X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiXSearch.pm;h=2d399653591d1323749ff615929903ffcaa2bd6c;hb=f0731b9b653640afd8078aed994814b3049f230a;hp=2dc44414b29f12b17ffc4ccaaa8b6be7069bb4cb;hpb=5180ed0a1cd65139a6ba6b3c64e97f8c2c126204;p=public-inbox.git diff --git a/lib/PublicInbox/LeiXSearch.pm b/lib/PublicInbox/LeiXSearch.pm index 2dc44414..2d399653 100644 --- a/lib/PublicInbox/LeiXSearch.pm +++ b/lib/PublicInbox/LeiXSearch.pm @@ -8,15 +8,15 @@ package PublicInbox::LeiXSearch; use strict; use v5.10.1; use parent qw(PublicInbox::LeiSearch PublicInbox::IPC); -use PublicInbox::DS qw(dwaitpid now); +use PublicInbox::DS qw(now); use PublicInbox::PktOp qw(pkt_do); -use PublicInbox::Import; use File::Temp 0.19 (); # 0.19 for ->newdir use File::Spec (); use PublicInbox::Search qw(xap_terms); use PublicInbox::Spawn qw(popen_rd spawn which); use PublicInbox::MID qw(mids); use PublicInbox::Smsg; +use PublicInbox::Eml; use Fcntl qw(SEEK_SET F_SETFL O_APPEND O_RDWR); sub new { @@ -99,31 +99,44 @@ sub _mset_more ($$) { $size >= $mo->{limit} && (($mo->{offset} += $size) < $mo->{limit}); } -# $startq will EOF when query_prepare is done augmenting and allow +# $startq will EOF when do_augment is done augmenting and allow # query_mset and query_thread_mset to proceed. sub wait_startq ($) { - my ($startq) = @_; - $_[0] = undef; - read($startq, my $query_prepare_done, 1); + my ($lei) = @_; + my $startq = delete $lei->{startq} or return; + while (1) { + my $n = sysread($startq, my $do_augment_done, 1); + if (defined $n) { + return if $n == 0; # no MUA + if ($do_augment_done eq 'q') { + $lei->{opt}->{quiet} = 1; + delete $lei->{opt}->{verbose}; + delete $lei->{-progress}; + } else { + $lei->fail("$$ WTF `$do_augment_done'"); + } + return; + } + return $lei->fail("$$ wait_startq: $!") unless $!{EINTR}; + } } sub mset_progress { my $lei = shift; - return unless $lei->{-progress}; + return if $lei->{early_mua} || !$lei->{-progress}; if ($lei->{pkt_op_p}) { pkt_do($lei->{pkt_op_p}, 'mset_progress', @_); } else { # single lei-daemon consumer my ($desc, $mset_size, $mset_total_est) = @_; $lei->{-mset_total} += $mset_size; - $lei->err("# $desc $mset_size/$mset_total_est"); + $lei->qerr("# $desc $mset_size/$mset_total_est"); } } -sub query_thread_mset { # for --thread +sub query_thread_mset { # for --threads my ($self, $ibxish) = @_; local $0 = "$0 query_thread_mset"; my $lei = $self->{lei}; - my $startq = delete $lei->{startq}; my ($srch, $over) = ($ibxish->search, $ibxish->over); my $desc = $ibxish->{inboxdir} // $ibxish->{topdir}; return warn("$desc not indexed by Xapian\n") unless ($srch && $over); @@ -141,7 +154,7 @@ sub query_thread_mset { # for --thread while ($over->expand_thread($ctx)) { for my $n (@{$ctx->{xids}}) { my $smsg = $over->get_art($n) or next; - wait_startq($startq) if $startq; + wait_startq($lei); my $mitem = delete $n2item{$smsg->{num}}; $each_smsg->($smsg, $mitem); } @@ -152,11 +165,10 @@ sub query_thread_mset { # for --thread $lei->{ovv}->ovv_atexit_child($lei); } -sub query_mset { # non-parallel for non-"--thread" users +sub query_mset { # non-parallel for non-"--threads" users my ($self) = @_; local $0 = "$0 query_mset"; my $lei = $self->{lei}; - my $startq = delete $lei->{startq}; my $mo = { %{$lei->{mset_opt}} }; my $mset; for my $loc (locals($self)) { @@ -169,7 +181,7 @@ sub query_mset { # non-parallel for non-"--thread" users $mset->size, $mset->get_matches_estimated); for my $mitem ($mset->items) { my $smsg = smsg_for($self, $mitem) or next; - wait_startq($startq) if $startq; + wait_startq($lei); $each_smsg->($smsg, $mitem); } } while (_mset_more($mset, $mo)); @@ -177,14 +189,15 @@ sub query_mset { # non-parallel for non-"--thread" users $lei->{ovv}->ovv_atexit_child($lei); } -sub each_eml { # callback for MboxReader->mboxrd +sub each_remote_eml { # callback for MboxReader->mboxrd my ($eml, $self, $lei, $each_smsg) = @_; + $lei->{sto}->ipc_do('set_eml', $eml) if $lei->{sto}; # --import-remote my $smsg = bless {}, 'PublicInbox::Smsg'; $smsg->populate($eml); $smsg->parse_references($eml, mids($eml)); $smsg->{$_} //= '' for qw(from to cc ds subject references mid); delete @$smsg{qw(From Subject -ds -ts)}; - if (my $startq = delete($lei->{startq})) { wait_startq($startq) } + wait_startq($lei); if ($lei->{-progress}) { ++$lei->{-nr_remote_eml}; my $now = now(); @@ -198,90 +211,66 @@ sub each_eml { # callback for MboxReader->mboxrd $each_smsg->($smsg, undef, $eml); } -# PublicInbox::OnDestroy callback -sub kill_reap { - my ($pid) = @_; - kill('KILL', $pid); # spawn() blocks other signals - waitpid($pid, 0); -} - sub query_remote_mboxrd { my ($self, $uris) = @_; local $0 = "$0 query_remote_mboxrd"; local $SIG{TERM} = sub { exit(0) }; # for DESTROY (File::Temp, $reap) my $lei = $self->{lei}; - my ($opt, $env) = @$lei{qw(opt env)}; + my $opt = $lei->{opt}; my @qform = (q => $lei->{mset_opt}->{qstr}, x => 'm'); - push(@qform, t => 1) if $opt->{thread}; - my @cmd = ($self->{curl}, qw(-sSf -d), ''); + push(@qform, t => 1) if $opt->{threads}; my $verbose = $opt->{verbose}; - my $reap; + my ($reap_tail, $reap_curl); my $cerr = File::Temp->new(TEMPLATE => 'curl.err-XXXX', TMPDIR => 1); fcntl($cerr, F_SETFL, O_APPEND|O_RDWR) or warn "set O_APPEND: $!"; - my $rdr = { 2 => $cerr }; - my $coff = 0; + my $rdr = { 2 => $cerr, pgid => 0 }; + my $sigint_reap = $lei->can('sigint_reap'); if ($verbose) { # spawn a process to force line-buffering, otherwise curl # will write 1 character at-a-time and parallel outputs # mmmaaayyy llloookkk llliiikkkeee ttthhhiiisss - push @cmd, '-v'; - my $o = { 1 => $lei->{2}, 2 => $lei->{2} }; + my $o = { 1 => $lei->{2}, 2 => $lei->{2}, pgid => 0 }; my $pid = spawn(['tail', '-f', $cerr->filename], undef, $o); - $reap = PublicInbox::OnDestroy->new(\&kill_reap, $pid); + $reap_tail = PublicInbox::OnDestroy->new($sigint_reap, $pid); } - for my $o ($lei->curl_opt) { - $o =~ s/\|[a-z0-9]\b//i; # remove single char short option - if ($o =~ s/=[is]@\z//) { - my $ary = $opt->{$o} or next; - push @cmd, map { ("--$o", $_) } @$ary; - } elsif ($o =~ s/=[is]\z//) { - my $val = $opt->{$o} // next; - push @cmd, "--$o", $val; - } elsif ($opt->{$o}) { - push @cmd, "--$o"; - } - } - $opt->{torsocks} = 'false' if $opt->{'no-torsocks'}; - my $tor = $opt->{torsocks} //= 'auto'; + my $curl = PublicInbox::LeiCurl->new($lei, $self->{curl}) or return; + push @$curl, '-s', '-d', ''; my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei); for my $uri (@$uris) { $lei->{-current_url} = $uri->as_string; $lei->{-nr_remote_eml} = 0; $uri->query_form(@qform); - my $cmd = [ @cmd, $uri->as_string ]; - if ($tor eq 'auto' && substr($uri->host, -6) eq '.onion' && - (($env->{LD_PRELOAD}//'') !~ /torsocks/)) { - unshift @$cmd, which('torsocks'); - } elsif (PublicInbox::Config::git_bool($tor)) { - unshift @$cmd, which('torsocks'); - } - - # continue anyways if torsocks is missing; a proxy may be - # specified via CLI, curlrc, environment variable, or even - # firewall rule - shift(@$cmd) if !$cmd->[0]; - - $lei->err("# @$cmd") if $verbose; - my ($fh, $pid) = popen_rd($cmd, $env, $rdr); + my $cmd = $curl->for_uri($lei, $uri); + $lei->qerr("# $cmd"); + my ($fh, $pid) = popen_rd($cmd, undef, $rdr); + $reap_curl = PublicInbox::OnDestroy->new($sigint_reap, $pid); $fh = IO::Uncompress::Gunzip->new($fh); - PublicInbox::MboxReader->mboxrd($fh, \&each_eml, $self, + PublicInbox::MboxReader->mboxrd($fh, \&each_remote_eml, $self, $lei, $each_smsg); - waitpid($pid, 0) == $pid or die "BUG: waitpid (curl): $!"; + my $err = waitpid($pid, 0) == $pid ? undef + : "BUG: waitpid($cmd): $!"; + @$reap_curl = (); # cancel OnDestroy + die $err if $err; + my $nr = $lei->{-nr_remote_eml}; + if ($nr && $lei->{sto}) { + my $wait = $lei->{sto}->ipc_do('done'); + } if ($? == 0) { - my $nr = $lei->{-nr_remote_eml}; mset_progress($lei, $lei->{-current_url}, $nr, $nr); next; } - seek($cerr, $coff, SEEK_SET) or warn "seek(curl stderr): $!\n"; - my $e = do { local $/; <$cerr> } // - die "read(curl stderr): $!\n"; - $coff += length($e); - truncate($cerr, 0); - next if (($? >> 8) == 22 && $e =~ /\b404\b/); - $lei->child_error($?); + $err = ''; + if (-s $cerr) { + seek($cerr, 0, SEEK_SET) or + $lei->err("seek($cmd stderr): $!"); + $err = do { local $/; <$cerr> } // + "read($cmd stderr): $!"; + truncate($cerr, 0) or + $lei->err("truncate($cmd stderr): $!"); + } + next if (($? >> 8) == 22 && $err =~ /\b404\b/); $uri->query_form(q => $lei->{mset_opt}->{qstr}); - # --verbose already showed the error via tail(1) - $lei->err("E: $uri \$?=$?