replace Xapian skeleton with SQLite overview DB

[public-inbox.git] / lib / PublicInbox / SearchIdxPart.pm

diff --git a/lib/PublicInbox/SearchIdxPart.pm b/lib/PublicInbox/SearchIdxPart.pm
index 477a4f979624b9f8998327c5399f79b64c9ca6ef..e5766a825ed511af4518d77fc556a3711efb65de 100644 (file)
--- a/lib/PublicInbox/SearchIdxPart.pm
+++ b/lib/PublicInbox/SearchIdxPart.pm
@@ -6,9 +6,18 @@ use warnings;
 use base qw(PublicInbox::SearchIdx);
 
 sub new {
-       my ($class, $v2writable, $part, $threader) = @_;
+       my ($class, $v2writable, $part) = @_;
        my $self = $class->SUPER::new($v2writable->{-inbox}, 1, $part);
-       $self->{threader} = $threader;
+       # create the DB before forking:
+       $self->_xdb_acquire;
+       $self->_xdb_release;
+       $self->{over} = $v2writable->{over};
+       $self->spawn_worker($v2writable, $part) if $v2writable->{parallel};
+       $self;
+}
+
+sub spawn_worker {
+       my ($self, $v2writable, $part) = @_;
        my ($r, $w);
        pipe($r, $w) or die "pipe failed: $!\n";
        binmode $r, ':raw';
@@ -18,7 +27,7 @@ sub new {
        if ($pid == 0) {
                $v2writable->atfork_child;
                $v2writable = undef;
-               close $w;
+               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%
@@ -31,53 +40,67 @@ sub new {
        }
        $self->{pid} = $pid;
        $self->{w} = $w;
-       close $r;
-       $self;
+       close $r or die "failed to close: $!";
 }
 
 sub partition_worker_loop ($$$) {
        my ($self, $r, $part) = @_;
        $0 = "pi-v2-partition[$part]";
-       my $xdb = $self->_xdb_acquire;
-       $xdb->begin_transaction;
-       my $txn = 1;
+       $self->begin_txn_lazy;
        while (my $line = $r->getline) {
                if ($line eq "commit\n") {
-                       $xdb->commit_transaction if $txn;
-                       $txn = undef;
+                       $self->commit_txn_lazy;
                } elsif ($line eq "close\n") {
                        $self->_xdb_release;
-                       $xdb = $txn = undef;
+               } elsif ($line eq "barrier\n") {
+                       $self->commit_txn_lazy;
+                       print { $self->{over}->{w} } "barrier $part\n" or
+                                       die "write failed to overview $!\n";
+               } elsif ($line =~ /\AD ([a-f0-9]{40,}) (.+)\n\z/s) {
+                       my ($oid, $mid) = ($1, $2);
+                       $self->begin_txn_lazy;
+                       $self->remove_by_oid($oid, $mid);
                } else {
                        chomp $line;
-                       my ($len, $artnum, $object_id) = split(/ /, $line);
-                       $xdb ||= $self->_xdb_acquire;
-                       if (!$txn) {
-                               $xdb->begin_transaction;
-                               $txn = 1;
-                       }
+                       my ($len, $artnum, $oid, $mid0) = split(/ /, $line);
+                       $self->begin_txn_lazy;
                        my $n = read($r, my $msg, $len) or die "read: $!\n";
                        $n == $len or die "short read: $n != $len\n";
                        my $mime = PublicInbox::MIME->new(\$msg);
                        $artnum = int($artnum);
-                       $self->add_message($mime, $n, $artnum, $object_id);
+                       $self->add_message($mime, $n, $artnum, $oid, $mid0);
                }
        }
-       warn "$$ still in transaction\n" if $txn;
-       warn "$$ xdb active\n" if $xdb;
+       $self->worker_done;
 }
 
 # called by V2Writable
 sub index_raw {
-       my ($self, $len, $msgref, $artnum, $object_id) = @_;
-       my $w = $self->{w};
-       print $w "$len $artnum $object_id\n", $$msgref or die
-               "failed to write partition $!\n";
-       $w->flush or die "failed to flush: $!\n";
+       my ($self, $bytes, $msgref, $artnum, $oid, $mid0, $mime) = @_;
+       if (my $w = $self->{w}) {
+               print $w "$bytes $artnum $oid $mid0\n", $$msgref or die
+                       "failed to write partition $!\n";
+               $w->flush or die "failed to flush: $!\n";
+       } else {
+               $$msgref = undef;
+               $self->begin_txn_lazy;
+               $self->add_message($mime, $bytes, $artnum, $oid, $mid0);
+       }
 }
 
 sub atfork_child {
        close $_[0]->{w} or die "failed to close write pipe: $!\n";
 }
 
+# called by V2Writable:
+sub remote_barrier {
+       my ($self) = @_;
+       if (my $w = $self->{w}) {
+               print $w "barrier\n" or die "failed to print: $!";
+               $w->flush or die "failed to flush: $!";
+       } else {
+               $self->commit_txn_lazy;
+       }
+}
+
 1;