-# 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>
# Like most Perl modules in public-inbox, this is internal and
# operate in. This can be useful to ensure smaller inboxes can
# be cloned while cloning of large inboxes is maxed out.
#
-# This does not depend on PublicInbox::DS or any other external
-# scheduling mechanism, you just need to call start() and finish()
-# appropriately. However, public-inbox-httpd (which uses PublicInbox::DS)
-# will be able to schedule this based on readability of stdout from
-# the spawned process. See GitHTTPBackend.pm and SolverGit.pm for
-# usage examples. It does not depend on any form of threading.
+# This does not depend on the PublicInbox::DS->EventLoop or any
+# other external scheduling mechanism, you just need to call
+# start() and finish() appropriately. However, public-inbox-httpd
+# (which uses PublicInbox::DS) will be able to schedule this
+# based on readability of stdout from the spawned process.
+# See GitHTTPBackend.pm and SolverGit.pm for usage examples.
+# It does not depend on any form of threading.
#
# This is useful for scheduling CGI execution of both long-lived
# git-http-backend(1) process (for "git clone") as well as short-lived
package PublicInbox::Qspawn;
use strict;
-use warnings;
use PublicInbox::Spawn qw(popen_rd);
-require Plack::Util;
+use PublicInbox::GzipFilter;
+use PublicInbox::DS qw(dwaitpid); # doesn't need event loop
# n.b.: we get EAGAIN with public-inbox-httpd, and EINTR on other PSGI servers
use Errno qw(EAGAIN EINTR);
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()) {
+ 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);
-
- # drop any IO handles opt was holding open via $opt->{hold}
- # No need to hold onto the descriptor once the child process has it.
- $self->{args} = $cmd; # keep this around for logging
+ die "E: $!" unless defined($self->{pid});
- if (defined $self->{pid}) {
$limiter->{running}++;
- } else {
- $self->{err} = $!;
- }
- $start_cb->($self);
+ $start_cb->($self); # EPOLL_CTL_ADD may ENOSPC/ENOMEM
+ };
+ finish($self, $@) if $@;
}
sub child_err ($) {
$env->{'psgi.errors'}->print($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)};
}
if ($err) {
- $self->{err} = $err;
- if ($env && !$env->{'qspawn.quiet'}) {
- log_err($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");
}
}
- eval { $qx_cb->($qx_buf, $qx_arg) } if $qx_cb;
-}
-
-sub do_waitpid ($) {
- my ($self) = @_;
- my $pid = $self->{pid};
- # PublicInbox::DS may not be loaded
- eval { PublicInbox::DS::dwaitpid($pid, \&waitpid_err, $self) };
- # done if we're running in PublicInbox::DS::EventLoop
- if ($@) {
- # non public-inbox-{httpd,nntpd} callers may block:
- my $ret = waitpid($pid, 0);
- waitpid_err($self, $ret);
+ if ($qx_cb) {
+ eval { $qx_cb->($qx_buf, $qx_arg) };
+ } elsif (my $wcb = delete $env->{'qspawn.wcb'}) {
+ # have we started writing, yet?
+ require PublicInbox::WwwStatic;
+ $wcb->(PublicInbox::WwwStatic::r(500));
}
}
-sub finish ($) {
- my ($self) = @_;
+# callback for dwaitpid
+sub waitpid_err { finalize($_[0], child_err($?)) }
+
+sub finish ($;$) {
+ my ($self, $err) = @_;
if (delete $self->{rpipe}) {
- do_waitpid($self);
+ dwaitpid $self->{pid}, \&waitpid_err, $self;
} else {
- my ($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);
}
}
$async->async_pass($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 $! == EINTR;
start($self, $limiter, \&psgi_qx_start);
}
-# create a filter for "push"-based streaming PSGI writes used by HTTPD::Async
-sub filter_fh ($$) {
- my ($fh, $filter) = @_;
- Plack::Util::inline_object(
- close => sub {
- $fh->write($filter->(undef));
- $fh->close;
- },
- write => sub {
- $fh->write($filter->($_[0]));
- });
-}
-
# this is called on pipe EOF to reap the process, may be called
# via PublicInbox::DS event loop OR via GetlineBody for generic
# PSGI servers.
my $ret;
my $total_rd = 0;
my $hdr_buf = $self->{hdr_buf};
+ my ($ph_cb, $ph_arg) = @{$self->{parse_hdr}};
do {
my $r = sysread($self->{rpipe}, $$hdr_buf, 4096,
length($$hdr_buf));
if (defined($r)) {
$total_rd += $r;
- $ret = $self->{parse_hdr}->($total_rd, $hdr_buf);
+ 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 $! == EAGAIN;
my ($self) = @_;
my $r = rd_hdr($self) or return;
my $env = $self->{psgi_env};
- my $filter = delete $env->{'qspawn.filter'};
+ my $filter = delete $env->{'qspawn.filter'} //
+ PublicInbox::GzipFilter::qsp_maybe($r->[1], $env);
+
my $wcb = delete $env->{'qspawn.wcb'};
my $async = delete $self->{async};
if (scalar(@$r) == 3) { # error
} elsif ($async) {
# done reading headers, handoff to read body
my $fh = $wcb->($r); # scalar @$r == 2
- $fh = filter_fh($fh, $filter) if $filter;
+ $fh = $filter->attach($fh) if $filter;
$self->{fh} = $fh;
$async->async_pass($env->{'psgix.io'}, $fh,
delete($self->{hdr_buf}));
${$self->{hdr_buf}}, $filter);
$wcb->($r);
}
-
- # Workaround a leak under Perl 5.16.3 when combined with
- # Plack::Middleware::Deflater:
- $wcb = undef;
}
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 callback, receives a string as input,
-# undef on EOF
+# $env->{'qspawn.filter'} - filter object, responds to ->attach for
+# pi-httpd.async and ->translate for generic
+# PSGI servers
#
# $limiter - the Limiter object to use (uses the def_limiter if not given)
#
# psgix.io. 3-element arrays means the body is available
# immediately (or streamed via ->getline (pull-based)).
sub psgi_return {
- my ($self, $env, $limiter, $parse_hdr) = @_;
+ my ($self, $env, $limiter, $parse_hdr, $hdr_arg) = @_;
$self->{psgi_env} = $env;
$self->{hdr_buf} = \(my $hdr_buf = '');
- $self->{parse_hdr} = $parse_hdr;
+ $self->{parse_hdr} = [ $parse_hdr, $hdr_arg ];
$limiter ||= $def_limiter ||= PublicInbox::Qspawn::Limiter->new(32);
# the caller already captured the PSGI write callback from
}
sub setup_rlimit {
- my ($self, $name, $config) = @_;
- foreach my $rlim (PublicInbox::Spawn::RLIMITS()) {
+ my ($self, $name, $cfg) = @_;
+ foreach my $rlim (@PublicInbox::Spawn::RLIMITS) {
my $k = lc($rlim);
$k =~ tr/_//d;
$k = "publicinboxlimiter.$name.$k";
- defined(my $v = $config->{$k}) or next;
+ defined(my $v = $cfg->{$k}) or next;
my @rlimit = split(/\s*,\s*/, $v);
if (scalar(@rlimit) == 1) {
push @rlimit, $rlimit[0];