X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FIPC.pm;h=548a72ebb11c70dba1ba1360fdc8d6d5598b9c95;hb=HEAD;hp=078aaa2c47e1adc3d0984e8eeed4e02a00557b12;hpb=a93947277940b9b4a22a21f70166703fe69198df;p=public-inbox.git diff --git a/lib/PublicInbox/IPC.pm b/lib/PublicInbox/IPC.pm index 078aaa2c..548a72eb 100644 --- a/lib/PublicInbox/IPC.pm +++ b/lib/PublicInbox/IPC.pm @@ -1,26 +1,25 @@ -# Copyright (C) 2020-2021 all contributors +# Copyright (C) all contributors # License: AGPL-3.0+ # 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, +# - wq_io_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 +# use wq_io_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 Carp qw(croak); +use PublicInbox::DS qw(awaitpid); use PublicInbox::Spawn; use PublicInbox::OnDestroy; use PublicInbox::WQWorker; use Socket qw(AF_UNIX MSG_EOR SOCK_STREAM); +my $MY_MAX_ARG_STRLEN = 4096 * 33; # extra 4K for serialization 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, $dec); # ->imports at BEGIN turns sereal_*_with_object into custom ops on 5.14+ # and eliminate method call overhead @@ -38,19 +37,20 @@ if ($enc && $dec) { # should be custom ops *ipc_freeze = sub ($) { 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; - *ipc_freeze = \&Storable::freeze; - *ipc_thaw = \&Storable::thaw; - $enc = 1; - } // warn("Storable (part of Perl) missing: $@\n"); + require Storable; + *ipc_freeze = \&Storable::freeze; + *ipc_thaw = \&Storable::thaw; } my $recv_cmd = PublicInbox::Spawn->can('recv_cmd4'); -my $send_cmd = PublicInbox::Spawn->can('send_cmd4') // do { +our $send_cmd = PublicInbox::Spawn->can('send_cmd4') // do { require PublicInbox::CmdIPC4; $recv_cmd //= PublicInbox::CmdIPC4->can('recv_cmd4'); PublicInbox::CmdIPC4->can('send_cmd4'); +} // do { + require PublicInbox::Syscall; + $recv_cmd //= PublicInbox::Syscall->can('recv_cmd4'); + PublicInbox::Syscall->can('send_cmd4'); }; sub _get_rec ($) { @@ -62,15 +62,10 @@ sub _get_rec ($) { ipc_thaw($buf); } -sub _pack_rec ($) { - my ($ref) = @_; - my $buf = ipc_freeze($ref); - length($buf) . "\n" . $buf; -} - sub _send_rec ($$) { my ($w, $ref) = @_; - print $w _pack_rec($ref) or croak "print: $!"; + my $buf = ipc_freeze($ref); + print $w length($buf), "\n", $buf or croak "print: $!"; } sub ipc_return ($$$) { @@ -101,8 +96,7 @@ sub ipc_worker_loop ($$$) { # starts a worker if Sereal or Storable is installed sub ipc_worker_spawn { - my ($self, $ident, $oldset) = @_; - return unless $enc; # no Sereal or Storable + my ($self, $ident, $oldset, $fields, @cb_args) = @_; return if ($self->{-ipc_ppid} // -1) == $$; # idempotent delete(@$self{qw(-ipc_req -ipc_res -ipc_ppid -ipc_pid)}); pipe(my ($r_req, $w_req)) or die "pipe: $!"; @@ -113,21 +107,24 @@ sub ipc_worker_spawn { my $pid = fork // die "fork: $!"; if ($pid == 0) { srand($seed); + eval { Net::SSLeay::randomize() }; eval { PublicInbox::DS->Reset }; delete @$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); # ensure we properly exit even if warn() dies: my $end = PublicInbox::OnDestroy->new($$, sub { exit(!!