X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=t%2Fcheck-www-inbox.perl;h=033b90d174dc16d4ccca8bc2a1c2ab189b2ca0af;hp=1e88e95229297b2da3de142579aa979acdce41d4;hb=4eee5af6011cc8cdefb66c9729952c7eff5c0b0b;hpb=c440c879d38e67f62bdbb74f616dc84d20899c33

diff --git a/t/check-www-inbox.perl b/t/check-www-inbox.perl
index 1e88e952..033b90d1 100644
--- a/t/check-www-inbox.perl
+++ b/t/check-www-inbox.perl
@@ -1,5 +1,5 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 # Parallel WWW checker
 my $usage = "$0 [-j JOBS] [-s SLOW_THRESHOLD] URL_OF_INBOX\n";
@@ -14,6 +14,12 @@ use POSIX qw(:sys_wait_h);
 use Time::HiRes qw(gettimeofday tv_interval);
 use WWW::Mechanize;
 use Data::Dumper;
+
+# we want to use vfork+exec with spawn, WWW::Mechanize can use too much
+# memory and fork(2) fails
+use PublicInbox::Spawn qw(spawn which);
+$ENV{PERL_INLINE_DIRECTORY} or warn "PERL_INLINE_DIRECTORY unset, may OOM\n";
+
 our $tmp_owner = $$;
 my $nproc = 4;
 my $slow = 0.5;
@@ -24,13 +30,34 @@ my %opts = (
 GetOptions(%opts) or die "bad command-line args\n$usage";
 my $root_url = shift or die $usage;
 
-chomp(my $xmlstarlet = `which xmlstarlet 2>/dev/null`);
+chomp(my $xmlstarlet = which('xmlstarlet'));
 my $atom_check = eval {
-	require IPC::Run;
 	my $cmd = [ qw(xmlstarlet val -e -) ];
 	sub {
 		my ($in, $out, $err) = @_;
-		IPC::Run::run($cmd, $in, $out, $err);
+		use autodie;
+		open my $in_fh, '+>', undef;
+		open my $out_fh, '+>', undef;
+		open my $err_fh, '+>', undef;
+		print $in_fh $$in;
+		$in_fh->flush;
+		sysseek($in_fh, 0, 0);
+		my $rdr = {
+			0 => fileno($in_fh),
+			1 => fileno($out_fh),
+			2 => fileno($err_fh),
+		};
+		my $pid = spawn($cmd, undef, $rdr);
+		while (waitpid($pid, 0) != $pid) {
+			next if $!{EINTR};
+			warn "waitpid(xmlstarlet, $pid) $!";
+			return $!;
+		}
+		sysseek($out_fh, 0, 0);
+		sysread($out_fh, $$out, -s $out_fh);
+		sysseek($err_fh, 0, 0);
+		sysread($err_fh, $$err, -s $err_fh);
+		$?
 	}
 } if $xmlstarlet;
 
@@ -64,7 +91,7 @@ foreach my $p (1..$nproc) {
 	}
 }
 
-my ($fh, $tmp) = tempfile('www-check-XXXXXXXX',
+my ($fh, $tmp) = tempfile('www-check-XXXX',
 			SUFFIX => '.gdbm', UNLINK => 1, TMPDIR => 1);
 my $gdbm = tie my %seen, 'GDBM_File', $tmp, &GDBM_WRCREAT, 0600;
 defined $gdbm or die "gdbm open failed: $!\n";
@@ -120,8 +147,10 @@ while (keys %workers) { # reacts to SIGCHLD
 
 sub worker_loop {
 	my ($todo_rd, $done_wr) = @_;
+	$SIG{CHLD} = 'DEFAULT';
 	my $m = WWW::Mechanize->new(autocheck => 0);
 	my $cc = LWP::ConnCache->new;
+	$m->stack_depth(0); # no history
 	$m->conn_cache($cc);
 	while (1) {
 		$todo_rd->recv(my $u, 65535, 0);
@@ -146,7 +175,7 @@ sub worker_loop {
 		my $s;
 		# blocking
 		foreach my $l (@links, "DONE\t$u") {
-			next if $l eq '';
+			next if $l eq '' || $l =~ /\.mbox(?:\.gz)\z/;
 			do {
 				$s = $done_wr->send($l, MSG_EOR);
 			} while (!defined $s && $!{EINTR});
@@ -164,8 +193,8 @@ sub worker_loop {
 		if ($atom_check && $ct =~ m!\bapplication/atom\+xml\b!) {
 			my $raw = $r->decoded_content;
 			my ($out, $err) = ('', '');
-			$atom_check->(\$raw, \$out, \$err) and
-				warn "Atom ($?) - $u - <1:$out> <2:$err>\n";
+			my $fail = $atom_check->(\$raw, \$out, \$err);
+			warn "Atom ($fail) - $u - <1:$out> <2:$err>\n" if $fail;
 		}
 
 		next if $ct !~ m!\btext/html\b!;