||
$a->[1] <=> $b->[1] # break ties with {xnum}
} @$xr3;
- my $top_blob = unpack('H*', $xr3->[0]->[2]);
my $new_smsg = $req->{new_smsg};
- return if $top_blob ne $new_smsg->{blob}; # loser
+ return if $xr3->[0]->[2] ne pack('H*', $new_smsg->{blob}); # loser
# replace the old smsg with the more boosted one
$new_smsg->{num} = $smsg->{num};
}
}
-sub eidx_gc {
- my ($self, $opt) = @_;
- $self->{cfg} or die "E: GC requires ->attach_config\n";
- $opt->{-idx_gc} = 1;
- $self->idx_init($opt); # acquire lock via V2Writable::_idx_init
-
- my $dbh = $self->{oidx}->dbh;
- $dbh->do('PRAGMA case_sensitive_like = ON'); # only place we use LIKE
- my $x3_doc = $dbh->prepare('SELECT docid FROM xref3 WHERE ibx_id = ?');
- my $ibx_ck = $dbh->prepare('SELECT ibx_id,eidx_key FROM inboxes');
- my $lc_i = $dbh->prepare(<<'');
-SELECT key FROM eidx_meta WHERE key LIKE ? ESCAPE ?
-
+sub eidx_gc_scan_inboxes ($$) {
+ my ($self, $sync) = @_;
+ my ($x3_doc, $ibx_ck);
+restart:
+ $x3_doc = $self->{oidx}->dbh->prepare(<<EOM);
+SELECT docid FROM xref3 WHERE ibx_id = ?
+EOM
+ $ibx_ck = $self->{oidx}->dbh->prepare(<<EOM);
+SELECT ibx_id,eidx_key FROM inboxes
+EOM
$ibx_ck->execute;
while (my ($ibx_id, $eidx_key) = $ibx_ck->fetchrow_array) {
next if $self->{ibx_map}->{$eidx_key};
$x3_doc->execute($ibx_id);
while (defined(my $docid = $x3_doc->fetchrow_array)) {
gc_unref_doc($self, $ibx_id, $eidx_key, $docid);
+ if (checkpoint_due($sync)) {
+ $x3_doc = $ibx_ck = undef;
+ reindex_checkpoint($self, $sync);
+ goto restart;
+ }
}
- $dbh->prepare_cached(<<'')->execute($ibx_id);
+ $self->{oidx}->dbh->do(<<'', undef, $ibx_id);
DELETE FROM inboxes WHERE ibx_id = ?
# drop last_commit info
my $pat = $eidx_key;
$pat =~ s/([_%\\])/\\$1/g;
+ $self->{oidx}->dbh->do('PRAGMA case_sensitive_like = ON');
+ my $lc_i = $self->{oidx}->dbh->prepare(<<'');
+SELECT key FROM eidx_meta WHERE key LIKE ? ESCAPE ?
+
$lc_i->execute("lc-%:$pat//%", '\\');
while (my ($key) = $lc_i->fetchrow_array) {
next if $key !~ m!\Alc-v[1-9]+:\Q$eidx_key\E//!;
warn "I: removing $key\n";
- $dbh->prepare_cached(<<'')->execute($key);
+ $self->{oidx}->dbh->do(<<'', undef, $key);
DELETE FROM eidx_meta WHERE key = ?
}
-
warn "I: $eidx_key removed\n";
}
+}
- # it's not real unless it's in `over', we use parallelism here,
- # shards will be reading directly from over, so commit
- $self->{oidx}->commit_lazy;
- $self->{oidx}->begin_lazy;
-
- for my $idx (@{$self->{idx_shards}}) {
- warn "I: cleaning up shard #$idx->{shard}\n";
- $idx->shard_over_check($self->{oidx});
- }
- my $nr = $dbh->do(<<'');
+sub eidx_gc_scan_shards ($$) { # TODO: use for lei/store
+ my ($self, $sync) = @_;
+ my $nr = $self->{oidx}->dbh->do(<<'');
DELETE FROM xref3 WHERE docid NOT IN (SELECT num FROM over)
warn "I: eliminated $nr stale xref3 entries\n" if $nr != 0;
+ reindex_checkpoint($self, $sync) if checkpoint_due($sync);
# fixup from old bugs:
- $nr = $dbh->do(<<'');
-DELETE FROM over WHERE num NOT IN (SELECT docid FROM xref3)
+ $nr = $self->{oidx}->dbh->do(<<'');
+DELETE FROM over WHERE num > 0 AND num NOT IN (SELECT docid FROM xref3)
warn "I: eliminated $nr stale over entries\n" if $nr != 0;
+ reindex_checkpoint($self, $sync) if checkpoint_due($sync);
+
+ my ($cur) = $self->{oidx}->dbh->selectrow_array(<<EOM);
+SELECT MIN(num) FROM over WHERE num > 0
+EOM
+ $cur // return; # empty
+ my ($r, $n, %active);
+ $nr = 0;
+ while (1) {
+ $r = $self->{oidx}->dbh->selectcol_arrayref(<<"", undef, $cur);
+SELECT num FROM over WHERE num >= ? ORDER BY num ASC LIMIT 10000
+
+ last unless scalar(@$r);
+ while (defined($n = shift @$r)) {
+ for my $i ($cur..($n - 1)) {
+ my $idx = idx_shard($self, $i);
+ $idx->ipc_do('xdb_remove_quiet', $i);
+ $active{$idx} = $idx;
+ }
+ $cur = $n + 1;
+ }
+ if (checkpoint_due($sync)) {
+ for my $idx (values %active) {
+ $nr += $idx->ipc_do('nr_quiet_rm')
+ }
+ %active = ();
+ reindex_checkpoint($self, $sync);
+ }
+ }
+ warn "I: eliminated $nr stale Xapian documents\n" if $nr != 0;
+}
+
+sub eidx_gc {
+ my ($self, $opt) = @_;
+ $self->{cfg} or die "E: GC requires ->attach_config\n";
+ $opt->{-idx_gc} = 1;
+ my $sync = {
+ need_checkpoint => \(my $need_checkpoint = 0),
+ check_intvl => 10,
+ next_check => now() + 10,
+ checkpoint_unlocks => 1,
+ -opt => $opt,
+ };
+ $self->idx_init($opt); # acquire lock via V2Writable::_idx_init
+ eidx_gc_scan_inboxes($self, $sync);
+ eidx_gc_scan_shards($self, $sync);
done($self);
}
my $ibx_id = $ibx->{-ibx_id};
my $slice = 1000;
my ($beg, $end) = (1, $slice);
+ my $err = sync_inbox($self, $sync, $ibx) and return;
+ my $max = $ibx->over->max;
+ $end = $max if $end > $max;
# first, check if we missed any messages in target $ibx
my $msgs;
local $sync->{-regen_fmt} =
"$ekey checking unseen %u/".$ibx->over->max."\n";
${$sync->{nr}} = 0;
-
+ my $fast = $sync->{-opt}->{fast};
while (scalar(@{$msgs = $ibx->over->query_xover($beg, $end)})) {
${$sync->{nr}} = $beg;
$beg = $msgs->[-1]->{num} + 1;
$end = $beg + $slice;
+ $end = $max if $end > $max;
if (checkpoint_due($sync)) {
reindex_checkpoint($self, $sync); # release lock
}
# the first time around ASAP:
if (scalar(@$docids) == 0) {
reindex_unseen($self, $sync, $ibx, $xsmsg);
- } else { # already seen, reindex later
+ } elsif (!$fast) { # already seen, reindex later
for my $r (@$docids) {
$self->{oidx}->eidxq_add($r->[0]);
}
my $fetching;
my $ekey = $ibx->eidx_key;
local $sync->{-regen_fmt} =
- "$ekey check stale/missing %u/".$ibx->over->max."\n";
+ "$ekey checking stale/missing %u/".$ibx->over->max."\n";
${$sync->{nr}} = 0;
do {
if (checkpoint_due($sync)) {
$del->execute;
# get_xref3 over-fetches, but this is a rare path:
- my $xr3 = $self->{oidx}->get_xref3($docid);
+ my $xr3 = $self->{oidx}->get_xref3($docid, 1);
my $idx = $self->idx_shard($docid);
if (scalar(@$xr3) == 0) { # all gone
$self->{oidx}->delete_by_num($docid);
$self->{oidx}->eidxq_del($docid);
$idx->ipc_do('xdb_remove', $docid);
} else { # enqueue for reindex of remaining messages
- $idx->ipc_do('remove_eidx_info',
- $docid, $ibx->eidx_key);
+ $idx->ipc_do('remove_eidx_info', $docid, $ekey);
$self->{oidx}->eidxq_add($docid); # yes, add
}
}
my $err = _sync_inbox($self, $sync, $ibx);
delete @$ibx{qw(mm over)};
warn $err, "\n" if defined($err);
+ $err;
}
sub dd_smsg { # git->cat_async callback