Mercurial > hg
view mercurial/pvec.py @ 20182:04036798ebed
branches: avoid unnecessary changectx.branch() calls
This requires reading from the changelog, which can be costly over NFS.
Note that this does not totally remove reading from the changelog; we
still do that when calling changectx.closesbranch(). That call will be
removed in a later patch.
Running hg branches on the PyPy repo (with 996) over a busy NFS server,
before this change:
$ time hg --profile branches > /dev/null
CallCount Recursive Total(s) Inline(s) module:lineno(function)
2042 0 2.2827 2.2827 <open>
2036 0 0.9840 0.9840 <method 'close' of 'file' objects>
2036 0 0.0464 0.0464 <method 'read' of 'file' objects>
5233 0 0.1985 0.0453 mercurial.repoview:161(changelog)
10462 0 0.0791 0.0314 mercurial.changelog:133(tip)
5233 0 0.0388 0.0176 mercurial.localrepo:26(__get__)
10462 0 0.0250 0.0126 <len>
5233 0 0.0059 0.0039 mercurial.repoview:112(filterrevs)
10462 0 0.0029 0.0029 <hash>
2034 0 0.0444 0.0444 <method 'seek' of 'file' objects>
5340 0 0.0390 0.0390 mercurial.revlog:296(rev)
2582 0 0.0371 0.0371 <zlib.decompress>
3155 0 0.1963 0.0366 mercurial.context:202(__init__)
3155 0 0.1238 0.0306 mercurial.repoview:161(changelog)
3155 0 0.0261 0.0080 mercurial.changelog:183(rev)
9465 0 0.0061 0.0061 <isinstance>
1096 0 0.0023 0.0023 <binascii.unhexlify>
4251 0 0.0014 0.0014 <len>
2059 0 3.7341 0.0332 mercurial.changelog:270(read)
2059 0 3.6304 0.0307 mercurial.revlog:907(revision)
2057 0 0.0262 0.0137 mercurial.changelog:28(decodeextra)
4118 0 0.0094 0.0094 <method 'split' of 'str' objects>
4118 0 0.0270 0.0048 mercurial.encoding:61(tolocal)
2059 0 0.0040 0.0040 <method 'index' of 'str' objects>
10462 0 0.0791 0.0314 mercurial.changelog:133(tip)
10462 0 0.0289 0.0207 mercurial.changelog:190(node)
10462 0 0.0188 0.0091 <len>
52433 20932 0.0478 0.0310 <len>
20932 0 0.0221 0.0168 mercurial.revlog:262(__len__)
2059 0 3.6304 0.0307 mercurial.revlog:907(revision)
real 0m4.361s
user 0m0.986s
sys 0m0.237s
After this change:
$ time hg --profile branches > /dev/null
CallCount Recursive Total(s) Inline(s) module:lineno(function)
1069 0 1.1098 1.1098 <open>
1063 0 0.4865 0.4865 <method 'close' of 'file' objects>
4122 0 0.1811 0.0404 mercurial.repoview:161(changelog)
8240 0 0.0712 0.0272 mercurial.changelog:133(tip)
4122 0 0.0378 0.0177 mercurial.localrepo:26(__get__)
8240 0 0.0221 0.0115 <len>
4122 0 0.0057 0.0033 mercurial.repoview:112(filterrevs)
8240 0 0.0025 0.0025 <hash>
3029 0 0.1979 0.0371 mercurial.context:202(__init__)
3029 0 0.1278 0.0310 mercurial.repoview:161(changelog)
3029 0 0.0230 0.0081 mercurial.changelog:183(rev)
9087 0 0.0061 0.0061 <isinstance>
1096 0 0.0026 0.0026 <binascii.unhexlify>
4125 0 0.0014 0.0014 <len>
4229 0 0.0337 0.0337 mercurial.revlog:296(rev)
1061 0 0.0296 0.0296 <method 'seek' of 'file' objects>
1063 0 0.0292 0.0292 <method 'read' of 'file' objects>
8240 0 0.0712 0.0272 mercurial.changelog:133(tip)
8240 0 0.0271 0.0196 mercurial.changelog:190(node)
8240 0 0.0169 0.0083 <len>
40476 16488 0.0422 0.0271 <len>
16488 0 0.0193 0.0152 mercurial.revlog:262(__len__)
1342 0 0.0241 0.0241 <zlib.decompress>
9445 0 0.0336 0.0224 mercurial.changelog:190(node)
9445 0 0.0112 0.0112 mercurial.revlog:317(node)
1074 0 1.9102 0.0224 mercurial.changelog:270(read)
1074 0 1.8397 0.0202 mercurial.revlog:907(revision)
1073 0 0.0187 0.0099 mercurial.changelog:28(decodeextra)
2148 0 0.0061 0.0061 <method 'split' of 'str' objects>
2148 0 0.0184 0.0034 mercurial.encoding:61(tolocal)
real 0m2.402s
user 0m0.735s
sys 0m0.177s
author | Brodie Rao <brodie@sf.io> |
---|---|
date | Fri, 15 Nov 2013 23:18:08 -0500 |
parents | 5093d2a87ff6 |
children | bcc319d936a3 |
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 ''' import base85, util from node import nullrev _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 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 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 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(base85.b85encode(bs)) class pvec(object): def __init__(self, hashorctx): if isinstance(hashorctx, str): self._bs = hashorctx self._depth, self._vec = _split(base85.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