X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiXSearch.pm;h=1e5d7ca6b2f106ffdfcd10614545a5dacce6ad06;hb=cfc2f64069e245a700b60113705be477857c51e5;hp=afd2fc24793328fc63e23e523320791d145afaf9;hpb=ac35655d75706ce297a71b6537334a2f690b6247;p=public-inbox.git diff --git a/lib/PublicInbox/LeiXSearch.pm b/lib/PublicInbox/LeiXSearch.pm index afd2fc24..1e5d7ca6 100644 --- a/lib/PublicInbox/LeiXSearch.pm +++ b/lib/PublicInbox/LeiXSearch.pm @@ -8,14 +8,15 @@ package PublicInbox::LeiXSearch; use strict; use v5.10.1; use parent qw(PublicInbox::LeiSearch PublicInbox::IPC); -use PublicInbox::DS qw(dwaitpid); -use PublicInbox::OpPipe; -use PublicInbox::Import; +use PublicInbox::DS qw(now); +use PublicInbox::PktOp qw(pkt_do); use File::Temp 0.19 (); # 0.19 for ->newdir use File::Spec (); use PublicInbox::Search qw(xap_terms); -use PublicInbox::Spawn qw(popen_rd); +use PublicInbox::Spawn qw(popen_rd spawn which); use PublicInbox::MID qw(mids); +use PublicInbox::Smsg; +use Fcntl qw(SEEK_SET F_SETFL O_APPEND O_RDWR); sub new { my ($class) = @_; @@ -32,7 +33,7 @@ sub attach_external { my $srch = $ibxish->search or return warn("$desc not indexed for Xapian\n"); my @shards = $srch->xdb_shards_flat or - return warn("$desc has no Xapian shardsXapian\n"); + return warn("$desc has no Xapian shards\n"); if (delete $self->{xdb}) { # XXX: do we need this? # clobber existing {xdb} if amending @@ -94,7 +95,7 @@ sub over {} sub _mset_more ($$) { my ($mset, $mo) = @_; my $size = $mset->size; - $size && (($mo->{offset} += $size) < ($mo->{limit} // 10000)); + $size >= $mo->{limit} && (($mo->{offset} += $size) < $mo->{limit}); } # $startq will EOF when query_prepare is done augmenting and allow @@ -105,24 +106,33 @@ sub wait_startq ($) { read($startq, my $query_prepare_done, 1); } +sub mset_progress { + my $lei = shift; + return unless $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"); + } +} + sub query_thread_mset { # for --thread - my ($self, $lei, $ibxish) = @_; + my ($self, $ibxish) = @_; local $0 = "$0 query_thread_mset"; - my $startq = delete $self->{5}; - my %sig = $lei->atfork_child_wq($self); - local @SIG{keys %sig} = values %sig; - + my $lei = $self->{lei}; + my $startq = delete $lei->{startq}; my ($srch, $over) = ($ibxish->search, $ibxish->over); - unless ($srch && $over) { - my $desc = $ibxish->{inboxdir} // $ibxish->{topdir}; - warn "$desc not indexed by Xapian\n"; - return; - } + my $desc = $ibxish->{inboxdir} // $ibxish->{topdir}; + return warn("$desc not indexed by Xapian\n") unless ($srch && $over); my $mo = { %{$lei->{mset_opt}} }; my $mset; my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $ibxish); do { $mset = $srch->mset($mo->{qstr}, $mo); + mset_progress($lei, $desc, $mset->size, + $mset->get_matches_estimated); my $ids = $srch->mset_to_artnums($mset, $mo); my $ctx = { ids => $ids }; my $i = 0; @@ -142,11 +152,10 @@ sub query_thread_mset { # for --thread } sub query_mset { # non-parallel for non-"--thread" users - my ($self, $lei) = @_; + my ($self) = @_; local $0 = "$0 query_mset"; - my $startq = delete $self->{5}; - my %sig = $lei->atfork_child_wq($self); - local @SIG{keys %sig} = values %sig; + my $lei = $self->{lei}; + my $startq = delete $lei->{startq}; my $mo = { %{$lei->{mset_opt}} }; my $mset; for