From d63bd02ca7ef26190d073896fe063c497ef60d85 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Tue, 24 Nov 2020 00:35:51 +0000 Subject: [PATCH] gcf2: workaround libgit2 alternates bug for extindex While libgit2 handles alternates with relative paths properly for v2 epochs; nesting them another layer with extindex uses the wrong relative path expansion (and is inconsistent with git(1) behavior). Fortunately, it's possible to work around this libgit2 bug entirely within Gcf2 and avoid further special cases throughout the rest of our code to support extindex. Link: https://bugs.debian.org/975607 --- lib/PublicInbox/Gcf2.pm | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/lib/PublicInbox/Gcf2.pm b/lib/PublicInbox/Gcf2.pm index 7983c841..041dffe7 100644 --- a/lib/PublicInbox/Gcf2.pm +++ b/lib/PublicInbox/Gcf2.pm @@ -56,17 +56,37 @@ undef $c_src; undef %CFG; undef $lockfh; +sub add_alt ($$) { + my ($gcf2, $objdir) = @_; + + # libgit2 (tested 0.27.7+dfsg.1-0.2 and 0.28.3+dfsg.1-1~bpo10+1 + # in Debian) doesn't handle relative epochs properly when nested + # multiple levels. Add all the absolute paths to workaround it, + # since $EXTINDEX_DIR/ALL.git/objects/info/alternates uses absolute + # paths to reference $V2INBOX_DIR/all.git/objects and + # $V2INBOX_DIR/all.git/objects/info/alternates uses relative paths + # to refer to $V2INBOX_DIR/git/$EPOCH.git/objects + # + # See https://bugs.debian.org/975607 + if (open(my $fh, '<', "$objdir/info/alternates")) { + chomp(my @abs_alt = grep(m!^/!, <$fh>)); + $gcf2->add_alternate($_) for @abs_alt; + } + $gcf2->add_alternate($objdir); +} + # Usage: $^X -MPublicInbox::Gcf2 -e 'PublicInbox::Gcf2::loop()' # (see lib/PublicInbox/Gcf2Client.pm) sub loop { my $gcf2 = new(); + my %seen; STDERR->autoflush(1); STDOUT->autoflush(1); while () { chomp; my ($oid, $git_dir) = split(/ /, $_, 2); - $gcf2->add_alternate("$git_dir/objects"); + $seen{$git_dir}++ or add_alt($gcf2, "$git_dir/objects"); if (!$gcf2->cat_oid(1, $oid)) { # retry once if missing. We only get unabbreviated OIDs # from SQLite or Xapian DBs, here, so malicious clients @@ -74,7 +94,8 @@ sub loop { warn "I: $$ $oid missing, retrying in $git_dir\n"; $gcf2 = new(); - $gcf2->add_alternate("$git_dir/objects"); + %seen = ($git_dir => 1); + add_alt($gcf2, "$git_dir/objects"); if ($gcf2->cat_oid(1, $oid)) { warn "I: $$ $oid found after retry\n"; -- 2.44.0