[PATCH 3 of 2] treemanifest: store sub-manifests revlog per directory
Drew Gottlieb
drgott at google.com
Wed Apr 15 15:37:43 CDT 2015
What if we different flags for using in-memory tree manifests and actually
using tree revlogs?
On Wed, Apr 15, 2015 at 4:35 PM Martin von Zweigbergk <martinvonz at google.com>
wrote:
> # HG changeset patch
> # User Martin von Zweigbergk <martinvonz at google.com>
> # Date 1428968680 25200
> # Mon Apr 13 16:44:40 2015 -0700
> # Node ID 71ffbbae4096ca945a3106fd9a2297137ddad168
> # Parent f739948917053db6732e30c62a1089390f4ba06f
> treemanifest: store sub-manifests revlog per directory
>
> With this change, when experiment.treemanifest=True, commits will be
> written with one manifest revlog per directory. The manifest revlogs
> are stored in .hg/store/metadata/$dir/00manifest.[id].
>
> Flat manifests can still be read and interacted with as usual (they
> are also read into treemanifest instances). The functionality for
> writing treemanifest as trees to disk is in addition to the current
> functionality of writing treemanifest as a flat manifest to disk;
> tests still pass with '_treeinmem=True' hardcoded.
>
> Important functionality that is not yet done:
>
> * .hg/requires is not updated, so running e.g. 'hg diff --change .'
> will crash if '.' is stored as a tree
>
> * Exchange is not implemented. It will probably involve a
> changegroupv3 that allows multiple manifest revlogs.
>
> diff -r f73994891705 -r 71ffbbae4096 mercurial/manifest.py
> --- a/mercurial/manifest.py Sun Apr 12 23:01:18 2015 -0700
> +++ b/mercurial/manifest.py Mon Apr 13 16:44:40 2015 -0700
> @@ -444,11 +444,15 @@
> class treemanifest(object):
> def __init__(self, dir='', text=''):
> self._dir = dir
> + self._node = revlog.nullid
> self._dirs = {}
> # Using _lazymanifest here is a little slower than plain old dicts
> self._files = {}
> self._flags = {}
> - self.parse(text)
> + def readsubtree(subdir, subm):
> + raise AssertionError('treemanifest constructor only accepts '
> + 'flat manifests')
> + self.parse(text, readsubtree)
>
> def _subpath(self, path):
> return self._dir + path
> @@ -464,7 +468,22 @@
> util.all(m._isempty() for m in self._dirs.values())))
>
> def __str__(self):
> - return '<treemanifest dir=%s>' % self._dir
> + return ('<treemanifest dir=%s, node=%s>' %
> + (self._dir, revlog.hex(self._node)))
> +
> + def dir(self):
> + '''The directory that this tree manifest represents, including a
> + trailing '/'. Empty string for the repo root directory.'''
> + return self._dir
> +
> + def node(self):
> + '''This node of this instance. nullid for unsaved instances.
> Should
> + be updated when the instance is read or written from a revlog.
> + '''
> + return self._node
> +
> + def setnode(self, node):
> + self._node = node
>
> def iteritems(self):
> for p, n in sorted(self._dirs.items() + self._files.items()):
> @@ -557,6 +576,7 @@
>
> def setflag(self, f, flags):
> """Set the flags (symlink, executable) for path f."""
> + assert 'd' not in flags
> dir, subpath = _splittopdir(f)
> if dir:
> if dir not in self._dirs:
> @@ -567,6 +587,7 @@
>
> def copy(self):
> copy = treemanifest(self._dir)
> + copy._node = self._node
> for d in self._dirs:
> copy._dirs[d] = self._dirs[d].copy()
> copy._files = dict.copy(self._files)
> @@ -737,11 +758,18 @@
> _diff(self, m2)
> return result
>
> - def parse(self, text):
> + def parse(self, text, readsubtree):
> for f, n, fl in _parse(text):
> - self[f] = n
> - if fl:
> - self.setflag(f, fl)
> + if fl == 'd':
> + f = f + '/'
> + self._dirs[f] = readsubtree(self._subpath(f), n)
> + else:
> + # Use __setitem__ and setflag rather than assigning
> directly
> + # to _files and _flags, thereby letting us parse flat
> manifests
> + # as well as tree manifests.
