-# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 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::event_loop 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 v5.10.1;
use PublicInbox::Spawn qw(popen_rd);
+use PublicInbox::GzipFilter;
# n.b.: we get EAGAIN with public-inbox-httpd, and EINTR on other PSGI servers
use Errno qw(EAGAIN EINTR);
# $cmd is the command to spawn
# $cmd_env is the environ for the child process (not PSGI env)
# $opt can include redirects and perhaps other process spawning options
-sub new ($$$;) {
+# {qsp_err} is an optional error buffer callers may access themselves
+sub new {
my ($class, $cmd, $cmd_env, $opt) = @_;
bless { args => [ $cmd, $cmd_env, $opt ] }, $class;
}
sub _do_spawn {
my ($self, $start_cb, $limiter) = @_;
my $err;
- my ($cmd, $cmd_env, $opts) = @{$self->{args}};
- my %opts = %{$opts || {}};
+ my ($cmd, $cmd_env, $opt) = @{delete $self->{args}};
+ my %o = %{$opt || {}};
$self->{limiter} = $limiter;
- foreach my $k (PublicInbox::Spawn::RLIMITS()) {
+ foreach my $k (@PublicInbox::Spawn::RLIMITS) {
if (defined(my $rlimit = $limiter->{$k})) {
- $opts{$k} = $rlimit;
+ $o{$k} = $rlimit;
}
}
+ $self->{cmd} = $o{quiet} ? undef : $cmd;
+ eval {
+ # popen_rd may die on EMFILE, ENFILE
+ $self->{rpipe} = popen_rd($cmd, $cmd_env, \%o);
- ($self->{rpipe}, $self->{pid}) = popen_rd($cmd, $cmd_env, \%opts);
+ die "E: $!" unless defined($self->{rpipe});
- # drop any IO handles opt was holding open via $opt->{hold}
- # No need to hold onto the descriptor once the child process has it.
- $self->{args} = $cmd; # keep this around for logging
-
- if (defined $self->{pid}) {
$limiter->{running}++;
- } else {
- $self->{err} = $!;
- }
- $start_cb->($self);
+ $start_cb->($self); # EPOLL_CTL_ADD may ENOSPC/ENOMEM
+ };
+ finish($self, $@) if $@;
}
sub child_err ($) {
$msg;
}
-sub log_err ($$) {
- my ($env, $msg) = @_;
- $env->{'psgi.errors'}->print($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}}) . ": $err");
+ utf8::decode($err);
+ if (my $dst = $self->{qsp_err}) {
+ $$dst .= $$dst ? " $err" : "; $err";
}
+ warn "@{$self->{cmd}}: $err" if $self->{cmd};
}
- 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) };
+ return unless $@;
+ warn "E: $@"; # hope qspawn.wcb can handle it
+ }
+ return if $self->{passed}; # another command chained it
+ if (my $wcb = delete $env->{'qspawn.wcb'}) {
+ # have we started writing, yet?
+ require PublicInbox::WwwStatic;
+ $wcb->(PublicInbox::WwwStatic::r(500));
}
}
-sub finish ($) {
- my ($self) = @_;
- 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 $qx_cb;
- }
+# callback for dwaitpid or ProcessPipe
+sub waitpid_err { finalize($_[0], child_err($?)) }
+
+sub finish ($;$) {
+ my ($self, $err) = @_;
+ my $tied_pp = delete($self->{rpipe}) or return finalize($self, $err);
+ my PublicInbox::ProcessPipe $pp = tied *$tied_pp;
+ @$pp{qw(cb arg)} = (\&waitpid_err, $self); # for ->DESTROY
}
sub start ($$$) {
sub psgi_qx_init_cb {
my ($self) = @_;
- my $async = delete $self->{async};
+ my $async = delete $self->{async}; # PublicInbox::HTTPD::Async
my ($r, $buf);
my $qx_fh = $self->{qx_fh};
reread:
$async->async_pass($self->{psgi_env}->{'psgix.io'},
$qx_fh, \$buf);
} elsif (defined $r) {
- $r ? $qx_fh->write($buf) : event_step($self, undef);
+ $r ? (print $qx_fh $buf) : event_step($self, undef);
} else {
return if $! == EAGAIN; # try again when notified
goto reread if $! == EINTR;
# PSGI servers.
sub event_step {
my ($self, $err) = @_; # $err: $!
