D3154: filelog: wrap revlog instead of inheriting it (API)
This revision was automatically updated to reflect the committed changes. Closed by commit rHG1541e1a8e87d: filelog: wrap revlog instead of inheriting it (API) (authored by indygreg, committed by ). REPOSITORY rHG Mercurial CHANGES SINCE LAST UPDATE https://phab.mercurial-scm.org/D3154?vs=7860&id=7919 REVISION DETAIL https://phab.mercurial-scm.org/D3154 AFFECTED FILES mercurial/bundlerepo.py mercurial/filelog.py mercurial/unionrepo.py CHANGE DETAILS diff --git a/mercurial/unionrepo.py b/mercurial/unionrepo.py --- a/mercurial/unionrepo.py +++ b/mercurial/unionrepo.py @@ -92,7 +92,7 @@ return mdiff.textdiff(self.revision(rev1), self.revision(rev2)) -def revision(self, nodeorrev, raw=False): +def revision(self, nodeorrev, _df=None, raw=False): """return an uncompressed revision of a given node or revision number. """ @@ -163,13 +163,15 @@ def baserevdiff(self, rev1, rev2): return manifest.manifestrevlog.revdiff(self, rev1, rev2) -class unionfilelog(unionrevlog, filelog.filelog): +class unionfilelog(filelog.filelog): def __init__(self, opener, path, opener2, linkmapper, repo): filelog.filelog.__init__(self, opener, path) filelog2 = filelog.filelog(opener2, path) -unionrevlog.__init__(self, opener, self.indexfile, filelog2, - linkmapper) +self._revlog = unionrevlog(opener, self.indexfile, + filelog2._revlog, linkmapper) self._repo = repo +self.repotiprev = self._revlog.repotiprev +self.revlog2 = self._revlog.revlog2 def baserevision(self, nodeorrev): return filelog.filelog.revision(self, nodeorrev) diff --git a/mercurial/filelog.py b/mercurial/filelog.py --- a/mercurial/filelog.py +++ b/mercurial/filelog.py @@ -11,18 +11,112 @@ interface as zi, ) from . import ( +error, repository, revlog, ) @zi.implementer(repository.ifilestorage) -class filelog(revlog.revlog): +class filelog(object): def __init__(self, opener, path): -super(filelog, self).__init__(opener, -"/".join(("data", path + ".i")), - censorable=True) +self._revlog = revlog.revlog(opener, + '/'.join(('data', path + '.i')), + censorable=True) # full name of the user visible file, relative to the repository root self.filename = path +self.index = self._revlog.index +self.version = self._revlog.version +self.storedeltachains = self._revlog.storedeltachains +self._generaldelta = self._revlog._generaldelta + +def __len__(self): +return len(self._revlog) + +def __iter__(self): +return self._revlog.__iter__() + +def revs(self, start=0, stop=None): +return self._revlog.revs(start=start, stop=stop) + +def parents(self, node): +return self._revlog.parents(node) + +def parentrevs(self, rev): +return self._revlog.parentrevs(rev) + +def rev(self, node): +return self._revlog.rev(node) + +def node(self, rev): +return self._revlog.node(rev) + +def lookup(self, node): +return self._revlog.lookup(node) + +def linkrev(self, rev): +return self._revlog.linkrev(rev) + +def flags(self, rev): +return self._revlog.flags(rev) + +def commonancestorsheads(self, node1, node2): +return self._revlog.commonancestorsheads(node1, node2) + +def descendants(self, revs): +return self._revlog.descendants(revs) + +def headrevs(self): +return self._revlog.headrevs() + +def heads(self, start=None, stop=None): +return self._revlog.heads(start, stop) + +def children(self, node): +return self._revlog.children(node) + +def deltaparent(self, rev): +return self._revlog.deltaparent(rev) + +def candelta(self, baserev, rev): +return self._revlog.candelta(baserev, rev) + +def iscensored(self, rev): +return self._revlog.iscensored(rev) + +def rawsize(self, rev): +return self._revlog.rawsize(rev) + +def checkhash(self, text, node, p1=None, p2=None, rev=None): +return self._revlog.checkhash(text, node, p1=p1, p2=p2, rev=rev) + +def revision(self, node, _df=None, raw=False): +return self._revlog.revision(node, _df=_df, raw=raw) + +def revdiff(self, rev1, rev2): +return self._revlog.revdiff(rev1, rev2) + +def addrevision(self, revisiondata, transaction, linkrev, p1, p2, +node=None, flags=revlog.REVIDX_DEFAULT_FLAGS, +cachedelta=None): +return self._revlog.addrevision(revisiondata, transaction, linkrev, +p1, p2, node=node, flags=flags, +cachedelta=cachedelta) + +def addgroup(self
