From 2c972f3d70caf99488fff300341450e48be6ebf1 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Sat, 9 Jul 2016 03:18:35 +0000
Subject: www: add configurable limiters

Currently only for git-http-backend use, this allows limiting
the number of spawned processes per-inbox or by group, if there
are multiple large inboxes amidst a sea of small ones.

For example, a "big" repo limiter could be used for big inboxes:
which would be shared between multiple repos:

[limiter "big"]
	max = 4
[publicinbox "git"]
	address = git@vger.kernel.org
	mainrepo = /path/to/git.git
	; shared limiter with giant:
	httpbackendmax = big
[publicinbox "giant"]
	address = giant@project.org
	mainrepo = /path/to/giant.git
	; shared limiter with git:
	httpbackendmax = big

; This is a tiny inbox, use the default limiter with 32 slots:
[publicinbox "meta"]
	address = meta@public-inbox.org
	mainrepo = /path/to/meta.git
---
 lib/PublicInbox/Config.pm         | 13 ++++++++++++-
 lib/PublicInbox/GitHTTPBackend.pm | 10 ++++++++--
 lib/PublicInbox/Inbox.pm          | 25 ++++++++++++++++++++++++-
 lib/PublicInbox/Qspawn.pm         |  7 ++++---
 4 files changed, 48 insertions(+), 7 deletions(-)

(limited to 'lib')

diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm
index d34d11ad..d7eaa3e8 100644
--- a/lib/PublicInbox/Config.pm
+++ b/lib/PublicInbox/Config.pm
@@ -20,6 +20,7 @@ sub new {
 	$self->{-by_addr} ||= {};
 	$self->{-by_name} ||= {};
 	$self->{-by_newsgroup} ||= {};
+	$self->{-limiters} ||= {};
 	$self;
 }
 
@@ -85,6 +86,15 @@ sub lookup_newsgroup {
 	undef;
 }
 
+sub limiter {
+	my ($self, $name) = @_;
+	$self->{-limiters}->{$name} ||= do {
+		require PublicInbox::Qspawn;
+		my $key = "limiter.$name.max";
+		PublicInbox::Qspawn::Limiter->new($self->{$key});
+	};
+}
+
 sub get {
 	my ($self, $inbox, $key) = @_;
 
@@ -131,7 +141,7 @@ sub _fill {
 	my $rv = {};
 
 	foreach my $k (qw(mainrepo address filter url newsgroup
-			watch watchheader)) {
+			watch watchheader httpbackendmax)) {
 		my $v = $self->{"$pfx.$k"};
 		$rv->{$k} = $v if defined $v;
 	}
@@ -139,6 +149,7 @@ sub _fill {
 	my $name = $pfx;
 	$name =~ s/\Apublicinbox\.//;
 	$rv->{name} = $name;
+	$rv->{-pi_config} = $self;
 	$rv = PublicInbox::Inbox->new($rv);
 	my $v = $rv->{address};
 	if (ref($v) eq 'ARRAY') {
diff --git a/lib/PublicInbox/GitHTTPBackend.pm b/lib/PublicInbox/GitHTTPBackend.pm
index ed8fdf00..d4914795 100644
--- a/lib/PublicInbox/GitHTTPBackend.pm
+++ b/lib/PublicInbox/GitHTTPBackend.pm
@@ -179,7 +179,6 @@ sub prepare_range {
 # returns undef if 403 so it falls back to dumb HTTP
 sub serve_smart {
 	my ($env, $git, $path) = @_;
-	my $limiter = $default_limiter;
 	my $in = $env->{'psgi.input'};
 	my $fd = eval { fileno($in) };
 	unless (defined $fd && $fd >= 0) {
@@ -197,7 +196,14 @@ sub serve_smart {
 		my $val = $env->{$name};
 		$env{$name} = $val if defined $val;
 	}
-	my $git_dir = ref $git ? $git->{git_dir} : $git;
+	my ($git_dir, $limiter);
+	if (ref $git) {
+		$limiter = $git->{-httpbackend_limiter} || $default_limiter;
+		$git_dir = $git->{git_dir};
+	} else {
+		$limiter = $default_limiter;
+		$git_dir = $git;
+	}
 	$env{GIT_HTTP_EXPORT_ALL} = '1';
 	$env{PATH_TRANSLATED} = "$git_dir/$path";
 	my %rdr = ( 0 => fileno($in) );
diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index dc9980b7..23b77213 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -34,6 +34,7 @@ sub new {
 	my $v = $opts->{address} ||= 'public-inbox@example.com';
 	my $p = $opts->{-primary_address} = ref($v) eq 'ARRAY' ? $v->[0] : $v;
 	$opts->{domain} = ($p =~ /\@(\S+)\z/) ? $1 : 'localhost';
+	weaken($opts->{-pi_config});
 	bless $opts, $class;
 }
 
@@ -44,11 +45,33 @@ sub _weaken_fields {
 	}
 }
 
+sub _set_limiter ($$$) {
+	my ($self, $git, $pfx) = @_;
+	my $lkey = "-${pfx}_limiter";
+	$git->{$lkey} = $self->{$lkey} ||= eval {
+		my $mkey = $pfx.'max';
+		my $val = $self->{$mkey} or return;
+		my $lim;
+		if ($val =~ /\A\d+\z/) {
+			require PublicInbox::Qspawn;
+			$lim = PublicInbox::Qspawn::Limiter->new($val);
+		} elsif ($val =~ /\A[a-z][a-z0-9]*\z/) {
+			$lim = $self->{-pi_config}->limiter($val);
+			warn "$mkey limiter=$val not found\n" if !$lim;
+		} else {
+			warn "$mkey limiter=$val not understood\n";
+		}
+		$lim;
+	}
+}
+
 sub git {
 	my ($self) = @_;
 	$self->{git} ||= eval {
 		_weaken_later($self);
-		PublicInbox::Git->new($self->{mainrepo});
+		my $g = PublicInbox::Git->new($self->{mainrepo});
+		_set_limiter($self, $g, 'httpbackend');
+		$g;
 	};
 }
 
diff --git a/lib/PublicInbox/Qspawn.pm b/lib/PublicInbox/Qspawn.pm
index cc9c340d..697c55a1 100644
--- a/lib/PublicInbox/Qspawn.pm
+++ b/lib/PublicInbox/Qspawn.pm
@@ -47,7 +47,7 @@ sub start {
 	my ($self, $limiter, $cb) = @_;
 	$self->{limiter} = $limiter;
 
-	if ($limiter->{running} < $limiter->{limit}) {
+	if ($limiter->{running} < $limiter->{max}) {
 		_do_spawn($self, $cb);
 	} else {
 		push @{$limiter->{run_queue}}, [ $self, $cb ];
@@ -59,9 +59,10 @@ use strict;
 use warnings;
 
 sub new {
-	my ($class, $limit) = @_;
+	my ($class, $max) = @_;
 	bless {
-		limit => $limit || 1,
+		# 32 is same as the git-daemon connection limit
+		max => $max || 32,
 		running => 0,
 		run_queue => [],
 	}, $class;
-- 
cgit v1.2.3-24-ge0c7