diff mercurial/merge.py @ 32200:4d504e541d3d

rebase: use matcher to optimize manifestmerge

The old merge code would call manifestmerge and calculate the complete diff
between the source to the destination. In many cases, like rebase, the vast
majority of differences between the source and destination are irrelevant
because they are differences between the destination and the common ancestor
only, and therefore don't affect the merge. Since most actions are 'keep', all
the effort to compute them is wasted.

Instead, let's compute the difference between the source and the common ancestor
and only perform the diff of those files against the merge destination. When
using treemanifest, this lets us avoid loading almost the entire tree when
rebasing from a very old ancestor. This speeds up rebase of an old stack of 27
commits by 20x.

In mozilla-central, without treemanifest, when rebasing a commit from
default~100000 to default, this speeds up the manifestmerge step from 2.6s to
1.2s.  However, the additional diff adds an overhead to all manifestmerge calls,
especially for flat manifests. When rebasing a commit from default~1 to default
it appears to add 100ms in mozilla-central. While we could put this optimization
behind a flag, I think the fact that it makes merge O(number of changes being
applied) instead of O(number of changes between X and Y) justifies it.

--- a/mercurial/merge.py	Tue May 02 23:47:10 2017 -0700
+++ b/mercurial/merge.py	Wed May 03 10:43:59 2017 -0700
@@ -786,7 +786,7 @@
     return True
 
 def manifestmerge(repo, wctx, p2, pa, branchmerge, force, matcher,
-                  acceptremote, followcopies):
+                  acceptremote, followcopies, forcefulldiff=False):
     """
     Merge wctx and p2 with ancestor pa and generate merge action list
 
@@ -821,6 +821,26 @@
         if any(wctx.sub(s).dirty() for s in wctx.substate):
             m1['.hgsubstate'] = modifiednodeid
 
+    # Don't use m2-vs-ma optimization if:
+    # - ma is the same as m1 or m2, which we're just going to diff again later
+    # - The matcher is set already, so we can't override it
+    # - The caller specifically asks for a full diff, which is useful during bid
+    #   merge.
+    if (pa not in ([wctx, p2] + wctx.parents()) and
+        matcher is None and not forcefulldiff):
+        # Identify which files are relevant to the merge, so we can limit the
+        # total m1-vs-m2 diff to just those files. This has significant
+        # performance benefits in large repositories.
+        relevantfiles = set(ma.diff(m2).keys())
+
+        # For copied and moved files, we need to add the source file too.
+        for copykey, copyvalue in copy.iteritems():
+            if copyvalue in relevantfiles:
+                relevantfiles.add(copykey)
+        for movedirkey in movewithdir.iterkeys():
+            relevantfiles.add(movedirkey)
+        matcher = scmutil.matchfiles(repo, relevantfiles)
+
     diff = m1.diff(m2, match=matcher)
 
     if matcher is None:
@@ -974,7 +994,7 @@
             repo.ui.note(_('\ncalculating bids for ancestor %s\n') % ancestor)
             actions, diverge1, renamedelete1 = manifestmerge(
                 repo, wctx, mctx, ancestor, branchmerge, force, matcher,
-                acceptremote, followcopies)
+                acceptremote, followcopies, forcefulldiff=True)
             _checkunknownfiles(repo, wctx, mctx, force, actions, mergeforce)
 
             # Track the shortest set of warning on the theory that bid