D3154: filelog: wrap revlog instead of inheriting it (API)
indygreg updated this revision to Diff 7860. REPOSITORY rHG Mercurial CHANGES SINCE LAST UPDATE https://phab.mercurial-scm.org/D3154?vs=7768&id=7860 REVISION DETAIL https://phab.mercurial-scm.org/D3154 AFFECTED FILES mercurial/bundlerepo.py mercurial/filelog.py mercurial/unionrepo.py CHANGE DETAILS diff --git a/mercurial/unionrepo.py b/mercurial/unionrepo.py --- a/mercurial/unionrepo.py +++ b/mercurial/unionrepo.py @@ -92,7 +92,7 @@ return mdiff.textdiff(self.revision(rev1), self.revision(rev2)) -def revision(self, nodeorrev, raw=False): +def revision(self, nodeorrev, _df=None, raw=False): """return an uncompressed revision of a given node or revision number. """ @@ -163,13 +163,15 @@ def baserevdiff(self, rev1, rev2): return manifest.manifestrevlog.revdiff(self, rev1, rev2) -class unionfilelog(unionrevlog, filelog.filelog): +class unionfilelog(filelog.filelog): def __init__(self, opener, path, opener2, linkmapper, repo): filelog.filelog.__init__(self, opener, path) filelog2 = filelog.filelog(opener2, path) -unionrevlog.__init__(self, opener, self.indexfile, filelog2, - linkmapper) +self._revlog = unionrevlog(opener, self.indexfile, + filelog2._revlog, linkmapper) self._repo = repo +self.repotiprev = self._revlog.repotiprev +self.revlog2 = self._revlog.revlog2 def baserevision(self, nodeorrev): return filelog.filelog.revision(self, nodeorrev) diff --git a/mercurial/filelog.py b/mercurial/filelog.py --- a/mercurial/filelog.py +++ b/mercurial/filelog.py @@ -11,18 +11,112 @@ interface as zi, ) from . import ( +error, repository, revlog, ) @zi.implementer(repository.ifilestorage) -class filelog(revlog.revlog): +class filelog(object): def __init__(self, opener, path): -super(filelog, self).__init__(opener, -"/".join(("data", path + ".i")), - censorable=True) +self._revlog = revlog.revlog(opener, + '/'.join(('data', path + '.i')), + censorable=True) # full name of the user visible file, relative to the repository root self.filename = path +self.index = self._revlog.index +self.version = self._revlog.version +self.storedeltachains = self._revlog.storedeltachains +self._generaldelta = self._revlog._generaldelta + +def __len__(self): +return len(self._revlog) + +def __iter__(self): +return self._revlog.__iter__() + +def revs(self, start=0, stop=None): +return self._revlog.revs(start=start, stop=stop) + +def parents(self, node): +return self._revlog.parents(node) + +def parentrevs(self, rev): +return self._revlog.parentrevs(rev) + +def rev(self, node): +return self._revlog.rev(node) + +def node(self, rev): +return self._revlog.node(rev) + +def lookup(self, node): +return self._revlog.lookup(node) + +def linkrev(self, rev): +return self._revlog.linkrev(rev) + +def flags(self, rev): +return self._revlog.flags(rev) + +def commonancestorsheads(self, node1, node2): +return self._revlog.commonancestorsheads(node1, node2) + +def descendants(self, revs): +return self._revlog.descendants(revs) + +def headrevs(self): +return self._revlog.headrevs() + +def heads(self, start=None, stop=None): +return self._revlog.heads(start, stop) + +def children(self, node): +return self._revlog.children(node) + +def deltaparent(self, rev): +return self._revlog.deltaparent(rev) + +def candelta(self, baserev, rev): +return self._revlog.candelta(baserev, rev) + +def iscensored(self, rev): +return self._revlog.iscensored(rev) + +def