sapling/mercurial/repoview.py

243 lines
8.9 KiB
Python
Raw Normal View History

# repoview.py - Filtered view of a localrepo object
#
# Copyright 2012 Pierre-Yves David <pierre-yves.david@ens-lyon.org>
# Logilab SA <contact@logilab.fr>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
2015-08-09 05:58:05 +03:00
from __future__ import absolute_import
import copy
2015-08-09 05:58:05 +03:00
from .node import nullrev
from . import (
obsolete,
phases,
tags as tagsmod,
)
def hideablerevs(repo):
"""Revision candidates to be hidden
This is a standalone function to allow extensions to wrap it.
Because we use the set of immutable changesets as a fallback subset in
branchmap (see mercurial.branchmap.subsettable), you cannot set "public"
changesets as "hideable". Doing so would break multiple code assertions and
lead to crashes."""
return obsolete.getrevs(repo, 'obsolete')
def pinnedrevs(repo):
"""revisions blocking hidden changesets from being filtered
"""
cl = repo.changelog
pinned = set()
pinned.update([par.rev() for par in repo[None].parents()])
pinned.update([cl.rev(bm) for bm in repo._bookmarks.values()])
tags = {}
tagsmod.readlocaltags(repo.ui, repo, tags, {})
if tags:
rev, nodemap = cl.rev, cl.nodemap
pinned.update(rev(t[0]) for t in tags.values() if t[0] in nodemap)
return pinned
hidden: simplify the computation of consistency blocker For a couple of years, we now have precomputed set for all mutable phases. We can use this set restrict our search and quickly detect non-hideable children of hideable changesets. This speeds up the hidden computation. See docstring of the new function for details. This new version reuses the '_domainancestors' function to keep the computation of revealed changeset in O(len(visible)) Below are perfvolatilesets timing from two Mozilla repositories with different contents. hidden cache is disabled while obtaining them. 1) Mozilla repository with: * 400667 changesets * 35 hidden changesets (first rev-268334) * 288 visible drafts * 1 unstable changeset Before: ! visible ! wall 0.001744 comb 0.000000 user 0.000000 sys 0.000000 (best of 1563) After: ! visible ! wall 0.000742 comb 0.000000 user 0.000000 sys 0.000000 (best of 3755) The timing above include the computation of obsolete changeset: ! obsolete ! wall 0.000396 comb 0.000000 user 0.000000 sys 0.000000 (best of 6816) So adjusted time give 1.3ms before versus 0.3ms after. A 4x speedup. 2) Mozilla repository with: * 405645 changesets * 4312 hidden changesets (first rev-326004) * 264 visible drafts * 1 unstable changeset Before: ! visible ! wall 0.025476 comb 0.030000 user 0.030000 sys 0.000000 (best of 111) After ! visible ! wall 0.007703 comb 0.010000 user 0.010000 sys 0.000000 (best of 358) The timing above include the computation of obsolete changeset: ! obsolete ! wall 0.006408 comb 0.010000 user 0.010000 sys 0.000000 (best of 404) So adjusted time give 19ms before versus 1.3ms after. A 17x speedup.
2017-05-21 17:01:20 +03:00
def _revealancestors(pfunc, hidden, revs):
"""reveals contiguous chains of hidden ancestors of 'revs' by removing them
from 'hidden'
- pfunc(r): a funtion returning parent of 'r',
- hidden: the (preliminary) hidden revisions, to be updated
- revs: iterable of revnum,
(Ancestors are revealed exclusively, i.e. the elements in 'revs' are
*not* revealed)
"""
stack = list(revs)
while stack:
for p in pfunc(stack.pop()):
if p != nullrev and p in hidden:
hidden.remove(p)
stack.append(p)
def computehidden(repo):
"""compute the set of hidden revision to filter
During most operation hidden should be filtered."""
assert not repo.changelog.filteredrevs
hidden = hideablerevs(repo)
if hidden:
hidden = set(hidden - pinnedrevs(repo))
pfunc = repo.changelog.parentrevs
mutablephases = (phases.draft, phases.secret)
mutable = repo._phasecache.getrevset(repo, mutablephases)
visible = mutable - hidden
_revealancestors(pfunc, hidden, visible)
return frozenset(hidden)
def computeunserved(repo):
"""compute the set of revision that should be filtered when used a server
Secret and hidden changeset should not pretend to be here."""
