strip: make --keep option not set all dirstate times to 0

hg strip -k was using dirstate.rebuild() which reset all the dirstate
entries timestamps to 0.  This meant that the next time hg status was
run every file was considered to be 'unsure', which caused it to do
expensive read operations on every filelog. On a repo with >150,000
files it took 70 seconds when everything was in memory.  From a cold
cache it took several minutes.

The fix is to only reset files that have changed between the working
context and the destination context.

For reference, --keep means the working directory is left alone during
the strip. We have users wanting to use this operation to store their
work-in-progress as a commit on a branch while they go work on another
branch, then come back later and be able to uncommit that work and
continue working.  They currently use 'git reset HARD^' to accomplish
this in git.

hgext/mq.py

@@ -3037,7 +3037,22 @@ def strip(ui, repo, *revs, **opts):
         wlock = repo.wlock()
         try:
             urev = repo.mq.qparents(repo, revs[0])
-            repo.dirstate.rebuild(urev, repo[urev].manifest())
+            uctx = repo[urev]
+
+            # only reset the dirstate for files that would actually change
+            # between the working context and uctx
+            descendantrevs = repo.revs("%s::." % uctx.rev())
+            changedfiles = []
+            for rev in descendantrevs:
+                # blindy reset the files, regardless of what actually changed
+                changedfiles.extend(repo[rev].files())
+
+            # reset files that only changed in the dirstate too
+            dirstate = repo.dirstate
+            dirchanges = [f for f in dirstate if dirstate[f] != 'n']
+            changedfiles.extend(dirchanges)
+
+            repo.dirstate.rebuild(urev, uctx.manifest(), changedfiles)
             repo.dirstate.write()
             update = False
         finally:

mercurial/dirstate.py

@@ -498,13 +498,18 @@ class dirstate(object):
         self._lastnormaltime = 0
         self._dirty = True
 
-    def rebuild(self, parent, files):
+    def rebuild(self, parent, allfiles, changedfiles=None):
+        changedfiles = changedfiles or allfiles
+        oldmap = self._map
         self.clear()
-        for f in files:
-            if 'x' in files.flags(f):
-                self._map[f] = ('n', 0777, -1, 0)
+        for f in allfiles:
+            if f not in changedfiles:
+                self._map[f] = oldmap[f]
             else:
-                self._map[f] = ('n', 0666, -1, 0)
+                if 'x' in allfiles.flags(f):
+                    self._map[f] = ('n', 0777, -1, 0)
+                else:
+                    self._map[f] = ('n', 0666, -1, 0)
         self._pl = (parent, nullid)
         self._dirty = True
 

tests/test-mq-strip.t

@@ -420,6 +420,25 @@ Verify strip protects against stripping wc parent when there are uncommited mods
   $ hg status
   M bar
   ? b
+
+Strip adds, removes, modifies with --keep
+
+  $ touch b
+  $ hg add b
+  $ hg commit -mb
+  $ touch c
+  $ hg add c
+  $ hg rm bar
+  $ hg commit -mc
+  $ echo b > b
+  $ echo d > d
+  $ hg strip --keep tip
+  saved backup bundle to $TESTTMP/test/.hg/strip-backup/*-backup.hg (glob)
+  $ hg status
+  M b
+  ! bar
+  ? c
+  ? d
   $ cd ..
 
 stripping many nodes on a complex graph (issue3299)