$@) }); eval { + $fields //= {}; + local @$self{keys %$fields} = values(%$fields); my $on_destroy = $self->ipc_atfork_child; - local %SIG = %SIG; + local @SIG{keys %SIG} = values %SIG; + PublicInbox::DS::sig_setmask($sigset); ipc_worker_loop($self, $r_req, $w_res); }; - die "worker $ident PID:$$ died: $@\n" if $@; + warn "worker $ident PID:$$ died: $@\n" if $@; undef $end; # trigger exit } PublicInbox::DS::sig_setmask($sigset) unless $oldset; @@ -136,21 +133,18 @@ sub ipc_worker_spawn { $self->{-ipc_req} = $w_req; $self->{-ipc_res} = $r_res; $self->{-ipc_ppid} = $$; + awaitpid($pid, \&ipc_worker_reap, $self, @cb_args); $self->{-ipc_pid} = $pid; } -sub ipc_worker_reap { # dwaitpid callback - my ($args, $pid) = @_; +sub ipc_worker_reap { # awaitpid callback + my ($pid, $self, $cb, @args) = @_; + delete $self->{-wq_workers}->{$pid}; + return $cb->($pid, $self, @args) if $cb; return if !$?; - # 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.$$"} or return; - dwaitpid($_, \&ipc_worker_reap, [$self, $args]) for @$pids; + # TERM(15) is our default exit signal, PIPE(13) is likely w/ pager + warn "$self->{-wq_ident} PID:$pid died \$?=$?\n" if $s != 15 && $s != 13 } # for base class, override in sub classes @@ -167,7 +161,7 @@ sub ipc_atfork_child { # idempotent, can be called regardless of whether worker is active or not sub ipc_worker_stop { - my ($self, $args) = @_; + my ($self) = @_; my ($pid, $ppid) = delete(@$self{qw(-ipc_pid -ipc_ppid)}); my ($w_req, $r_res) = delete(@$self{qw(-ipc_req -ipc_res)}); if (!$w_req && !$r_res) { @@ -176,32 +170,23 @@ sub ipc_worker_stop { } die 'no PID with IPC pipes' unless $pid; $w_req = $r_res = undef; - - return if $$ != $ppid; - dwaitpid($pid, \&ipc_worker_reap, [$self, $args]); + awaitpid($pid) if $$ == $ppid; # for non-event loop } # use this if we have multiple readers reading curl or "pigz -dc" # and writing to the same store sub ipc_lock_init { my ($self, $f) = @_; + $f // die 'BUG: no filename given'; require PublicInbox::Lock; $self->{-ipc_lock} //= bless { lock_path => $f }, 'PublicInbox::Lock' } -sub ipc_async_wait ($$) { - my ($self, $max) = @_; # max == -1 to wait for all - my $aif = $self->{-async_inflight} or return; - my $r_res = $self->{-ipc_res} or die 'BUG: no ipc_res'; - while (my ($sub, $bytes, $cb, $cb_arg) = splice(@$aif, 0, 4)) { - my $ret = _get_rec($r_res) // - die "no response on $sub (req.size=$bytes)"; - $self->{-async_inflight_bytes} -= $bytes; - - eval { $cb->($cb_arg, $ret) }; - warn "E: $sub callback error: $@\n" if $@; - return if --$max == 0; - } +sub _wait_return ($$) { + my ($r_res, $sub) = @_; + my $ret = _get_rec($r_res) // die "no response on $sub"; + die $$ret if ref($ret) eq 'PublicInbox::IPC::Die'; + wantarray ? @$ret : $$ret; } # call $self->$sub(@args), on a worker if ipc_worker_spawn was used @@ -211,12 +196,9 @@ sub ipc_do { my $ipc_lock = $self->{-ipc_lock}; my $lock = $ipc_lock ? $ipc_lock->lock_for_scope : undef; if (defined(wantarray)) { - my $r_res = $self->{-ipc_res} or die 'BUG: no ipc_res'; - ipc_async_wait($self, -1); + my $r_res = $self->{-ipc_res} or die 'no ipc_res'; _send_rec($w_req, [ wantarray, $sub, @args ]); - my $ret = _get_rec($r_res) // die "no response on $sub"; - die $$ret if ref($ret) eq 'PublicInbox::IPC::Die'; - wantarray ? @$ret : $$ret; + _wait_return($r_res, $sub); } else { # likely, fire-and-forget into pipe _send_rec($w_req, [ undef , $sub, @args ]); } @@ -225,30 +207,6 @@ sub ipc_do { } } -sub ipc_async { - my ($self, $sub, $sub_args, $cb, $cb_arg) = @_; - if (my $w_req = $self->{-ipc_req}) { # run in worker - my $rec = _pack_rec([ 1, $sub, @$sub_args ]); - my $cur_bytes = \($self->{-async_inflight_bytes} //= 0); - while (($$cur_bytes + length($rec)) > PIPE_BUF) { - ipc_async_wait($self, 1); - } - my $ipc_lock = $self->{-ipc_lock}; - my $lock = $ipc_lock ? $ipc_lock->lock_for_scope : undef; - print $w_req $rec or croak "print: $!"; - $$cur_bytes += length($rec); - push @{$self->{-async_inflight}}, - $sub, length($rec), $cb, $cb_arg; - } else { - my $ret = [ eval { $self->$sub(@$sub_args) } ]; - if (my $exc = $@) { - $ret = ( bless(\$exc, 'PublicInbox::IPC::Die') ); - } - eval { $cb->($cb_arg, $ret) }; - warn "E: $sub callback error: $@\n" if $@; - } -} - # needed when there's multiple IPC workers and the parent forking # causes newer siblings to inherit older siblings sockets sub ipc_sibling_atfork_child { @@ -260,7 +218,7 @@ sub ipc_sibling_atfork_child { sub recv_and_run { my ($self, $s2, $len, $full_stream) = @_; - my @fds = $recv_cmd->($s2, my $buf, $len); + my @fds = $recv_cmd->($s2, my $buf, $len // $MY_MAX_ARG_STRLEN); return if scalar(@fds) && !defined($fds[0]); my $n = length($buf) or return 0; my $nfd = 0; @@ -282,191 +240,201 @@ sub recv_and_run { undef $buf; my $sub = shift @$args; eval { $self->$sub(@$args) }; - warn "$$ wq_worker: $@" if $@; + warn "$$ $0 wq_worker: $sub: $@" if $@; delete @$self{0..($nfd-1)}; $n; } -sub wq_worker_loop ($) { - my ($self) = @_; - my $wqw = PublicInbox::WQWorker->new($self); +sub wq_worker_loop ($$) { + my ($self, $bcast2) = @_; + my $wqw = PublicInbox::WQWorker->new($self, $self->{-wq_s2}); + PublicInbox::WQWorker->new($self, $bcast2) if $bcast2; PublicInbox::DS->SetPostLoopCallback(sub { $wqw->{sock} }); - PublicInbox::DS->EventLoop; + PublicInbox::DS::event_loop(); PublicInbox::DS->Reset; } -sub do_sock_stream { # via wq_do, for big requests +sub do_sock_stream { # via wq_io_do, for big requests my ($self, $len) = @_; - recv_and_run($self, delete $self->{0}, $len, 1); + recv_and_run($self, my $s2 = delete $self->{0}, $len, 1); +} + +sub wq_broadcast { + my ($self, $sub, @args) = @_; + if (my $wkr = $self->{-wq_workers}) { + my $buf = ipc_freeze([$sub, @args]); + for my $bcast1 (values %$wkr) { + my $sock = $bcast1 // $self->{-wq_s1} // next; + send($sock, $buf, MSG_EOR) // croak "send: $!"; + # XXX shouldn't have to deal with EMSGSIZE here... + } + } else { + eval { $self->$sub(@args) }; + warn "wq_broadcast: $@" if $@; + } } -sub wq_do { # always async +sub stream_in_full ($$$) { + my ($s1, $fds, $buf) = @_; + socketpair(my $r, my $w, AF_UNIX, SOCK_STREAM, 0) or + croak "socketpair: $!"; + my $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 += $x; + } +} + +sub wq_io_do { # always async my ($self, $sub, $ios, @args) = @_; if (my $s1 = $self->{-wq_s1}) { # run in worker my $fds = [ map { fileno($_) } @$ios ]; 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 += $x; + if (length($buf) > $MY_MAX_ARG_STRLEN) { + stream_in_full($s1, $fds, $buf); + } else { + my $n = $send_cmd->($s1, $fds, $buf, MSG_EOR); + return if defined($n); # likely + $!