diff options
Diffstat (limited to 'lib/PublicInbox/ExtSearchIdx.pm')
| -rw-r--r-- | lib/PublicInbox/ExtSearchIdx.pm | 556 |
1 files changed, 324 insertions, 232 deletions
diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm index 6b29789a..763a124c 100644 --- a/lib/PublicInbox/ExtSearchIdx.pm +++ b/lib/PublicInbox/ExtSearchIdx.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org> +# Copyright (C) all contributors <meta@public-inbox.org> # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt> # Detached/external index cross inbox search indexing support @@ -16,12 +16,13 @@ package PublicInbox::ExtSearchIdx; use strict; use v5.10.1; -use parent qw(PublicInbox::ExtSearch PublicInbox::Lock); +use parent qw(PublicInbox::ExtSearch PublicInbox::Umask PublicInbox::Lock); use Carp qw(croak carp); +use Scalar::Util qw(blessed); use Sys::Hostname qw(hostname); -use POSIX qw(strftime); use File::Glob qw(bsd_glob GLOB_NOSORT); use PublicInbox::MultiGit; +use PublicInbox::Spawn (); use PublicInbox::Search; use PublicInbox::SearchIdx qw(prepare_stack is_ancestor is_bad_blob); use PublicInbox::OverIdx; @@ -33,6 +34,7 @@ use PublicInbox::ContentHash qw(content_hash); use PublicInbox::Eml; use PublicInbox::DS qw(now add_timer); use DBI qw(:sql_types); # SQL_BLOB +use PublicInbox::Admin qw(fmt_localtime); sub new { my (undef, $dir, $opt) = @_; @@ -58,6 +60,7 @@ 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 } @@ -89,6 +92,7 @@ sub attach_config { $self->{ibx_map}->{$ibx->eidx_key} //= do { push @{$self->{ibx_active}}, $ibx; push @{$self->{ibx_known}}, $ibx; + $ibx; } } # invalidate cache @@ -110,18 +114,36 @@ sub check_batch_limit ($) { ${$req->{need_checkpoint}} = 1 if $n >= $self->{batch_bytes}; } +sub bad_ibx_id ($$;$) { + my ($self, $ibx_id, $cb) = @_; + my $msg = "E: bad/stale ibx_id=#$ibx_id encountered"; + my $ekey = $self->{oidx}->dbh->selectrow_array(<<EOM, undef, $ibx_id); +SELECT eidx_key FROM inboxes WHERE ibx_id = ? LIMIT 1 +EOM + $msg .= " (formerly `$ekey')" if defined $ekey; + $cb //= \&carp; + $cb->($msg, "\nE: running $0 --gc may be required"); +} + +sub check_xr3 ($$$) { + my ($self, $id2pos, $xr3) = @_; + @$xr3 = grep { + defined($id2pos->{$_->[0]}) ? 1 : bad_ibx_id($self, $_->[0]) + } @$xr3; +} + sub apply_boost ($$) { my ($req, $smsg) = @_; my $id2pos = $req->{id2pos}; # index in ibx_sorted my $xr3 = $req->{self}->{oidx}->get_xref3($smsg->{num}, 1); - @$xr3 = sort { + check_xr3($req->{self}, $id2pos, $xr3); + @$xr3 = sort { # sort ascending $id2pos->{$a->[0]} <=> $id2pos->{$b->[0]} || $a->[1] <=> $b->[1] # break ties with {xnum} } @$xr3; - my $top_blob = unpack('H*', $xr3->[0]->[2]); my $new_smsg = $req->{new_smsg}; - return if $top_blob ne $new_smsg->{blob}; # loser + return if $xr3->[0]->[2] ne $new_smsg->oidbin; # loser # replace the old smsg with the more boosted one $new_smsg->{num} = $smsg->{num}; @@ -129,32 +151,81 @@ sub apply_boost ($$) { $req->{self}->{oidx}->add_overview($req->{eml}, $new_smsg); } +sub remove_doc ($$) { + my ($self, $docid) = @_; + $self->{oidx}->delete_by_num($docid); + $self->{oidx}->eidxq_del($docid); + $self->idx_shard($docid)->ipc_do('xdb_remove', $docid); +} + +sub _unref_doc ($$$$$;$) { + my ($sync, $docid, $ibx, $xnum, $oidbin, $eml) = @_; + my $smsg; + if (ref($docid)) { + $smsg = $docid; + $docid = $smsg->{num}; + } + if (defined($oidbin) && defined($xnum) && blessed($ibx) && $ibx->over) { + my $smsg = $ibx->over->get_art($xnum); + if ($smsg && $smsg->oidbin eq $oidbin) { + carp("BUG: (non-fatal) ".