- $self->spawn_worker($v2w, $shard) if $v2w->{parallel};
- $self;
-}
-
-sub spawn_worker {
- my ($self, $v2w, $shard) = @_;
- my ($r, $w);
- pipe($r, $w) or die "pipe failed: $!\n";
- $w->autoflush(1);
- my $oldset = PublicInbox::Sigfd::block_signals();
- my $pid = fork;
- defined $pid or die "fork failed: $!\n";
- if ($pid == 0) {
- # these signals are localized in parent
- $SIG{$_} = 'IGNORE' for (qw(TERM INT QUIT));
- PublicInbox::Sigfd::sig_setmask($oldset);
- my $bnote = $v2w->atfork_child;
- close $w or die "failed to close: $!";
-
- # F_SETPIPE_SZ = 1031 on Linux; increasing the pipe size here
- # speeds V2Writable batch imports across 8 cores by nearly 20%
- fcntl($r, 1031, 1048576) if $^O eq 'linux';
-
- eval { shard_worker_loop($self, $v2w, $r, $shard, $bnote) };
- die "worker $shard died: $@\n" if $@;
- die "unexpected MM $self->{mm}" if $self->{mm};
- exit;
- }
- PublicInbox::Sigfd::sig_setmask($oldset);
- $self->{pid} = $pid;
- $self->{w} = $w;
- close $r or die "failed to close: $!";
-}
-
-sub eml ($$) {
- my ($r, $len) = @_;
- return if $len == 0;
- my $n = read($r, my $bref, $len) or die "read: $!\n";
- $n == $len or die "short read: $n != $len\n";
- PublicInbox::Eml->new(\$bref);
-}
-
-# this reads all the writes to $self->{w} from the parent process
-sub shard_worker_loop ($$$$$) {
- my ($self, $v2w, $r, $shard, $bnote) = @_;
- $0 = "shard[$shard]";
- $self->begin_txn_lazy;
- while (my $line = readline($r)) {
- $v2w->{current_info} = "[$shard] $line";
- if ($line eq "commit\n") {
- $self->commit_txn_lazy;
- } elsif ($line eq "close\n") {
- $self->idx_release;
- } elsif ($line eq "barrier\n") {
- $self->commit_txn_lazy;
- # no need to lock < 512 bytes is atomic under POSIX
- print $bnote "barrier $shard\n" or
- die "write failed for barrier $!\n";
- } elsif ($line =~ /\AD ([0-9]+)\n\z/s) {
- $self->remove_by_docid($1 + 0);
- } elsif ($line =~ s/\A\+X //) {
- my ($len, $docid, $eidx_key) = split(/ /, $line, 3);
- chomp $eidx_key;
- $self->add_eidx_info($docid, $eidx_key, eml($r, $len));
- } elsif ($line =~ s/\A-X //) {
- my ($len, $docid, $eidx_key) = split(/ /, $line, 3);
- chomp $eidx_key;
- $self->remove_eidx_info($docid, $eidx_key,
- eml($r, $len));
- } elsif ($line =~ s/\AO ([^\n]+)\n//) {
- my $over_fn = $1;
- $over_fn =~ tr/\0/\n/;
- $self->over_check(PublicInbox::Over->new($over_fn));
- } else {
- chomp $line;
- my $eidx_key;
- if ($line =~ s/\AX=(.+)\0//) {
- $eidx_key = $1;
- $v2w->{current_info} =~ s/\0/\\0 /;
- }
- # n.b. $mid may contain spaces(!)
- my ($len, $bytes, $num, $oid, $ds, $ts, $tid, $mid)
- = split(/ /, $line, 8);
- $self->begin_txn_lazy;
- my $smsg = bless {
- bytes => $bytes,
- num => $num + 0,
- blob => $oid,
- mid => $mid,
- tid => $tid,
- ds => $ds,
- ts => $ts,
- }, 'PublicInbox::Smsg';
- $smsg->{eidx_key} = $eidx_key if defined($eidx_key);
- $self->add_message(eml($r, $len), $smsg);
- }
- }
- $self->worker_done;
-}
-
-sub index_raw {
- my ($self, $msgref, $eml, $smsg, $eidx_key) = @_;
- if (my $w = $self->{w}) {
- my @ekey = defined($eidx_key) ? ("X=$eidx_key\0") : ();
- $msgref //= \($eml->as_string);
- $smsg->{raw_bytes} //= length($$msgref);
- # mid must be last, it can contain spaces (but not LF)
- print $w @ekey, join(' ', @$smsg{qw(raw_bytes bytes
- num blob ds ts tid mid)}),
- "\n", $$msgref or die "failed to write shard $!\n";
- } else {
- if ($eml) {
- undef($$msgref) if $msgref;
- } else { # --xapian-only + --sequential-shard:
- $eml = PublicInbox::Eml->new($msgref);