use Sys::Hostname qw(hostname);
use POSIX qw(strftime);
use File::Glob qw(bsd_glob GLOB_NOSORT);
+use PublicInbox::MultiGit;
use PublicInbox::Search;
use PublicInbox::SearchIdx qw(prepare_stack is_ancestor is_bad_blob);
use PublicInbox::OverIdx;
$self->{ibx_map}->{$ibx->eidx_key} //= do {
push @{$self->{ibx_active}}, $ibx;
push @{$self->{ibx_known}}, $ibx;
+ $ibx;
}
}
# invalidate cache
||
$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};
my $xref3 = $self->{oidx}->get_xref3($smsg->{num});
my @keep = grep(!/:$smsg->{blob}\z/, @$xref3);
if (@keep) {
+ warn "E: $smsg->{blob} gone, removing #$smsg->{num}\n";
$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});
+ $self->{oidx}->update_blob($smsg, $oidhex) or warn <<EOM;
+E: #$smsg->{num} gone ($smsg->{blob} => $oidhex)
+EOM
} else {
+ warn "E: $smsg->{blob} gone, removing #$smsg->{num}\n";
$self->{oidx}->delete_by_num($smsg->{num});
}
}
sub gc_unref_doc ($$$$) {
my ($self, $ibx_id, $eidx_key, $docid) = @_;
- my $dbh = $self->{oidx}->dbh;
-
+ my $remain = 0;
# for debug/info purposes, oids may no longer be accessible
+ my $dbh = $self->{oidx}->dbh;
my $sth = $dbh->prepare_cached(<<'', undef, 1);
SELECT oidbin FROM xref3 WHERE docid = ? AND ibx_id = ?
$sth->execute($docid, $ibx_id);
my @oid = map { unpack('H*', $_->[0]) } @{$sth->fetchall_arrayref};
-
- $dbh->prepare_cached(<<'')->execute($docid, $ibx_id);
-DELETE FROM xref3 WHERE docid = ? AND ibx_id = ?
-
- my $remain = $self->{oidx}->get_xref3($docid);
- if (scalar(@$remain)) {
+ for my $oid (@oid) {
+ $remain += $self->{oidx}->remove_xref3($docid, $oid, $eidx_key);
+ }
+ if ($remain) {
$self->{oidx}->eidxq_add($docid); # enqueue for reindex
for my $oid (@oid) {
warn "I: unref #$docid $eidx_key $oid\n";
}
}
-sub eidx_gc {
- my ($self, $opt) = @_;
- $self->{cfg} or die "E: GC requires ->attach_config\n";
- $opt->{-idx_gc} = 1;
- $self->idx_init($opt); # acquire lock via V2Writable::_idx_init
-
- my $dbh = $self->{oidx}->dbh;
- $dbh->do('PRAGMA case_sensitive_like = ON'); # only place we use LIKE
- my $x3_doc = $dbh->prepare('SELECT docid FROM xref3 WHERE ibx_id = ?');
- my $ibx_ck = $dbh->prepare('SELECT ibx_id,eidx_key FROM inboxes');
- my $lc_i = $dbh->prepare(<<'');
-SELECT key FROM eidx_meta WHERE key LIKE ? ESCAPE ?
-
+sub eidx_gc_scan_inboxes ($$) {
+ 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;
+ # 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 $nr != 0;
+
+ my ($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', $cur);
+ if (checkpoint_due($sync)) {
+ $exists = undef;
+ reindex_checkpoint($self, $sync);
+ goto restart;
+ }
+ }
+}
+
+sub eidx_gc {
+ my ($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);
}
sub eidxq_process ($$) { # for reindexing
my ($self, $sync) = @_;
+ return unless $self->{cfg};
return unless eidxq_lock_acquire($self);
my $dbh = $self->{oidx}->dbh;
sub eidx_reindex {
my ($self, $sync) = @_;
+ return unless $self->{cfg};
# acquire eidxq_lock early because full reindex takes forever
# and incremental -extindex processes can run during our checkpoints
$self->git->cleanup;
my $mode = 0644;
- my $ALL = $self->git->{git_dir}; # ALL.git
- my $old = -d $ALL;
+ my $ALL = $self->git->{git_dir}; # topdir/ALL.git
+ my ($has_new, $alt, $seen);
if ($opt->{-private}) { # LeiStore
+ my $local = "$self->{topdir}/local"; # lei/store
+ $self->{mg} //= PublicInbox::MultiGit->new($self->{topdir},
+ 'ALL.git', 'local');
$mode = 0600;
- if (!$old) {
- umask 077; # don't bother restoring
+ unless (-d $ALL) {
+ umask 077; # don't bother restoring for lei
PublicInbox::Import::init_bare($ALL);
$self->git->qx(qw(config core.sharedRepository 0600));
}
- } else {
