X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FExtSearchIdx.pm;h=401b18d00754176a69eb1c2a90d380bc926a84b3;hb=refs%2Fheads%2Fmaster;hp=a08a9451558244f39818c1f9a7170c799d083909;hpb=3688ac90abfaa8ad55b0767202aebcc8e2d02147;p=public-inbox.git diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm index a08a9451..401b18d0 100644 --- a/lib/PublicInbox/ExtSearchIdx.pm +++ b/lib/PublicInbox/ExtSearchIdx.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2020-2021 all contributors +# Copyright (C) all contributors # License: AGPL-3.0+ # Detached/external index cross inbox search indexing support @@ -59,6 +59,7 @@ sub new { nproc_shards({ nproc => $opt->{jobs} }); my $oidx = PublicInbox::OverIdx->new("$self->{xpfx}/over.sqlite3"); $self->{-no_fsync} = $oidx->{-no_fsync} = 1 if !$opt->{fsync}; + $self->{-dangerous} = 1 if $opt->{dangerous}; $self->{oidx} = $oidx; $self } @@ -292,8 +293,8 @@ sub ck_existing { # git->cat_async callback # is the messages visible in the inbox currently being indexed? # return the number if so -sub cur_ibx_xnum ($$) { - my ($req, $bref) = @_; +sub cur_ibx_xnum ($$;$) { + my ($req, $bref, $mismatch) = @_; my $ibx = $req->{ibx} or die 'BUG: current {ibx} missing'; $req->{eml} = PublicInbox::Eml->new($bref); @@ -303,6 +304,7 @@ sub cur_ibx_xnum ($$) { my ($id, $prev); while (my $x = $ibx->over->next_by_mid($mid, \$id, \$prev)) { return $x->{num} if $x->{blob} eq $req->{oid}; + push @$mismatch, $x if $mismatch; } } undef; @@ -317,8 +319,15 @@ sub index_oid { # git->cat_async callback for 'm' blob => $oid, }, 'PublicInbox::Smsg'; $new_smsg->set_bytes($$bref, $size); - defined($req->{xnum} = cur_ibx_xnum($req, $bref)) or return; ++${$req->{nr}}; + my $mismatch = []; + $req->{xnum} = cur_ibx_xnum($req, $bref, $mismatch) // do { + warn "# deleted\n"; + warn "# mismatch $_->{blob}\n" for @$mismatch; + ${$req->{latest_cmt}} = $req->{cur_cmt} // + die "BUG: {cur_cmt} unset ($oid)\n"; + return; + }; do_step($req); } @@ -397,14 +406,14 @@ EOM while (my ($ibx_id, $eidx_key) = $ibx_ck->fetchrow_array) { next if $self->{ibx_map}->{$eidx_key}; $self->{midx}->remove_eidx_key($eidx_key); - warn "I: deleting messages for $eidx_key...\n"; + warn "# deleting messages for $eidx_key...\n"; $x3_doc->execute($ibx_id); my $ibx = { -ibx_id => $ibx_id, -gc_eidx_key => $eidx_key }; while (my ($docid, $xnum, $oid) = $x3_doc->fetchrow_array) { my $r = _unref_doc($sync, $docid, $ibx, $xnum, $oid); $oid = unpack('H*', $oid); $r = $r ? 'unref' : 'remove'; - warn "I: $r #$docid $eidx_key $oid\n"; + warn "# $r #$docid $eidx_key $oid\n"; if (checkpoint_due($sync)) { $x3_doc = $ibx_ck = undef; reindex_checkpoint($self, $sync); @@ -424,12 +433,12 @@ 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"; + warn "# removing $key\n"; $self->{oidx}->dbh->do(<<'', undef, $key); DELETE FROM eidx_meta WHERE key = ? } - warn "I: $eidx_key removed\n"; + warn "# $eidx_key removed\n"; } } @@ -438,20 +447,20 @@ sub eidx_gc_scan_shards ($$) { # TODO: use for lei/store my $nr = $self->{oidx}->dbh->do(<<''); DELETE FROM xref3 WHERE docid NOT IN (SELECT num FROM over) - warn "I: eliminated $nr stale xref3 entries\n" if $nr != 0; + warn "# eliminated $nr stale xref3 entries\n" if $nr != 0; reindex_checkpoint($self, $sync) if checkpoint_due($sync); # fixup from old bugs: $nr = $self->{oidx}->dbh->do(<<''); DELETE FROM over WHERE num > 0 AND num NOT IN (SELECT docid FROM xref3) - warn "I: eliminated $nr stale over entries\n" if $nr != 0; + warn "# eliminated $nr stale over entries\n" if $nr != 0; reindex_checkpoint($self, $sync) if checkpoint_due($sync); $nr = $self->{oidx}->dbh->do(<<''); DELETE FROM eidxq WHERE docid NOT IN (SELECT num FROM over) - warn "I: eliminated $nr stale reindex queue entries\n" if $nr != 0; + warn "# eliminated $nr stale reindex queue