> + self[f] = n
> + if fl:
> + self.setflag(f, fl)
>
> def text(self, usemanifestv2=False):
> """Get the full data of this manifest as a bytestring."""
> @@ -749,8 +777,26 @@
> return _text(((f, self[f], flags(f)) for f in self.keys()),
> usemanifestv2)
>
> + def dirtext(self, usemanifestv2=False):
> + """Get the full data of this directory as a bytestring. Make sure
> that
> + any submanifests have been written first, so their nodeids are
> correct.
> + """
> + flags = self.flags
> + dirs = [(d[:-1], self._dirs[d]._node, 'd') for d in self._dirs]
> + files = [(f, self._files[f], flags(f)) for f in self._files]
> + return _text(sorted(dirs + files), usemanifestv2)
> +
> + def writesubtrees(self, m1, m2, writesubtree):
> + emptytree = treemanifest()
> + for d, subm in self._dirs.iteritems():
> + subp1 = m1._dirs.get(d, emptytree)._node
> + subp2 = m2._dirs.get(d, emptytree)._node
> + if subp1 == revlog.nullid:
> + subp1, subp2 = subp2, subp1
> + writesubtree(subm, subp1, subp2)
> +
> class manifest(revlog.revlog):
> - def __init__(self, opener):
> + def __init__(self, opener, dir=''):
> # During normal operations, we expect to deal with not more than
> four
> # revs at a time (such as during commit --amend). When rebasing
> large
> # stacks of commits, the number can go up, hence the config knob
> below.
> @@ -763,14 +809,19 @@
> usetreemanifest = opts.get('usetreemanifest', usetreemanifest)
> usemanifestv2 = opts.get('manifestv2', usemanifestv2)
> self._mancache = util.lrucachedict(cachesize)
> - revlog.revlog.__init__(self, opener, "00manifest.i")
> self._treeinmem = usetreemanifest
> self._treeondisk = usetreemanifest
> self._usemanifestv2 = usemanifestv2
> + indexfile = "00manifest.i"
> + if dir:
> + assert self._treeondisk
> + indexfile = "metadata/" + dir + "00manifest.i"
> + revlog.revlog.__init__(self, opener, indexfile)
> + self._dir = dir
>
> def _newmanifest(self, data=''):
> if self._treeinmem:
> - return treemanifest('', data)
> + return treemanifest(self._dir, data)
> return manifestdict(data)
>
> def _slowreaddelta(self, node):
> @@ -806,8 +857,17 @@
> if node in self._mancache:
> return self._mancache[node][0]
> text = self.revision(node)
> - arraytext = array.array('c', text)
> - m = self._newmanifest(text)
> + if self._treeondisk:
> + def readsubtree(dir, subm):
> + sublog = manifest(self.opener, dir)
> + return sublog.read(subm)
> + m = self._newmanifest()
> + m.parse(text, readsubtree)
> + m.setnode(node)
> + arraytext = None
> + else:
> + m = self._newmanifest(text)
> + arraytext = array.array('c', text)
> self._mancache[node] = (m, arraytext)
> return m
>
> @@ -845,10 +905,34 @@
> # just encode a fulltext of the manifest and pass that
> # through to the revlog layer, and let it handle the delta
> # process.
