diff options
author | Eric Wong <e@80x24.org> | 2019-06-27 17:31:30 +0000 |
---|---|---|
committer | Eric Wong <e@80x24.org> | 2019-06-27 22:36:24 +0000 |
commit | ea71a5606c633f82975e8208a6c552053f7f5af8 (patch) | |
tree | 4f6fc0bb3417d6b97c948469e1e3ab6599ceb3ac /lib/PublicInbox/NNTP.pm | |
parent | 71ea9961786fa14ea0a67200847bac5a76abf751 (diff) | |
download | public-inbox-ea71a5606c633f82975e8208a6c552053f7f5af8.tar.gz |
Chances are we already have extra buffer space following the expensive LF => CRLF conversion that we can safely append an extra CRLF in those places without incurring a copy of the full string buffer. While we're at it, document where our pain points are in terms of memory usage, since tracking/controlling memory use isn't exactly obvious in high-level languages. Perhaps we should start storing messages in git as CRLF...
Diffstat (limited to 'lib/PublicInbox/NNTP.pm')
-rw-r--r-- | lib/PublicInbox/NNTP.pm | 22 |
1 files changed, 12 insertions, 10 deletions
diff --git a/lib/PublicInbox/NNTP.pm b/lib/PublicInbox/NNTP.pm index 30d3dab6..5a886a3c 100644 --- a/lib/PublicInbox/NNTP.pm +++ b/lib/PublicInbox/NNTP.pm @@ -521,10 +521,12 @@ found: sub msg_body_write ($$) { my ($self, $msg) = @_; + + # these can momentarily double the memory consumption :< $$msg =~ s/^\./../smg; - $$msg =~ s/(?<!\r)\n/\r\n/sg; + $$msg =~ s/(?<!\r)\n/\r\n/sg; # Alpine barfs without this + $$msg .= "\r\n" unless $$msg =~ /\r\n\z/s; msg_more($self, $$msg); - msg_more($self, "\r\n") unless $$msg =~ /\r\n\z/s; '.' } @@ -533,18 +535,19 @@ sub set_art { $self->{article} = $art if defined $art && $art =~ /\A[0-9]+\z/; } -sub _header ($) { - my $hdr = $_[0]->as_string; +sub msg_hdr_write ($$$) { + my ($self, $hdr, $body_follows) = @_; + $hdr = $hdr->as_string; utf8::encode($hdr); - $hdr =~ s/(?<!\r)\n/\r\n/sg; + $hdr =~ s/(?<!\r)\n/\r\n/sg; # Alpine barfs without this # for leafnode compatibility, we need to ensure Message-ID headers # are only a single line. We can't subclass Email::Simple::Header # and override _default_fold_at in here, either; since that won't # affect messages already in the archive. $hdr =~ s/^(Message-ID:)[ \t]*\r\n[ \t]+([^\r]+)\r\n/$1 $2\r\n/igsm; - - $hdr + $hdr .= "\r\n" if $body_follows; + msg_more($self, $hdr); } sub cmd_article ($;$) { @@ -554,8 +557,7 @@ sub cmd_article ($;$) { my ($n, $mid, $msg, $hdr) = @$r; set_art($self, $art); more($self, "220 $n <$mid> article retrieved - head and body follow"); - msg_more($self, _header($hdr)); - msg_more($self, "\r\n"); + msg_hdr_write($self, $hdr, 1); msg_body_write($self, $msg); } @@ -566,7 +568,7 @@ sub cmd_head ($;$) { my ($n, $mid, undef, $hdr) = @$r; set_art($self, $art); more($self, "221 $n <$mid> article retrieved - head follows"); - msg_more($self, _header($hdr)); + msg_hdr_write($self, $hdr, 0); '.' } |