, b):
    '''find the hamming distance between two longs'''
    d = a ^ b
    c = 0
    while d:
        c += _htab[d & 0xff]
        d >>= 8
    return c

def _mergevec(x, y, c):
    # Ideally, this function would be x ^ y ^ ancestor, but finding
    # ancestors is a nuisance. So instead we find the minimal number
    # of changes to balance the depth and hamming distance

    d1, v1 = x
    d2, v2 = y
    if d1 < d2:
        d1, d2, v1, v2 = d2, d1, v2, v1

    hdist = _hamming(v1, v2)
    ddist = d1 - d2
    v = v1
    m = v1 ^ v2 # mask of different bits
    i = 1

    if hdist > ddist:
        # if delta = 10 and hdist = 100, then we need to go up 55 steps
        # to the ancestor and down 45
        changes = (hdist - ddist + 1) / 2
    else:
        # must make at least one change
        changes = 1
    depth = d1 + changes

    # copy changes from v2
    if m:
        while changes:
            if m & i:
                v ^= i
                changes -= 1
            i <<= 1
    else:
        v = _flipbit(v, c)

    return depth, v

def _flipbit(v, node):
    # converting bit strings to longs is slow
    bit = (hash(node) & 0xffffffff) % _vecbits
    return v ^ (1<<bit)

def ctxpvec(ctx):
    '''construct a pvec for ctx while filling in the cache'''
    r = ctx.repo()
    if not util.safehasattr(r, "_pveccache"):
        r._pveccache = {}
    pvc = r._pveccache
    if ctx.rev() not in pvc:
        cl = r.changelog
        for n in pycompat.xrange(ctx.rev() + 1):
            if n not in pvc:
                node = cl.node(n)
                p1, p2 = cl.parentrevs(n)
                if p1 == nullrev:
                    # start with a 'random' vector at root
                    pvc[n] = (0, _bin((node * 3)[:_vecbytes]))
                elif p2 == nullrev:
                    d, v = pvc[p1]
                    pvc[n] = (d + 1, _flipbit(v, node))
                else:
                    pvc[n] = _mergevec(pvc[p1], pvc[p2], node)
    bs = _join(*pvc[ctx.rev()])
    return pvec(util.b85encode(bs))

class pvec(object):
    def __init__(self, hashorctx):
        if isinstance(hashorctx, str):
            self._bs = hashorctx
            self._depth, self._vec = _split(util.b85decode(hashorctx))
        else:
            self._vec = ctxpvec(hashorctx)

    def __str__(self):
        return self._bs

    def __eq__(self, b):
        return self._vec == b._vec and self._depth == b._depth

    def __lt__(self, b):
        delta = b._depth - self._depth
        if delta < 0:
            return False # always correct
        if _hamming(self._vec, b._vec) > delta:
            return False
        return True

    def __gt__(self, b):
        return b < self

    def __or__(self, b):
        delta = abs(b._depth - self._depth)
        if _hamming(self._vec, b._vec) <= delta:
            return False
        return True

    def __sub__(self, b):
        if self | b:
            raise ValueError("concurrent pvecs")
        return self._depth - b._depth

    def distance(self, b):
        d = abs(b._depth - self._depth)
        h = _hamming(self._vec, b._vec)
        return max(d, h)

    def near(self, b):
        dist = abs(b.depth - self._depth)
        if dist > _radius or _hamming(self._vec, b._vec) > _radius:
            return False