X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FMsgmap.pm;h=ec3d4f9d8101fe0e226895207f2a486016e8a223;hp=6b6d1c6ee6086b8fd61ce4a04a45ab5b5619f961;hb=cfb8d16578e7f2f2e300f9f436205e4a8fc7f322;hpb=119463b3b8517e5ec149198bb83588999118ee1d diff --git a/lib/PublicInbox/Msgmap.pm b/lib/PublicInbox/Msgmap.pm index 6b6d1c6e..ec3d4f9d 100644 --- a/lib/PublicInbox/Msgmap.pm +++ b/lib/PublicInbox/Msgmap.pm @@ -12,6 +12,7 @@ use strict; use warnings; use DBI; use DBD::SQLite; +use File::Temp qw(tempfile); sub new { my ($class, $git_dir, $writable) = @_; @@ -23,9 +24,8 @@ sub new { new_file($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, @@ -34,6 +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) { @@ -45,6 +53,19 @@ sub new_file { $self; } +# used to keep track of used numeric mappings for v2 reindex +sub tmp_clone { + my ($self) = @_; + 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 + $tmp->{pid} = $$; + close $fh or die "failed to close $fn: $!"; + $tmp; +} + # n.b. invoked directly by scripts/xhdr-num2mid sub meta_accessor { my ($self, $key, $value) = @_; @@ -71,6 +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); @@ -79,10 +108,10 @@ sub created_at { 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; + my $sth = $dbh->prepare_cached(<<''); +INSERT OR IGNORE INTO msgmap (mid) VALUES (?) + + return if $sth->execute($mid) == 0; $dbh->last_insert_id(undef, undef, 'msgmap', 'num'); } @@ -109,10 +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; - $sth->fetchrow_array; + my $min = $sth->fetchrow_array; + $sth = $dbh->prepare_cached('SELECT MAX(num) FROM msgmap', undef, 1); + $sth->execute; + ($min, $sth->fetchrow_array); } sub mid_prefixes { @@ -140,6 +173,14 @@ sub mid_delete { $sth->execute; } +sub num_delete { + my ($self, $num) = @_; + my $dbh = $self->{dbh}; + my $sth = $dbh->prepare('DELETE FROM msgmap WHERE num = ?'); + $sth->bind_param(1, $num); + $sth->execute; +} + sub create_tables { my ($dbh) = @_; my $e; @@ -157,17 +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 + + $$beg = $mids->[-1]->[0] + 1 if @$mids; + $mids } # only used for mapping external serial numbers (e.g. articles from gmane) @@ -181,4 +231,31 @@ sub mid_set { $sth->execute($num, $mid); } +sub DESTROY { + my ($self) = @_; + delete $self->{dbh}; + my $f = delete $self->{tmp_name}; + if (defined $f && $self->{pid} == $$) { + 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;