$ibx->eidx_key. + " #$xnum $smsg->{blob} still valid"); + return; + } + } + my $s = 'DELETE FROM xref3 WHERE oidbin = ?'; + $s .= ' AND ibx_id = ?' if defined($ibx); + $s .= ' AND xnum = ?' if defined($xnum); + my $del = $sync->{self}->{oidx}->dbh->prepare_cached($s); + my $col = 0; + $del->bind_param(++$col, $oidbin, SQL_BLOB); + $del->bind_param(++$col, $ibx->{-ibx_id}) if $ibx; + $del->bind_param(++$col, $xnum) if defined($xnum); + $del->execute; + my $xr3 = $sync->{self}->{oidx}->get_xref3($docid); + if (scalar(@$xr3) == 0) { # all gone + remove_doc($sync->{self}, $docid); + } else { # enqueue for reindex of remaining messages + if ($ibx) { + my $ekey = $ibx->{-gc_eidx_key} // $ibx->eidx_key; + my $idx = $sync->{self}->idx_shard($docid); + $idx->ipc_do('remove_eidx_info', $docid, $ekey, $eml); + } # else: we can't remove_eidx_info in reindex-only path + + # replace invalidated blob ASAP with something which should be + # readable since we may commit the transaction on checkpoint. + # eidxq processing will re-apply boost + $smsg //= $sync->{self}->{oidx}->get_art($docid); + my $hex = unpack('H*', $oidbin); + if ($smsg && $smsg->{blob} eq $hex) { + $xr3->[0] =~ /:([a-f0-9]{40,}+)\z/ or + die "BUG: xref $xr3->[0] has no OID"; + $sync->{self}->{oidx}->update_blob($smsg, $1); + } + # yes, add, we'll need to re-apply boost + $sync->{self}->{oidx}->eidxq_add($docid); + } + @$xr3 +} + sub do_xpost ($$) { my ($req, $smsg) = @_; my $self = $req->{self}; my $docid = $smsg->{num}; - my $idx = $self->idx_shard($docid); my $oid = $req->{oid}; my $xibx = $req->{ibx}; my $eml = $req->{eml}; - my $eidx_key = $xibx->eidx_key; if (my $new_smsg = $req->{new_smsg}) { # 'm' on cross-posted message + my $eidx_key = $xibx->eidx_key; my $xnum = $req->{xnum}; $self->{oidx}->add_xref3($docid, $xnum, $oid, $eidx_key); + my $idx = $self->idx_shard($docid); $idx->ipc_do('add_eidx_info', $docid, $eidx_key, $eml); apply_boost($req, $smsg) if $req->{boost_in_use}; - } else { # 'd' - my $rm_eidx_info; - my $nr = $self->{oidx}->remove_xref3($docid, $oid, $eidx_key, - \$rm_eidx_info); - if ($nr == 0) { - $self->{oidx}->eidxq_del($docid); - $idx->ipc_do('xdb_remove', $docid); - } elsif ($rm_eidx_info) { - $idx->ipc_do('remove_eidx_info', - $docid, $eidx_key, $eml); - $self->{oidx}->eidxq_add($docid); # yes, add - } + } else { # 'd' no {xnum} + $self->git->async_wait_all; + $oid = pack('H*', $oid); + _unref_doc($req, $docid, $xibx, undef, $oid, $eml); } } @@ -216,21 +287,12 @@ sub do_step ($) { # main iterator for adding messages to the index do_finalize($req); } -sub _blob_missing ($$) { # called when $smsg->{blob} is bad +sub _blob_missing ($$) { # called when a known $smsg->{blob} is gone my ($req, $smsg) = @_; - my $self = $req->{self}; - my $xref3 = $self->{oidx}->get_xref3($smsg->{num}); - my @keep = grep(!