##// END OF EJS Templates
obsolete: order of magnitude speedup in _computebumpedset...
obsolete: order of magnitude speedup in _computebumpedset Reminder: a changeset is said "bumped" if it tries to obsolete a immutable changeset. The previous algorithm for computing bumped changeset was: 1) Get all public changesets 2) Find all they successors 3) Search for stuff that are eligible for being "bumped" (mutable and non obsolete) The entry size of this algorithm is `O(len(public))` which is mostly the same as `O(len(repo))`. Even this this approach mean fewer obsolescence marker are traveled, this is not very scalable. The new algorithm is: 1) For each potential bumped changesets (non obsolete mutable) 2) iterate over precursors 3) if a precursors is public. changeset is bumped We travel more obsolescence marker, but the entry size is much smaller since the amount of potential bumped should remains mostly stable with time `O(1)`. On some confidential gigantic repo this move bumped computation from 15.19s to 0.46s (×33 speedup…). On "smaller" repo (mercurial, cubicweb's review) no significant gain were seen. The additional traversal of obsolescence marker is probably probably counter balance the advantage of it. Other optimisation could be done in the future (eg: sharing precursors cache for divergence detection)

File last commit:

r19148:3bda242b default
r20207:cd62532c default
Show More
filelog.py
92 lines | 2.7 KiB | text/x-python | PythonLexer
# filelog.py - file history class for mercurial
#
# Copyright 2005-2007 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.
import revlog
import re
_mdre = re.compile('\1\n')
def _parsemeta(text):
"""return (metadatadict, keylist, metadatasize)"""
# text can be buffer, so we can't use .startswith or .index
if text[:2] != '\1\n':
return None, None, None
s = _mdre.search(text, 2).start()
mtext = text[2:s]
meta = {}
keys = []
for l in mtext.splitlines():
k, v = l.split(": ", 1)
meta[k] = v
keys.append(k)
return meta, keys, (s + 2)
def _packmeta(meta, keys=None):
if not keys:
keys = sorted(meta.iterkeys())
return "".join("%s: %s\n" % (k, meta[k]) for k in keys)
class filelog(revlog.revlog):
def __init__(self, opener, path):
super(filelog, self).__init__(opener,
"/".join(("data", path + ".i")))
def read(self, node):
t = self.revision(node)
if not t.startswith('\1\n'):
return t
s = t.index('\1\n', 2)
return t[s + 2:]
def add(self, text, meta, transaction, link, p1=None, p2=None):
if meta or text.startswith('\1\n'):
text = "\1\n%s\1\n%s" % (_packmeta(meta), text)
return self.addrevision(text, transaction, link, p1, p2)
def renamed(self, node):
if self.parents(node)[0] != revlog.nullid:
return False
t = self.revision(node)
m = _parsemeta(t)[0]
if m and "copy" in m:
return (m["copy"], revlog.bin(m["copyrev"]))
return False
def size(self, rev):
"""return the size of a given revision"""
# for revisions with renames, we have to go the slow way
node = self.node(rev)
if self.renamed(node):
return len(self.read(node))
# XXX if self.read(node).startswith("\1\n"), this returns (size+4)
return super(filelog, self).size(rev)
def cmp(self, node, text):
"""compare text with a given file revision
returns True if text is different than what is stored.
"""
t = text
if text.startswith('\1\n'):
t = '\1\n\1\n' + text
samehashes = not super(filelog, self).cmp(node, t)
if samehashes:
return False
# renaming a file produces a different hash, even if the data
# remains unchanged. Check if it's the case (slow):
if self.renamed(node):
t2 = self.read(node)
return t2 != text
return True
def _file(self, f):
return filelog(self.opener, f)