mercurial/pvec.py

exchange: improve computation of relevant markers for large repos

Compute the candidate nodes with relevant markers directly
from keys of the predecessors/successors/children dictionaries of
obsstore. This is faster than iterating over all nodes directly.
This test could be further improved for repositories with relative
few markers compared to the repository size, but this is no longer
hot already. With the current loop structure, the obshashrange use
works as well as before as it passes lists with a single node.

Adjust the interface by allowing revision lists as well as node lists.
This helps cases that computes ancestors as it reduces the
materialisation cost. Use this in _pushdiscoveryobsmarker and
_getbundleobsmarkerpart. Improve the latter further by directly using
ancestors().


Performance benchmarks show notable and welcome improvement to no-op push and
pull (that would also apply to other push/pull). This apply to push and pull
done without evolve.

### push/pull Benchmark parameter
  # bin-env-vars.hg.flavor          = default
  # benchmark.variants.explicit-rev = none
  # benchmark.variants.protocol     = ssh
  # benchmark.variants.revs         = none

 ## benchmark.name                  = hg.command.pull
  # data-env-vars.name              = mercurial-devel-2024-03-22-zstd-sparse-revlog
before: 5.968537 seconds
after:  5.668507 seconds (-5.03%, -0.30)
  # data-env-vars.name              = tryton-devel-2024-03-22-zstd-sparse-revlog
before: 1.446232 seconds
after:  0.835553 seconds (-42.23%, -0.61)
  # data-env-vars.name              = netbsd-src-draft-2024-09-19-zstd-sparse-revlog
before: 5.777412 seconds
after:  2.523454 seconds (-56.32%, -3.25)

 ## benchmark.name                  = hg.command.push
  # data-env-vars.name              = mercurial-devel-2024-03-22-zstd-sparse-revlog
before: 6.155501 seconds
after:  5.885072 seconds (-4.39%, -0.27)

  # data-env-vars.name              = tryton-devel-2024-03-22-zstd-sparse-revlog
before: 1.491054 seconds
after:  0.934882 seconds (-37.30%, -0.56)

  # data-env-vars.name              = netbsd-src-draft-2024-09-19-zstd-sparse-revlog
before: 5.902494 seconds
after:  2.957644 seconds (-49.89%, -2.94)

There is not notable different in these result using the "rust" flavor instead
of the "default".  The performance impact on the same operation when using
evolve were also tested and no impact was noted.

# pvec.py - probabilistic vector clocks for Mercurial
#
# Copyright 2012 Olivia Mackall <[e-mail]>
#
# 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 annotations

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: int, l: int) -> bytes:
    bs = b""
    for p in range(l):
        bs = pycompat.bytechr(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 range(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 hasattr(r, "_pveccache"):
        r._pveccache = {}
    pvc = r._pveccache
    if ctx.rev() not in pvc:
        cl = r.changelog
        for n in range(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:
    def __init__(self, hashorctx):
        if isinstance(hashorctx, bytes):
            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(b"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