# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# base class for remote IPC calls and workqueues, requires Storable or Sereal
+# - ipc_do and ipc_worker_* is for a single worker/producer and uses pipes
+# - wq_do and wq_worker* is for a single producer and multiple workers,
+# using SOCK_SEQPACKET for work distribution
+# use ipc_do when you need work done on a certain process
+# use wq_do when your work can be done on any idle worker
package PublicInbox::IPC;
use strict;
use v5.10.1;
+use parent qw(Exporter);
use Carp qw(confess croak);
use PublicInbox::DS qw(dwaitpid);
use PublicInbox::Spawn;
-use POSIX qw(WNOHANG);
-use Socket qw(AF_UNIX MSG_EOR);
+use PublicInbox::OnDestroy;
+use PublicInbox::WQWorker;
+use Socket qw(AF_UNIX MSG_EOR SOCK_STREAM);
my $SEQPACKET = eval { Socket::SOCK_SEQPACKET() }; # portable enough?
use constant PIPE_BUF => $^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF();
+our @EXPORT_OK = qw(ipc_freeze ipc_thaw);
my $WQ_MAX_WORKERS = 4096;
my ($enc, $dec);
# ->imports at BEGIN turns sereal_*_with_object into custom ops on 5.14+
};
if ($enc && $dec) { # should be custom ops
- *freeze = sub ($) { sereal_encode_with_object $enc, $_[0] };
- *thaw = sub ($) { sereal_decode_with_object $dec, $_[0], my $ret };
+ *ipc_freeze = sub ($) { sereal_encode_with_object $enc, $_[0] };
+ *ipc_thaw = sub ($) { sereal_decode_with_object $dec, $_[0], my $ret };
} else {
eval { # some distros have Storable as a separate package from Perl
require Storable;
- Storable->import(qw(freeze thaw));
+ *ipc_freeze = \&Storable::freeze;
+ *ipc_thaw = \&Storable::thaw;
$enc = 1;
} // warn("Storable (part of Perl) missing: $@\n");
}
-my $recv_cmd1; # PublicInbox::CmdIPC1::recv_cmd1;
my $recv_cmd = PublicInbox::Spawn->can('recv_cmd4');
my $send_cmd = PublicInbox::Spawn->can('send_cmd4') // do {
require PublicInbox::CmdIPC4;
$recv_cmd //= PublicInbox::CmdIPC4->can('recv_cmd4');
PublicInbox::CmdIPC4->can('send_cmd4');
-} // do {
- # IO::FDPass only allows sending a single FD at-a-time, which
- # means we can't guarantee all packets end up on the same worker,
- # so we cap WQ_MAX_WORKERS
- require PublicInbox::CmdIPC1;
- $recv_cmd1 = PublicInbox::CmdIPC1->can('recv_cmd1');
- $WQ_MAX_WORKERS = 1 if $recv_cmd1;
- wq_set_recv_fds(3);
- PublicInbox::CmdIPC1->can('send_cmd1');
};
-# needed to tell recv_cmd1 how many times to loop IO::FDPass::recv
-sub wq_set_recv_fds {
- return unless $recv_cmd1;
- my $nfds = pop;
- my $sub = sub {
- my ($sock, $fds, undef, $flags) = @_;
- $recv_cmd1->($sock, $fds, $_[2], $flags, $nfds);
- };
- my $self = pop;
- if (ref $self) {
- $self->{-wq_recv_cmd} = $sub;
- } else {
- $recv_cmd = $sub;
- }
-}
-
sub _get_rec ($) {
my ($r) = @_;
defined(my $len = <$r>) or return;
chop($len) eq "\n" or croak "no LF byte in $len";
defined(my $n = read($r, my $buf, $len)) or croak "read error: $!";
$n == $len or croak "short read: $n != $len";
- thaw($buf);
+ ipc_thaw($buf);
}
sub _pack_rec ($) {
my ($ref) = @_;
- my $buf = freeze($ref);
+ my $buf = ipc_freeze($ref);
length($buf) . "\n" . $buf;
}
pipe(my ($r_req, $w_req)) or die "pipe: $!";
pipe(my ($r_res, $w_res)) or die "pipe: $!";
my $sigset = $oldset // PublicInbox::DS::block_signals();
- my $parent = $$;
$self->ipc_atfork_prepare;