rawsize(self, rev): +return self._revlog.rawsize(rev) + +def checkhash(self, text, node, p1=None, p2=None, rev=None): +return self._revlog.checkhash(text, node, p1=p1, p2=p2, rev=rev) + +def revision(self, node, _df=None, raw=False): +return self._revlog.revision(node, _df=_df, raw=raw) + +def revdiff(self, rev1, rev2): +return self._revlog.revdiff(rev1, rev2) + +def addrevision(self, revisiondata, transaction, linkrev, p1, p2, +node=None, flags=revlog.REVIDX_DEFAULT_FLAGS, +cachedelta=None): +return self._revlog.addrevision(revisiondata, transaction, linkrev, +p1, p2, node=node, flags=flags, +cachedelta=cachedelta) + +def addgroup(self, deltas, linkmapper, transaction, addrevisioncb=None): +return self._revlog.addgroup(deltas, linkmapper, transaction, +
D3154: filelog: wrap revlog instead of inheriting it (API)
indygreg added a comment. In https://phab.mercurial-scm.org/D3154#51010, @durin42 wrote: > test-unionrepo.t: > + t = self.revision(node) > +File "/tmp/hgtests.wmoy8H/install/lib/python/mercurial/filelog.py", line 93, in revision > + return self._revlog.revision(node, _df=_df, raw=raw) > + TypeError: revision() got an unexpected keyword argument '_df' > + [1] > I remember this error and I thought I fixed it! But alas I can reproduce locally. I must have fixed it on a different class. REPOSITORY rHG Mercurial REVISION DETAIL https://phab.mercurial-scm.org/D3154 To: indygreg, #hg-reviewers, durin42 Cc: mercurial-devel ___ Mercurial-devel mailing list Mercurial-devel@mercurial-scm.org https://www.mercurial-scm.org/mailman/listinfo/mercurial-devel
D3154: filelog: wrap revlog instead of inheriting it (API)
durin42 added a comment. test-unionrepo.t: + t = self.revision(node) +File "/tmp/hgtests.wmoy8H/install/lib/python/mercurial/filelog.py", line 93, in revision + return self._revlog.revision(node, _df=_df, raw=raw) + TypeError: revision() got an unexpected keyword argument '_df' + [1] REPOSITORY rHG Mercurial REVISION DETAIL https://phab.mercurial-scm.org/D3154 To: indygreg, #hg-reviewers, durin42 Cc: mercurial-devel ___ Mercurial-devel mailing list Mercurial-devel@mercurial-scm.org https://www.mercurial-scm.org/mailman/listinfo/mercurial-devel
D3154: filelog: wrap revlog instead of inheriting it (API)
indygreg added a comment. I want to draw attention to this patch for the potential performance concerns. Like I said in the commit message, I'd love to know what the performance impact is. I'm just not sure which revlog/filelog attributes/methods are called in tight loops outside of revlog/filelog itself. If the proxy methods are an issue, it /might/ be faster to use `__new__` to hack up each instance so its `self.__dict__[x]` contained pointers to `revlog` functions bound as methods to the `self._revlog` instance. Super hacky. That's why I'd like evidence that performance is a real concern before implementing it. REPOSITORY rHG Mercurial REVISION DETAIL https://phab.mercurial-scm.org/D3154 To: indygreg, #hg-reviewers Cc: mercurial-devel ___ Mercurial-devel mailing list Mercurial-devel@mercurial-scm.org https://www.mercurial-scm.org/mailman/listinfo/mercurial-devel
D3154: filelog: wrap revlog instead of inheriting it (API)
indygreg created this revision. Herald added a subscriber: mercurial-devel. Herald added a reviewer: hg-reviewers. REVISION SUMMARY The revlog base class exposes a ton of methods. Inheriting the revlog class for filelog will make it difficult to expose a clean interface. There will be abstraction violations. This commit breaks the inheritance of revlog by the filelog class. Filelog instances now contain a reference to a revlog instance. Various properties and methods are now proxied to that instance. There is precedence for doing this: manifestlog does something similar. Although, manifestlog has a cleaner interface