X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMsgmap.pm;h=feef8ba79ab9a657d8135b0c65ca0186dd7bed51;hb=74b92712fa7a21fe504b9908edebcf11bb9dc170;hp=78922d3693c9647e0b11c3dc7fc300ce1a985147;hpb=2e5d47e4c02757c027461149b3e1568d713252b1;p=public-inbox.git

diff --git a/lib/PublicInbox/Msgmap.pm b/lib/PublicInbox/Msgmap.pm
index 78922d36..feef8ba7 100644
--- a/lib/PublicInbox/Msgmap.pm
+++ b/lib/PublicInbox/Msgmap.pm
@@ -24,9 +24,8 @@ sub new {
 	new_file($class, "$d/msgmap.sqlite3", $writable);
 }
 
-sub new_file {
-	my ($class, $f, $writable) = @_;
-
+sub dbh_new {
+	my ($f, $writable) = @_;
 	my $dbh = DBI->connect("dbi:SQLite:dbname=$f",'','', {
 		AutoCommit => 1,
 		RaiseError => 1,
@@ -35,6 +34,14 @@ sub new_file {
 		sqlite_use_immediate_transaction => 1,
 	});
 	$dbh->do('PRAGMA case_sensitive_like = ON');
+	$dbh;
+}
+
+sub new_file {
+	my ($class, $f, $writable) = @_;
+	return if !$writable && !-r $f;
+
+	my $dbh = dbh_new($f, $writable);
 	my $self = bless { dbh => $dbh }, $class;
 
 	if ($writable) {
@@ -49,12 +56,13 @@ sub new_file {
 # used to keep track of used numeric mappings for v2 reindex
 sub tmp_clone {
 	my ($self) = @_;
-	my ($fh, $fn) = tempfile(EXLOCK => 0);
+	my ($fh, $fn) = tempfile('msgmap-XXXXXXXX', EXLOCK => 0, TMPDIR => 1);
 	$self->{dbh}->sqlite_backup_to_file($fn);
 	my $tmp = ref($self)->new_file($fn, 1);
 	$tmp->{dbh}->do('PRAGMA synchronous = OFF');
 	$tmp->{tmp_name} = $fn; # SQLite won't work if unlinked, apparently
-	$fh = undef;
+	$tmp->{pid} = $$;
+	close $fh or die "failed to close $fn: $!";
 	$tmp;
 }
 
@@ -84,6 +92,14 @@ sub last_commit {
 	$self->meta_accessor('last_commit', $commit);
 }
 
+# v2 uses this to keep track of how up-to-date Xapian is
+# old versions may be automatically GC'ed away in the future,
+# but it's a trivial amount of storage.
+sub last_commit_xap {
+	my ($self, $version, $i, $commit) = @_;
+	$self->meta_accessor("last_xap$version-$i", $commit);
+}
+
 sub created_at {
 	my ($self, $second) = @_;
 	$self->meta_accessor('created_at', $second);
@@ -122,10 +138,14 @@ sub num_for {
 sub minmax {
 	my ($self) = @_;
 	my $dbh = $self->{dbh};
-	my $sth = $self->{num_minmax} ||=
-		$dbh->prepare('SELECT MIN(num),MAX(num) FROM msgmap');
+	# breaking MIN and MAX into separate queries speeds up from 250ms
+	# to around 700us with 2.7million messages.
+	my $sth = $dbh->prepare_cached('SELECT MIN(num) FROM msgmap', undef, 1);
+	$sth->execute;
+	my $min = $sth->fetchrow_array;
+	$sth = $dbh->prepare_cached('SELECT MAX(num) FROM msgmap', undef, 1);
 	$sth->execute;
-        $sth->fetchrow_array;
+	($min, $sth->fetchrow_array);
 }
 
 sub mid_prefixes {
@@ -178,17 +198,26 @@ sub create_tables {
 }
 
 # used by NNTP.pm
-sub id_batch {
-	my ($self, $num, $cb) = @_;
+sub ids_after {
+	my ($self, $num) = @_;
+	my $ids = $self->{dbh}->selectcol_arrayref(<<'', undef, $$num);
+SELECT num FROM msgmap WHERE num > ?
+ORDER BY num ASC LIMIT 1000
+
+	$$num = $ids->[-1] if @$ids;
+	$ids;
+}
+
+sub msg_range {
+	my ($self, $beg, $end) = @_;
 	my $dbh = $self->{dbh};
-	my $sth = $dbh->prepare('SELECT num FROM msgmap WHERE num > ? '.
-				'ORDER BY num ASC LIMIT 1000');
-	$sth->execute($num);
-	my $ary = $sth->fetchall_arrayref;
-	@$ary = map { $_->[0] } @$ary;
-	my $nr = scalar @$ary;
-	$cb->($ary) if $nr;
-	$nr;
+	my $attr = { Columns => [] };
+	my $mids = $dbh->selectall_arrayref(<<'', $attr, $$beg, $end);
+SELECT num,mid FROM msgmap WHERE num >= ? AND num <= ?
+ORDER BY num ASC
+
+	$$beg = $mids->[-1]->[0] + 1 if @$mids;
+	$mids
 }
 
 # only used for mapping external serial numbers (e.g. articles from gmane)
@@ -205,7 +234,28 @@ sub mid_set {
 sub DESTROY {
 	my ($self) = @_;
 	delete $self->{dbh};
-	unlink $self->{tmp_name} if defined $self->{tmp_name};
+	my $f = delete $self->{tmp_name};
+	if (defined $f && $self->{pid} == $$) {
+		unlink $f or warn "failed to unlink $f: $!\n";
+	}
+}
+
+sub atfork_parent {
+	my ($self) = @_;
+	my $f = $self->{tmp_name} or die "not a temporary clone\n";
+	delete $self->{dbh} and die "tmp_clone dbh not prepared for parent";
+	my $dbh = $self->{dbh} = dbh_new($f, 1);
+	$dbh->do('PRAGMA synchronous = OFF');
+}
+
+sub atfork_prepare {
+	my ($self) = @_;
+	my $f = $self->{tmp_name} or die "not a temporary clone\n";
+	$self->{pid} == $$ or
+		die "BUG: atfork_prepare not called from $self->{pid}\n";
+	$self->{dbh} or die "temporary clone not open\n";
+	# must clobber prepared statements
+	%$self = (tmp_name => $f, pid => $$);
 }
 
 1;