qspawn: capture errors from parse_hdr callback

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

diff --git a/lib/PublicInbox/Qspawn.pm b/lib/PublicInbox/Qspawn.pm
index 65bb178aba44a216f73c221338aebd5f7a9dba92..aebcb1f7db091ea8d3283407a2c0cbd559d407f8 100644 (file)
--- a/lib/PublicInbox/Qspawn.pm
+++ b/lib/PublicInbox/Qspawn.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # Like most Perl modules in public-inbox, this is internal and
@@ -45,25 +45,25 @@ sub new ($$$;) {
 sub _do_spawn {
        my ($self, $start_cb, $limiter) = @_;
        my $err;
-       my ($cmd, $cmd_env, $opts) = @{$self->{args}};
-       my %opts = %{$opts || {}};
+       my ($cmd, $cmd_env, $opt) = @{delete $self->{args}};
+       my %o = %{$opt || {}};
        $self->{limiter} = $limiter;
        foreach my $k (PublicInbox::Spawn::RLIMITS()) {
                if (defined(my $rlimit = $limiter->{$k})) {
-                       $opts{$k} = $rlimit;
+                       $o{$k} = $rlimit;
                }
        }
+       $self->{cmd} = $o{quiet} ? undef : $cmd;
+       eval {
+               # popen_rd may die on EMFILE, ENFILE
+               ($self->{rpipe}, $self->{pid}) = popen_rd($cmd, $cmd_env, \%o);
 
-       ($self->{rpipe}, $self->{pid}) = popen_rd($cmd, $cmd_env, \%opts);
+               die "E: $!" unless defined($self->{pid});
 
-       $self->{args} = $opts{quiet} ? undef : $cmd;
-
-       if (defined $self->{pid}) {
                $limiter->{running}++;
-       } else {
-               $self->{err} = $!;
-       }
-       $start_cb->($self);
+               $start_cb->($self); # EPOLL_CTL_ADD may ENOSPC/ENOMEM
+       };
+       finish($self, $@) if $@;
 }
 
 sub child_err ($) {
@@ -80,16 +80,8 @@ sub log_err ($$) {
        $env->{'psgi.errors'}->print($msg, "\n");
 }
 
-# callback for dwaitpid
-sub waitpid_err ($$) {
-       my ($self, $pid) = @_;
-       my $xpid = delete $self->{pid};
-       my $err;
-       if ($pid > 0) { # success!
-               $err = child_err($?);
-       } elsif ($pid < 0) { # ??? does this happen in our case?
-               $err = "W: waitpid($xpid, 0) => $pid: $!";
-       } # else should not be called with pid == 0
+sub finalize ($$) {
+       my ($self, $err) = @_;
 
        my ($env, $qx_cb, $qx_arg, $qx_buf) =
                delete @$self{qw(psgi_env qx_cb qx_arg qx_buf)};
@@ -105,12 +97,37 @@ sub waitpid_err ($$) {
        }
 
        if ($err) {
-               $self->{err} = $err;
-               if ($env && $self->{args}) {
-                       log_err($env, join(' ', @{$self->{args}}) . ": $err");
+               if (defined $self->{err}) {
+                       $self->{err} .= "; $err";
+               } else {
+                       $self->{err} = $err;
                }
+               if ($env && $self->{cmd}) {
+                       log_err($env, join(' ', @{$self->{cmd}}) . ": $err");
+               }
+       }
+       if ($qx_cb) {
+               eval { $qx_cb->($qx_buf, $qx_arg) };
+       } elsif (my $wcb = delete $env->{'qspawn.wcb'}) {
+               # have we started writing, yet?
+               require PublicInbox::WwwStatic;
+               $wcb->(PublicInbox::WwwStatic::r(500));
        }
-       eval { $qx_cb->($qx_buf, $qx_arg) } if $qx_cb;
+}
+
+# callback for dwaitpid
+sub waitpid_err ($$) {
+       my ($self, $pid) = @_;
+       my $xpid = delete $self->{pid};
+       my $err;
+       if (defined $pid) {
+               if ($pid > 0) { # success!
+                       $err = child_err($?);
+               } elsif ($pid < 0) { # ??? does this happen in our case?
+                       $err = "W: waitpid($xpid, 0) => $pid: $!";
+               } # else should not be called with pid == 0
+       }
+       finalize($self, $err);
 }
 
 sub do_waitpid ($) {
@@ -126,14 +143,12 @@ sub do_waitpid ($) {
        }
 }
 
-sub finish ($) {
-       my ($self) = @_;
+sub finish ($;$) {
+       my ($self, $err) = @_;
        if (delete $self->{rpipe}) {
                do_waitpid($self);
        } else {
-               my ($env, $qx_cb, $qx_arg, $qx_buf) =
-                       delete @$self{qw(psgi_env qx_cb qx_arg qx_buf)};
-               eval { $qx_cb->($qx_buf, $qx_arg) } if $qx_cb;
+               finalize($self, $err);
        }
 }
 
@@ -157,7 +172,7 @@ reread:
                $async->async_pass($self->{psgi_env}->{'psgix.io'},
                                        $qx_fh, \$buf);
        } elsif (defined $r) {
-               $r ? $qx_fh->write($buf) : event_step($self, undef);
+               $r ? (print $qx_fh $buf) : event_step($self, undef);
        } else {
                return if $! == EAGAIN; # try again when notified
                goto reread if $! == EINTR;
@@ -219,7 +234,11 @@ sub rd_hdr ($) {
                                length($$hdr_buf));
                if (defined($r)) {
                        $total_rd += $r;
-                       $ret = $ph_cb->($total_rd, $hdr_buf, $ph_arg);
+                       eval { $ret = $ph_cb->($total_rd, $hdr_buf, $ph_arg) };
+                       if ($@) {
+                               log_err($self->{psgi_env}, "parse_hdr: $@");
+                               $ret = [ 500, [], [ "Internal error\n" ] ];
+                       }
                } else {
                        # caller should notify us when it's ready:
                        return if $! == EAGAIN;
@@ -236,6 +255,7 @@ sub psgi_return_init_cb {
        my ($self) = @_;
        my $r = rd_hdr($self) or return;
        my $env = $self->{psgi_env};
+       my $filter = delete $env->{'qspawn.filter'};
        my $wcb = delete $env->{'qspawn.wcb'};
        my $async = delete $self->{async};
        if (scalar(@$r) == 3) { # error
@@ -250,6 +270,7 @@ sub psgi_return_init_cb {
        } elsif ($async) {
                # done reading headers, handoff to read body
                my $fh = $wcb->($r); # scalar @$r == 2
+               $fh = $filter->attach($fh) if $filter;
                $self->{fh} = $fh;
                $async->async_pass($env->{'psgix.io'}, $fh,
                                        delete($self->{hdr_buf}));
@@ -257,7 +278,7 @@ sub psgi_return_init_cb {
                require PublicInbox::GetlineBody;
                $r->[2] = PublicInbox::GetlineBody->new($self->{rpipe},
                                        \&event_step, $self,
-                                       ${$self->{hdr_buf}});
+                                       ${$self->{hdr_buf}}, $filter);
                $wcb->($r);
        }
 
@@ -287,6 +308,10 @@ sub psgi_return_start { # may run later, much later...
 #                          psgi_return will return an anonymous
 #                          sub for the PSGI server to call
 #
+#   $env->{'qspawn.filter'} - filter object, responds to ->attach for
+#                             pi-httpd.async and ->translate for generic
+#                             PSGI servers
+#
 # $limiter - the Limiter object to use (uses the def_limiter if not given)
 #
 # $parse_hdr - Initial read function; often for parsing CGI header output.