-# 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
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');
$dbh;
}
if ($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 $max = $self->max // 0;
+ $self->num_highwater($max);
$dbh->commit;
}
$self;
$self->{dbh}->sqlite_backup_to_file($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
$tmp->{pid} = $$;
close $fh or die "failed to close $fn: $!";
$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('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 {
$sth->fetchrow_array;
}
-sub minmax {
- my ($self) = @_;
- my $dbh = $self->{dbh};
- my $sth = $self->{num_minmax} ||=
- $dbh->prepare('SELECT MIN(num),MAX(num) FROM msgmap');
+sub max {
+ my $sth = $_[0]->{dbh}->prepare_cached('SELECT MAX(num) FROM msgmap',
+ undef, 1);
$sth->execute;
- $sth->fetchrow_array;
+ $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, '\\');
+sub minmax {
+ # breaking MIN and MAX into separate queries speeds up from 250ms
+ # to around 700us with 2.7million messages.
+ my $sth = $_[0]->{dbh}->prepare_cached('SELECT MIN(num) FROM msgmap',
+ undef, 1);
+ $sth->execute;
+ ($sth->fetchrow_array, max($_[0]));
}
sub mid_delete {
}
sub msg_range {
- my ($self, $beg, $end) = @_;
+ my ($self, $beg, $end, $cols) = @_;
+ $cols //= 'num,mid';
my $dbh = $self->{dbh};
my $attr = { Columns => [] };
- my $mids = $dbh->selectall_arrayref(<<'', $attr, $$beg, $end);
-SELECT num,mid FROM msgmap WHERE num >= ? AND num <= ?
-ORDER BY num ASC
+ 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
$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);
+ $result;
}
sub DESTROY {
%$self = (tmp_name => $f, pid => $$);
}
+sub skip_artnum {
+ my ($self, $skip_artnum) = @_;
+ return meta_accessor($self, 'skip_artnum') if !defined($skip_artnum);
+
+ my $cur = num_highwater($self) // 0;
+ if ($skip_artnum < $cur) {
+ die "E: current article number $cur ",
+ "exceeds --skip-artnum=$skip_artnum\n";
+ } else {
+ my $ok;
+ for (1..10) {
+ my $mid = 'skip'.rand.'@'.rand.'.example.com';
+ $ok = mid_set($self, $skip_artnum, $mid);
+ if ($ok) {
+ mid_delete($self, $mid);
+ last;
+ }
+ }
+ $ok or die '--skip-artnum failed';
+
+ # in the future, the indexer may use this value for
+ # new messages in old epochs
+ meta_accessor($self, 'skip_artnum', $skip_artnum);
+ }
+}
+
1;