gitweb: Use git-for-each-ref to generate list of heads and/or tags

Add two subroutines: git_get_heads_list and git_get_refs_list, which
fill out needed parts of refs info (heads and tags respectively) info
using single call to git-for-each-ref, instead of using
git-peek-remote to get list of references and using parse_ref for each
ref to get ref info, which in turn uses at least one call of git
command.

Replace call to git_get_refs_list in git_summary by call to
git_get_references, git_get_heads_list and git_get_tags_list
(simplifying this subroutine a bit). Use git_get_heads_list in
git_heads and git_get_tags_list in git_tags. Modify git_tags_body
slightly to accept output from git_get_tags_list.

Remove no longer used, and a bit hackish, git_get_refs_list.
parse_ref is no longer used, but is left for now.

Generating "summary" and "tags" views should be much faster for
projects which have large number of tags.

CHANGES IN OUTPUT: Before, if ref in refs/tags was tag pointing to
commit we used committer epoch as epoch for ref, and used tagger epoch
as epoch only for tag pointing to object of other type. If ref in
refs/tags was commit, we used committer epoch as epoch for ref (see
parse_ref; we sorted in gitweb by 'epoch' field).

Currently we use committer epoch for refs pointing to commit objects,
and tagger epoch for refs pointing to tag object, even if tag points
to commit.

Simple ab benchmark before and after this patch for my git.git
repository (git/jnareb-git.git) with some heads and tags added
as compared to git.git repository, shows around 2.4-3.0 times speedup
for "summary" and "tags" views:

 summary   3134 +/- 24.2 ms  -->   1081 +/- 30.2 ms
 tags      2886 +/- 18.9 ms  -->   1196 +/- 15.6 ms

Signed-off-by: Jakub Narebski <jnareb@gmail.com>
Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index bf5f8299442ffe3ad8c4de6629af79667a67e5e2..7710cc2319449b065cb959ee3f41f32a3ffee7dd 100755 (executable)
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -1294,47 +1294,88 @@ sub parse_ls_tree_line ($;%) {
 ## ......................................................................
 ## parse to array of hashes functions
 
-sub git_get_refs_list {
-       my $type = shift || "";
-       my %refs;
-       my @reflist;
-
-       my @refs;
-       open my $fd, "-|", $GIT, "peek-remote", "$projectroot/$project/"
+sub git_get_heads_list {
+       my $limit = shift;
+       my @headslist;
+
+       open my $fd, '-|', git_cmd(), 'for-each-ref',
+               ($limit ? '--count='.($limit+1) : ()), '--sort=-committerdate',
+               '--format=%(objectname) %(refname) %(subject)%00%(committer)',
+               'refs/heads'
                or return;
        while (my $line = <$fd>) {
-               chomp $line;
-               if ($line =~ m/^([0-9a-fA-F]{40})\trefs\/($type\/?([^\^]+))(\^\{\})?$/) {
-                       if (defined $refs{$1}) {
-                               push @{$refs{$1}}, $2;
-                       } else {
-                               $refs{$1} = [ $2 ];
-                       }
+               my %ref_item;
 
-                       if (! $4) { # unpeeled, direct reference
-                               push @refs, { hash => $1, name => $3 }; # without type
-                       } elsif ($3 eq $refs[-1]{'name'}) {
-                               # most likely a tag is followed by its peeled
-                               # (deref) one, and when that happens we know the
-                               # previous one was of type 'tag'.
-                               $refs[-1]{'type'} = "tag";
-                       }
+               chomp $line;
+               my ($refinfo, $committerinfo) = split(/\0/, $line);
+               my ($hash, $name, $title) = split(' ', $refinfo, 3);
+               my ($committer, $epoch, $tz) =
+                       ($committerinfo =~ /^(.*) ([0-9]+) (.*)$/);
+               $name =~ s!^refs/heads/!!;
+
+               $ref_item{'name'}  = $name;
+               $ref_item{'id'}    = $hash;
+               $ref_item{'title'} = $title || '(no commit message)';
+               $ref_item{'epoch'} = $epoch;
+               if ($epoch) {
+                       $ref_item{'age'} = age_string(time - $ref_item{'epoch'});
+               } else {
+                       $ref_item{'age'} = "unknown";
                }
+
+               push @headslist, \%ref_item;
        }
        close $fd;
 
-       foreach my $ref (@refs) {
-               my $ref_file = $ref->{'name'};
-               my $ref_id   = $ref->{'hash'};
+       return wantarray ? @headslist : \@headslist;
+}
+
+sub git_get_tags_list {
+       my $limit = shift;
+       my @tagslist;
 
-               my $type = $ref->{'type'} || git_get_type($ref_id) || next;
-               my %ref_item = parse_ref($ref_file, $ref_id, $type);
+       open my $fd, '-|', git_cmd(), 'for-each-ref',
+               ($limit ? '--count='.($limit+1) : ()), '--sort=-creatordate',
+               '--format=%(objectname) %(objecttype) %(refname) '.
+               '%(*objectname) %(*objecttype) %(subject)%00%(creator)',
+               'refs/tags'
+               or return;
+       while (my $line = <$fd>) {
+               my %ref_item;
 