> - text = m.text(self._usemanifestv2)
> - arraytext = array.array('c', text)
> - n = self.addrevision(text, transaction, link, p1, p2)
> + if self._treeondisk:
> + m1 = self.read(p1)
> + m2 = self.read(p2)
> + n = self._addtree(m, transaction, link, m1, m2)
> + arraytext = None
> + else:
> + text = m.text(self._usemanifestv2)
> + n = self.addrevision(text, transaction, link, p1, p2)
> + arraytext = array.array('c', text)
>
> self._mancache[n] = (m, arraytext)
>
> return n
> +
> + def _addtree(self, m, transaction, link, m1, m2):
> + def writesubtree(subm, subp1, subp2):
> + sublog = manifest(self.opener, subm.dir())
> + sublog.add(subm, transaction, link, subp1, subp2, None, None)
> + m.writesubtrees(m1, m2, writesubtree)
> + text = m.dirtext(self._usemanifestv2)
> + # If the manifest is unchanged compared to one parent,
> + # don't write a new revision
> + if text == m1.dirtext(self._usemanifestv2):
> + n = m1.node()
> + elif text == m2.dirtext(self._usemanifestv2):
> + n = m2.node()
> + else:
> + n = self.addrevision(text, transaction, link, m1.node(),
> m2.node())
> + # Save nodeid so parent manifest can calculate its nodeid
> + m.setnode(n)
> + return n
> diff -r f73994891705 -r 71ffbbae4096 tests/test-manifest-tree.t
> --- /dev/null Thu Jan 01 00:00:00 1970 +0000
> +++ b/tests/test-manifest-tree.t Mon Apr 13 16:44:40 2015 -0700
> @@ -0,0 +1,158 @@
> +
> +Set up repo
> +
> + $ hg init repo
> + $ cd repo
> +
> + $ cat >> .hg/hgrc <<EOF
> + > [experimental]
> + > treemanifest = True
> + > EOF
> +
> +Without directories, looks like any other repo
> +
> + $ echo 0 > a
> + $ echo 0 > b
> + $ hg ci -Aqm initial
> + $ hg debugdata -m 0
> + a\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
> + b\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
> +
> +Submanifest is stored in separate revlog
> +
> + $ mkdir dir1
> + $ echo 1 > dir1/a
> + $ echo 1 > dir1/b
> + $ echo 1 > e
> + $ hg ci -Aqm 'add dir1'
> + $ hg debugdata -m 1
> + a\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
> + b\x00362fef284ce2ca02aecc8de6d5e8a1c3af0556fe (esc)
> + dir1\x008b3ffd73f901e83304c83d33132c8e774ceac44ed (esc)
> + e\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
> + $ hg debugdata .hg/store/metadata/dir1/00manifest.i 0
> + a\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
> + b\x00b8e02f6433738021a065f94175c7cd23db5f05be (esc)
> +
> +Can add nested directories
> +
> + $ mkdir dir1/dir1
> + $ echo 2 > dir1/dir1/a
> + $ echo 2 > dir1/dir1/b
> + $ mkdir dir1/dir2
> + $ echo 2 > dir1/dir2/a
> + $ echo 2 > dir1/dir2/b
> + $ hg ci -Aqm 'add dir1/dir1'
> + $ hg files -r .
