git-svn: Reduce temp file usage when dealing with non-links
authorMarcus Griep <marcus@griep.us>
Tue, 12 Aug 2008 16:45:39 +0000 (12:45 -0400)
committerEric Wong <normalperson@yhbt.net>
Wed, 13 Aug 2008 03:46:54 +0000 (20:46 -0700)
Currently, in sub 'close_file', git-svn creates a temporary file and
copies the contents of the blob to be written into it. This is useful
for symlinks because svn stores symlinks in the form:

link $FILE_PATH

Git creates a blob only out of '$FILE_PATH' and uses file mode to
indicate that the blob should be interpreted as a symlink.

As git-hash-object is invoked with --stdin-paths, a duplicate of the
link from svn must be created that leaves off the first five bytes,
i.e. 'link '. However, this is wholly unnecessary for normal blobs,
though, as we already have a temp file with their contents. Copying
the entire file gains nothing, and effectively requires a file to be
written twice before making it into the object db.

This patch corrects that issue, holding onto the substr-like
duplication for symlinks, but skipping it altogether for normal blobs
by reusing the existing temp file.

Signed-off-by: Marcus Griep <marcus@griep.us>
Acked-by: Eric Wong <normalperson@yhbt.net>
git-svn.perl
index 9eae5e8d8984a6b11d24c57d037db3226a2e3874..099fd02b3fcf10b230e8397e695b3b8af8301d5a 100755 (executable)
@@ -3268,38 +3268,36 @@ sub close_file {
                                    "expected: $exp\n    got: $got\n";
                        }
                }
-               sysseek($fh, 0, 0) or croak $!;
                if ($fb->{mode_b} == 120000) {
-                       eval {
-                               sysread($fh, my $buf, 5) == 5 or croak $!;
-                               $buf eq 'link ' or die "$path has mode 120000",
-                                                      " but is not a link";
-                       };
-                       if ($@) {
-                               warn "$@\n";
-                               sysseek($fh, 0, 0) or croak $!;
-                       }
-               }
-
-               my $tmp_fh = Git::temp_acquire('svn_hash');
-               my $result;
-               while ($result = sysread($fh, my $string, 1024)) {
-                       my $wrote = syswrite($tmp_fh, $string, $result);
-                       defined($wrote) && $wrote == $result
-                               or croak("write ",
-                                       $tmp_fh->filename, ": $!\n");
-               }
-               defined $result or croak $!;
+                       sysseek($fh, 0, 0) or croak $!;
+                       sysread($fh, my $buf, 5) == 5 or croak $!;
 
+                       unless ($buf eq 'link ') {
+                               warn "$path has mode 120000",
+                                               " but is not a link\n";
+                       } else {
+                               my $tmp_fh = Git::temp_acquire('svn_hash');
+                               my $res;
+                               while ($res = sysread($fh, my $str, 1024)) {
+                                       my $out = syswrite($tmp_fh, $str, $res);
+                                       defined($out) && $out == $res
+                                               or croak("write ",
+                                                       $tmp_fh->filename,
+                                                       ": $!\n");
+                               }
+                               defined $res or croak $!;
 
-               Git::temp_release($fh, 1);
+                               ($fh, $tmp_fh) = ($tmp_fh, $fh);
+                               Git::temp_release($tmp_fh, 1);
+                       }
+               }
 
                $hash = $::_repository->hash_and_insert_object(
-                               $tmp_fh->filename);
+                               $fh->filename);
                $hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n";
 
                Git::temp_release($fb->{base}, 1);
-               Git::temp_release($tmp_fh, 1);
+               Git::temp_release($fh, 1);
        } else {
                $hash = $fb->{blob} or die "no blob information\n";
        }