[PATCH 2/2] www: discard multipart parent on iteration

[Eric Wong <e@yhbt.net>]

We're often iterating through messages while writing to another
buffer in our WWW interface, causing memory usage to multiply.
Since we know we won't need to keep the MIME object around in
some cases, and can tell msg_iter to clobber the on-stack
variable while it operates on subparts of multipart messages.

With xt/mem-msgview.t switched to multipart from the previous
commit, this shows a 13 MB memory reduction on that test.
---
 lib/PublicInbox/MsgIter.pm       | 5 +++--
 lib/PublicInbox/SolverGit.pm     | 5 ++---
 lib/PublicInbox/View.pm          | 6 +++---
 lib/PublicInbox/WwwAtomStream.pm | 4 ++--
 lib/PublicInbox/WwwAttach.pm     | 2 +-
 5 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/lib/PublicInbox/MsgIter.pm b/lib/PublicInbox/MsgIter.pm
index cdd78b39..f238954b 100644
--- a/lib/PublicInbox/MsgIter.pm
+++ b/lib/PublicInbox/MsgIter.pm
@@ -12,10 +12,11 @@ use PublicInbox::MIME;
 # Like Email::MIME::walk_parts, but this is:
 # * non-recursive
 # * passes depth and indices to the iterator callback
-sub msg_iter ($$;$) {
-	my ($mime, $cb, $cb_arg) = @_;
+sub msg_iter ($$;$$) {
+	my ($mime, $cb, $cb_arg, $do_undef) = @_;
 	my @parts = $mime->subparts;
 	if (@parts) {
+		$mime = $_[0] = undef if $do_undef; # saves some memory
 		my $i = 0;
 		@parts = map { [ $_, 1, ++$i ] } @parts;
 		while (my $p = shift @parts) {
diff --git a/lib/PublicInbox/SolverGit.pm b/lib/PublicInbox/SolverGit.pm
index 8629f0da..b48e8ac4 100644
--- a/lib/PublicInbox/SolverGit.pm
+++ b/lib/PublicInbox/SolverGit.pm
@@ -233,9 +233,8 @@ sub find_extract_diffs ($$$) {
 	my $diffs = [];
 	foreach my $smsg (@$msgs) {
 		$ibx->smsg_mime($smsg) or next;
-		my $mime = delete $smsg->{mime};
-		msg_iter($mime, \&extract_diff,
-				[$self, $diffs, $pre, $post, $ibx, $smsg]);
+		msg_iter(delete $smsg->{mime}, \&extract_diff,
+				[$self, $diffs, $pre, $post, $ibx, $smsg], 1);
 	}
 	@$diffs ? $diffs : undef;
 }
diff --git a/lib/PublicInbox/View.pm b/lib/PublicInbox/View.pm
index 405da2a9..d88b34da 100644
--- a/lib/PublicInbox/View.pm
+++ b/lib/PublicInbox/View.pm
@@ -275,7 +275,7 @@ sub index_entry {
 	# scan through all parts, looking for displayable text
 	$ctx->{mhref} = $mhref;
 	$ctx->{rv} = \$rv;
-	msg_iter($mime, \&add_text_body, $ctx);
+	msg_iter($mime, \&add_text_body, $ctx, 1);
 	delete $ctx->{rv};
 
 	# add the footer
@@ -506,12 +506,12 @@ sub thread_html_i { # PublicInbox::WwwStream::getline callback
 }
 
 sub multipart_text_as_html {
-	my ($mime, $mhref, $ctx) = @_;
+	my (undef, $mhref, $ctx) = @_; # $mime = $_[0]
 	$ctx->{mhref} = $mhref;
 	$ctx->{rv} = \(my $rv = '');
 
 	# scan through all parts, looking for displayable text
-	msg_iter($mime, \&add_text_body, $ctx);
+	msg_iter($_[0], \&add_text_body, $ctx, 1);
 	${delete $ctx->{rv}};
 }
 
diff --git a/lib/PublicInbox/WwwAtomStream.pm b/lib/PublicInbox/WwwAtomStream.pm
index 9430dd97..9ec1383d 100644
--- a/lib/PublicInbox/WwwAtomStream.pm
+++ b/lib/PublicInbox/WwwAtomStream.pm
@@ -101,9 +101,9 @@ sub atom_header {
 sub feed_entry {
 	my ($self, $smsg) = @_;
 	my $ctx = $self->{ctx};
-	my $mime = $smsg->{mime};
+	my $mid = $smsg->mid; # may extract Message-ID from {mime}
+	my $mime = delete $smsg->{mime};
 	my $hdr = $mime->header_obj;
-	my $mid = $smsg->mid;
 	my $irt = PublicInbox::View::in_reply_to($hdr);
 	my $uuid = to_uuid($mid);
 	my $base = $ctx->{feed_base_url};
diff --git a/lib/PublicInbox/WwwAttach.pm b/lib/PublicInbox/WwwAttach.pm
index cda1c6c8..92f47e49 100644
--- a/lib/PublicInbox/WwwAttach.pm
+++ b/lib/PublicInbox/WwwAttach.pm
@@ -40,7 +40,7 @@ sub get_attach ($$$) {
 	my $mime = $ctx->{-inbox}->msg_by_mid($ctx->{mid}) or return $res;
 	$mime = PublicInbox::MIME->new($mime);
 	$res->[3] = $idx;
-	msg_iter($mime, \&get_attach_i, $res);
+	msg_iter($mime, \&get_attach_i, $res, 1);
 	pop @$res; # cleanup before letting PSGI server see it
 	$res
 }