- defined(my $pid = fork) or die "fork: $!";
+ my $seed = rand(0xffffffff);
+ my $pid = fork // die "fork: $!";
if ($pid == 0) {
+ srand($seed);
eval { PublicInbox::DS->Reset };
+ delete @$self{qw(-wq_s1 -wq_s2 -wq_workers -wq_ppid)};
$w_req = $r_res = undef;
$w_res->autoflush(1);
$SIG{$_} = 'IGNORE' for (qw(TERM INT QUIT));
local $0 = $ident;
PublicInbox::DS::sig_setmask($sigset);
- my $on_destroy = $self->ipc_atfork_child;
- eval { ipc_worker_loop($self, $r_req, $w_res) };
+ # ensure we properly exit even if warn() dies:
+ my $end = PublicInbox::OnDestroy->new($$, sub { exit(!!$@) });
+ eval {
+ my $on_destroy = $self->ipc_atfork_child;
+ local %SIG = %SIG;
+ ipc_worker_loop($self, $r_req, $w_res);
+ };
die "worker $ident PID:$$ died: $@\n" if $@;
- exit;
+ undef $end; # trigger exit
}
PublicInbox::DS::sig_setmask($sigset) unless $oldset;
$r_req = $w_res = undef;
}
sub ipc_worker_reap { # dwaitpid callback
- my ($self, $pid) = @_;
- warn "PID:$pid died with \$?=$?\n" if $?;
+ my ($args, $pid) = @_;
+ return if !$?;
+ # TERM(15) is our default exit signal, PIPE(13) is likely w/ pager
+ my $s = $? & 127;
+ warn "PID:$pid died with \$?=$?\n" if $s != 15 && $s != 13;
+}
+
+sub wq_wait_old {
+ my ($self, $args) = @_;
+ my $pids = delete $self->{"-wq_old_pids.$$"} or return;
+ dwaitpid($_, \&ipc_worker_reap, [$self, $args]) for @$pids;
}
# for base class, override in sub classes
sub ipc_atfork_prepare {}
+sub wq_atexit_child {}
+
sub ipc_atfork_child {
my ($self) = @_;
my $io = delete($self->{-ipc_atfork_child_close}) or return;
# idempotent, can be called regardless of whether worker is active or not
sub ipc_worker_stop {
- my ($self) = @_;
+ my ($self, $args) = @_;
my ($pid, $ppid) = delete(@$self{qw(-ipc_pid -ipc_ppid)});
my ($w_req, $r_res) = delete(@$self{qw(-ipc_req -ipc_res)});
if (!$w_req && !$r_res) {
$w_req = $r_res = undef;
return if $$ != $ppid;
- dwaitpid($pid, \&ipc_worker_reap, $self);
+ dwaitpid($pid, \&ipc_worker_reap, [$self, $args]);
}
# use this if we have multiple readers reading curl or "pigz -dc"
$pid == $$ and die "BUG: $$ ipc_atfork_child called on itself";
}
-sub _close_recvd ($) {
- my ($self) = @_;
- close($_) for (grep { defined } (delete @$self{0..2}));
+sub recv_and_run {
+ my ($self, $s2, $len, $full_stream) = @_;
+ my @fds = $recv_cmd->($s2, my $buf, $len);
+ return if scalar(@fds) && !defined($fds[0]);
+ my $n = length($buf) or return 0;
+ my $nfd = 0;
+ for my $fd (@fds) {
+ if (open(my $cmdfh, '+<&=', $fd)) {
+ $self->{$nfd++} = $cmdfh;
+ $cmdfh->autoflush(1);
+ } else {
+ die "$$ open(+<&=$fd) (FD:$nfd): $!";
+ }
+ }
+ while ($full_stream && $n < $len) {
+ my $r = sysread($s2, $buf, $len - $n, $n) // croak "read: $!";
+ croak "read EOF after $n/$len bytes" if $r == 0;
+ $n = length($buf);
+ }
+ # Sereal dies on truncated data, Storable returns undef
+ my $args = ipc_thaw($buf) // die "thaw error on buffer of size: $n";
+ undef $buf;
+ my $sub = shift @$args;
+ eval { $self->$sub(@$args) };
+ warn "$$ wq_worker: $@" if $@;
+ delete @$self{0..($nfd-1)};
+ $n;
}
sub wq_worker_loop ($) {
my ($self) = @_;
- my $buf;
- my $len = $self->{wq_req_len} // (4096 * 33);
- my ($sub, $args);
- my $s2 = $self->{-wq_s2} // die 'BUG: no -wq_s2';
- local $SIG{PIPE} = sub {
- my $cur_sub = $sub;
