-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# bidirectional Message-ID <-> Article Number mapping for the NNTP
new_file($class, "$d/msgmap.sqlite3", $writable);
}
-sub new_file {
- my ($class, $f, $writable) = @_;
-
+sub dbh_new {
+ my ($f, $writable) = @_;
+ if ($writable && !-f $f) { # SQLite defaults mode to 0644, we want 0666
+ open my $fh, '+>>', $f or die "failed to open $f: $!";
+ }
my $dbh = DBI->connect("dbi:SQLite:dbname=$f",'','', {
AutoCommit => 1,
RaiseError => 1,
ReadOnly => !$writable,
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) {
create_tables($dbh);
+
+ # TRUNCATE reduces I/O compared to the default (DELETE)
+ $dbh->do('PRAGMA journal_mode = TRUNCATE');
+
$dbh->begin_work;
$self->created_at(time) unless $self->created_at;
+
+ my (undef, $max) = $self->minmax();
+ $max ||= 0;
+ $self->num_highwater($max);
$dbh->commit;
}
$self;
# used to keep track of used numeric mappings for v2 reindex
sub tmp_clone {
my ($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->{dbh}->do('PRAGMA journal_mode = MEMORY');
$tmp->{tmp_name} = $fn; # SQLite won't work if unlinked, apparently
- $fh = undef;
+ $tmp->{pid} = $$;
+ close $fh or die "failed to close $fn: $!";
$tmp;
}
$prev = $dbh->selectrow_array($sql, undef, $key);
if (defined $prev) {
- $sql = 'UPDATE meta SET val = ? WHERE key = ? LIMIT 1';
+ $sql = 'UPDATE meta SET val = ? WHERE key = ?';
$dbh->do($sql, undef, $value, $key);
} else {
$sql = 'INSERT INTO meta (key,val) VALUES (?,?)';
$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);
}
+sub num_highwater {
+ my ($self, $num) = @_;
+ my $high = $self->{num_highwater} ||=
+ $self->meta_accessor('num_highwater');
+ if (defined($num) && (!defined($high) || ($num > $high))) {
+ $self->{num_highwater} = $num;
+ $self->meta_accessor('num_highwater', $num);
+ }
+ $self->{num_highwater};
+}
+
sub mid_insert {
my ($self, $mid) = @_;
my $dbh = $self->{dbh};
- my $sql = 'INSERT OR IGNORE INTO msgmap (mid) VALUES (?)';
- my $sth = $self->{mid_insert} ||= $dbh->prepare($sql);
- $sth->bind_param(1, $mid);
- return if $sth->execute == 0;
- $dbh->last_insert_id(undef, undef, 'msgmap', 'num');
+ my $sth = $dbh->prepare_cached(<<'');
+INSERT INTO msgmap (mid) VALUES (?)
+
+ return unless eval { $sth->execute($mid) };
+ my $num = $dbh->last_insert_id(undef, undef, 'msgmap', 'num');
+ $self->num_highwater($num) if defined($num);
+ $num;
}
sub mid_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;
- $sth->fetchrow_array;
-}
-
-sub mid_prefixes {
- my ($self, $pfx, $limit) = @_;
-
- die "No prefix given" unless (defined $pfx && $pfx ne '');
- $pfx =~ s/([%_])/\\$1/g;
- $pfx .= '%';
-
- $limit ||= 100;
- $limit += 0; # force to integer
- $limit ||= 100;
-
- $self->{dbh}->selectcol_arrayref('SELECT mid FROM msgmap ' .
- 'WHERE mid LIKE ? ESCAPE ? ' .
- "ORDER BY num DESC LIMIT $limit",
- undef, $pfx, '\\');
+ my $min = $sth->fetchrow_array;
+ $sth = $dbh->prepare_cached('SELECT MAX(num) FROM msgmap', undef, 1);
+ $sth->execute;
+ ($min, $sth->fetchrow_array);
}
sub mid_delete {
}
# 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
+
+ $$num = $ids->[-1] if @$ids;
+ $ids;
+}
+
+sub msg_range {
+ my ($self, $beg, $end, $cols) = @_;
+ $cols //= 'num,mid';
my $dbh = $self->{dbh};
- my $sth = $dbh->prepare('SELECT num FROM msgmap WHERE num > ? '.
- 'ORDER BY num ASC LIMIT 1000');
- $sth->execute($num);
- my $ary = $sth->fetchall_arrayref;
- @$ary = map { $_->[0] } @$ary;
- my $nr = scalar @$ary;
- $cb->($ary) if $nr;
- $nr;
+ my $attr = { Columns => [] };
+ my $mids = $dbh->selectall_arrayref(<<"", $attr, $$beg, $end);
+SELECT $cols FROM msgmap WHERE num >= ? AND num <= ?
+ORDER BY num ASC LIMIT 1000
+
+ $$beg = $mids->[-1]->[0] + 1 if @$mids;
+ $mids
}
# only used for mapping external serial numbers (e.g. articles from gmane)
$self->{dbh}->prepare(
'INSERT OR IGNORE INTO msgmap (num,mid) VALUES (?,?)');
};
- $sth->execute($num, $mid);
+ my $result = $sth->execute($num, $mid);
+ $self->num_highwater($num) if (defined($result) && $result == 1);
+ $result;
}
sub DESTROY {
my ($self) = @_;
delete $self->{dbh};
- unlink $self->{tmp_name} if defined $self->{tmp_name};
+ my $f = delete $self->{tmp_name};
+ if (defined $f && $self->{pid} == $$) {
+ 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;