assert not repo.changelog.filteredrevs
# fast path in simple case to avoid impact of non optimised code
hiddens = filterrevs(repo, 'visible')
if phases.hassecret(repo):
cl = repo.changelog
secret = phases.secret
getphase = repo._phasecache.phase
first = min(cl.rev(n) for n in repo._phasecache.phaseroots[secret])
revs = cl.revs(start=first)
secrets = set(r for r in revs if getphase(repo, r) >= secret)
return frozenset(hiddens | secrets)
else:
return hiddens
def computemutable(repo):
assert not repo.changelog.filteredrevs
# fast check to avoid revset call on huge repo
if any(repo._phasecache.phaseroots[1:]):
getphase = repo._phasecache.phase
maymutable = filterrevs(repo, 'base')
return frozenset(r for r in maymutable if getphase(repo, r))
return frozenset()
def computeimpactable(repo):
"""Everything impactable by mutable revision
The immutable filter still have some chance to get invalidated. This will
happen when:
- you garbage collect hidden changeset,
- public phase is moved backward,
- something is changed in the filtering (this could be fixed)
This filter out any mutable changeset and any public changeset that may be
impacted by something happening to a mutable revision.
This is achieved by filtered everything with a revision number egal or
higher than the first mutable changeset is filtered."""
assert not repo.changelog.filteredrevs
cl = repo.changelog
firstmutable = len(cl)
for roots in repo._phasecache.phaseroots[1:]:
if roots:
firstmutable = min(firstmutable, min(cl.rev(r) for r in roots))
# protect from nullrev root
firstmutable = max(0, firstmutable)
return frozenset(xrange(firstmutable, len(cl)))
# function to compute filtered set
#
# When adding a new filter you MUST update the table at:
# mercurial.branchmap.subsettable
# Otherwise your filter will have to recompute all its branches cache
# from scratch (very slow).
filtertable = {'visible': computehidden,
'served': computeunserved,
'immutable': computemutable,
'base': computeimpactable}
def filterrevs(repo, filtername):
"""returns set of filtered revision for this filter name"""
if filtername not in repo.filteredrevcache:
func = filtertable[filtername]
repo.filteredrevcache[filtername] = func(repo.unfiltered())
return repo.filteredrevcache[filtername]
class repoview(object):
"""Provide a read/write view of a repo through a filtered changelog
This object is used to access a filtered version of a repository without
altering the original repository object itself. We can not alter the
original object for two main reasons:
- It prevents the use of a repo with multiple filters at the same time. In
particular when multiple threads are involved.
- It makes scope of the filtering harder to control.
This object behaves very closely to the original repository. All attribute
operations are done on the original repository:
- An access to `repoview.someattr` actually returns `repo.someattr`,
- A write to `repoview.someattr` actually sets value of `repo.someattr`,
- A deletion of `repoview.someattr` actually drops `someattr`
from `repo.__dict__`.
The only exception is the `changelog` property. It is overridden to return
a (surface) copy of `repo.changelog` with some revisions filtered. The
`filtername` attribute of the view control the revisions that need to be
filtered. (the fact the changelog is copied is an implementation detail).
Unlike attributes, this object intercepts all method calls. This means that
all methods are run on the `repoview` object with the filtered `changelog`
property. For this purpose the simple `repoview` class must be mixed with
the actual class of the repository. This ensures that the resulting
`repoview` object have the very same methods than the repo object. This
leads to the property below.
repoview.method() --> repo.__class__.method(repoview)
The inheritance has to be done dynamically because `repo` can be of any
subclasses of `localrepo`. Eg: `bundlerepo` or `statichttprepo`.
