phases: drop the list with phase of each rev, always comput phase sets

Change the C implementation of phasecache.loadphaserevs to provide only
the sets for draft and secret phase as well as the number of revisions
seen.

Change the pure Python implementation of the same functino to compute
the sets instead of the list of phases for each revision.

Change phasecache.phase to check the phase sets and assume public if the
revision is in neither draft nor secret set. This is computationally
slightly more expensive.

Change phasecache.getrevset for public() based queries to compute the
set of non-matching revisions and return the result as filtered
fullreposet. A shortcut is taken when no draft or secret revision
exists.

Bump the module version for the changed interface contract.

Overall, this saves around 16 Bytes per revision whenever the phasecache
is used, for the test case in issue5691 it is around 3MB. getrevset()
for a large repository is around 13% slower here, that seems an
acceptable trade off. Performance impact for phase() should be similar.

Differential Revision: https://phab.mercurial-scm.org/D1606

mercurial/cext/parsers.c

@@ -710,7 +710,7 b' void dirs_module_init(PyObject *mod);'
 void manifest_module_init(PyObject *mod);
 void revlog_module_init(PyObject *mod);
 
-static const int version = 3;
+static const int version = 4;
 
 static void module_init(PyObject *mod)
 {

mercurial/cext/revlog.c

@@ -628,7 +628,7 b' static PyObject *compute_phases_map_sets'
 {
 	PyObject *roots = Py_None;
 	PyObject *ret = NULL;
-	PyObject *phaseslist = NULL;
+	PyObject *phasessize = NULL;
 	PyObject *phaseroots = NULL;
 	PyObject *phaseset = NULL;
 	PyObject *phasessetlist = NULL;
@@ -685,12 +685,10 b' static PyObject *compute_phases_map_sets'
 		}
 	}
 	/* Transform phase list to a python list */
-	phaseslist = PyList_New(len);
-	if (phaseslist == NULL)
+	phasessize = PyInt_FromLong(len);
+	if (phasessize == NULL)
 		goto release;
 	for (i = 0; i < len; i++) {
-		PyObject *phaseval;
-
 		phase = phases[i];
 		/* We only store the sets of phase for non public phase, the public phase
 		 * is computed as a difference */
@@ -702,15 +700,11 b' static PyObject *compute_phases_map_sets'
 			PySet_Add(phaseset, rev);
 			Py_XDECREF(rev);
 		}
-		phaseval = PyInt_FromLong(phase);
-		if (phaseval == NULL)
-			goto release;
-		PyList_SET_ITEM(phaseslist, i, phaseval);
 	}
-	ret = PyTuple_Pack(2, phaseslist, phasessetlist);
+	ret = PyTuple_Pack(2, phasessize, phasessetlist);
 
 release:
-	Py_XDECREF(phaseslist);
+	Py_XDECREF(phasessize);
 	Py_XDECREF(phasessetlist);
 done:
 	free(phases);

mercurial/localrepo.py

@@ -688,8 +688,8 b' class localrepository(object):'
     def _activebookmark(self):
         return self._bookmarks.active
 
-    # _phaserevs and _phasesets depend on changelog. what we need is to
-    # call _phasecache.invalidate() if '00changelog.i' was changed, but it
+    # _phasesets depend on changelog. what we need is to call
+    # _phasecache.invalidate() if '00changelog.i' was changed, but it
     # can't be easily expressed in filecache mechanism.
     @storecache('phaseroots', '00changelog.i')
     def _phasecache(self):

mercurial/phases.py

@@ -115,6 +115,7 b' from .node import ('
 )
 from . import (
     error,
+    pycompat,
     smartset,
     txnutil,
     util,
@@ -202,7 +203,7 b' class phasecache(object):'
         if _load:
             # Cheap trick to allow shallow-copy without copy module
             self.phaseroots, self.dirty = _readroots(repo, phasedefaults)
-            self._phaserevs = None
+            self._phasemaxrev = nullrev
             self._phasesets = None
             self.filterunknown(repo)
             self.opener = repo.svfs
@@ -210,23 +211,30 b' class phasecache(object):'
     def getrevset(self, repo, phases):
         """return a smartset for the given phases"""
         self.loadphaserevs(repo) # ensure phase's sets are loaded
-
-        if self._phasesets and all(self._phasesets[p] is not None
-                                   for p in phases):
-            # fast path - use _phasesets
-            revs = self._phasesets[phases[0]]
-            if len(phases) > 1:
-                revs = revs.copy() # only copy when needed
-                for p in phases[1:]:
-                    revs.update(self._phasesets[p])
+        phases = set(phases)
+        if public not in phases:
+            # fast path: _phasesets contains the interesting sets,
+            # might only need a union and post-filtering.
+            if len(phases) == 1:
+                [p] = phases
+                revs = self._phasesets[p]
+            else:
+                revs = set.union(*[self._phasesets[p] for p in phases])
             if repo.changelog.filteredrevs:
                 revs = revs - repo.changelog.filteredrevs
             return smartset.baseset(revs)
         else:
-            # slow path - enumerate all revisions
-            phase = self.phase
-            revs = (r for r in repo if phase(repo, r) in phases)
-            return smartset.generatorset(revs, iterasc=True)
+            phases = set(allphases).difference(phases)
+            if not phases:
+                return smartset.fullreposet(repo)
+            if len(phases) == 1:
+                [p] = phases
+                revs = self._phasesets[p]
+            else:
+                revs = set.union(*[self._phasesets[p] for p in phases])
+            if not revs:
+                return smartset.fullreposet(repo)
+            return smartset.fullreposet(repo).filter(lambda r: r not in revs)
 