- log_err($self->{psgi_env}, "psgi_{return,qx} $err") if defined($err);
+ warn "psgi_{return,qx} $err" if defined($err);
finish($self);
- my ($fh, $qx_fh) = delete(@$self{qw(fh qx_fh)});
+ my ($fh, $qx_fh) = delete(@$self{qw(qfh qx_fh)});
$fh->close if $fh; # async-only (psgi_return)
}
sub rd_hdr ($) {
my ($self) = @_;
# typically used for reading CGI headers
- # we must loop until EAGAIN for EPOLLET in HTTPD/Async.pm
# We also need to check EINTR for generic PSGI servers.
my $ret;
my $total_rd = 0;
length($$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, $ph_arg) };
+ if ($@) {
+ warn "parse_hdr: $@";
+ $ret = [ 500, [], [ "Internal error\n" ] ];
+ }
} else {
# caller should notify us when it's ready:
return if $! == EAGAIN;
next if $! == EINTR; # immediate retry
- log_err($self->{psgi_env}, "error reading header: $!");
+ warn "error reading header: $!";
$ret = [ 500, [], [ "Internal error\n" ] ];
}
} until (defined $ret);
my ($self) = @_;
my $r = rd_hdr($self) or return;
my $env = $self->{psgi_env};
+ my $filter;
+ if (ref($r) eq 'ARRAY' && Scalar::Util::blessed($r->[2]) &&
+ $r->[2]->can('attach')) {
+ $filter = pop @$r;
+ }
+ $filter //= delete($env->{'qspawn.filter'}) // (ref($r) eq 'ARRAY' ?
+ PublicInbox::GzipFilter::qsp_maybe($r->[1], $env) : undef);
+
my $wcb = delete $env->{'qspawn.wcb'};
- my $async = delete $self->{async};
- if (scalar(@$r) == 3) { # error
- if ($async) {
- # calls rpipe->close && ->event_step
- $async->close;
- } else {
- $self->{rpipe}->close;
+ my $async = delete $self->{async}; # PublicInbox::HTTPD::Async
+ if (ref($r) ne 'ARRAY' || scalar(@$r) == 3) { # error
+ if ($async) { # calls rpipe->close && ->event_step
+ $async->close; # PublicInbox::HTTPD::Async::close
+ } else { # generic PSGI:
+ delete($self->{rpipe})->close;
event_step($self);
+ waitpid_err($self);
}
- $wcb->($r);
+ if (ref($r) eq 'ARRAY') { # error
+ $wcb->($r)
+ } elsif (ref($r) eq 'CODE') { # chain another command
+ $r->($wcb);
+ $self->{passed} = 1;
+ }
+ # else do nothing
} elsif ($async) {
# done reading headers, handoff to read body
my $fh = $wcb->($r); # scalar @$r == 2
- $self->{fh} = $fh;
+ $fh = $filter->attach($fh) if $filter;
+ $self->{qfh} = $fh;
$async->async_pass($env->{'psgix.io'}, $fh,
delete($self->{hdr_buf}));
} else { # for synchronous PSGI servers
require PublicInbox::GetlineBody;
+ my $buf = delete $self->{hdr_buf};
$r->[2] = PublicInbox::GetlineBody->new($self->{rpipe},
- \&event_step, $self,
- ${$self->{hdr_buf}});
+ \&event_step, $self, $$buf, $filter);
$wcb->($r);
}
-
- # Workaround a leak under Perl 5.16.3 when combined with
- # Plack::Middleware::Deflater:
- $wcb = undef;
}
sub psgi_return_start { # may run later, much later...
my ($self) = @_;
- if (my $async = $self->{psgi_env}->{'pi-httpd.async'}) {
+ if (my $cb = $self->{psgi_env}->{'pi-httpd.async'}) {
# PublicInbox::HTTPD::Async->new(rpipe, $cb, $cb_arg, $end_obj)
- $self->{async} = $async->($self->{rpipe},
+ $self->{async} = $cb->($self->{rpipe},
\&psgi_return_init_cb, $self, $self);
} else { # generic PSGI
psgi_return_init_cb($self) while $self->{parse_hdr};
# 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)
#
# $parse_hdr - Initial read function; often for parsing CGI header output.
}
sub setup_rlimit {
- my ($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];