entries\n" if $nr != 0; reindex_checkpoint($self, $sync) if checkpoint_due($sync); my ($cur) = $self->{oidx}->dbh->selectrow_array(<= ? ORDER BY num ASC LIMIT 10000 reindex_checkpoint($self, $sync); } } - warn "I: eliminated $nr stale Xapian documents\n" if $nr != 0; + warn "# eliminated $nr stale Xapian documents\n" if $nr != 0; } sub eidx_gc { @@ -719,15 +728,14 @@ sub eidxq_lock_acquire ($) { return $locked if $locked eq $cur; } my ($pid, $time, $euid, $ident) = split(/-/, $cur, 4); - my $t = strftime('%Y-%m-%d %k:%M:%S', gmtime($time)); + my $t = strftime('%Y-%m-%d %k:%M %z', localtime($time)); + local $self->{current_info} = 'eidxq'; if ($euid == $> && $ident eq host_ident) { - if (kill(0, $pid)) { - warn < $xsmsg->{num}, # {mids} and {chash} will be filled in at _reindex_unseen }; - warn "I: reindex_unseen ${\$ibx->eidx_key}:$req->{xnum}:$req->{oid}\n"; + warn "# reindex_unseen ${\$ibx->eidx_key}:$req->{xnum}:$req->{oid}\n"; $self->git->cat_async($xsmsg->{blob}, \&_reindex_unseen, $req); } @@ -839,7 +847,7 @@ sub _unref_stale_range ($$$) { $r = $sync->{self}->{oidx}->dbh->selectall_arrayref( <{-ibx_id}); SELECT docid,xnum,oidbin FROM xref3 -WHERE ibx_id = ? AND xnum $lt_or_gt LIMIT $lim +WHERE ibx_id = ? AND $lt_or_gt LIMIT $lim EOS return if $sync->{quit}; for (@$r) { # hopefully rare, not worth optimizing: @@ -858,18 +866,24 @@ sub _reindex_check_ibx ($$$) { my $slice = 10000; my $opt = { limit => $slice }; my ($beg, $end) = (1, $slice); - my $err = sync_inbox($self, $sync, $ibx) and return; - my $max = $ibx->over->max; + my $ekey = $ibx->eidx_key; + my ($max, $max0); + do { + $max0 = $ibx->mm->num_highwater; + sync_inbox($self, $sync, $ibx) and return; # warned + $max = $ibx->mm->num_highwater; + return if $sync->{quit}; + } while ($max > $max0 && + warn("# $ekey moved $max0..$max, resyncing..\n")); $end = $max if $end > $max; # first, check if we missed any messages in target $ibx my $msgs; my $pr = $sync->{-opt}->{-progress}; - my $ekey = $ibx->eidx_key; local $sync->{-regen_fmt} = "$ekey checking %u/$max\n"; ${$sync->{nr}} = 0; my $fast = $sync->{-opt}->{fast}; - my $dsu; # _unref_stale_range (< $lo) called + my $usr; # _unref_stale_range (< $lo) called my ($lo, $hi); while (scalar(@{$msgs = $ibx->over->query_xover($beg, $end, $opt)})) { ${$sync->{nr}} = $beg; @@ -880,7 +894,7 @@ sub _reindex_check_ibx ($$$) { reindex_checkpoint($self, $sync); # release lock } ($lo, $hi) = ($msgs->[0]->{num}, $msgs->[-1]->{num}); - $dsu //= _unref_stale_range($sync, $ibx, "< $lo"); + $usr //= _unref_stale_range($sync, $ibx, "xnum < $lo"); my $x3a = $self->{oidx}->dbh->selectall_arrayref( <<"", undef, $ibx_id, $lo, $hi); SELECT xnum,oidbin,docid FROM xref3 WHERE @@ -901,10 +915,9 @@ ibx_id = ? AND xnum >= ? AND xnum <= ? for my $num (@$docids) { $self->{oidx}->eidxq_add($num); } - return if $sync->{quit}; } + return if $sync->{quit}; } - return if $sync->{quit}; next unless scalar keys %x3m; $self->git->async_wait_all; # wait for reindex_unseen @@ -914,14 +927,26 @@ ibx_id = ? AND xnum >= ? AND xnum <= ? my ($xnum, $hex) = unpack('JH*', $k); my $bin = pack('H*', $hex); my $exp = $mismatch{$xnum}; + if (defined $exp) { + my $smsg = $ibx->over->get_art($xnum) // next; + # $xnum may be expired by another process + if ($smsg->{blob} eq $hex) { + warn <<""; +BUG: (non-fatal) $ekey #$xnum $smsg->{blob} still matches (old exp: $exp) + + next; + } # else: continue to unref + } my $m = defined($exp) ? "mismatch (!= $exp)" : 'stale'; warn("# $xnum:$hex (#@$docids): $m\n"); for my $i (@$docids) { _unref_doc($sync, $i, $ibx, $xnum, $bin); } + return if $sync->{quit}; } } - _unref_stale_range($sync, $ibx, "> $hi") if defined($hi); + defined($hi) and ($hi < $max) and + _unref_stale_range($sync, $ibx, "xnum > $hi AND xnum <= $max"); } sub _reindex_inbox ($$$) {