\n", $verbose ? () : $e); + $lei->child_error($?, "E: <$uri> $err"); } undef $each_smsg; $lei->{ovv}->ovv_atexit_child($lei); @@ -309,12 +298,18 @@ sub git_tmp ($) { $git; } +sub xsearch_done_wait { # dwaitpid callback + my ($arg, $pid) = @_; + my ($wq, $lei) = @$arg; + $lei->child_error($?, 'non-fatal error from '.ref($wq)) if $?; +} + sub query_done { # EOF callback for main daemon my ($lei) = @_; my $l2m = delete $lei->{l2m}; - $l2m->wq_wait_old($lei) if $l2m; + $l2m->wq_wait_old(\&xsearch_done_wait, $lei) if $l2m; if (my $lxs = delete $lei->{lxs}) { - $lxs->wq_wait_old($lei); + $lxs->wq_wait_old(\&xsearch_done_wait, $lei); } $lei->{ovv}->ovv_end($lei); if ($l2m) { # close() calls LeiToMail reap_compress @@ -326,7 +321,12 @@ Error closing $lei->{ovv}->{dst}: $! } $lei->{1} = $out; } - $l2m->lock_free ? $l2m->poke_dst : $lei->start_mua; + if ($l2m->lock_free) { + $l2m->poke_dst; + $lei->poke_mua; + } else { # mbox users + $lei->start_mua; + } } $lei->{-progress} and $lei->err('# ', $lei->{-mset_total} // 0, " matches"); @@ -335,38 +335,48 @@ Error closing $lei->{ovv}->{dst}: $! sub do_post_augment { my ($lei) = @_; - eval { $lei->{l2m}->post_augment($lei) }; - if (my $err = $@) { + my $l2m = $lei->{l2m} or die 'BUG: unexpected do_post_augment'; + my $err; + eval { $l2m->post_augment($lei) }; + $err = $@; + if ($err) { if (my $lxs = delete $lei->{lxs}) { $lxs->wq_kill; - $lxs->wq_close; + $lxs->wq_close(0, undef, $lei); } $lei->fail("$err"); } - close(delete $lei->{au_done}); # triggers wait_startq + if (!$err && delete $lei->{early_mua}) { # non-augment case + $lei->start_mua; + } + close(delete $lei->{au_done}); # triggers wait_startq in lei_xsearch +} + +sub incr_post_augment { # called whenever an l2m shard finishes augment + my ($lei) = @_; + my $l2m = $lei->{l2m} or die 'BUG: unexpected incr_post_augment'; + return if ++$lei->{nr_post_augment} != $l2m->{-wq_nr_workers}; + do_post_augment($lei); } my $MAX_PER_HOST = 4; sub concurrency { my ($self, $opt) = @_; - my $nl = $opt->{thread} ? locals($self) : 1; + my $nl = $opt->{threads} ? locals($self) : 1; my $nr = remotes($self); $nr = $MAX_PER_HOST if $nr > $MAX_PER_HOST; $nl + $nr; } sub start_query { # always runs in main (lei-daemon) process - my ($self, $lei) = @_; - if (my $l2m = $lei->{l2m}) { - $lei->start_mua if $l2m->lock_free; - } - if ($lei->{opt}->{thread}) { + my ($self) = @_; + if ($self->{threads}) { for my $ibxish (locals($self)) { - $self->wq_do('query_thread_mset', [], $ibxish); + $self->wq_io_do('query_thread_mset', [], $ibxish); } } elsif (locals($self)) { - $self->wq_do('query_mset', []); + $self->wq_io_do('query_mset', []); } my $i = 0; my $q = []; @@ -374,77 +384,70 @@ sub start_query { # always runs in main (lei-daemon) process push @{$q->[$i++ % $MAX_PER_HOST]}, $uri; } for my $uris (@$q) { - $self->wq_do('query_remote_mboxrd', [], $uris); + $self->wq_io_do('query_remote_mboxrd', [], $uris); } + $self->wq_close(1); # lei_xsearch workers stop when done +} + +sub incr_start_query { # called whenever an l2m shard starts do_post_auth + my ($self, $l2m) = @_; + return if ++$self->{nr_start_query} != $l2m->{-wq_nr_workers}; + start_query($self); } sub ipc_atfork_child { my ($self) = @_; $self->{lei}->lei_atfork_child; + $SIG{__WARN__} = PublicInbox::Eml::warn_ignore_cb(); $self->SUPER::ipc_atfork_child; } -sub query_prepare { # called by wq_do - my ($self) = @_; - local $0 = "$0 query_prepare"; - my $lei = $self->{lei}; - eval { $lei->{l2m}->do_augment($lei) }; - $lei->fail($@) if $@; - pkt_do($lei->{pkt_op_p}, '.') == 1 or die "do_post_augment trigger: $!" -} - -sub fail_handler ($;$$) { - my ($lei, $code, $io) = @_; - for my $f (qw(lxs l2m)) { - my $wq = delete $lei->{$f} or next; - $wq->wq_wait_old($lei) if $wq->wq_kill_old; # lei-daemon - } - close($io) if $io; # needed to avoid warnings on SIGPIPE - $lei->x_it($code // (1 >> 8)); -} - -sub sigpipe_handler { # handles SIGPIPE from l2m/lxs workers - fail_handler($_[0], 13, delete $_[0]->{1}); -} - sub do_query { my ($self, $lei) = @_; + my $l2m = $lei->{l2m}; my $ops = { - '|' => [ \&sigpipe_handler, $lei ], - '!' => [ \&fail_handler, $lei ], + '|' => [ $lei->can('sigpipe_handler'), $lei ], + '!' => [ $lei->can('fail_handler'), $lei ], '.' => [ \&do_post_augment, $lei ], + '+' => [ \&incr_post_augment, $lei ], '' => [ \&query_done, $lei ], 'mset_progress' => [ \&mset_progress, $lei ], 'x_it' => [ $lei->can('x_it'), $lei ], 'child_error' => [ $lei->can('child_error'), $lei ], + 'incr_start_query' => [ \&incr_start_query, $self, $l2m ], }; + $lei->{auth}->op_merge($ops, $l2m) if $l2m && $lei->{auth}; ($lei->{pkt_op_c}, $lei->{pkt_op_p}) = PublicInbox::PktOp->pair($ops); $lei->{1}->autoflush(1); $lei->start_pager if delete $lei->{need_pager}; $lei->{ovv}->ovv_begin($lei); - my $l2m = $lei->{l2m}; if ($l2m) { $l2m->pre_augment($lei); - $l2m->wq_workers_start('lei2mail', $l2m->{jobs}, + if ($lei->{opt}->{augment} && delete $lei->{early_mua}) { + $lei->start_mua; + } + $l2m->wq_workers_start('lei2mail', undef, $lei->oldset, { lei => $lei }); pipe($lei->{startq}, $lei->{au_done}) or die "pipe: $!"; # 1031: F_SETPIPE_SZ fcntl($lei->{startq}, 1031, 4096) if $^O eq 'linux'; } - if (!$lei->{opt}->{thread} && locals($self)) { # for query_mset + if (!$lei->{opt}->{threads} && locals($self)) { # for query_mset # lei->{git_tmp} is set for wq_wait_old so we don't # delete until all lei2mail + lei_xsearch workers are reaped $lei->{git_tmp} = $self->{git_tmp} = git_tmp($self); } - $self->wq_workers_start('lei_xsearch', $self->{jobs}, + $self->wq_workers_start('lei_xsearch', undef, $lei->oldset, { lei => $lei }); my $op = delete $lei->{pkt_op_c}; delete $lei->{pkt_op_p}; - $l2m->wq_close(1) if $l2m; + $self->{threads} = $lei->{opt}->{threads}; + if ($l2m) { + $l2m->net_merge_complete unless $lei->{auth}; + } else { + start_query($self); + } $lei->event_step_init; # wait for shutdowns - $self->wq_do('query_prepare', []) if $l2m; - start_query($self, $lei); - $self->wq_close(1); # lei_xsearch workers stop when done if ($lei->{oneshot}) { while ($op->{sock}) { $op->event_step } } @@ -455,6 +458,7 @@ sub add_uri { if (my $curl = $self->{curl} //= which('curl') // 0) { require PublicInbox::MboxReader; require IO::Uncompress::Gunzip; + require PublicInbox::LeiCurl; push @{$self->{remotes}}, $uri; } else { warn "curl missing, ignoring $uri\n";