than filelog. We'll get there with filelog... The new filelog class exposes a handful of extra properties and methods that aren't part of the declared filelog interface. Every extra item was added in order to get a test to pass. The set of tests that failed without these extra proxies has significant overlap with the set of tests that don't work with the simple store repo. There should be no surprise there. Hopefully the hardest part about this commit to review are the changes to bundlerepo and unionrepo. Both repository types define a custom revlog or revlog-like class and then have a custom filelog that inherits from both filelog and their custom revlog. This code has been changed so the filelog types don't inherit from revlog. Instead, they replace the revlog instance on the created filelog. This is super hacky. I plan to fix this in a future commit by parameterizing filelog.__init__. Because Python function call overhead is a thing, this change could impact performance by introducing a nearly empty proxy function for various methods and properties. I would gladly measure the performance impact of it, but I'm not sure what operations have tight loops over filelog attribute lookups or function calls. I know some of the DAG traversal code can be sensitive about the performance of e.g. parentrevs(). However, many of these functions are implemented on the revlog class and therefore have direct access to self.parentrevs() and aren't going through a proxy. .. api:: filelog.filelog is now a standalone class and doesn't inherit from revlog. Instead, it wraps a revlog instance at self._revlog. This change was made in an attempt to formalize storage APIs and prevent revlog implementation details leaking through to callers. REPOSITORY rHG Mercurial REVISION DETAIL https://phab.mercurial-scm.org/D3154 AFFECTED FILES mercurial/bundlerepo.py mercurial/filelog.py mercurial/unionrepo.py CHANGE DETAILS diff --git a/mercurial/unionrepo.py b/mercurial/unionrepo.py --- a/mercurial/unionrepo.py +++ b/mercurial/unionrepo.py @@ -163,13 +163,15 @@ def baserevdiff(self, rev1, rev2): return manifest.manifestrevlog.revdiff(self, rev1, rev2) -class unionfilelog(unionrevlog, filelog.filelog): +class unionfilelog(filelog.filelog): def __init__(self, opener, path, opener2, linkmapper, repo): filelog.filelog.__init__(self, opener, path) filelog2 = filelog.filelog(opener2, path) -unionrevlog.__init__(self, opener, self.indexfile, filelog2, - linkmapper) +self._revlog = unionrevlog(opener, self.indexfile, + filelog2._revlog, linkmapper) self._repo = repo +self.repotiprev = self._revlog.repotiprev +self.revlog2 = self._revlog.revlog2 def baserevision(self, nodeorrev): return filelog.filelog.revision(self, nodeorrev) diff --git a/mercurial/filelog.py b/mercurial/filelog.py --- a/mercurial/filelog.py +++ b/mercurial/filelog.py @@ -11,18 +11,112 @@ interface as zi, ) from . import ( +error, repository, revlog, ) @zi.implementer(repository.ifilestorage) -class filelog(revlog.revlog): +class filelog(object): def __init__(self, opener, path): -super(filelog, self).__init__(opener, -"/".join(("data", path + ".i")), - censorable=True) +self._revlog = revlog.revlog(opener, + '/'.join(('data', path + '.i')), + censorable=True) # full name of the user visible file, relative to the repository root self.filename = path +self.index = self._revlog.index +self.version = self._revlog.version +self.storedeltachains = self._revlog.storedeltachains +self._generaldelta = self._revlog._generaldelta + +def __len__(self): +return len(self._revlog) + +def __iter__(self): +return self._revlog.__iter__() + +def revs(self, start=0, stop=None): +return self._revlog.revs(start=start, stop=stop) + +def parents(self, node): +return self._revlog.parents(node) + +def parentrevs(self, rev): +return se