/:$smsg->{blob}\z/, @$xref3); - if (@keep) { - $keep[0] =~ /:([a-f0-9]{40,}+)\z/ or - die "BUG: xref $keep[0] has no OID"; - my $oidhex = $1; - $self->{oidx}->remove_xref3($smsg->{num}, $smsg->{blob}); - my $upd = $self->{oidx}->update_blob($smsg, $oidhex); - my $saved = $self->{oidx}->get_art($smsg->{num}); - } else { - $self->{oidx}->delete_by_num($smsg->{num}); - } + # xnum and ibx are unknown, we only call this when an entry from + # /ei*/over.sqlite3 is bad, not on entries from xap*/over.sqlite3 + $req->{self}->git->async_wait_all; + _unref_doc($req, $smsg, undef, undef, $smsg->oidbin); } sub ck_existing { # git->cat_async callback @@ -251,8 +313,8 @@ 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); @@ -262,6 +324,7 @@ sub cur_ibx_xnum ($$) { my ($id, $prev); while (my $x = $ibx->over->next_by_mid($mid, \$id, \$prev)) { return $x->{num} if $x->{blob} eq $req->{oid}; + push @$mismatch, $x if $mismatch; } } undef; @@ -276,8 +339,15 @@ sub index_oid { # git->cat_async callback for 'm' blob => $oid, }, 'PublicInbox::Smsg'; $new_smsg->set_bytes($$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); } @@ -342,96 +412,130 @@ sub _sync_inbox ($$$) { undef; } -sub gc_unref_doc ($$$$) { - my ($self, $ibx_id, $eidx_key, $docid) = @_; - my $remain = 0; - # for debug/info purposes, oids may no longer be accessible - my $dbh = $self->{oidx}->dbh; - my $sth = $dbh->prepare_cached(<<'', undef, 1); -SELECT oidbin FROM xref3 WHERE docid = ? AND ibx_id = ? - - $sth->execute($docid, $ibx_id); - my @oid = map { unpack('H*', $_->[0]) } @{$sth->fetchall_arrayref}; - for my $oid (@oid) { - $remain += $self->{oidx}->remove_xref3($docid, $oid, $eidx_key); - } - if ($remain) { - $self->{oidx}->eidxq_add($docid); # enqueue for reindex - for my $oid (@oid) { - warn "I: unref #$docid $eidx_key $oid\n"; - } - } else { - warn "I: remove #$docid $eidx_key @oid\n"; - $self->idx_shard($docid)->ipc_do('xdb_remove', $docid); - } -} - -sub eidx_gc { - my ($self, $opt) = @_; - $self->{cfg} or die "E: GC requires ->attach_config\n"; - $opt->{-idx_gc} = 1; - $self->idx_init($opt); # acquire lock via V2Writable::_idx_init - - my $dbh = $self->{oidx}->dbh; - $dbh->do('PRAGMA case_sensitive_like = ON'); # only place we use LIKE - my $x3_doc = $dbh->prepare('SELECT docid FROM xref3 WHERE ibx_id = ?'); - my $ibx_ck = $dbh->prepare('SELECT ibx_id,eidx_key FROM inboxes'); - my $lc_i = $dbh->prepare(<<''); -SELECT key FROM eidx_meta WHERE key LIKE ? ESCAPE ? - +sub eidx_gc_scan_inboxes ($$) { + my ($self, $sync) = @_; + my ($x3_doc, $ibx_ck); +restart: + $x3_doc = $self->{oidx}->dbh->prepare(<<EOM); +SELECT docid,xnum,oidbin 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}; $self->{midx}->remove_eidx_key($eidx_key); - warn "I: deleting messages for $eidx_key...\n"; + warn "# deleting messages for $eidx_key...\n"; $x3_doc->execute($ibx_id); - while (defined(my $docid = $x3_doc->fetchrow_array)) { - gc_unref_doc($self, $ibx_id, $eidx_key, $docid); + 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 "# $r #$docid $eidx_key $oid\n"; + if (checkpoint_due($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); + 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"; } +} - # 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; + warn "# 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 "# 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 over 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(<<EOM); +SELECT MIN(num) FROM over WHERE num > 0 +EOM + $cur // return; # empty + my ($r, $n, %active_shards); + $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); + $active_shards{$idx} = $idx; + } + $cur = $n + 1; + } + if (checkpoint_due($sync)) { + for my $idx (values %active_shards) { + $nr += $idx->ipc_do('nr_quiet_rm') + } + %active_shards = (); + reindex_checkpoint($self, $sync); + } + } + warn "# 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 => $self, + }; + $self->idx_init($opt); # acquire lock via V2Writable::_idx_init + eidx_gc_scan_inboxes($self, $sync); + eidx_gc_scan_shards($self, $sync); done($self); } sub _ibx_for ($$$) { my ($self, $sync, $smsg) = @_; - my $ibx_id = delete($smsg->{ibx_id}) // die '{ibx_id} unset'; - my $pos = $sync->{id2pos}->{$ibx_id} // die "$ibx_id no pos"; + my $ibx_id = delete($smsg->{ibx_id}) // die 'BUG: {ibx_id} unset'; + my $pos = $sync->{id2pos}->{$ibx_id} // + bad_ibx_id($self, $ibx_id, \&croak); $self->{-ibx_ary_known}->[$pos] // die "BUG: ibx for $smsg->{blob} not mapped" } @@ -488,12 +592,14 @@ sub _reindex_finalize ($$$) { } return if $nr == 1; # likely, all good + $self->git->async_wait_all; warn "W: #$docid split into $nr due to deduplication change\n"; my @todo; for my $ary (values %$by_chash) { for my $x (reverse @$ary) { warn "removing #$docid xref3 $x->{blob}\n"; - my $n = $self->{oidx}->remove_xref3($docid, $x->{blob}); + my $bin = $x->oidbin; + my $n = _unref_doc($sync, $docid, undef, undef, $bin); die "BUG: $x->{blob} invalidated #$docid" if $n == 0; } my $x = pop(@$ary) // die "BUG: #$docid {by_chash} empty"; @@ -524,15 +630,14 @@ sub _reindex_oid { # git->cat_async callback my $expect_oid = $req->{xr3r}->[$req->{ix}]->[2]; my $docid = $orig_smsg->{num}; if (is_bad_blob($oid, $type, $size, $expect_oid)) { - my $remain = $self->{oidx}->remove_xref3($docid, $expect_oid); + my $oidbin = pack('H*', $expect_oid); + my $remain = _unref_doc($sync, $docid, undef, undef, $oidbin); if ($remain == 0) { - warn "W: #$docid gone or corrupted\n"; - $self->idx_shard($docid)->ipc_do('xdb_remove', $docid); + warn "W: #$docid ($oid) gone or corrupt\n"; } elsif (my $next_oid = $req->{xr3r}->[++$req->{ix}]->[2]) { $self->git->cat_async($next_oid, \&_reindex_oid, $req); } else { - warn "BUG: #$docid gone (UNEXPECTED)\n"; - $self->idx_shard($docid)->ipc_do('xdb_remove', $docid); + warn "BUG: #$docid ($oid) gone (UNEXPECTED)\n"; } return; } @@ -565,8 +670,7 @@ sub _reindex_smsg ($$$) { warn <<""; BUG? #$docid $smsg->{blob} is not referenced by inboxes during reindex - $self->{oidx}->delete_by_num($docid); - $self->idx_shard($docid)->ipc_do('xdb_remove', $docid); + remove_doc($self, $docid); return; } @@ -574,7 +678,8 @@ BUG? #$docid $smsg->{blob} is not referenced by inboxes during reindex # hit the common case in _reindex_finalize without rereading # from git (or holding multiple messages in memory). my $id2pos = $sync->{id2pos}; # index in ibx_sorted - @$xr3 = sort { + check_xr3($self, $id2pos, $xr3); + @$xr3 = sort { # sort descending $id2pos->{$b->[0]} <=> $id2pos->{$a->[0]} || $b->[1] <=> $a->[1] # break ties with {xnum} @@ -645,15 +750,14 @@ sub eidxq_lock_acquire ($) { return $locked if $locked eq $cur; } my ($pid, $time, $euid, $ident) = split(/-/, $cur, 4); - my $t = strftime('%Y-%m-%d %k:%M:%S', gmtime($time)); + my $t = fmt_localtime($time); + local $self->{current_info} = 'eidxq'; if ($euid == $> && $ident eq host_ident) { - if (kill(0, $pid)) { - warn <<EOM; return; -I: PID:$pid (re)indexing Xapian since $t, it will continue our work + kill(0, $pid) and warn <<EOM and return; +# PID:$pid (re)indexing since $t, it will continue our work EOM - } if ($!