[PATCH 5/6] qspawn: allow configurable limiters

[Eric Wong <e@80x24.org>]

And bump the default limit to 32 so we match git-daemon
behavior.  This shall allow us to configure different levels
of concurrency for different repositories and prevent clones
of giant repos from stalling service to small repos.
---
 lib/PublicInbox/GitHTTPBackend.pm |  6 +++++-
 lib/PublicInbox/Qspawn.pm         | 38 ++++++++++++++++++++++++++++----------
 t/qspawn.t                        | 10 ++++++----
 3 files changed, 39 insertions(+), 15 deletions(-)

diff --git a/lib/PublicInbox/GitHTTPBackend.pm b/lib/PublicInbox/GitHTTPBackend.pm
index ebb0850..ed8fdf0 100644
--- a/lib/PublicInbox/GitHTTPBackend.pm
+++ b/lib/PublicInbox/GitHTTPBackend.pm
@@ -13,6 +13,9 @@ use HTTP::Status qw(status_message);
 use Plack::Util;
 use PublicInbox::Qspawn;
 
+# 32 is same as the git-daemon connection limit
+my $default_limiter = PublicInbox::Qspawn::Limiter->new(32);
+
 # n.b. serving "description" and "cloneurl" should be innocuous enough to
 # not cause problems.  serving "config" might...
 my @text = qw[HEAD info/refs
@@ -176,6 +179,7 @@ sub prepare_range {
 # returns undef if 403 so it falls back to dumb HTTP
 sub serve_smart {
 	my ($env, $git, $path) = @_;
+	my $limiter = $default_limiter;
 	my $in = $env->{'psgi.input'};
 	my $fd = eval { fileno($in) };
 	unless (defined $fd && $fd >= 0) {
@@ -248,7 +252,7 @@ sub serve_smart {
 		# holding the input here is a waste of FDs and memory
 		$env->{'psgi.input'} = undef;
 
-		$x->start(sub { # may run later, much later...
+		$x->start($limiter, sub { # may run later, much later...
 			($rpipe) = @_;
 			$in = undef;
 			if ($async) {
diff --git a/lib/PublicInbox/Qspawn.pm b/lib/PublicInbox/Qspawn.pm
index 9299096..cc9c340 100644
--- a/lib/PublicInbox/Qspawn.pm
+++ b/lib/PublicInbox/Qspawn.pm
@@ -1,12 +1,14 @@
 # Copyright (C) 2016 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+
+# Limits the number of processes spawned
+# This does not depend on Danga::Socket or any other external
+# scheduling mechanism, you just need to call start and finish
+# appropriately
 package PublicInbox::Qspawn;
 use strict;
 use warnings;
 use PublicInbox::Spawn qw(popen_rd);
-our $LIMIT = 1;
-my $running = 0;
-my @run_queue;
 
 sub new ($$$;) {
 	my ($class, $cmd, $env, $opt) = @_;
@@ -16,9 +18,10 @@ sub new ($$$;) {
 sub _do_spawn {
 	my ($self, $cb) = @_;
 	my $err;
+
 	($self->{rpipe}, $self->{pid}) = popen_rd(@{$self->{args}});
 	if (defined $self->{pid}) {
-		$running++;
+		$self->{limiter}->{running}++;
 	} else {
 		$self->{err} = $!;
 	}
@@ -27,26 +30,41 @@ sub _do_spawn {
 
 sub finish ($) {
 	my ($self) = @_;
+	my $limiter = $self->{limiter};
 	if (delete $self->{rpipe}) {
 		my $pid = delete $self->{pid};
 		$self->{err} = $pid == waitpid($pid, 0) ? $? :
 				"PID:$pid still running?";
-		$running--;
+		$limiter->{running}--;
 	}
-	if (my $next = shift @run_queue) {
+	if (my $next = shift @{$limiter->{run_queue}}) {
 		_do_spawn(@$next);
 	}
 	$self->{err};
 }
 
-sub start ($$) {
-	my ($self, $cb) = @_;
+sub start {
+	my ($self, $limiter, $cb) = @_;
+	$self->{limiter} = $limiter;
 
-	if ($running < $LIMIT) {
+	if ($limiter->{running} < $limiter->{limit}) {
 		_do_spawn($self, $cb);
 	} else {
-		push @run_queue, [ $self, $cb ];
+		push @{$limiter->{run_queue}}, [ $self, $cb ];
 	}
 }
 
+package PublicInbox::Qspawn::Limiter;
+use strict;
+use warnings;
+
+sub new {
+	my ($class, $limit) = @_;
+	bless {
+		limit => $limit || 1,
+		running => 0,
+		run_queue => [],
+	}, $class;
+}
+
 1;
diff --git a/t/qspawn.t b/t/qspawn.t
index 05072e2..9c42e10 100644
--- a/t/qspawn.t
+++ b/t/qspawn.t
@@ -2,10 +2,12 @@
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 use Test::More;
 use_ok 'PublicInbox::Qspawn';
+
+my $limiter = PublicInbox::Qspawn::Limiter->new(1);
 {
 	my $x = PublicInbox::Qspawn->new([qw(true)]);
 	my $run = 0;
-	$x->start(sub {
+	$x->start($limiter, sub {
 		my ($rpipe) = @_;
 		is(0, sysread($rpipe, my $buf, 1), 'read zero bytes');
 		ok(!$x->finish, 'no error on finish');
@@ -17,7 +19,7 @@ use_ok 'PublicInbox::Qspawn';
 {
 	my $x = PublicInbox::Qspawn->new([qw(false)]);
 	my $run = 0;
-	$x->start(sub {
+	$x->start($limiter, sub {
 		my ($rpipe) = @_;
 		is(0, sysread($rpipe, my $buf, 1), 'read zero bytes from false');
 		my $err = $x->finish;
@@ -30,7 +32,7 @@ use_ok 'PublicInbox::Qspawn';
 foreach my $cmd ([qw(sleep 1)], [qw(sh -c), 'sleep 1; false']) {
 	my $s = PublicInbox::Qspawn->new($cmd);
 	my @run;
-	$s->start(sub {
+	$s->start($limiter, sub {
 		my ($rpipe) = @_;
 		push @run, 'sleep';
 		is(0, sysread($rpipe, my $buf, 1), 'read zero bytes');
@@ -39,7 +41,7 @@ foreach my $cmd ([qw(sleep 1)], [qw(sh -c), 'sleep 1; false']) {
 	my @t = map {
 		my $i = $n++;
 		my $x = PublicInbox::Qspawn->new([qw(true)]);
-		$x->start(sub {
+		$x->start($limiter, sub {
 			my ($rpipe) = @_;
 			push @run, $i;
 		});
-- 
EW