- _close_recvd($self);
- die(bless(\$cur_sub, __PACKAGE__.'::PIPE')) if $cur_sub;
- };
- my $rcv = $self->{-wq_recv_cmd} // $recv_cmd;
- while (1) {
- my (@fds) = $rcv->($s2, $buf, $len) or return; # EOF
- my $i = 0;
- my @m = @{$self->{wq_open_modes} // [qw( +<&= >&= >&= )]};
- for my $fd (@fds) {
- my $mode = shift(@m);
- if (open(my $cmdfh, $mode, $fd)) {
- $self->{$i++} = $cmdfh;
- $cmdfh->autoflush(1);
- } else {
- die "$$ open($mode$fd) (FD:$i): $!";
- }
- }
- # Sereal dies on truncated data, Storable returns undef
- $args = thaw($buf) //
- die "thaw error on buffer of size:".length($buf);
- eval {
- $sub = shift @$args;
- eval { $self->$sub(@$args) };
- undef $sub; # quiet SIG{PIPE} handler
- die $@ if $@;
- };
- warn "$$ wq_worker: $@" if $@ && ref $@ ne __PACKAGE__.'::PIPE';
- # need to close explicitly to avoid warnings after SIGPIPE
- _close_recvd($self);
- }
+ my $wqw = PublicInbox::WQWorker->new($self);
+ PublicInbox::DS->SetPostLoopCallback(sub { $wqw->{sock} });
+ PublicInbox::DS->EventLoop;
+ PublicInbox::DS->Reset;
+}
+
+sub do_sock_stream { # via wq_do, for big requests
+ my ($self, $len) = @_;
+ recv_and_run($self, delete $self->{0}, $len, 1);
}
sub wq_do { # always async
my ($self, $sub, $ios, @args) = @_;
if (my $s1 = $self->{-wq_s1}) { # run in worker
my $fds = [ map { fileno($_) } @$ios ];
- $send_cmd->($s1, $fds, freeze([$sub, @args]), MSG_EOR);
+ my $buf = ipc_freeze([$sub, @args]);
+ my $n = $send_cmd->($s1, $fds, $buf, MSG_EOR);
+ return if defined($n); # likely
+ croak "sendmsg: $! (check RLIMIT_NOFILE)" if $!{ETOOMANYREFS};
+ croak "sendmsg: $!" if !$!{EMSGSIZE};
+ socketpair(my $r, my $w, AF_UNIX, SOCK_STREAM, 0) or
+ croak "socketpair: $!";
+ $n = $send_cmd->($s1, [ fileno($r) ],
+ ipc_freeze(['do_sock_stream', length($buf)]),
+ MSG_EOR) // croak "sendmsg: $!";
+ undef $r;
+ $n = $send_cmd->($w, $fds, $buf, 0) // croak "sendmsg: $!";
+ while ($n < length($buf)) {
+ my $x = syswrite($w, $buf, length($buf) - $n, $n) //
+ croak "syswrite: $!";
+ croak "syswrite wrote 0 bytes" if $x == 0;
+ $n += $x;
+ }
} else {
@$self{0..$#$ios} = @$ios;
eval { $self->$sub(@args) };
warn "wq_do: $@" if $@;
- delete @$self{0..$#$ios};
+ delete @$self{0..$#$ios}; # don't close
}
}
-sub _wq_worker_start ($$) {
- my ($self, $oldset) = @_;
+sub _wq_worker_start ($$$) {
+ my ($self, $oldset, $fields) = @_;
+ my $seed = rand(0xffffffff);
my $pid = fork // die "fork: $!";
if ($pid == 0) {
+ srand($seed);
eval { PublicInbox::DS->Reset };
- close(delete $self->{-wq_s1});
- delete $self->{qw(-wq_workers -wq_ppid)};
- $SIG{$_} = 'IGNORE' for (qw(PIPE TTOU TTIN));
- $SIG{$_} = 'DEFAULT' for (qw(TERM QUIT INT CHLD));
+ delete @$self{qw(-wq_s1 -wq_workers -wq_ppid)};
+ @$self{keys %$fields} = values(%$fields) if $fields;
+ $SIG{$_} = 'IGNORE' for (qw(PIPE));
+ $SIG{$_} = 'DEFAULT' for (qw(TTOU TTIN TERM QUIT INT CHLD));
local $0 = $self->{-wq_ident};
PublicInbox::DS::sig_setmask($oldset);
# ensure we properly exit even if warn() dies:
my $end = PublicInbox::OnDestroy->new($$, sub { exit(!!$@) });
- my $on_destroy = $self->ipc_atfork_child;
- eval { wq_worker_loop($self) };
+ eval {
+ my $on_destroy = $self->ipc_atfork_child;
+ local %SIG = %SIG;
+ wq_worker_loop($self);
+ };
warn "worker $self->{-wq_ident} PID:$$ died: $@" if $@;
