From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
X-Spam-Status: No, score=-3.9 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00
	shortcircuit=no autolearn=ham autolearn_force=no version=3.4.0
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id 8DD122018A
	for <meta@public-inbox.org>; Sat, 25 Jun 2016 00:45:35 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 3/4] mbox: reduce small packets for gzipped mboxes
Date: Sat, 25 Jun 2016 00:45:32 +0000
Message-Id: <20160625004533.5061-4-e@80x24.org>
In-Reply-To: <20160625004533.5061-1-e@80x24.org>
References: <20160625004533.5061-1-e@80x24.org>
List-Id: <meta@public-inbox.org>

We want to avoid sending 10 or 20-byte gzip headers as
separate TCP packets to reduce syscalls and avoid wasting
bandwidth.
---
 lib/PublicInbox/Mbox.pm | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 63ec605..1c97f95 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -110,7 +110,7 @@ use warnings;
 
 sub new {
 	my ($class, $ctx, $cb) = @_;
-	my $buf;
+	my $buf = '';
 	bless {
 		buf => \$buf,
 		gz => IO::Compress::Gzip->new(\$buf, Time => 0),
@@ -121,19 +121,11 @@ sub new {
 	}, $class;
 }
 
-sub _flush_buf {
-	my ($self) = @_;
-	my $ret = $self->{buf};
-	$ret = $$ret;
-	${$self->{buf}} = undef;
-	$ret;
-}
-
 # called by Plack::Util::foreach or similar
 sub getline {
 	my ($self) = @_;
+	my $ctx = $self->{ctx} or return;
 	my $res;
-	my $ctx = $self->{ctx};
 	my $ibx = $ctx->{-inbox};
 	my $gz = $self->{gz};
 	do {
@@ -141,8 +133,12 @@ sub getline {
 			my $msg = eval { $ibx->msg_by_mid($smsg->mid) } or next;
 			$msg = Email::Simple->new($msg);
 			$gz->write(PublicInbox::Mbox::msg_str($ctx, $msg));
-			my $ret = _flush_buf($self);
-			return $ret if $ret;
+			my $bref = $self->{buf};
+			if (length($$bref) >= 8192) {
+				my $ret = $$bref; # copy :<
+				${$self->{buf}} = '';
+				return $ret;
+			}
 		}
 		$res = $self->{cb}->($self->{opts});
 		$self->{msgs} = $res->{msgs};
@@ -150,7 +146,8 @@ sub getline {
 		$self->{opts}->{offset} += $res;
 	} while ($res);
 	$gz->close;
-	_flush_buf($self);
+	delete $self->{ctx};
+	${delete $self->{buf}};
 }
 
 sub close {} # noop