extindex: speed up Xapian cleanup in --gc

[public-inbox.git] / lib / PublicInbox / ExtSearchIdx.pm

diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm
index 7cc8dd952559d17b3c5c600a7ac8155547ad34ce..04948b8b9e282cf28b0443623bc583d827a31d9a 100644 (file)
--- a/lib/PublicInbox/ExtSearchIdx.pm
+++ b/lib/PublicInbox/ExtSearchIdx.pm
@@ -421,34 +421,43 @@ sub eidx_gc_scan_shards ($$) { # TODO: use for lei/store
 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 = $self->{oidx}->dbh->do(<<'');
 DELETE FROM over WHERE 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) = $self->{oidx}->dbh->selectrow_array(<<EOM);
 SELECT MIN(num) FROM over
 EOM
-       my ($max) = $self->{oidx}->dbh->selectrow_array(<<EOM);
-SELECT MAX(num) FROM over
-EOM
-       my $exists;
-restart:
-       $exists = $self->{oidx}->dbh->prepare(<<EOM);
-SELECT COUNT(num) FROM over WHERE num = ?
-EOM
-       for (; $cur <= $max; $cur++) {
-               $exists->execute($cur);
-               next if $exists->fetchrow_array != 0;
-               $self->idx_shard($cur)->ipc_do('xdb_remove_quiet', $cur);
+       $cur // return; # empty
+       my ($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)) {
-                       $exists = undef;
+                       for my $idx (values %active) {
+                               $nr += $idx->ipc_do('nr_quiet_rm')
+                       }
+                       %active = ();
                        reindex_checkpoint($self, $sync);
-                       goto restart;
                }
        }
+       warn "I: eliminated $nr stale Xapian documents\n" if $nr != 0;
 }
 
 sub eidx_gc {
@@ -811,7 +820,7 @@ sub _reindex_check_unseen ($$$) {
        local $sync->{-regen_fmt} =
                        "$ekey checking unseen %u/".$ibx->over->max."\n";
        ${$sync->{nr}} = 0;
-
+       my $fast = $sync->{-opt}->{fast};
        while (scalar(@{$msgs = $ibx->over->query_xover($beg, $end)})) {
                ${$sync->{nr}} = $beg;
                $beg = $msgs->[-1]->{num} + 1;
@@ -835,7 +844,7 @@ ibx_id = ? AND xnum = ? AND oidbin = ?
                        # the first time around ASAP:
                        if (scalar(@$docids) == 0) {
                                reindex_unseen($self, $sync, $ibx, $xsmsg);
-                       } else { # already seen, reindex later
+                       } elsif (!$fast) { # already seen, reindex later
                                for my $r (@$docids) {
                                        $self->{oidx}->eidxq_add($r->[0]);
                                }
@@ -853,7 +862,7 @@ sub _reindex_check_stale ($$$) {
        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)) {