{ESRCH}) { - warn "I: eidxq_lock is stale ($cur), clobbering\n"; + warn "# eidxq_lock is stale ($cur), clobbering\n"; return _eidxq_take($self); } warn "E: kill(0, $pid) failed: $!\n"; # fall-through: @@ -688,8 +792,8 @@ sub prep_id2pos ($) { sub eidxq_process ($$) { # for reindexing my ($self, $sync) = @_; - - return unless eidxq_lock_acquire($self); + local $self->{current_info} = 'eidxq process'; + return unless ($self->{cfg} && eidxq_lock_acquire($self)); my $dbh = $self->{oidx}->dbh; my $tot = $dbh->selectrow_array('SELECT COUNT(*) FROM eidxq') or return; ${$sync->{nr}} = 0; @@ -753,118 +857,118 @@ sub reindex_unseen ($$$$) { xnum => $xsmsg->{num}, # {mids} and {chash} will be filled in at _reindex_unseen }; - warn "I: reindex_unseen ${\$ibx->eidx_key}:$req->{xnum}:$req->{oid}\n"; + warn "# reindex_unseen ${\$ibx->eidx_key}:$req->{xnum}:$req->{oid}\n"; $self->git->cat_async($xsmsg->{blob}, \&_reindex_unseen, $req); } -sub _reindex_check_unseen ($$$) { +sub _unref_stale_range ($$$) { + my ($sync, $ibx, $lt_or_gt) = @_; + my $r; + my $lim = 10000; + do { + $r = $sync->{self}->{oidx}->dbh->selectall_arrayref( + <<EOS, undef, $ibx->{-ibx_id}); +SELECT docid,xnum,oidbin FROM xref3 +WHERE ibx_id = ? AND $lt_or_gt LIMIT $lim +EOS + return if $sync->{quit}; + for (@$r) { # hopefully rare, not worth optimizing: + my ($docid, $xnum, $oidbin) = @$_; + my $hex = unpack('H*', $oidbin); + warn("# $xnum:$hex (#$docid): stale\n"); + _unref_doc($sync, $docid, $ibx, $xnum, $oidbin); + } + } while (scalar(@$r) == $lim); + 1; +} + +sub _reindex_check_ibx ($$$) { my ($self, $sync, $ibx) = @_; my $ibx_id = $ibx->{-ibx_id}; - my $slice = 1000; + my $slice = 10000; + my $opt = { limit => $slice }; my ($beg, $end) = (1, $slice); + 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 unseen %u/".$ibx->over->max."\n"; + local $sync->{-regen_fmt} = "$ekey checking %u/$max\n"; ${$sync->{nr}} = 0; - - while (scalar(@{$msgs = $ibx->over->query_xover($beg, $end)})) { + my $fast = $sync->{-opt}->{fast}; + my $usr; # _unref_stale_range (< $lo) called + my ($lo, $hi); + while (scalar(@{$msgs = $ibx->over->query_xover($beg, $end, $opt)})) { ${$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 } - - my $inx3 = $self->{oidx}->dbh->prepare_cached(<<'', undef, 1); -SELECT DISTINCT(docid) FROM xref3 WHERE -ibx_id = ? AND xnum = ? AND oidbin = ? - + ($lo, $hi) = ($msgs->[0]->{num}, $msgs->[-1]->{num}); + $usr //= _unref_stale_range($sync, $ibx, "xnum < $lo"); + my $x3a = $self->{oidx}->dbh->selectall_arrayref( + <<"", undef, $ibx_id, $lo, $hi); +SELECT xnum,oidbin,docid FROM xref3 WHERE +ibx_id = ? AND xnum >= ? AND xnum <= ? + + my %x3m; + for (@$x3a) { + my $k = pack('J', $_->[0]) . $_->[1]; + push @{$x3m{$k}}, $_->[2]; + } + undef $x3a; for my $xsmsg (@$msgs) { - my $oidbin = pack('H*', $xsmsg->{blob}); - $inx3->bind_param(1, $ibx_id); - $inx3->bind_param(2, $xsmsg->{num}); - $inx3->bind_param(3, $oidbin, SQL_BLOB); - $inx3->execute; - my $docids = $inx3->fetchall_arrayref; - # index messages which were totally missed - # the first time around ASAP: - if (scalar(@$docids) == 0) { + my $k = pack('JH*', $xsmsg->{num}, $xsmsg->{blob}); + my $docids = delete($x3m{$k}); + if (!defined($docids)) { reindex_unseen($self, $sync, $ibx, $xsmsg); - } else { # already seen, reindex later - for my $r (@$docids) { - $self->{oidx}->eidxq_add($r->[0]); + } elsif (!