- PublicInbox::Import::init_bare($ALL) unless $old;
- }
- my $info_dir = "$ALL/objects/info";
- my $alt = "$info_dir/alternates";
- my (@old, @new, %seen); # seen: st_dev + st_ino
- if (-e $alt) {
- open(my $fh, '<', $alt) or die "open $alt: $!";
- $mode = (stat($fh))[2] & 07777;
- while (my $line = <$fh>) {
- chomp(my $d = $line);
-
- # expand relative path (/local/ stuff)
- substr($d, 0, 3) eq '../' and
- $d = "$ALL/objects/$d";
- if (my @st = stat($d)) {
- next if $seen{"$st[0]\0$st[1]"}++;
- } else {
- warn "W: stat($d) failed (from $alt): $!\n";
- next if $opt->{-idx_gc};
- }
- push @old, $line;
- }
+ ($alt, $seen) = $self->{mg}->read_alternates(\$mode);
+ $has_new = $self->{mg}->merge_epochs($alt, $seen);
+ } else { # extindex has no epochs
+ $self->{mg} //= PublicInbox::MultiGit->new($self->{topdir},
+ 'ALL.git');
+ ($alt, $seen) = $self->{mg}->read_alternates(\$mode,
+ $opt->{-idx_gc});
+ PublicInbox::Import::init_bare($ALL);
}
- # for LeiStore, and possibly some mirror-only state
- if (opendir(my $dh, my $local = "$self->{topdir}/local")) {
- # highest numbered epoch first
- for my $n (sort { $b <=> $a } map { substr($_, 0, -4) + 0 }
- grep(/\A[0-9]+\.git\z/, readdir($dh))) {
- my $d = "$local/$n.git/objects"; # absolute path
- if (my @st = stat($d)) {
- next if $seen{"$st[0]\0$st[1]"}++;
- # favor relative paths for rename-friendliness
- push @new, "../../local/$n.git/objects\n";
- } else {
- warn "W: stat($d) failed: $!\n";
- }
- }
- }
# git-multi-pack-index(1) can speed up "git cat-file" startup slightly
- my $dh;
my $git_midx = 0;
my $pd = "$ALL/objects/pack";
- if (!mkdir($pd) && $!{EEXIST} && opendir($dh, $pd)) {
- # drop stale symlinks
+ if (opendir(my $dh, $pd)) { # drop stale symlinks
while (defined(my $dn = readdir($dh))) {
if ($dn =~ /\.(?:idx|pack|promisor|bitmap|rev)\z/) {
my $f = "$pd/$dn";
unlink($f) if -l $f && !-e $f;
}
}
- undef $dh;
+ } elsif ($!{ENOENT}) {
+ mkdir($pd) or die "mkdir($pd): $!";
+ } else {
+ die "opendir($pd): $!";
}
+ my $new = '';
for my $ibx (@{ibx_sorted($self, 'active')}) {
# create symlinks for multi-pack-index
$git_midx += symlink_packs($ibx, $pd);
# add new lines to our alternates file
- my $line = $ibx->git->{git_dir} . "/objects\n";
- chomp(my $d = $line);
+ my $d = $ibx->git->{git_dir} . '/objects';
+ next if exists $alt->{$d};
if (my @st = stat($d)) {
- next if $seen{"$st[0]\0$st[1]"}++;
+ next if $seen->{"$st[0]\0$st[1]"}++;
} else {
warn "W: stat($d) failed (from $ibx->{inboxdir}): $!\n";
next if $opt->{-idx_gc};
}
- push @new, $line;
- }
- if (scalar @new) {
- push @old, @new;
- my $o = \@old;
- PublicInbox::V2Writable::write_alternates($info_dir, $mode, $o);
+ $new .= "$d\n";
}
+ ($has_new || $new ne '') and
+ $self->{mg}->write_alternates($mode, $alt, $new);
$git_midx and $self->with_umask(sub {
my @cmd = ('multi-pack-index');
push @cmd, '--no-progress' if ($opt->{quiet}//0) > 1;
$self->with_umask(\&_idx_init, $self, $opt);
$self->{oidx}->begin_lazy;
$self->{oidx}->eidx_prep;
- $self->{midx}->create_xdb if @new;
+ $self->{midx}->create_xdb if $new ne '';
}
sub _watch_commit { # PublicInbox::DS::add_timer callback
sub eidx_watch { # public-inbox-extindex --watch main loop
my ($self, $opt) = @_;
- local %SIG = %SIG;
+ local @SIG{keys %SIG} = values %SIG;
for my $sig (qw(HUP USR1 TSTP QUIT INT TERM)) {
$SIG{$sig} = sub { warn "SIG$sig ignored while scanning\n" };
}
};
my $quit = PublicInbox::SearchIdx::quit_cb($sync);
$sig->{QUIT} = $sig->{INT} = $sig->{TERM} = $quit;
- my $sigfd = PublicInbox::Sigfd->new($sig,
- $PublicInbox::Syscall::SFD_NONBLOCK);
- %SIG = (%SIG, %$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} });
$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);
}