     def copy(self):
         # Shallow copy meant to ensure isolation in
@@ -235,13 +243,14 b' class phasecache(object):'
         ph.phaseroots = self.phaseroots[:]
         ph.dirty = self.dirty
         ph.opener = self.opener
-        ph._phaserevs = self._phaserevs
+        ph._phasemaxrev = self._phasemaxrev
         ph._phasesets = self._phasesets
         return ph
 
     def replace(self, phcache):
         """replace all values in 'self' with content of phcache"""
-        for a in ('phaseroots', 'dirty', 'opener', '_phaserevs', '_phasesets'):
+        for a in ('phaseroots', 'dirty', 'opener', '_phasemaxrev',
+                  '_phasesets'):
             setattr(self, a, getattr(phcache, a))
 
     def _getphaserevsnative(self, repo):
@@ -253,42 +262,38 b' class phasecache(object):'
 
     def _computephaserevspure(self, repo):
         repo = repo.unfiltered()
-        revs = [public] * len(repo.changelog)
-        self._phaserevs = revs
-        self._populatephaseroots(repo)
-        for phase in trackedphases:
-            roots = list(map(repo.changelog.rev, self.phaseroots[phase]))
-            if roots:
-                for rev in roots:
-                    revs[rev] = phase
-                for rev in repo.changelog.descendants(roots):
-                    revs[rev] = phase
+        cl = repo.changelog
+        self._phasesets = [set() for phase in allphases]
+        roots = pycompat.maplist(cl.rev, self.phaseroots[secret])
+        if roots:
+            ps = set(cl.descendants(roots))
+            for root in roots:
+                ps.add(root)
+            self._phasesets[secret] = ps
+        roots = pycompat.maplist(cl.rev, self.phaseroots[draft])
+        if roots:
+            ps = set(cl.descendants(roots))
+            for root in roots:
+                ps.add(root)
+            ps.difference_update(self._phasesets[secret])
+            self._phasesets[draft] = ps
+        self._phasemaxrev = len(cl)
 
     def loadphaserevs(self, repo):
         """ensure phase information is loaded in the object"""
-        if self._phaserevs is None:
+        if self._phasesets is None:
             try:
                 res = self._getphaserevsnative(repo)
-                self._phaserevs, self._phasesets = res
+                self._phasemaxrev, self._phasesets = res
             except AttributeError:
                 self._computephaserevspure(repo)
 
     def invalidate(self):
-        self._phaserevs = None
+        self._phasemaxrev = nullrev
         self._phasesets = None
 
-    def _populatephaseroots(self, repo):
-        """Fills the _phaserevs cache with phases for the roots.
-        """
-        cl = repo.changelog
-        phaserevs = self._phaserevs
-        for phase in trackedphases:
-            roots = map(cl.rev, self.phaseroots[phase])
-            for root in roots:
-                phaserevs[root] = phase
-
     def phase(self, repo, rev):
-        # We need a repo argument here to be able to build _phaserevs
+        # We need a repo argument here to be able to build _phasesets
         # if necessary. The repository instance is not stored in
         # phasecache to avoid reference cycles. The changelog instance
         # is not stored because it is a filecache() property and can
@@ -297,10 +302,13 b' class phasecache(object):'
             return public
         if rev < nullrev:
             raise ValueError(_('cannot lookup negative revision'))
-        if self._phaserevs is None or rev >= len(self._phaserevs):
+        if rev >= self._phasemaxrev:
             self.invalidate()
             self.loadphaserevs(repo)
-        return self._phaserevs[rev]
+        for phase in trackedphases:
+            if rev in self._phasesets[phase]:
+                return phase
+        return public
 
     def write(self):
         if not self.dirty:
@@ -455,10 +463,10 b' class phasecache(object):'
         if filtered:
             self.dirty = True
         # filterunknown is called by repo.destroyed, we may have no changes in
-        # root but phaserevs contents is certainly invalid (or at least we
+        # root but _phasesets contents is certainly invalid (or at least we
         # have not proper way to check that). related to issue 3858.
         #
-        # The other caller is __init__ that have no _phaserevs initialized
+        # The other caller is __init__ that have no _phasesets initialized
         # anyway. If this change we should consider adding a dedicated
         # "destroyed" function to phasecache or a proper cache key mechanism
         # (see branchmap one)

mercurial/policy.py

@@ -75,7 +75,7 b' def _importfrom(pkgname, modname):'
     (r'cext', r'diffhelpers'): 1,
     (r'cext', r'mpatch'): 1,
     (r'cext', r'osutil'): 1,
-    (r'cext', r'parsers'): 3,
+    (r'cext', r'parsers'): 4,
 }
 
 # map import request to other package or module