comparison mercurial/branchmap.py @ 23786:7d63398fbfd1

branchmap: use revbranchcache when updating branch map

The revbranchcache is read on demand before it will be used for updating the
branch map. It is written back when the branchmap is written and it will thus
use the same locking as branchmap. The revbranchcache instance is short-lived;
it is only stored in the branchmap from .update() is invoked and until .write()
is invoked. Branchmap already assume that the repo is locked in that case.

The use of revbranchcache for branch map updates will make sure that the
revbranchcache "always" is kept up-to-date.

The perfbranchmap benchmark is somewhat bogus, especially when we can see that
the caching makes a significant difference between the realistic case of a
first run and the rare case of rerunning it with a full cache. Here are some
'base' numbers on mozilla-central:
Before:
! wall 6.912745 comb 6.910000 user 6.840000 sys 0.070000 (best of 3)
After - initial, cache is empty:
! wall 7.792569 comb 7.790000 user 7.720000 sys 0.070000 (best of 3)
After - cache is full:
! wall 0.879688 comb 0.880000 user 0.870000 sys 0.010000 (best of 4)

The overhead when running with empty cache comes from checking, missing and
updating it every time.

Most of the performance improvement comes from not having to extract the branch
info from the changelog. The last doubling of performance comes from no longer
having to convert all branch names to local encoding but reuse the few already
converted branch names.

On the hg repo:
Before:
! wall 0.715703 comb 0.710000 user 0.710000 sys 0.000000 (best of 14)
After:
! wall 0.105489 comb 0.110000 user 0.110000 sys 0.000000 (best of 87)

23785:cb99bacb9b4e

        # heads.
        if closednodes is None:
            self._closednodes = set()
        else:
            self._closednodes = closednodes

    def _hashfiltered(self, repo):
        """build hash of revision filtered in the current cache

        Tracking tipnode and tiprev is not enough to ensure validity of the

                        repo.filtername, len(self), nodecount)
        except (IOError, OSError, util.Abort), inst:
            repo.ui.debug("couldn't write branch cache: %s\n" % inst)
            # Abort may be raise by read only opener
            pass

    def update(self, repo, revgen):
        """Given a branchhead cache, self, that may have extra nodes or be
        missing heads, and a generator of nodes that are strictly a superset of
        heads missing, this function updates self to be correct.
        """
        starttime = time.time()
        cl = repo.changelog
        # collect new branch entries
        newbranches = {}
        getbranchinfo = cl.branchinfo
        for r in revgen:
            branch, closesbranch = getbranchinfo(r)
            newbranches.setdefault(branch, []).append(r)
            if closesbranch:
                self._closednodes.add(cl.node(r))

        # fetch current topological heads to speed up filtering

        if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
            first = len(self._rbcrevs) // _rbcrecsize
            self._rbcrevs.extend('\0' * (len(changelog) * _rbcrecsize -
                                         len(self._rbcrevs)))
            for r in xrange(first, len(changelog)):
                self._branchinfo(r)

        # fast path: extract data from cache, use it if node is matching
        reponode = changelog.node(rev)[:_rbcnodelen]
        cachenode, branchidx = unpack(
            _rbcrecfmt, buffer(self._rbcrevs, rbcrevidx, _rbcrecsize))

            branchidx &= _rbcbranchidxmask
        if cachenode == reponode:
            return self._names[branchidx], close
        # fall back to slow path and make sure it will be written to disk
        self._rbcrevslen = min(self._rbcrevslen, rev)
        return self._branchinfo(rev)

    def _branchinfo(self, changelog, rev):
        """Retrieve branch info from changelog and update _rbcrevs"""
        b, close = changelog.branchinfo(rev)
        if b in self._namesreverse:

23786:7d63398fbfd1

        # heads.
        if closednodes is None:
            self._closednodes = set()
        else:
            self._closednodes = closednodes
        self._revbranchcache = None

    def _hashfiltered(self, repo):
        """build hash of revision filtered in the current cache

        Tracking tipnode and tiprev is not enough to ensure validity of the

                        repo.filtername, len(self), nodecount)
        except (IOError, OSError, util.Abort), inst:
            repo.ui.debug("couldn't write branch cache: %s\n" % inst)
            # Abort may be raise by read only opener
            pass
        if self._revbranchcache:
            self._revbranchcache.write(repo.unfiltered())
            self._revbranchcache = None

    def update(self, repo, revgen):
        """Given a branchhead cache, self, that may have extra nodes or be
        missing heads, and a generator of nodes that are strictly a superset of
        heads missing, this function updates self to be correct.
        """
        starttime = time.time()
        cl = repo.changelog
        # collect new branch entries
        newbranches = {}
        urepo = repo.unfiltered()
        self._revbranchcache = revbranchcache(urepo)
        getbranchinfo = self._revbranchcache.branchinfo
        ucl = urepo.changelog
        for r in revgen:
            branch, closesbranch = getbranchinfo(ucl, r)
            newbranches.setdefault(branch, []).append(r)
            if closesbranch:
                self._closednodes.add(cl.node(r))

        # fetch current topological heads to speed up filtering

        if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
            first = len(self._rbcrevs) // _rbcrecsize
            self._rbcrevs.extend('\0' * (len(changelog) * _rbcrecsize -
                                         len(self._rbcrevs)))
            for r in xrange(first, len(changelog)):
                self._branchinfo(changelog, r)

        # fast path: extract data from cache, use it if node is matching
        reponode = changelog.node(rev)[:_rbcnodelen]
        cachenode, branchidx = unpack(
            _rbcrecfmt, buffer(self._rbcrevs, rbcrevidx, _rbcrecsize))

            branchidx &= _rbcbranchidxmask
        if cachenode == reponode:
            return self._names[branchidx], close
        # fall back to slow path and make sure it will be written to disk
        self._rbcrevslen = min(self._rbcrevslen, rev)
        return self._branchinfo(changelog, rev)

    def _branchinfo(self, changelog, rev):
        """Retrieve branch info from changelog and update _rbcrevs"""
        b, close = changelog.branchinfo(rev)
        if b in self._namesreverse: