# HG changeset patch
# User Durham Goode <durham@fb.com>
# Date 1494268523 25200
# Node ID 7bcc9a5ab96ef6497adc8264bda9b8edf679206e
# Parent  a2be2abe947621a655f9b89f43de4f183d04a04b
strip: make tree stripping O(changes) instead of O(repo)

The old tree stripping logic iterated over every tree revlog in the repo looking
for commits that had revs to be stripped. That's very inefficient in large
repos. Instead, let's look at what files are touched by the strip and only
inspect those revlogs.

I don't have actual perf numbers, since internally we don't use a true
treemanifest, but simply iterating over hundreds of thousands of revlogs takes
many, many seconds, so this should help tremendously when stripping only a few
commits.

diff -r a2be2abe9476 -r 7bcc9a5ab96e mercurial/repair.py
--- a/mercurial/repair.py	Mon May 08 11:35:23 2017 -0700
+++ b/mercurial/repair.py	Mon May 08 11:35:23 2017 -0700
@@ -238,11 +238,12 @@
 def striptrees(repo, tr, striprev, files):
     if 'treemanifest' in repo.requirements: # safe but unnecessary
                                             # otherwise
-        for unencoded, encoded, size in repo.store.datafiles():
-            if (unencoded.startswith('meta/') and
-                unencoded.endswith('00manifest.i')):
-                dir = unencoded[5:-12]
-                repo.manifestlog._revlog.dirlog(dir).strip(striprev, tr)
+        treerevlog = repo.manifestlog._revlog
+        for dir in util.dirs(files):
+            # If the revlog doesn't exist, this returns an empty revlog and is a
+            # no-op.
+            rl = treerevlog.dirlog(dir)
+            rl.strip(striprev, tr)
 
 def rebuildfncache(ui, repo):
     """Rebuilds the fncache file from repo history.