"""
def __init__(self, repo, filtername):
object.__setattr__(self, r'_unfilteredrepo', repo)
object.__setattr__(self, r'filtername', filtername)
object.__setattr__(self, r'_clcachekey', None)
object.__setattr__(self, r'_clcache', None)
# not a propertycache on purpose we shall implement a proper cache later
@property
def changelog(self):
"""return a filtered version of the changeset
this changelog must not be used for writing"""
# some cache may be implemented later
unfi = self._unfilteredrepo
unfichangelog = unfi.changelog
# bypass call to changelog.method
unfiindex = unfichangelog.index
unfilen = len(unfiindex) - 1
unfinode = unfiindex[unfilen - 1][7]
revs = filterrevs(unfi, self.filtername)
cl = self._clcache
newkey = (unfilen, unfinode, hash(revs), unfichangelog._delayed)
repoview: discard filtered changelog if index isn't shared with unfiltered Before this patch, revisions rollbacked at failure of previous transaction might be visible at subsequent operations unintentionally, if repoview object is reused even after failure of transaction: e.g. command server and HTTP server are typical cases. 'repoview' uses the tuple of values below of unfiltered changelog as "the key" to examine validity of filtered changelog cache. - length - tip node - filtered revisions (as hashed value) - '_delayed' field 'repoview' compares between "the key" of unfiltered changelog at previous caching and now, and reuses filtered changelog cache if no change is detected. But this comparison indicates only that there is no change between unfiltered 'repo.changelog' at last caching and now, but not that filtered changelog cache is valid for current unfiltered one. 'repoview' uses "shallow copy" of unfiltered changelog to create filtered changelog cache. In this case, 'index' buffer of unfiltered changelog is also referred by filtered changelog. At failure of transaction, unfiltered changelog itself is invalidated (= un-referred) on the 'repo' side (see b7829fc79508 also). But 'index' of it still contains revisions to be rollbacked at this failure, and is referred by filtered changelog. Therefore, even if there is no change between unfiltered 'repo.changelog' at last caching and now, steps below makes rollbacked revisions visible via filtered changelog unintentionally. 1. instantiate unfiltered changelog as 'repo.changelog' (call it CL1) 2. make filtered (= shallow copy of) CL1 (call it FCL1) 3. cache FCL1 with "the key" of CL1 4. revisions are appended to 'index', which is shared by CL1 and FCL1 5. invalidate 'repo.changelog' (= CL1) at failure of transaction 6. instantiate 'repo.changelog' again at next operation (call it CL2) CL2 doesn't have revisions added at (4), because it is instantiated from '00changelog.i', which isn't changed while failed transaction. 7. compare between "the key" of CL1 and CL2 8. FCL1 cached at (3) is reused, because comparison at (7) doesn't detect change between CL1 at (1) and CL2 9. revisions rollbacked at (5) are visible via FCL1 unintentionally, because FCL1 still refers 'index' changed at (4) The root cause of this issue is that there is no examination about validity of filtered changelog cache against current unfiltered one. This patch discards filtered changelog cache, if its 'index' object isn't shared with unfiltered one. BTW, at the time of this patch, redundant truncation of '00changelog.i' at failure of transaction (see b7829fc79508 for detail) often prevents "hg serve" from making already rollbacked revisions visible, because updating timestamps of '00changelog.i' by truncation makes "hg serve" discard old repoview object with invalid filtered changelog cache. This is reason why this issue is overlooked before this patch, even though test-bundle2-exchange.t has tests in similar situation: failure of "hg push" via HTTP by pretxnclose hook on server side doesn't prevent subsequent commands from looking up outgoing revisions correctly. But timestamp on the filesystem doesn't have enough resolution for recent computation power, and it can't be assumed that this avoidance always works as expected. Therefore, without this patch, this issue might appear occasionally.
2016-02-24 00:10:46 +03:00
# if cl.index is not unfiindex, unfi.changelog would be
# recreated, and our clcache refers to garbage object
if (cl is not None and
(cl.index is not unfiindex or newkey != self._clcachekey)):
cl = None
# could have been made None by the previous if
if cl is None:
cl = copy.copy(unfichangelog)
cl.filteredrevs = revs
object.__setattr__(self, r'_clcache', cl)
object.__setattr__(self, r'_clcachekey', newkey)
return cl
def unfiltered(self):
"""Return an unfiltered version of a repo"""
return self._unfilteredrepo
def filtered(self, name):
"""Return a filtered version of a repository"""
if name == self.filtername:
return self
return self.unfiltered().filtered(name)
# everything access are forwarded to the proxied repo
def __getattr__(self, attr):
return getattr(self._unfilteredrepo, attr)
def __setattr__(self, attr, value):
return setattr(self._unfilteredrepo, attr, value)
def __delattr__(self, attr):
return delattr(self._unfilteredrepo, attr)