From patchwork Wed Oct  3 19:10:49 2018
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Subject: [6, of, 8,
 V3] context: floor adjustlinkrev graph walk during copy tracing
From: Boris Feld <boris.feld@octobus.net>
X-Patchwork-Id: 35421
Message-Id: <fd0da35824d09d0a0fa6.1538593849@localhost.localdomain>
To: mercurial-devel@mercurial-scm.org
Cc: gregory.szorc@gmail.com
Date: Wed, 03 Oct 2018 21:10:49 +0200

# HG changeset patch
# User Boris Feld <boris.feld@octobus.net>
# Date 1536255188 14400
#      Thu Sep 06 13:33:08 2018 -0400
# Node ID fd0da35824d09d0a0fa66a23627dd24209c6c3b1
# Parent  964fbe39ab182eb0d65830dc87ef39d0382a41fa
# EXP-Topic copy-perf
# Available At https://bitbucket.org/octobus/mercurial-devel/
#              hg pull https://bitbucket.org/octobus/mercurial-devel/ -r fd0da35824d0
context: floor adjustlinkrev graph walk during copy tracing

The `_adjustlinkrev` method gains an optional "stoprev" argument. The linkrev
adjustment will give up once this floor is reached. The relevant functions
using `_adjustlinkrev` are updated to pass an appropriate value in the copy
tracing code.

In some private repository, about 10% of the status call triggered
pathological case addressed by this change. The speedup varies from one call
to another, the best-observed win is moving from 170s to 11s.

diff --git a/mercurial/context.py b/mercurial/context.py
--- a/mercurial/context.py
+++ b/mercurial/context.py
@@ -569,7 +569,7 @@ class basefilectx(object):
     def _changeid(self):
         return self._findchangerev()
 
-    def _findchangerev(self):
+    def _findchangerev(self, stoprev=None):
         if r'_changeid' in self.__dict__:
             changeid = self._changeid
         elif r'_changectx' in self.__dict__:
@@ -577,10 +577,11 @@ class basefilectx(object):
         elif r'_descendantrev' in self.__dict__:
             # this file context was created from a revision with a known
             # descendant, we can (lazily) correct for linkrev aliases
-            changeid = self._adjustlinkrev(self._descendantrev)
+            changeid = self._adjustlinkrev(self._descendantrev, stoprev=stoprev)
         else:
             changeid = self._filelog.linkrev(self._filerev)
-        self._changeid = changeid
+        if changeid is not None:
+            self._changeid = changeid
         return changeid
 
     @propertycache
@@ -724,7 +725,7 @@ class basefilectx(object):
 
         return True
 
-    def _adjustlinkrev(self, srcrev, inclusive=False):
+    def _adjustlinkrev(self, srcrev, inclusive=False, stoprev=None):
         """return the first ancestor of <srcrev> introducing <fnode>
 
         If the linkrev of the file revision does not point to an ancestor of
@@ -733,6 +734,10 @@ class basefilectx(object):
 
         :srcrev: the changeset revision we search ancestors from
         :inclusive: if true, the src revision will also be checked
+        :stoprev: an optional revision to stop the walk at. If no introduction
+                  of this file content could be found before this floor
+                  revision, the function will returns "None" and stops its
+                  iteration.
         """
         repo = self._repo
         cl = repo.unfiltered().changelog
@@ -758,6 +763,8 @@ class basefilectx(object):
             fnode = self._filenode
             path = self._path
             for a in iteranc:
+                if stoprev is not None and a < stoprev:
+                    return None
                 ac = cl.read(a) # get changeset data (we avoid object creation)
                 if path in ac[3]: # checking the 'files' field.
                     # The file has been touched, check if the content is
@@ -773,8 +780,12 @@ class basefilectx(object):
     def isintroducedafter(self, changelogrev):
         """True if a filectx have been introduced after a given floor revision
         """
-        return (changelogrev <= self.linkrev()
-                or changelogrev <= self._introrev())
+        if changelogrev <= self.linkrev():
+            return True
+        introrev = self._introrev(stoprev=changelogrev)
+        if introrev is None:
+            return False
+        return changelogrev <= introrev
 
     def _lazyrevavailable(self):
         """return True if self.rev() is available without computation,
@@ -804,7 +815,15 @@ class basefilectx(object):
         """
         return self._introrev()
 
-    def _introrev(self):
+    def _introrev(self, stoprev=None):
+        """
+        Same as `introrev` but, with an extra argument to limit changelog
+        iteration range in some internal usecase.
+
+        If `stoprev` is set, the `introrev` will not be searched past that
+        `stoprev` revision and "None" might be returned. This is useful to
+        limit iteration range.
+        """
         lkr = self.linkrev()
         attrs = vars(self)
         lazyavailable = self._lazyrevavailable()
@@ -813,9 +832,10 @@ class basefilectx(object):
             if rev == lkr:
                 return rev
             else:
-                return self._adjustlinkrev(rev, inclusive=True)
+                return self._adjustlinkrev(rev, inclusive=True,
+                                           stoprev=stoprev)
         else:
-            return self._findchangerev()
+            return self._findchangerev(stoprev=stoprev)
 
     def introfilectx(self):
         """Return filectx having identical contents, but pointing to the