changeset 24636:36872036169b

treemanifest: further optimize treemanifest.matches() The matches function was previously traversing all submanifests to look for matching files, even though it was possible to know if a submanifest won't contain any matches. This change adds a visitdir function on the match object to decide quickly if a directory should be visited when traversing. The function also decides if _all_ subdirectories should be traversed. Adding this logic as methods on the match object also makes the logic modifiable by extensions, such as largefiles. An example of a command this speeds up is running hg status --rev .^ python/ on the Mozilla repo with the treemanifest experiment enabled. It goes from 2.03s to 1.85s. More improvements to speed from this change will happen when treemanifests are lazily loaded. Because a flat manifest is still loaded and then converted into treemanifests, speed improvements are limited. This change has no negative effect on speed. For a worst-case example, this command is not negatively impacted: hg status --rev .^ 'relglob:*.js' on the Mozilla repo. It goes from 2.83s to 2.82s.
author Drew Gottlieb <drgott@google.com>
date Mon, 06 Apr 2015 10:51:53 -0700
parents 21e1ece30f8c
children c1cb6523e968
files mercurial/manifest.py mercurial/match.py
diffstat 2 files changed, 27 insertions(+), 3 deletions(-) [+]
line wrap: on
line diff
--- a/mercurial/manifest.py	Mon Apr 06 14:36:08 2015 -0700
+++ b/mercurial/manifest.py	Mon Apr 06 10:51:53 2015 -0700
@@ -581,11 +581,19 @@
 
         return self._matches(match)
 
-    def _matches(self, match):
+    def _matches(self, match, alldirs=False):
         '''recursively generate a new manifest filtered by the match argument.
-        '''
+
+        Will visit all subdirectories if alldirs is True, otherwise it will
+        only visit subdirectories for which match.visitdir is True.'''
 
         ret = treemanifest(self._dir)
+        if not alldirs:
+            # substring to strip trailing slash
+            visit = match.visitdir(self._dir[:-1] or '.')
+            if not visit:
+                return ret
+            alldirs = (visit == 'all')
 
         for fn in self._files:
             fullp = self._subpath(fn)
@@ -596,7 +604,7 @@
                 ret._flags[fn] = self._flags[fn]
 
         for dir, subm in self._dirs.iteritems():
-            m = subm._matches(match)
+            m = subm._matches(match, alldirs)
             if not m._isempty():
                 ret._dirs[dir] = m
 
--- a/mercurial/match.py	Mon Apr 06 14:36:08 2015 -0700
+++ b/mercurial/match.py	Mon Apr 06 10:51:53 2015 -0700
@@ -9,6 +9,8 @@
 import util, pathutil
 from i18n import _
 
+propertycache = util.propertycache
+
 def _rematcher(regex):
     '''compile the regexp with the best available regexp engine and return a
     matcher function'''
@@ -157,6 +159,20 @@
         else: optimal roots'''
         return self._files
 
+    @propertycache
+    def _dirs(self):
+        return set(util.dirs(self._fmap)) | set(['.'])
+
+    def visitdir(self, dir):
+        '''Helps while traversing a directory tree. Returns the string 'all' if
+        the given directory and all subdirectories should be visited. Otherwise
+        returns True or False indicating whether the given directory should be
+        visited. If 'all' is returned, calling this method on a subdirectory
+        gives an undefined result.'''
+        if not self._fmap or self.exact(dir):
+            return 'all'
+        return dir in self._dirs
+
     def exact(self, f):
         '''Returns True if f is in .files().'''
         return f in self._fmap