user/dev discussion of public-inbox itself
 help / color / Atom feed
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 1/4] nntp: rework and simplify art_lookup response
Date: Thu, 27 Jun 2019 22:51:45 +0000
Message-ID: <20190627225148.9657-2-e@80x24.org> (raw)
In-Reply-To: <20190627225148.9657-1-e@80x24.org>

We don't need some of the array elements returned from
art_lookup, anymore (and haven't used them in years).

We can also shorten the lifetime of the Email::Simple object by
relying on the fact Email::Simple->new will modify it's arg if
given a SCALARREF and allow us to avoid Email::Simple::body
calls.

Unfortunately, this doesn't seem to provide any noticeable
improvement in memory usage when dealing with a 30+ MB test
message, since our previous use of ->body_set('') was saving
some memory, but forcing a LF-only body to be CRLF was making
Perl allocate extra space for s///sg.
---
 lib/PublicInbox/NNTP.pm | 47 +++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 25 deletions(-)

diff --git a/lib/PublicInbox/NNTP.pm b/lib/PublicInbox/NNTP.pm
index 53e18281..30d3dab6 100644
--- a/lib/PublicInbox/NNTP.pm
+++ b/lib/PublicInbox/NNTP.pm
@@ -510,24 +510,21 @@ find_mid:
 found:
 	my $smsg = $ng->over->get_art($n) or return $err;
 	my $msg = $ng->msg_by_smsg($smsg) or return $err;
-	my $s = Email::Simple->new($msg);
-	if ($set_headers) {
-		set_nntp_headers($self, $s->header_obj, $ng, $n, $mid);
 
-		# must be last
-		$s->body_set('') if ($set_headers == 2);
-	}
-	[ $n, $mid, $s, $smsg->bytes, $smsg->lines, $ng ];
+	# Email::Simple->new will modify $msg in-place as documented
+	# in its manpage, so what's left is the body and we won't need
+	# to call Email::Simple::body(), later
+	my $hdr = Email::Simple->new($msg)->header_obj;
+	set_nntp_headers($self, $hdr, $ng, $n, $mid) if $set_headers;
+	[ $n, $mid, $msg, $hdr ];
 }
 
-sub simple_body_write ($$) {
-	my ($self, $s) = @_;
-	my $body = $s->body;
-	$s->body_set('');
-	$body =~ s/^\./../smg;
-	$body =~ s/(?<!\r)\n/\r\n/sg;
-	msg_more($self, $body);
-	msg_more($self, "\r\n") unless $body =~ /\r\n\z/s;
+sub msg_body_write ($$) {
+	my ($self, $msg) = @_;
+	$$msg =~ s/^\./../smg;
+	$$msg =~ s/(?<!\r)\n/\r\n/sg;
+	msg_more($self, $$msg);
+	msg_more($self, "\r\n") unless $$msg =~ /\r\n\z/s;
 	'.'
 }
 
@@ -537,7 +534,7 @@ sub set_art {
 }
 
 sub _header ($) {
-	my $hdr = $_[0]->header_obj->as_string;
+	my $hdr = $_[0]->as_string;
 	utf8::encode($hdr);
 	$hdr =~ s/(?<!\r)\n/\r\n/sg;
 
@@ -554,22 +551,22 @@ sub cmd_article ($;$) {
 	my ($self, $art) = @_;
 	my $r = art_lookup($self, $art, 1);
 	return $r unless ref $r;
-	my ($n, $mid, $s) = @$r;
+	my ($n, $mid, $msg, $hdr) = @$r;
 	set_art($self, $art);
 	more($self, "220 $n <$mid> article retrieved - head and body follow");
-	msg_more($self, _header($s));
+	msg_more($self, _header($hdr));
 	msg_more($self, "\r\n");
-	simple_body_write($self, $s);
+	msg_body_write($self, $msg);
 }
 
 sub cmd_head ($;$) {
 	my ($self, $art) = @_;
 	my $r = art_lookup($self, $art, 2);
 	return $r unless ref $r;
-	my ($n, $mid, $s) = @$r;
+	my ($n, $mid, undef, $hdr) = @$r;
 	set_art($self, $art);
 	more($self, "221 $n <$mid> article retrieved - head follows");
-	msg_more($self, _header($s));
+	msg_more($self, _header($hdr));
 	'.'
 }
 
@@ -577,17 +574,17 @@ sub cmd_body ($;$) {
 	my ($self, $art) = @_;
 	my $r = art_lookup($self, $art, 0);
 	return $r unless ref $r;
-	my ($n, $mid, $s) = @$r;
+	my ($n, $mid, $msg) = @$r;
 	set_art($self, $art);
 	more($self, "222 $n <$mid> article retrieved - body follows");
-	simple_body_write($self, $s);
+	msg_body_write($self, $msg);
 }
 
 sub cmd_stat ($;$) {
 	my ($self, $art) = @_;
 	my $r = art_lookup($self, $art, 0);
 	return $r unless ref $r;
-	my ($n, $mid, undef) = @$r;
+	my ($n, $mid) = @$r;
 	set_art($self, $art);
 	"223 $n <$mid> article retrieved - request text separately";
 }
@@ -815,7 +812,7 @@ sub hdr_mid_prefix ($$$$$) {
 }
 
 sub hdr_mid_response ($$$$$$) {
-	my ($self, $xhdr, $ng, $n, $mid, $v) = @_; # r: art_lookup result
+	my ($self, $xhdr, $ng, $n, $mid, $v) = @_;
 	my $res = '';
 	if ($xhdr) {
 		$res .= r221 . "\r\n";
-- 
EW


  reply index

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-27 22:51 [PATCH 0/4] www|nntp: optimize uses of Email::Simple Eric Wong
2019-06-27 22:51 ` Eric Wong [this message]
2019-06-27 22:51 ` [PATCH 2/4] mbox: use Email::Simple->new to do in-place modifications Eric Wong
2019-06-27 22:51 ` [PATCH 3/4] mbox: split header and body processing Eric Wong
2019-06-27 22:51 ` [PATCH 4/4] nntp: reduce syscalls for ARTICLE and BODY Eric Wong

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://public-inbox.org/README

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190627225148.9657-2-e@80x24.org \
    --to=e@80x24.org \
    --cc=meta@public-inbox.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

user/dev discussion of public-inbox itself

Archives are clonable:
	git clone --mirror https://public-inbox.org/meta
	git clone --mirror http://czquwvybam4bgbro.onion/meta
	git clone --mirror http://hjrcffqmbrq6wope.onion/meta
	git clone --mirror http://ou63pmih66umazou.onion/meta

Example config snippet for mirrors

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://ou63pmih66umazou.onion/inbox.comp.mail.public-inbox.meta
	nntp://czquwvybam4bgbro.onion/inbox.comp.mail.public-inbox.meta
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.org/gmane.mail.public-inbox.general

 note: .onion URLs require Tor: https://www.torproject.org/

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git