Mercurial > hg
view mercurial/pvec.py @ 51683:5f37c36f36b9
revlog: use mmap by default is pre-population is available
Using mmap has a great impact of memory usage on server, and a good impact on
performance in multiple case. Now that we pre-populate memory mapping by
default, there is case where it using mmap is slower. So we use it by default
(if pre-population is available).
Further work to reduce the performance impact of the pre-population will be done
later.
Some benchmark below (using the same setup as 522b4d729e89):
As for 522b4d729e89 the impact on small repository like Mercurial or Pypy is
tiny, ~1% best. However for large repositories we see some performance
improvement without seeing the performance regression that we could have without
pre-populate.
##### For netbeans
### data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog
## benchmark.name = hg.command.log
# bin-env-vars.hg.flavor = rust
# benchmark.variants.limit-rev = 1
# benchmark.variants.patch = yes
no-mmap: 0.171579
mmap: 0.166311 (-3.07%, -0.01)
# bin-env-vars.hg.flavor = default
no-mmap: 0.170716
mmap: 0.165218 (-3.22%, -0.01)
# benchmark.variants.patch = no
# benchmark.variants.rev = tip
no-mmap: 0.140862
mmap: 0.137566 (-2.34%, -0.00)
## benchmark.name = hg.command.unbundle
# bin-env-vars.hg.flavor = rust
# benchmark.variants.issue6528 = disabled
# benchmark.variants.reuse-external-delta-parent = yes
# benchmark.variants.revs = any-1-extra-rev
# benchmark.variants.source = unbundle
no-mmap: 0.238038
mmap: 0.239912
no-populate: 0.cbd4c9 (+11.71%, +0.03)
#### For Mozilla
### data-env-vars.name = mozilla-try-2019-02-18-ds2-pnm
# benchmark.name = hg.command.log
# bin-env-vars.hg.flavor = rust
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.limit-rev = 1
# benchmark.variants.patch = yes
no-mmap: 0.258440
mmap: 0.237813 (-7.98%, -0.02)
# benchmark.variants.limit-rev = 10
no-mmap: 1.235323
mmap: 1.213578 (-1.76%, -0.02)
## benchmark.name = hg.command.push
# bin-env-vars.hg.flavor = rust
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.explicit-rev = none
# benchmark.variants.issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.reuse-external-delta-parent = yes
# benchmark.variants.revs = any-1-extra-rev
no-mmap: 4.790135
mmap: 4.668971 (-2.53%, -0.12)
no-populate: 4.841141 (+1.06%, +0.05)
### data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog
## benchmark.name = hg.command.log
# bin-env-vars.hg.flavor = default
# benchmark.variants.limit-rev = 1000
# benchmark.variants.rev = tip
no-mmap: 0.206187
mmap: 0.197348 (-4.29%, -0.01)
## benchmark.name = hg.command.push
# bin-env-vars.hg.flavor = default
# benchmark.variants.explicit-rev = none
# benchmark.variants.issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.reuse-external-delta-parent = yes
# benchmark.variants.revs = any-1-extra-rev
no-mmap: 4.768259
mmap: 4.798632
no-populate: 4.953295 (+3.88%, +0.19)
# benchmark.variants.revs = any-100-extra-rev
no-mmap: 4.785946
mmap: 4.903618
no-populate: 5.014963 (+4.79%, +0.23)
## benchmark.name = hg.command.unbundle
# bin-env-vars.hg.flavor = default
# benchmark.variants.issue6528 = disabled
# benchmark.variants.reuse-external-delta-parent = yes
# benchmark.variants.revs = any-1-extra-rev
# benchmark.variants.source = unbundle
no-mmap: 1.400121
mmap: 1.423411
no-populate: 1.585365 (+13.23%, +0.19)
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Mon, 08 Jul 2024 15:48:34 +0200 |
parents | f15cb5111a1e |
children | f4733654f144 |
line wrap: on
line source
# pvec.py - probabilistic vector clocks for Mercurial # # Copyright 2012 Olivia Mackall <olivia@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 .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