$fast) { + for my $num (@$docids) { + $self->{oidx}->eidxq_add($num); } } - last if $sync->{quit}; - } - last if $sync->{quit}; - } -} - -sub _reindex_check_stale ($$$) { - my ($self, $sync, $ibx) = @_; - my $min = 0; - my $pr = $sync->{-opt}->{-progress}; - my $fetching; - my $ekey = $ibx->eidx_key; - local $sync->{-regen_fmt} = - "$ekey check stale/missing %u/".$ibx->over->max."\n"; - ${$sync->{nr}} = 0; - do { - if (checkpoint_due($sync)) { - reindex_checkpoint($self, $sync); # release lock - } - # now, check if there's stale xrefs - my $iter = $self->{oidx}->dbh->prepare_cached(<<'', undef, 1); -SELECT docid,xnum,oidbin FROM xref3 WHERE ibx_id = ? AND docid > ? -ORDER BY docid,xnum ASC LIMIT 10000 - - $iter->execute($ibx->{-ibx_id}, $min); - $fetching = undef; - - while (my ($docid, $xnum, $oidbin) = $iter->fetchrow_array) { return if $sync->{quit}; - ${$sync->{nr}} = $xnum; - - $fetching = $min = $docid; - my $smsg = $ibx->over->get_art($xnum); - my $err; - if (!$smsg) { - $err = 'stale'; - } elsif (pack('H*', $smsg->{blob}) ne $oidbin) { - $err = "mismatch (!= $smsg->{blob})"; - } else { - next; # likely, all good + } + next unless scalar keys %x3m; + $self->git->async_wait_all; # wait for reindex_unseen + + # eliminate stale/mismatched entries + my %mismatch = map { $_->{num} => $_->{blob} } @$msgs; + while (my ($k, $docids) = each %x3m) { + 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 } - # current_info already has eidx_key - my $oidhex = unpack('H*', $oidbin); - warn "$xnum:$oidhex (#$docid): $err\n"; - my $del = $self->{oidx}->dbh->prepare_cached(<<''); -DELETE FROM xref3 WHERE ibx_id = ? AND xnum = ? AND oidbin = ? - - $del->bind_param(1, $ibx->{-ibx_id}); - $del->bind_param(2, $xnum); - $del->bind_param(3, $oidbin, SQL_BLOB); - $del->execute; - - # get_xref3 over-fetches, but this is a rare path: - my $xr3 = $self->{oidx}->get_xref3($docid); - 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); - $self->{oidx}->eidxq_add($docid); # yes, add + 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}; } - } while (defined $fetching); + } + defined($hi) and ($hi < $max) and + _unref_stale_range($sync, $ibx, "xnum > $hi AND xnum <= $max"); } sub _reindex_inbox ($$$) { @@ -874,14 +978,14 @@ sub _reindex_inbox ($$$) { if (defined(my $err = _ibx_index_reject($ibx))) { warn "W: cannot reindex $ekey ($err)\n"; } else { - _reindex_check_unseen($self, $sync, $ibx); - _reindex_check_stale($self, $sync, $ibx) unless $sync->{quit}; + _reindex_check_ibx($self, $sync, $ibx); } delete @$ibx{qw(over mm search git)}; # won't need these for a bit } sub eidx_reindex { my ($self, $sync) = @_; + return unless $self->{cfg}; # acquire eidxq_lock early because full reindex takes forever # and incremental -extindex processes can run during our checkpoints @@ -902,6 +1006,7 @@ sub sync_inbox { my $err = _sync_inbox($self, $sync, $ibx); delete @$ibx{qw(mm over)}; warn $err, "\n" if defined($err); + $err; } sub dd_smsg { # git->cat_async callback @@ -928,9 +1033,8 @@ sub dd_smsg { # git->cat_async callback my $oidx = $self->{oidx}; for my $smsg (@$ary) { my $gone = $smsg->{num}; - $oidx->merge_xref3($keep->{num}, $gone, $smsg->{blob}); - $self->idx_shard($gone)->ipc_do('xdb_remove', $gone); - $oidx->delete_by_num($gone); + $oidx->merge_xref3($keep->{num}, $gone, $smsg->oidbin); + remove_doc($self, $gone); } } } @@ -1097,12 +1201,6 @@ sub update_last_commit { # overrides V2Writable $self->{oidx}->eidx_meta($meta_key, $latest_cmt); } -sub _idx_init { # with_umask callback - my ($self, $opt) = @_; - PublicInbox::V2Writable::_idx_init($self, $opt); # acquires ei.lock - $self->{midx} = PublicInbox::MiscIdx->new($self); -} - sub symlink_packs ($$) { my ($ibx, $pd) = @_; my $ret = 0; @@ -1135,7 +1233,7 @@ sub idx_init { # similar to V2Writable $self->git->cleanup; my $mode = 0644; my $ALL = $self->git->{git_dir}; # topdir/ALL.git - my ($has_new, $alt, $seen); + my ($has_new, $alt, $seen, $prune, $prune_nr); if ($opt->{-private}) { # LeiStore my $local = "$self->{topdir}/local"; # lei/store $self->{mg} //= PublicInbox::MultiGit->new($self->{topdir}, @@ -1151,8 +1249,8 @@ sub idx_init { # similar to V2Writable } else { # extindex has no epochs $self->{mg} //= PublicInbox::MultiGit->new($self->{topdir}, 'ALL.git'); - ($alt, $seen) = $self->{mg}->read_alternates(\$mode, - $opt->{-idx_gc}); + $prune = $opt->{-idx_gc} ? \$prune_nr : undef; + ($alt, $seen) = $self->{mg}->read_alternates(\$mode, $prune); PublicInbox::Import::init_bare($ALL); } @@ -1186,17 +1284,19 @@ sub idx_init { # similar to V2Writable } $new .= "$d\n"; } - ($has_new || $new ne '') and + ($has_new || $prune_nr || $new ne '') and $self->{mg}->write_alternates($mode, $alt, $new); - $git_midx and $self->with_umask(sub { + my $restore = $self->with_umask; + if ($git_midx) { my @cmd = ('multi-pack-index'); push @cmd, '--no-progress' if ($opt->{quiet}//0) > 1; my $lk = $self->lock_for_scope; system('git', "--git-dir=$ALL", @cmd, 'write'); # ignore errors, fairly new command, may not exist - }); + } $self->parallel_init($self->{indexlevel}); - $self->with_umask(\&_idx_init, $self, $opt); + PublicInbox::V2Writable::_idx_init($self, $opt); # acquires ei.lock + $self->{midx} = PublicInbox::MiscIdx->new($self); $self->{oidx}->begin_lazy; $self->{oidx}->eidx_prep; $self->{midx}->create_xdb if $new ne ''; @@ -1305,25 +1405,16 @@ sub eidx_watch { # public-inbox-extindex --watch main loop }; my $quit = PublicInbox::SearchIdx::quit_cb($sync); $sig->{QUIT} = $sig->{INT} = $sig->{TERM} = $quit; - my $sigfd = PublicInbox::Sigfd->new($sig, - $PublicInbox::Syscall::SFD_NONBLOCK); - @SIG{keys %$sig} = values(%$sig) if !$sigfd; local $self->{-watch_sync} = $sync; # for ->on_inbox_unlock - if (!$sigfd) { - # wake up every second to accept signals if we don't - # have signalfd or IO::KQueue: - PublicInbox::DS::sig_setmask($oldset); - PublicInbox::DS->SetLoopTimeout(1000); - } - PublicInbox::DS->SetPostLoopCallback(sub { !$sync->{quit} }); + local @PublicInbox::DS::post_loop_do = (sub { !$sync->{quit} }); $pr->("initial scan complete, entering event loop\n") if $pr; - PublicInbox::DS->EventLoop; # calls InboxIdle->event_step + # calls InboxIdle->event_step: + PublicInbox::DS::event_loop($sig, $oldset); done($self); } no warnings 'once'; *done = \&PublicInbox::V2Writable::done; -*with_umask = \&PublicInbox::InboxWritable::with_umask; *parallel_init = \&PublicInbox::V2Writable::parallel_init; *nproc_shards = \&PublicInbox::V2Writable::nproc_shards; *sync_prepare = \&PublicInbox::V2Writable::sync_prepare; @@ -1333,5 +1424,6 @@ no warnings 'once'; *idx_shard = \&PublicInbox::V2Writable::idx_shard; *reindex_checkpoint = \&PublicInbox::V2Writable::reindex_checkpoint; *checkpoint = \&PublicInbox::V2Writable::checkpoint; +*barrier = \&PublicInbox::V2Writable::barrier; 1; |