# HG changeset patch
# User Durham Goode <durham@fb.com>
# Date 1481828418 28800
# Node ID be520fe3a3e95edb4a8db75d424ed067cb5bf706
# Parent  99bd5479d58b03cf8474cdc0770c18108cef1d5b
changelog: keep track of file end in appender (issue5444)

Previously, changelog.appender.end() would compute the end of the file by
joining all the current appended data and checking the length. This is an O(n)
operation.  e240e914d226 introduced a seek call before every revlog write, which
means we are hitting this O(n) behavior n times, which causes changelog writes
during a pull to be n^2.

In our large repo, this caused pulling 100k commits to go from 17s to 130s. With
this fix, it's back to 17s.

diff -r 99bd5479d58b -r be520fe3a3e9 mercurial/changelog.py
--- a/mercurial/changelog.py	Thu Dec 15 11:14:00 2016 -0500
+++ b/mercurial/changelog.py	Thu Dec 15 11:00:18 2016 -0800
@@ -79,9 +79,10 @@
         self.fp = fp
         self.offset = fp.tell()
         self.size = vfs.fstat(fp).st_size
+        self._end = self.size
 
     def end(self):
-        return self.size + len("".join(self.data))
+        return self._end
     def tell(self):
         return self.offset
     def flush(self):
@@ -121,6 +122,7 @@
     def write(self, s):
         self.data.append(str(s))
         self.offset += len(s)
+        self._end += len(s)
 
 def _divertopener(opener, target):
     """build an opener that writes in 'target.a' instead of 'target'"""