{ETOOMANYREFS} and + croak "sendmsg: $! (check RLIMIT_NOFILE)"; + $!{EMSGSIZE} ? stream_in_full($s1, $fds, $buf) : + croak("sendmsg: $!"); } } else { @$self{0..$#$ios} = @$ios; eval { $self->$sub(@args) }; - warn "wq_do: $@" if $@; + warn "wq_io_do: $@" if $@; delete @$self{0..$#$ios}; # don't close } } -sub _wq_worker_start ($$$) { - my ($self, $oldset, $fields) = @_; +sub wq_sync_run { + my ($self, $wantarray, $sub, @args) = @_; + if ($wantarray) { + my @ret = eval { $self->$sub(@args) }; + ipc_return($self->{0}, \@ret, $@); + } else { # '' => wantscalar + my $ret = eval { $self->$sub(@args) }; + ipc_return($self->{0}, \$ret, $@); + } +} + +sub wq_do { + my ($self, $sub, @args) = @_; + if (defined(wantarray)) { + pipe(my ($r, $w)) or die "pipe: $!"; + wq_io_do($self, 'wq_sync_run', [ $w ], wantarray, $sub, @args); + undef $w; + _wait_return($r, $sub); + } else { + wq_io_do($self, $sub, [], @args); + } +} + +sub prepare_nonblock { + ($_[0]->{-wq_s1} // die 'BUG: no {-wq_s1}')->blocking(0); + require PublicInbox::WQBlocked; +} + +sub wq_nonblock_do { # always async + my ($self, $sub, @args) = @_; + my $buf = ipc_freeze([$sub, @args]); + if ($self->{wqb}) { # saturated once, assume saturated forever + $self->{wqb}->flush_send($buf); + } else { + $send_cmd->($self->{-wq_s1}, [], $buf, MSG_EOR) // + ($!{EAGAIN} ? PublicInbox::WQBlocked->new($self, $buf) + : croak("sendmsg: $!")); + } +} + +sub _wq_worker_start { + my ($self, $oldset, $fields, $one, @cb_args) = @_; + my ($bcast1, $bcast2); + $one or socketpair($bcast1, $bcast2, AF_UNIX, $SEQPACKET, 0) or + die "socketpair: $!"; my $seed = rand(0xffffffff); my $pid = fork // die "fork: $!"; if ($pid == 0) { srand($seed); + eval { Net::SSLeay::randomize() }; + undef $bcast1; eval { PublicInbox::DS->Reset }; - delete @$self{qw(-wq_s1 -wq_workers -wq_ppid)}; - $SIG{$_} = 'IGNORE' for (qw(PIPE)); + delete @$self{qw(-wq_s1 -wq_ppid)}; + $self->{-wq_worker_nr} = + keys %{delete($self->{-wq_workers}) // {}}; $SIG{$_} = 'DEFAULT' for (qw(TTOU TTIN TERM QUIT INT CHLD)); - local $0 = $self->{-wq_ident}; - PublicInbox::DS::sig_setmask($oldset); + local $0 = $one ? $self->{-wq_ident} : + "$self->{-wq_ident} $self->{-wq_worker_nr}"; # ensure we properly exit even if warn() dies: my $end = PublicInbox::OnDestroy->new($$, sub { exit(!!$@) }); eval { $fields //= {}; local @$self{keys %$fields} = values(%$fields); my $on_destroy = $self->ipc_atfork_child; - local %SIG = %SIG; - wq_worker_loop($self); + local @SIG{keys %SIG} = values %SIG; + PublicInbox::DS::sig_setmask($oldset); + wq_worker_loop($self, $bcast2); }; warn "worker $self->{-wq_ident} PID:$$ died: $@" if $@; undef $end; # trigger exit } else { - $self->{-wq_workers}->{$pid} = \undef; + $self->{-wq_workers}->{$pid} = $bcast1; + awaitpid($pid, \&ipc_worker_reap, $self, @cb_args); } } # starts workqueue workers if Sereal or Storable is installed sub wq_workers_start { - my ($self, $ident, $nr_workers, $oldset, $fields) = @_; - ($enc && $send_cmd && $recv_cmd && defined($SEQPACKET)) or return; + my ($self, $ident, $nr_workers, $oldset, $fields, @cb_args) = @_; + ($send_cmd && $recv_cmd && defined($SEQPACKET)) or return; return if $self->{-wq_s1}; # idempotent $self->{-wq_s1} = $self->{-wq_s2} = undef; socketpair($self->{-wq_s1}, $self->{-wq_s2}, AF_UNIX, $SEQPACKET, 0) or die "socketpair: $!"; $self->ipc_atfork_prepare; - $nr_workers //= 4; - $nr_workers = $WQ_MAX_WORKERS if $nr_workers > $WQ_MAX_WORKERS; + $nr_workers //= $self->{-wq_nr_workers}; # was set earlier my $sigset = $oldset // PublicInbox::DS::block_signals(); $self->{-wq_workers} = {}; $self->{-wq_ident} = $ident; - _wq_worker_start($self, $sigset, $fields) for (1..$nr_workers); + my $one = $nr_workers == 1; + $self->{-wq_nr_workers} = $nr_workers; + for (1..$nr_workers) { + _wq_worker_start($self, $sigset, $fields, $one, @cb_args); + } PublicInbox::DS::sig_setmask($sigset) unless $oldset; $self->{-wq_ppid} = $$; } -sub wq_worker_incr { # SIGTTIN handler - 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, $fields); - PublicInbox::DS::sig_setmask($sigset) unless $oldset; -} - -sub wq_exit { # wakes up wq_worker_decr_wait - send($_[0]->{-wq_s2}, $$, MSG_EOR) // die "$$ send: $!"; - exit; -} - -sub wq_worker_decr { # SIGTTOU handler, kills first idle worker +sub wq_close { my ($self) = @_; - return unless wq_workers($self); - my $s2 = $self->{-wq_s2} // die 'BUG: no wq_s2'; - $self->wq_do('wq_exit', [ $s2, $s2, $s2 ]); - # caller must call wq_worker_decr_wait in main loop -} - -sub wq_worker_decr_wait { - my ($self, $timeout) = @_; - return if $self->{-wq_ppid} != $$; # can't reap siblings or parents - my $s1 = $self->{-wq_s1} // croak 'BUG: no wq_s1'; - vec(my $rin = '', fileno($s1), 1) = 1; - select(my $rout = $rin, undef, undef, $timeout) or - croak 'timed out waiting for wq_exit'; - recv($s1, my $pid, 64, 0) // croak "recv: $!"; - my $workers = $self->{-wq_workers} // croak 'BUG: no wq_workers'; - delete $workers->{$pid} // croak "BUG: PID:$pid invalid"; - dwaitpid($pid, \&ipc_worker_reap, $self); -} - -# set or retrieve number of workers -sub wq_workers { - my ($self, $nr) = @_; - my $cur = $self->{-wq_workers} or return; - if (defined $nr) { - while (scalar(keys(%$cur)) > $nr) { - $self->wq_worker_decr; - $self->wq_worker_decr_wait; - } - $self->wq_worker_incr while scalar(keys(%$cur)) < $nr; + if (my $wqb = delete $self->{wqb}) { + $wqb->enq_close; } - scalar(keys(%$cur)); -} - -sub wq_close { - my ($self, $nohang) = @_; delete @$self{qw(-wq_s1 -wq_s2)} or return; - my $ppid = delete $self->{-wq_ppid} or return; - my $workers = delete $self->{-wq_workers} // die 'BUG: no wq_workers'; - return if $ppid != $$; # can't reap siblings or parents - 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', @$pids; + return if ($self->{-wq_ppid} // -1) != $$; + awaitpid($_) for keys %{$self->{-wq_workers}}; } sub wq_kill { my ($self, $sig) = @_; - my $workers = $self->{-wq_workers} or return; - kill($sig // 'TERM', keys %$workers); + kill($sig // 'TERM', keys %{$self->{-wq_workers}}); } -sub WQ_MAX_WORKERS { $WQ_MAX_WORKERS } - sub DESTROY { my ($self) = @_; my $ppid = $self->{-wq_ppid}; wq_kill($self) if $ppid && $ppid == $$; 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';