- undef $on_destroy;
undef $end; # trigger exit
} else {
$self->{-wq_workers}->{$pid} = \undef;
# starts workqueue workers if Sereal or Storable is installed
sub wq_workers_start {
- my ($self, $ident, $nr_workers, $oldset) = @_;
+ my ($self, $ident, $nr_workers, $oldset, $fields) = @_;
($enc && $send_cmd && $recv_cmd && defined($SEQPACKET)) or return;
return if $self->{-wq_s1}; # idempotent
- my ($s1, $s2);
- socketpair($s1, $s2, AF_UNIX, $SEQPACKET, 0) or die "socketpair: $!";
+ $self->{-wq_s1} = $self->{-wq_s2} = undef;
+ socketpair($self->{-wq_s1}, $self->{-wq_s2}, AF_UNIX, $SEQPACKET, 0) or
+ die "socketpair: $!";
$self->ipc_atfork_prepare;
$nr_workers //= 4;
$nr_workers = $WQ_MAX_WORKERS if $nr_workers > $WQ_MAX_WORKERS;
my $sigset = $oldset // PublicInbox::DS::block_signals();
$self->{-wq_workers} = {};
$self->{-wq_ident} = $ident;
- $self->{-wq_s1} = $s1;
- $self->{-wq_s2} = $s2;
- _wq_worker_start($self, $sigset) for (1..$nr_workers);
+ _wq_worker_start($self, $sigset, $fields) for (1..$nr_workers);
PublicInbox::DS::sig_setmask($sigset) unless $oldset;
$self->{-wq_ppid} = $$;
}
sub wq_worker_incr { # SIGTTIN handler
- my ($self, $oldset) = @_;
+ my ($self, $oldset, $fields) = @_;
$self->{-wq_s2} or return;
return if wq_workers($self) >= $WQ_MAX_WORKERS;
$self->ipc_atfork_prepare;
my $sigset = $oldset // PublicInbox::DS::block_signals();
- _wq_worker_start($self, $sigset);
+ _wq_worker_start($self, $sigset, $fields);
PublicInbox::DS::sig_setmask($sigset) unless $oldset;
}
}
sub wq_close {
- my ($self) = @_;
+ my ($self, $nohang) = @_;
delete @$self{qw(-wq_s1 -wq_s2)} or return;
my $ppid = delete $self->{-wq_ppid} or return;
my $workers = delete $self->{-wq_workers} // die 'BUG: no wq_workers';
return if $ppid != $$; # can't reap siblings or parents
- for my $pid (keys %$workers) {
- dwaitpid($pid, \&ipc_worker_reap, $self);
+ my @pids = map { $_ + 0 } keys %$workers;
+ if ($nohang) {
+ push @{$self->{"-wq_old_pids.$$"}}, @pids;
+ } else {
+ dwaitpid($_, \&ipc_worker_reap, $self) for @pids;
}
}
+sub wq_kill_old {
+ my ($self) = @_;
+ my $pids = $self->{"-wq_old_pids.$$"} or return;
+ kill 'TERM', @$pids;
+}
+
+sub wq_kill {
+ my ($self, $sig) = @_;
+ my $workers = $self->{-wq_workers} or return;
+ kill($sig // 'TERM', keys %$workers);
+}
+
sub WQ_MAX_WORKERS { $WQ_MAX_WORKERS }
sub DESTROY {
- wq_close($_[0]);
- ipc_worker_stop($_[0]);
+ my ($self) = @_;
+ my $ppid = $self->{-wq_ppid};
+ wq_kill($self) if $ppid && $ppid == $$;
+ wq_close($self);
+ wq_wait_old($self);
+ ipc_worker_stop($self);
+}
+
+# Sereal doesn't have dclone
+sub deep_clone { ipc_thaw(ipc_freeze($_[-1])) }
+
+sub detect_nproc () {
+ # _SC_NPROCESSORS_ONLN = 84 on both Linux glibc and musl
+ return POSIX::sysconf(84) if $^O eq 'linux';
+ return POSIX::sysconf(58) if $^O eq 'freebsd';
+ # TODO: more OSes
+
+ # getconf(1) is POSIX, but *NPROCESSORS* vars are not
+ for (qw(_NPROCESSORS_ONLN NPROCESSORS_ONLN)) {
+ `getconf $_ 2>/dev/null` =~ /^(\d+)$/ and return $1;
+ }
+ for my $nproc (qw(nproc gnproc)) { # GNU coreutils nproc
+ `$nproc 2>/dev/null` =~ /^(\d+)$/ and return $1;
+ }
+
+ # should we bother with `sysctl hw.ncpu`? Those only give
+ # us total processor count, not online processor count.
+ undef
}
1;