Anonymous avatar Anonymous committed 0b19138

git-svn: Make it incrementally faster by minimizing temp files

Currently, git-svn would create a temp file on four occasions:
1. Reading a blob out of the object db
2. Creating a delta from svn
3. Hashing and writing a blob into the object db
4. Reading a blob out of the object db (in another place in code)

Any time git-svn did the above, it would dutifully create and then
delete said temp file. Unfortunately, this means that between 2-4
temporary files are created/deleted per file 'add/modify'-ed in
svn (O(n)). This causes significant overhead and helps the inode
counter to spin beautifully.

By its nature, git-svn is a serial beast. Thus, reusing a temp file
does not pose significant problems. "truncate and seek" takes much
less time than "unlink and create". This patch centralizes the
tempfile creation and holds onto the tempfile until they are deleted
on exit. This significantly reduces file overhead, now requiring
at most three (3) temp files per run (O(1)).

Signed-off-by: Marcus Griep <marcus@griep.us>;
Acked-by: Eric Wong <normalperson@yhbt.net>;

Comments (0)

Files changed (1)

 	my $arg = shift;
 	my $ref = ref $arg;
 	my $md5 = Digest::MD5->new();
-        if ($ref eq 'GLOB' || $ref eq 'IO::File') {
+        if ($ref eq 'GLOB' || $ref eq 'IO::File' || $ref eq 'File::Temp') {
 		$md5->addfile($arg) or croak $!;
 	} elsif ($ref eq 'SCALAR') {
 		$md5->add($$arg) or croak $!;
 	}
 }
 
+
 my (%LOCKFILES, %INDEX_FILES);
 END {
 	unlink keys %LOCKFILES if %LOCKFILES;
 
 sub apply_textdelta {
 	my ($self, $fb, $exp) = @_;
-	my $fh = IO::File->new_tmpfile;
-	$fh->autoflush(1);
+	my $fh = Git::temp_acquire('svn_delta');
 	# $fh gets auto-closed() by SVN::TxDelta::apply(),
 	# (but $base does not,) so dup() it for reading in close_file
 	open my $dup, '<&', $fh or croak $!;
-	my $base = IO::File->new_tmpfile;
-	$base->autoflush(1);
+	my $base = Git::temp_acquire('git_blob');
 	if ($fb->{blob}) {
 		print $base 'link ' if ($fb->{mode_a} == 120000);
 		my $size = $::_repository->cat_blob($fb->{blob}, $base);
 		}
 	}
 	seek $base, 0, 0 or croak $!;
-	$fb->{fh} = $dup;
+	$fb->{fh} = $fh;
 	$fb->{base} = $base;
-	[ SVN::TxDelta::apply($base, $fh, undef, $fb->{path}, $fb->{pool}) ];
+	[ SVN::TxDelta::apply($base, $dup, undef, $fb->{path}, $fb->{pool}) ];
 }
 
 sub close_file {
 			}
 		}
 
-		my ($tmp_fh, $tmp_filename) = File::Temp::tempfile(UNLINK => 1);
+		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_filename: $!\n");
+				or croak("write ",
+					$tmp_fh->filename, ": $!\n");
 		}
 		defined $result or croak $!;
-		close $tmp_fh or croak $!;
 
-		close $fh or croak $!;
 
-		$hash = $::_repository->hash_and_insert_object($tmp_filename);
-		unlink($tmp_filename);
+		Git::temp_release($fh, 1);
+
+		$hash = $::_repository->hash_and_insert_object(
+				$tmp_fh->filename);
 		$hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n";
-		close $fb->{base} or croak $!;
+
+		Git::temp_release($fb->{base}, 1);
+		Git::temp_release($tmp_fh, 1);
 	} else {
 		$hash = $fb->{blob} or die "no blob information\n";
 	}
 	} elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) {
 		$self->change_file_prop($fbat,'svn:executable',undef);
 	}
-	my $fh = IO::File->new_tmpfile or croak $!;
+	my $fh = Git::temp_acquire('git_blob');
 	if ($m->{mode_b} =~ /^120/) {
 		print $fh 'link ' or croak $!;
 		$self->change_file_prop($fbat,'svn:special','*');
 	my $atd = $self->apply_textdelta($fbat, undef, $pool);
 	my $got = SVN::TxDelta::send_stream($fh, @$atd, $pool);
 	die "Checksum mismatch\nexpected: $exp\ngot: $got\n" if ($got ne $exp);
+	Git::temp_release($fh, 1);
 	$pool->clear;
-
-	close $fh or croak $!;
 }
 
 sub D {
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.