git-svn: Speed up fetch

We were spending a lot of time forking/execing git-cat-file and
git-hash-object. We now maintain a global Git repository object in order to use
Git.pm's more efficient hash_and_insert_object and cat_blob methods.

Signed-off-by: Adam Roben <aroben@apple.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/git-svn.perl b/git-svn.perl
index b70f8efaaa404d63c6a45486f8513348cbb368f5..33e9266fe689609034bb69da694f877ad6191672 100755 (executable)
--- a/git-svn.perl
+++ b/git-svn.perl
@@ -4,7 +4,7 @@
 use warnings;
 use strict;
 use vars qw/   $AUTHOR $VERSION
 use warnings;
 use strict;
 use vars qw/   $AUTHOR $VERSION

-               $sha1 $sha1_short $_revision
+               $sha1 $sha1_short $_revision $_repository

                $_q $_authors %users/;
 $AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
 $VERSION = '@@GIT_VERSION@@';
                $_q $_authors %users/;
 $AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
 $VERSION = '@@GIT_VERSION@@';


@@ -220,6 +220,7 @@ BEGIN
                }
                $ENV{GIT_DIR} = $git_dir;
        }
                }
                $ENV{GIT_DIR} = $git_dir;
        }

+       $_repository = Git->repository(Repository => $ENV{GIT_DIR});

 }
 
 my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd);
 }
 
 my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd);


@@ -301,6 +302,7 @@ sub do_git_init_db {
                        }
                }
                command_noisy(@init_db);
                        }
                }
                command_noisy(@init_db);

+               $_repository = Git->repository(Repository => ".git");

        }
        my $set;
        my $pfx = "svn-remote.$Git::SVN::default_repo_id";
        }
        my $set;
        my $pfx = "svn-remote.$Git::SVN::default_repo_id";


@@ -317,6 +319,7 @@ sub init_subdir {
        mkpath([$repo_path]) unless -d $repo_path;
        chdir $repo_path or die "Couldn't chdir to $repo_path: $!\n";
        $ENV{GIT_DIR} = '.git';
        mkpath([$repo_path]) unless -d $repo_path;
        chdir $repo_path or die "Couldn't chdir to $repo_path: $!\n";
        $ENV{GIT_DIR} = '.git';

+       $_repository = Git->repository(Repository => $ENV{GIT_DIR});

 }
 
 sub cmd_clone {
 }
 
 sub cmd_clone {


@@ -3017,6 +3020,7 @@ package SVN::Git::Fetcher;
 use strict;
 use warnings;
 use Carp qw/croak/;
 use strict;
 use warnings;
 use Carp qw/croak/;

+use File::Temp qw/tempfile/;

 use IO::File qw//;
 
 # file baton members: path, mode_a, mode_b, pool, fh, blob, base
 use IO::File qw//;
 
 # file baton members: path, mode_a, mode_b, pool, fh, blob, base


@@ -3172,14 +3176,9 @@ sub apply_textdelta {
        my $base = IO::File->new_tmpfile;
        $base->autoflush(1);
        if ($fb->{blob}) {
        my $base = IO::File->new_tmpfile;
        $base->autoflush(1);
        if ($fb->{blob}) {

-               defined (my $pid = fork) or croak $!;
-               if (!$pid) {
-                       open STDOUT, '>&', $base or croak $!;
-                       print STDOUT 'link ' if ($fb->{mode_a} == 120000);
-                       exec qw/git-cat-file blob/, $fb->{blob} or croak $!;
-               }
-               waitpid $pid, 0;
-               croak $? if $?;
+               print $base 'link ' if ($fb->{mode_a} == 120000);
+               my $size = $::_repository->cat_blob($fb->{blob}, $base);
+               die "Failed to read object $fb->{blob}" unless $size;

 
                if (defined $exp) {
                        seek $base, 0, 0 or croak $!;
 
                if (defined $exp) {
                        seek $base, 0, 0 or croak $!;


@@ -3220,14 +3219,18 @@ sub close_file {
                                sysseek($fh, 0, 0) or croak $!;
                        }
                }
                                sysseek($fh, 0, 0) or croak $!;
                        }
                }

-               defined(my $pid = open my $out,'-|') or die "Can't fork: $!\n";
-               if (!$pid) {
-                       open STDIN, '<&', $fh or croak $!;
-                       exec qw/git-hash-object -w --stdin/ or croak $!;
+
+               my ($tmp_fh, $tmp_filename) = File::Temp::tempfile(UNLINK => 1);
+               my $result;
+               while ($result = sysread($fh, my $string, 1024)) {
+                       syswrite($tmp_fh, $string, $result);

                }
                }

-               chomp($hash = do { local $/; <$out> });
-               close $out or croak $!;
+               defined $result or croak $!;
+               close $tmp_fh or croak $!;
+

                close $fh or croak $!;
                close $fh or croak $!;

+
+               $hash = $::_repository->hash_and_insert_object($tmp_filename);

                $hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n";
                close $fb->{base} or croak $!;
        } else {
                $hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n";
                close $fb->{base} or croak $!;
        } else {


@@ -3553,13 +3556,8 @@ sub chg_file {
        } elsif ($m->{mode_a} =~ /^120/ && $m->{mode_b} !~ /^120/) {
                $self->change_file_prop($fbat,'svn:special',undef);
        }
        } elsif ($m->{mode_a} =~ /^120/ && $m->{mode_b} !~ /^120/) {
                $self->change_file_prop($fbat,'svn:special',undef);
        }

-       defined(my $pid = fork) or croak $!;
-       if (!$pid) {
-               open STDOUT, '>&', $fh or croak $!;
-               exec qw/git-cat-file blob/, $m->{sha1_b} or croak $!;
-       }
-       waitpid $pid, 0;
-       croak $? if $?;
+       my $size = $::_repository->cat_blob($m->{sha1_b}, $fh);
+       croak "Failed to read object $m->{sha1_b}" unless $size;

        $fh->flush == 0 or croak $!;
        seek $fh, 0, 0 or croak $!;
 
        $fh->flush == 0 or croak $!;
        seek $fh, 0, 0 or croak $!;