Mercurial > hg
view mercurial/dagutil.py @ 29304:5e32852fa4bd
revset: make filteredset.__nonzero__ respect the order of the filteredset
This fix allows __nonzero__ to respect the direction of iteration of the
whole filteredset. Here's the case when it matters. Imagine that we have a
very large repository and we want to execute a command like:
$ hg log --rev '(tip:0) and user(ikostia)' --limit 1
(we want to get the latest commit by me).
Mercurial will evaluate a filteredset lazy data structure, an
instance of the filteredset class, which will know that it has to iterate
in a descending order (isdescending() will return True if called). This
means that when some code iterates over the instance of this filteredset,
the 'and user(ikostia)' condition will be first checked on the latest
revision, then on the second latest and so on, allowing Mercurial to
print matches as it founds them. However, cmdutil.getgraphlogrevs
contains the following code:
revs = _logrevs(repo, opts)
if not revs:
return revset.baseset(), None, None
The "not revs" expression is evaluated by calling filteredset.__nonzero__,
which in its current implementation will try to iterate the filteredset
in ascending order until it finds a revision that matches the 'and user(..'
condition. If the condition is only true on late revisions, a lot of
useless iterations will be done. These iterations could be avoided if
__nonzero__ followed the order of the filteredset, which in my opinion
is a sensible thing to do here.
The problem gets even worse when instead of 'user(ikostia)' some more
expensive check is performed, like grepping the commit diff.
I tested this fix on a very large repo where tip is my commit and my very
first commit comes fairly late in the revision history. Results of timing
of the above command on that very large repo.
-with my fix:
real 0m1.795s
user 0m1.657s
sys 0m0.135s
-without my fix:
real 1m29.245s
user 1m28.223s
sys 0m0.929s
I understand that this is a very specific kind of problem that presents
itself very rarely, only on very big repositories and with expensive
checks and so on. But I don't see any disadvantages to this kind of fix
either.
author | Kostia Balytskyi <ikostia@fb.com> |
---|---|
date | Thu, 02 Jun 2016 22:39:01 +0100 |
parents | 015ded095933 |
children | 09397d0dd3b7 |
line wrap: on
line source
# dagutil.py - dag utilities for mercurial # # Copyright 2010 Benoit Boissinot <bboissin@gmail.com> # and Peter Arrenbrecht <peter@arrenbrecht.ch> # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. from __future__ import absolute_import from .i18n import _ from .node import nullrev class basedag(object): '''generic interface for DAGs terms: "ix" (short for index) identifies a nodes internally, "id" identifies one externally. All params are ixs unless explicitly suffixed otherwise. Pluralized params are lists or sets. ''' def __init__(self): self._inverse = None def nodeset(self): '''set of all node ixs''' raise NotImplementedError def heads(self): '''list of head ixs''' raise NotImplementedError def parents(self, ix): '''list of parents ixs of ix''' raise NotImplementedError def inverse(self): '''inverse DAG, where parents becomes children, etc.''' raise NotImplementedError def ancestorset(self, starts, stops=None): ''' set of all ancestors of starts (incl), but stop walk at stops (excl) ''' raise NotImplementedError def descendantset(self, starts, stops=None): ''' set of all descendants of starts (incl), but stop walk at stops (excl) ''' return self.inverse().ancestorset(starts, stops) def headsetofconnecteds(self, ixs): ''' subset of connected list of ixs so that no node has a descendant in it By "connected list" we mean that if an ancestor and a descendant are in the list, then so is at least one path connecting them. ''' raise NotImplementedError def externalize(self, ix): '''return a node id''' return self._externalize(ix) def externalizeall(self, ixs): '''return a list of (or set if given a set) of node ids''' ids = self._externalizeall(ixs) if isinstance(ixs, set): return set(ids) return list(ids) def internalize(self, id): '''return a node ix''' return self._internalize(id) def internalizeall(self, ids, filterunknown=False): '''return a list of (or set if given a set) of node ixs''' ixs = self._internalizeall(ids, filterunknown) if isinstance(ids, set): return set(ixs) return list(ixs) class genericdag(basedag): '''generic implementations for DAGs''' def ancestorset(self, starts, stops=None): if stops: stops = set(stops) else: stops = set() seen = set() pending = list(starts) while pending: n = pending.pop() if n not in seen and n not in stops: seen.add(n) pending.extend(self.parents(n)) return seen def headsetofconnecteds(self, ixs): hds = set(ixs) if not hds: return hds for n in ixs: for p in self.parents(n): hds.discard(p) assert hds return hds class revlogbaseddag(basedag): '''generic dag interface to a revlog''' def __init__(self, revlog, nodeset): basedag.__init__(self) self._revlog = revlog self._heads = None self._nodeset = nodeset def nodeset(self): return self._nodeset def heads(self): if self._heads is None: self._heads = self._getheads() return self._heads def _externalize(self, ix): return self._revlog.index[ix][7] def _externalizeall(self, ixs): idx = self._revlog.index return [idx[i][7] for i in ixs] def _internalize(self, id): ix = self._revlog.rev(id) if ix == nullrev: raise LookupError(id, self._revlog.indexfile, _('nullid')) return ix def _internalizeall(self, ids, filterunknown): rl = self._revlog if filterunknown: return [r for r in map(rl.nodemap.get, ids) if (r is not None and r != nullrev and r not in rl.filteredrevs)] return map(self._internalize, ids) class revlogdag(revlogbaseddag): '''dag interface to a revlog''' def __init__(self, revlog): revlogbaseddag.__init__(self, revlog, set(revlog)) def _getheads(self): return [r for r in self._revlog.headrevs() if r != nullrev] def parents(self, ix): rlog = self._revlog idx = rlog.index revdata = idx[ix] prev = revdata[5] if prev != nullrev: prev2 = revdata[6] if prev2 == nullrev: return [prev] return [prev, prev2] prev2 = revdata[6] if prev2 != nullrev: return [prev2] return [] def inverse(self): if self._inverse is None: self._inverse = inverserevlogdag(self) return self._inverse def ancestorset(self, starts, stops=None): rlog = self._revlog idx = rlog.index if stops: stops = set(stops) else: stops = set() seen = set() pending = list(starts) while pending: rev = pending.pop() if rev not in seen and rev not in stops: seen.add(rev) revdata = idx[rev] for i in [5, 6]: prev = revdata[i] if prev != nullrev: pending.append(prev) return seen def headsetofconnecteds(self, ixs): if not ixs: return set() rlog = self._revlog idx = rlog.index headrevs = set(ixs) for rev in ixs: revdata = idx[rev] for i in [5, 6]: prev = revdata[i] if prev != nullrev: headrevs.discard(prev) assert headrevs return headrevs def linearize(self, ixs): '''linearize and topologically sort a list of revisions The linearization process tries to create long runs of revs where a child rev comes immediately after its first parent. This is done by visiting the heads of the given revs in inverse topological order, and for each visited rev, visiting its second parent, then its first parent, then adding the rev itself to the output list. ''' sorted = [] visit = list(self.headsetofconnecteds(ixs)) visit.sort(reverse=True) finished = set() while visit: cur = visit.pop() if cur < 0: cur = -cur - 1 if cur not in finished: sorted.append(cur) finished.add(cur) else: visit.append(-cur - 1) visit += [p for p in self.parents(cur) if p in ixs and p not in finished] assert len(sorted) == len(ixs) return sorted class inverserevlogdag(revlogbaseddag, genericdag): '''inverse of an existing revlog dag; see revlogdag.inverse()''' def __init__(self, orig): revlogbaseddag.__init__(self, orig._revlog, orig._nodeset) self._orig = orig self._children = {} self._roots = [] self._walkfrom = len(self._revlog) - 1 def _walkto(self, walkto): rev = self._walkfrom cs = self._children roots = self._roots idx = self._revlog.index while rev >= walkto: data = idx[rev] isroot = True for prev in [data[5], data[6]]: # parent revs if prev != nullrev: cs.setdefault(prev, []).append(rev) isroot = False if isroot: roots.append(rev) rev -= 1 self._walkfrom = rev def _getheads(self): self._walkto(nullrev) return self._roots def parents(self, ix): if ix is None: return [] if ix <= self._walkfrom: self._walkto(ix) return self._children.get(ix, []) def inverse(self): return self._orig