my $loc (locals($self)) { @@ -155,6 +164,8 @@ sub query_mset { # non-parallel for non-"--thread" users my $each_smsg = $lei->{ovv}->ovv_each_smsg_cb($lei, $self); do { $mset = $self->mset($mo->{qstr}, $mo); + mset_progress($lei, 'xsearch', $mset->size, + $mset->size, $mset->get_matches_estimated); for my $mitem ($mset->items) { my $smsg = smsg_for($self, $mitem) or next; wait_startq($startq) if $startq; @@ -169,76 +180,95 @@ sub each_eml { # callback for MboxReader->mboxrd my ($eml, $self, $lei, $each_smsg) = @_; my $smsg = bless {}, 'PublicInbox::Smsg'; $smsg->populate($eml); - PublicInbox::OverIdx::parse_references($smsg, $eml, mids($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($self->{5})) { wait_startq($startq) } + if (my $startq = delete($lei->{startq})) { wait_startq($startq) } + if ($lei->{-progress}) { + ++$lei->{-nr_remote_eml}; + my $now = now(); + my $next = $lei->{-next_progress} //= ($now + 1); + if ($now > $next) { + $lei->{-next_progress} = $now + 1; + my $nr = $lei->{-nr_remote_eml}; + $lei->err("# $lei->{-current_url} $nr/?"); + } + } $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, $lei, $uris) = @_; + my ($self, $uris) = @_; local $0 = "$0 query_remote_mboxrd"; - my %sig = $lei->atfork_child_wq($self); # keep $self->{5} startq - local @SIG{keys %sig} = values %sig; + local $SIG{TERM} = sub { exit(0) }; # for DESTROY (File::Temp, $reap) + my $lei = $self->{lei}; my ($opt, $env) = @$lei{qw(opt env)}; my @qform = (q => $lei->{mset_opt}->{qstr}, x => 'm'); push(@qform, t => 1) if $opt->{thread}; - my @cmd = (qw(curl -sSf -d), ''); my $verbose = $opt->{verbose}; - push @cmd, '-v' if $verbose; - 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"; - } + my $reap; + 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; + 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 + my $o = { 1 => $lei->{2}, 2 => $lei->{2} }; + my $pid = spawn(['tail', '-f', $cerr->filename], undef, $o); + $reap = PublicInbox::OnDestroy->new(\&kill_reap, $pid); } - $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, 'torsocks'; - } elsif (PublicInbox::Config::git_bool($tor)) { - unshift @$cmd, 'torsocks'; - } + my $cmd = $curl->for_uri($lei, $uri); $lei->err("# @$cmd") if $verbose; - $? = 0; - my $fh = popen_rd($cmd, $env, { 2 => $lei->{2} }); + my ($fh, $pid) = popen_rd($cmd, $env, $rdr); $fh = IO::Uncompress::Gunzip->new($fh); - eval { - PublicInbox::MboxReader->mboxrd($fh, \&each_eml, $self, - $lei, $each_smsg); - }; - return $lei->fail("E: @$cmd: $@") if $@; - if (($? >> 8) == 22) { # HTTP 404 from curl(1) - $uri->query_form(q => $lei->{mset_opt}->{qstr}); - $lei->err('# no results from '.$uri->as_string); - } elsif ($?) { - $uri->query_form(q => $lei->{mset_opt}->{qstr}); - $lei->err('E: '.$uri->as_string); - $lei->child_error($?); + PublicInbox::MboxReader->mboxrd($fh, \&each_eml, $self, + $lei, $each_smsg); + waitpid($pid, 0) == $pid or die "BUG: waitpid (curl): $!"; + 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($?); + $uri->query_form(q => $lei->{mset_opt}->{qstr}); + # --verbose already showed the error via tail(1) + $lei->err("E: $uri \$?=$?