http: improve error handling for aborted responses

[public-inbox.git] / lib / PublicInbox / GitHTTPBackend.pm

diff --git a/lib/PublicInbox/GitHTTPBackend.pm b/lib/PublicInbox/GitHTTPBackend.pm
index c44c67d5baba41df5bf6645442b21d3baea85af0..4b3969346acefda27f49ffd47c5f0b26db49a1c6 100644 (file)
--- a/lib/PublicInbox/GitHTTPBackend.pm
+++ b/lib/PublicInbox/GitHTTPBackend.pm
@@ -10,6 +10,14 @@ use Fcntl qw(:seek);
 use IO::File;
 use PublicInbox::Spawn qw(spawn);
 
+# TODO: make configurable, but keep in mind it's better to have
+# multiple -httpd worker processes which are already scaled to
+# the proper number of CPUs and memory.  git-pack-objects(1) may
+# also use threads and bust memory limits, too, so I recommend
+# limiting threads to 1 (via `pack.threads` knob in git) for serving.
+my $LIMIT = 1;
+my $nr_running = 0;
+
 # n.b. serving "description" and "cloneurl" should be innocuous enough to
 # not cause problems.  serving "config" might...
 my @text = qw[HEAD info/refs
@@ -31,6 +39,8 @@ sub r {
 
 sub serve {
        my ($cgi, $git, $path) = @_;
+       return serve_dumb($cgi, $git, $path) if $nr_running >= $LIMIT;
+
        my $service = $cgi->param('service') || '';
        if ($service =~ /\Agit-\w+-pack\z/ || $path =~ /\Agit-\w+-pack\z/) {
                my $ok = serve_smart($cgi, $git, $path);
@@ -85,6 +95,7 @@ sub serve_dumb {
                        $len -= $r;
                        $fh->write($buf);
                }
+               die "$f truncated with $len bytes remaining\n" if $len;
                $fh->close;
        }
 }
@@ -174,37 +185,46 @@ sub serve_smart {
        $wpipe = $in = undef;
        $buf = '';
        my ($vin, $fh, $res);
+       $nr_running++;
        my $end = sub {
                if ($fh) {
                        $fh->close;
                        $fh = undef;
                }
                if ($rpipe) {
-                       $rpipe->close; # _may_ be Danga::Socket::close
+                       # _may_ be Danga::Socket::close via
+                       # PublicInbox::HTTPD::Async::close:
+                       $rpipe->close;
                        $rpipe = undef;
+                       $nr_running--;
                }
-               if (defined $pid && $pid != waitpid($pid, 0)) {
-                       $err->print("git http-backend ($git_dir): $?\n");
-               } else {
-                       $pid = undef;
+               if (defined $pid) {
+                       my $e = $pid == waitpid($pid, 0) ?
+                               $? : "PID:$pid still running?";
+                       if ($e) {
+                               $err->print("http-backend ($git_dir): $e\n");
+                               if (my $io = $env->{'psgix.io'}) {
+                                       $io->close;
+                               }
+                       }
                }
                return unless $res;
                my $dumb = serve_dumb($cgi, $git, $path);
                ref($dumb) eq 'ARRAY' ? $res->($dumb) : $dumb->($res);
        };
        my $fail = sub {
-               my ($e) = @_;
-               if ($e eq 'EAGAIN') {
+               if ($!{EAGAIN} || $!{EINTR}) {
                        select($vin, undef, undef, undef) if defined $vin;
                        # $vin is undef on async, so this is a noop on EAGAIN
                        return;
                }
+               my $e = $!;
                $end->();
                $err->print("git http-backend ($git_dir): $e\n");
        };
        my $cb = sub { # read git-http-backend output and stream to client
                my $r = $rpipe ? $rpipe->sysread($buf, 8192, length($buf)) : 0;
-               return $fail->($!{EAGAIN} ? 'EAGAIN' : $!) unless defined $r;
+               return $fail->() unless defined $r;
                return $end->() if $r == 0; # EOF
                if ($fh) { # stream body from git-http-backend to HTTP client
                        $fh->write($buf);
@@ -233,6 +253,7 @@ sub serve_smart {
                } # else { keep reading ... }
        };
        if (my $async = $env->{'pi-httpd.async'}) {
+               # $async is PublicInbox::HTTPD::Async->new($rpipe, $cb)
                $rpipe = $async->($rpipe, $cb);
                sub { ($res) = @_ } # let Danga::Socket handle the rest.
        } else { # synchronous loop for other PSGI servers