git-svn: avoid redundant get_log calls between invocations

Prefill .rev_db to the maximum revision we tried to fetch;
and take advantage of that so we can avoid using get_log()
on ranges we've already seen (and have deemed uninteresting).

Signed-off-by: Eric Wong <normalperson@yhbt.net>

diff --git a/git-svn.perl b/git-svn.perl
index 2206f1b250125eb9f9d27b87c505b66bb7af531b..b1d91fa471b11ef6ab2f9c005bb1efac6ea53119 100755 (executable)
--- a/git-svn.perl
+++ b/git-svn.perl
@@ -655,18 +655,14 @@ sub fetch_all {
        my $ra = Git::SVN::Ra->new($url);
        my $head = $ra->get_latest_revnum;
        my $base = $head;
-       my $new_remote;
        foreach my $p (sort keys %$fetch) {
                my $gs = Git::SVN->new($fetch->{$p}, $repo_id, $p);
-               my $lr = $gs->last_rev;
+               my $lr = $gs->rev_db_max;
                if (defined $lr) {
                        $base = $lr if ($lr < $base);
-               } else {
-                       $new_remote = 1;
                }
                push @gs, $gs;
        }
-       $base = 0 if $new_remote;
        return if (++$base > $head);
        $ra->gs_fetch_loop_common($base, $head, @gs);
 }
@@ -899,13 +895,17 @@ sub last_rev_commit {
        $rl = readline $fh;
        defined $rl or return (undef, undef);
        chomp $rl;
-       while ($c ne $rl && tell $fh != 0) {
+       while (('0' x40) eq $rl && tell $fh != 0) {
                $offset -= 41;
                seek $fh, $offset, 2;
                $rl = readline $fh;
                defined $rl or return (undef, undef);
                chomp $rl;
        }
+       if ($c) {
+               die "$self->{db_path} and ", $self->refname,
+                   " inconsistent!:\n$c != $rl\n";
+       }
        my $rev = tell $fh;
        croak $! if ($rev < 0);
        $rev =  ($rev - 41) / 41;
@@ -917,7 +917,7 @@ sub last_rev_commit {
 sub get_fetch_range {
        my ($self, $min, $max) = @_;
        $max ||= $self->ra->get_latest_revnum;
-       $min ||= $self->last_rev || 0;
+       $min ||= $self->rev_db_max;
        (++$min, $max);
 }
 
@@ -1404,6 +1404,16 @@ sub rev_db_set {
        }
 }
 
+sub rev_db_max {
+       my ($self) = @_;
+       my @stat = stat $self->{db_path} or
+                       die "Couldn't stat $self->{db_path}: $!\n";
+       ($stat[7] % 41) == 0 or
+                       die "$self->{db_path} inconsistent size:$stat[7]\n";
+       my $max = $stat[7] / 41;
+       (($max > 0) ? $max - 1 : 0);
+}
+
 sub rev_db_get {
        my ($self, $rev) = @_;
        my $ret;
@@ -2404,6 +2414,12 @@ sub gs_fetch_loop_common {
                                }
                        }
                }
+               # pre-fill the .rev_db since it'll eventually get filled in
+               # with '0' x40 if something new gets committed
+               foreach my $gs (@gs) {
+                       next if defined $gs->rev_db_get($max);
+                       $gs->rev_db_set($max, 0 x40);
+               }
                last if $max >= $head;
                $min = $max + 1;
                $max += $inc;