\n", $verbose ? () : $e); } undef $each_smsg; $lei->{ovv}->ovv_atexit_child($lei); } -sub git { +# called by LeiOverview::each_smsg_cb +sub git { $_[0]->{git_tmp} // die 'BUG: caller did not set {git_tmp}' } + +sub git_tmp ($) { my ($self) = @_; my (%seen, @dirs); - my $tmp = File::Temp->newdir('lei_xsrch_git-XXXXXXXX', TMPDIR => 1); - for my $ibx (@{$self->{shard2ibx} // []}) { - my $d = File::Spec->canonpath($ibx->git->{git_dir}); + my $tmp = File::Temp->newdir("lei_xsearch_git.$$-XXXX", TMPDIR => 1); + for my $ibxish (locals($self)) { + my $d = File::Spec->canonpath($ibxish->git->{git_dir}); $seen{$d} //= push @dirs, "$d/objects\n" } my $git_dir = $tmp->dirname; @@ -252,15 +282,15 @@ sub git { $git; } -sub query_done { # EOF callback +sub query_done { # EOF callback for main daemon my ($lei) = @_; - my $has_l2m = exists $lei->{l2m}; - for my $f (qw(lxs l2m)) { - my $wq = delete $lei->{$f} or next; - $wq->wq_wait_old; + my $l2m = delete $lei->{l2m}; + $l2m->wq_wait_old($lei) if $l2m; + if (my $lxs = delete $lei->{lxs}) { + $lxs->wq_wait_old($lei); } $lei->{ovv}->ovv_end($lei); - if ($has_l2m) { # close() calls LeiToMail reap_compress + if ($l2m) { # close() calls LeiToMail reap_compress if (my $out = delete $lei->{old_1}) { if (my $mbout = $lei->{1}) { close($mbout) or return $lei->fail(<<""); @@ -269,15 +299,16 @@ Error closing $lei->{ovv}->{dst}: $! } $lei->{1} = $out; } - $lei->start_mua; + $l2m->lock_free ? $l2m->poke_dst : $lei->start_mua; } + $lei->{-progress} and + $lei->err('# ', $lei->{-mset_total} // 0, " matches"); $lei->dclose; } sub do_post_augment { - my ($lei, $zpipe, $au_done) = @_; - my $l2m = $lei->{l2m} or die 'BUG: no {l2m}'; - eval { $l2m->post_augment($lei, $zpipe) }; + my ($lei) = @_; + eval { $lei->{l2m}->post_augment($lei) }; if (my $err = $@) { if (my $lxs = delete $lei->{lxs}) { $lxs->wq_kill; @@ -285,11 +316,10 @@ sub do_post_augment { } $lei->fail("$err"); } - close $au_done; # triggers wait_startq + close(delete $lei->{au_done}); # triggers wait_startq } my $MAX_PER_HOST = 4; -sub MAX_PER_HOST { $MAX_PER_HOST } sub concurrency { my ($self, $opt) = @_; @@ -300,13 +330,16 @@ sub concurrency { } sub start_query { # always runs in main (lei-daemon) process - my ($self, $io, $lei) = @_; + my ($self, $lei) = @_; + if (my $l2m = $lei->{l2m}) { + $lei->start_mua if $l2m->lock_free; + } if ($lei->{opt}->{thread}) { for my $ibxish (locals($self)) { - $self->wq_do('query_thread_mset', $io, $lei, $ibxish); + $self->wq_do('query_thread_mset', [], $ibxish); } } elsif (locals($self)) { - $self->wq_do('query_mset', $io, $lei); + $self->wq_do('query_mset', []); } my $i = 0; my $q = []; @@ -314,88 +347,87 @@ sub start_query { # always runs in main (lei-daemon) process push @{$q->[$i++ % $MAX_PER_HOST]}, $uri; } for my $uris (@$q) { - $self->wq_do('query_remote_mboxrd', $io, $lei, $uris); + $self->wq_do('query_remote_mboxrd', [], $uris); } - @$io = (); +} + +sub ipc_atfork_child { + my ($self) = @_; + $self->{lei}->lei_atfork_child; + $self->SUPER::ipc_atfork_child; } sub query_prepare { # called by wq_do - my ($self, $lei) = @_; + my ($self) = @_; local $0 = "$0 query_prepare"; - my %sig = $lei->atfork_child_wq($self); - -p $lei->{0} or die "BUG: \$done pipe expected"; - local @SIG{keys %sig} = values %sig; + my $lei = $self->{lei}; eval { $lei->{l2m}->do_augment($lei) }; $lei->fail($@) if $@; - syswrite($lei->{0}, '.') == 1 or die "do_post_augment trigger: $!"; -} - -sub sigpipe_handler { # handles SIGPIPE from l2m/lxs workers - my ($lei) = @_; - my $lxs = delete $lei->{lxs}; - if ($lxs && $lxs->wq_kill_old) { - kill 'PIPE', $$; - $lxs->wq_wait_old; - } - close(delete $lei->{1}) if $lei->{1}; + pkt_do($lei->{pkt_op_p}, '.') == 1 or die "do_post_augment trigger: $!" } sub do_query { - my ($self, $lei_orig) = @_; - my ($lei, @io) = $lei_orig->atfork_parent_wq($self); - $io[0] = undef; - pipe(my $done, $io[0]) or die "pipe $!"; - $lei_orig->{1}->autoflush(1); - - $lei_orig->event_step_init; # wait for shutdowns - my $done_op = { - '' => [ \&query_done, $lei_orig ], - '!' => [ \&sigpipe_handler, $lei_orig ] + my ($self, $lei) = @_; + my $ops = { + '|' => [ $lei->can('sigpipe_handler'), $lei ], + '!' => [ $lei->can('fail_handler'), $lei ], + '.' => [ \&do_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 ], }; - my $in_loop = exists $lei_orig->{sock}; - $done = PublicInbox::OpPipe->new($done, $done_op, $in_loop); + ($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) { - # may redirect $lei->{1} for mbox - my $zpipe = $l2m->pre_augment($lei_orig); - $io[1] = $lei_orig->{1}; - pipe(my ($startq, $au_done)) or die "pipe: $!"; - $done_op->{'.'} = [ \&do_post_augment, $lei_orig, - $zpipe, $au_done ]; - local $io[4] = *STDERR{GLOB}; # don't send l2m->{-wq_s1} - die "BUG: unexpected \$io[5]: $io[5]" if $io[5]; - $self->wq_do('query_prepare', \@io, $lei); - fcntl($startq, 1031, 4096) if $^O eq 'linux'; # F_SETPIPE_SZ - $io[5] = $startq; - $io[1] = $zpipe->[1] if $zpipe; + $l2m->pre_augment($lei); + $l2m->wq_workers_start('lei2mail', $l2m->{jobs}, + $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 + # 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); } - start_query($self, \@io, $lei); - $self->wq_close(1); - unless ($in_loop) { - # for the $lei->atfork_child_wq PIPE handler: - while ($done->{sock}) { $done->event_step } + $self->wq_workers_start('lei_xsearch', $self->{jobs}, + $lei->oldset, { lei => $lei }); + my $op = delete $lei->{pkt_op_c}; + delete $lei->{pkt_op_p}; + $l2m->wq_close(1) if $l2m; + $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}) { $op->event_step } } } -sub ipc_atfork_prepare { - my ($self) = @_; - if (exists $self->{remotes}) { +sub add_uri { + my ($self, $uri) = @_; + if (my $curl = $self->{curl} //= which('curl') // 0) { require PublicInbox::MboxReader; - require PublicInbox::OverIdx; # parse_references require IO::Uncompress::Gunzip; + require PublicInbox::LeiCurl; + push @{$self->{remotes}}, $uri; + } else { + warn "curl missing, ignoring $uri\n"; } - # FDS: (0: done_wr, 1: stdout|mbox, 2: stderr, - # 3: sock, 4: $l2m->{-wq_s1}, 5: $startq) - $self->SUPER::ipc_atfork_prepare; # PublicInbox::IPC } sub prepare_external { my ($self, $loc, $boost) = @_; # n.b. already ordered by boost if (ref $loc) { # already a URI, or PublicInbox::Inbox-like object - return push(@{$self->{remotes}}, $loc) if $loc->can('scheme'); + return add_uri($self, $loc) if $loc->can('scheme'); } elsif ($loc =~ m!\Ahttps?://!) { require URI; - return push(@{$self->{remotes}}, URI->new($loc)); + return add_uri($self, URI->new($loc)); } elsif (-f "$loc/ei.lock") { require PublicInbox::ExtSearch; $loc = PublicInbox::ExtSearch->new($loc);