-               push @reflist, \%ref_item;
+               chomp $line;
+               my ($refinfo, $creatorinfo) = split(/\0/, $line);
+               my ($id, $type, $name, $refid, $reftype, $title) = split(' ', $refinfo, 6);
+               my ($creator, $epoch, $tz) =
+                       ($creatorinfo =~ /^(.*) ([0-9]+) (.*)$/);
+               $name =~ s!^refs/tags/!!;
+
+               $ref_item{'type'} = $type;
+               $ref_item{'id'} = $id;
+               $ref_item{'name'} = $name;
+               if ($type eq "tag") {
+                       $ref_item{'subject'} = $title;
+                       $ref_item{'reftype'} = $reftype;
+                       $ref_item{'refid'}   = $refid;
+               } else {
+                       $ref_item{'reftype'} = $type;
+                       $ref_item{'refid'}   = $id;
+               }
+
+               if ($type eq "tag" || $type eq "commit") {
+                       $ref_item{'epoch'} = $epoch;
+                       if ($epoch) {
+                               $ref_item{'age'} = age_string(time - $ref_item{'epoch'});
+                       } else {
+                               $ref_item{'age'} = "unknown";
+                       }
+               }
+
+               push @tagslist, \%ref_item;
        }
-       # sort refs by age
-       @reflist = sort {$b->{'epoch'} <=> $a->{'epoch'}} @reflist;
-       return (\@reflist, \%refs);
+       close $fd;
+
+       return wantarray ? @tagslist : \@tagslist;
 }
 
 ## ----------------------------------------------------------------------
@@ -2264,8 +2305,7 @@ sub git_tags_body {
        for (my $i = $from; $i <= $to; $i++) {
                my $entry = $taglist->[$i];
                my %tag = %$entry;
-               my $comment_lines = $tag{'comment'};
-               my $comment = shift @$comment_lines;
+               my $comment = $tag{'subject'};
                my $comment_short;
                if (defined $comment) {
                        $comment_short = chop_str($comment, 30, 5);
@@ -2298,7 +2338,7 @@ sub git_tags_body {
                      $cgi->a({-href => href(action=>$tag{'reftype'}, hash=>$tag{'refid'})}, $tag{'reftype'});
                if ($tag{'reftype'} eq "commit") {
                        print " | " . $cgi->a({-href => href(action=>"shortlog", hash=>$tag{'name'})}, "shortlog") .
-                             " | " . $cgi->a({-href => href(action=>"log", hash=>$tag{'refid'})}, "log");
+                             " | " . $cgi->a({-href => href(action=>"log", hash=>$tag{'name'})}, "log");
                } elsif ($tag{'reftype'} eq "blob") {
                        print " | " . $cgi->a({-href => href(action=>"blob_plain", hash=>$tag{'refid'})}, "raw");
                }
@@ -2323,23 +2363,23 @@ sub git_heads_body {
        my $alternate = 1;
        for (my $i = $from; $i <= $to; $i++) {
                my $entry = $headlist->[$i];
-               my %tag = %$entry;
-               my $curr = $tag{'id'} eq $head;
+               my %ref = %$entry;
+               my $curr = $ref{'id'} eq $head;
                if ($alternate) {
                        print "<tr class=\"dark\">\n";
                } else {
                        print "<tr class=\"light\">\n";
                }
                $alternate ^= 1;
-               print "<td><i>$tag{'age'}</i></td>\n" .
-                     ($tag{'id'} eq $head ? "<td class=\"current_head\">" : "<td>") .
-                     $cgi->a({-href => href(action=>"shortlog", hash=>$tag{'name'}),
-                              -class => "list name"},esc_html($tag{'name'})) .
+               print "<td><i>$ref{'age'}</i></td>\n" .
+                     ($curr ? "<td class=\"current_head\">" : "<td>") .
+                     $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'name'}),
+                              -class => "list name"},esc_html($ref{'name'})) .
                      "</td>\n" .
                      "<td class=\"link\">" .
-                     $cgi->a({-href => href(action=>"shortlog", hash=>$tag{'name'})}, "shortlog") . " | " .
-                     $cgi->a({-href => href(action=>"log", hash=>$tag{'name'})}, "log") . " | " .
-                     $cgi->a({-href => href(action=>"tree", hash=>$tag{'name'}, hash_base=>$tag{'name'})}, "tree") .
+                     $cgi->a({-href => href(action=>"shortlog", hash=>$ref{'name'})}, "shortlog") . " | " .
+                     $cgi->a({-href => href(action=>"log", hash=>$ref{'name'})}, "log") . " | " .
+                     $cgi->a({-href => href(action=>"tree", hash=>$ref{'name'}, hash_base=>$ref{'name'})}, "tree") .
                      "</td>\n" .
                      "</tr>";
        }
@@ -2489,18 +2529,9 @@ sub git_summary {
 
        my $owner = git_get_project_owner($project);
 
-       my ($reflist, $refs) = git_get_refs_list();
-
-       my @taglist;
-       my @headlist;
-       foreach my $ref (@$reflist) {
-               if ($ref->{'name'} =~ s!^heads/!!) {
-                       push @headlist, $ref;
-               } else {
-                       $ref->{'name'} =~ s!^tags/!!;
-                       push @taglist, $ref;
-               }
-       }
+       my $refs = git_get_references();
+       my @taglist  = git_get_tags_list(15);
+       my @headlist = git_get_heads_list(15);
 
        git_header_html();
        git_print_page_nav('summary','', $head);
@@ -2792,9 +2823,9 @@ sub git_tags {
        git_print_page_nav('','', $head,undef,$head);
        git_print_header_div('summary', $project);
 
-       my ($taglist) = git_get_refs_list("tags");
-       if (@$taglist) {
-               git_tags_body($taglist);
+       my @tagslist = git_get_tags_list();
+       if (@tagslist) {
+               git_tags_body(\@tagslist);
        }
        git_footer_html();
 }
@@ -2805,9 +2836,9 @@ sub git_heads {
        git_print_page_nav('','', $head,undef,$head);
        git_print_header_div('summary', $project);
 
-       my ($headlist) = git_get_refs_list("heads");
-       if (@$headlist) {
-               git_heads_body($headlist, $head);
+       my @headslist = git_get_heads_list();
+       if (@headslist) {
+               git_heads_body(\@headslist, $head);
        }
        git_footer_html();
 }