> + a
> + b
> + dir1/a
> + dir1/b
> + dir1/dir1/a
> + dir1/dir1/b
> + dir1/dir2/a
> + dir1/dir2/b
> + e
> +
> +Revision is not created for unchanged directory
> +
> + $ mkdir dir2
> + $ echo 3 > dir2/a
> + $ hg ci -Aqm 'add dir2'
> + $ hg debugdata -m 2 | grep -v dir1/ > before
> + $ hg debugdata -m 3 | grep -v dir2/ > after
> + $ diff before after
> + $ rm before after
> +
> +Removing directory does not create an revlog entry
> +
> + $ hg rm dir1/dir1
> + removing dir1/dir1/a
> + removing dir1/dir1/b
> + $ hg debugindex .hg/store/metadata/dir1/dir1/00manifest.i > before
> + $ hg ci -qm 'remove dir1/dir1'
> + $ hg debugindex .hg/store/metadata/dir1/dir1/00manifest.i > after
> + $ diff before after
> + $ rm before after
> +
> +Check that hg files (calls treemanifest.walk()) works
> +
> + $ hg co 'desc("add dir2")'
> + 2 files updated, 0 files merged, 0 files removed, 0 files unresolved
> + $ hg files -r . dir1
> + dir1/a
> + dir1/b
> + dir1/dir1/a
> + dir1/dir1/b
> + dir1/dir2/a
> + dir1/dir2/b
> +
> +Check that status between revisions works (calls treemanifest.matches())
> +
> + $ hg status --rev 'desc("add dir1")' --rev . dir1
> + A dir1/dir1/a
> + A dir1/dir1/b
> + A dir1/dir2/a
> + A dir1/dir2/b
> +
> +Merge creates 2-parent revision of directory revlog
> +
> + $ echo 5 > dir1/a
> + $ hg ci -Aqm 'modify dir1/a'
> + $ hg co '.^'
> + 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
> + $ echo 6 > dir1/b
> + $ hg ci -Aqm 'modify dir1/b'
> + $ hg merge 'desc("modify dir1/a")'
> + 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
> + (branch merge, don't forget to commit)
> + $ hg ci -m 'conflict-free merge involving dir1/'
> + $ cat dir1/a
> + 5
> + $ cat dir1/b
> + 6
> + $ hg debugindex .hg/store/metadata/dir1/00manifest.i
> + rev offset length base linkrev nodeid p1 p2
> + 0 0 54 0 1 8b3ffd73f901 000000000000
> 000000000000
> + 1 54 68 0 2 b66d046c644f 8b3ffd73f901
> 000000000000
> + 2 122 12 0 4 b87265673c8a b66d046c644f
> 000000000000
> + 3 134 95 0 5 aa5d3adcec72 b66d046c644f
> 000000000000
> + 4 229 81 0 6 e29b066b91ad b66d046c644f
> 000000000000
> + 5 310 107 5 7 a120ce2b83f5 e29b066b91ad
> aa5d3adcec72
> +
> +Merge keeping directory from parent 1 does not create revlog entry. (Note
> that
> +dir1's manifest does change, but only because dir1/a's filelog changes.)
> +
> + $ hg co 'desc("add dir2")'
> + 2 files updated, 0 files merged, 0 files removed, 0 files unresolved
> + $ echo 8 > dir2/a
> + $ hg ci -m 'modify dir2/a'
> + created new head
> +
> + $ hg debugindex .hg/store/metadata/dir2/00manifest.i > before
> + $ hg merge 'desc("modify dir1/a")'
> + 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
> + (branch merge, don't forget to commit)
> + $ hg revert -r 'desc("modify dir2/a")' .
> + reverting dir1/a (glob)
> + $ hg ci -m 'merge, keeping parent 1'
> + $ hg debugindex .hg/store/metadata/dir2/00manifest.i > after
> + $ diff before after
> + $ rm before after
> +
> +Merge keeping directory from parent 2 does not create revlog entry. (Note
> that
> +dir2's manifest does change, but only because dir2/a's filelog changes.)
> +
> + $ hg co 'desc("modify dir2/a")'
> + 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
> + $ hg debugindex .hg/store/metadata/dir1/00manifest.i > before
> + $ hg merge 'desc("modify dir1/a")'
> + 1 files updated, 0 files merged, 0 files removed, 0 files unresolved
> + (branch merge, don't forget to commit)
> + $ hg revert -r 'desc("modify dir1/a")' .
> + reverting dir2/a (glob)
> + $ hg ci -m 'merge, keeping parent 2'
> + created new head
> + $ hg debugindex .hg/store/metadata/dir1/00manifest.i > after
> + $ diff before after
> + $ rm before after
> _______________________________________________
> Mercurial-devel mailing list
> Mercurial-devel at selenic.com
> http://selenic.com/mailman/listinfo/mercurial-devel
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://selenic.com/pipermail/mercurial-devel/attachments/20150415/714f8190/attachment.html>
More information about the Mercurial-devel
mailing list