use parent qw(PublicInbox::ExtSearch PublicInbox::Lock);
use Carp qw(croak carp);
use PublicInbox::Search;
-use PublicInbox::SearchIdx qw(crlf_adjust);
+use PublicInbox::SearchIdx qw(crlf_adjust prepare_stack is_ancestor);
use PublicInbox::OverIdx;
+use PublicInbox::MiscIdx;
+use PublicInbox::MID qw(mids);
use PublicInbox::V2Writable;
use PublicInbox::InboxWritable;
+use PublicInbox::ContentHash qw(content_hash);
use PublicInbox::Eml;
use File::Spec;
sub new {
- my (undef, $dir, $opt, $shard) = @_;
+ my (undef, $dir, $opt) = @_;
+ $dir = File::Spec->canonpath($dir);
my $l = $opt->{indexlevel} // 'full';
$l !~ $PublicInbox::SearchIdx::INDEXLEVELS and
die "invalid indexlevel=$l\n";
sub attach_inbox {
my ($self, $ibx) = @_;
+ $ibx = PublicInbox::InboxWritable->new($ibx);
my $key = $ibx->eidx_key;
if (!$ibx->over || !$ibx->mm) {
warn "W: skipping $key (unindexed)\n";
$size == 0 ? 1 : 0; # size == 0 means purged
}
+sub check_batch_limit ($) {
+ my ($req) = @_;
+ my $self = $req->{self};
+ my $new_smsg = $req->{new_smsg};
+
+ # {raw_bytes} may be unset, so just use {bytes}
+ my $n = $self->{transact_bytes} += $new_smsg->{bytes};
+
+ # set flag for PublicInbox::V2Writable::index_todo:
+ ${$req->{need_checkpoint}} = 1 if $n >= $self->{batch_bytes};
+}
+
sub do_xpost ($$) {
my ($req, $smsg) = @_;
- my $self = $req->{eidx};
+ my $self = $req->{self};
my $docid = $smsg->{num};
my $idx = $self->idx_shard($docid);
my $oid = $req->{oid};
- my $xibx = $self->{sync}->{ibx};
+ my $xibx = $req->{ibx};
my $eml = $req->{eml};
if (my $new_smsg = $req->{new_smsg}) { # 'm' on cross-posted message
my $xnum = $req->{xnum};
- $idx->shard_add_xref3($docid, $xnum, $oid, $xibx, $eml);
+ $self->{oidx}->add_xref3($docid, $xnum, $oid, $xibx->eidx_key);
+ $idx->shard_add_eidx_info($docid, $oid, $xibx, $eml);
+ check_batch_limit($req);
} else { # 'd'
- $idx->shard_remove_xref3($docid, $oid, $xibx, $eml);
+ $self->{oidx}->remove_xref3($docid, $oid, $xibx->eidx_key);
+ $idx->shard_remove_eidx_info($docid, $oid, $xibx, $eml);
}
}
+# called by V2Writable::sync_prepare
+sub artnum_max { $_[0]->{oidx}->eidx_max }
+
sub index_unseen ($) {
my ($req) = @_;
my $new_smsg = $req->{new_smsg} or die 'BUG: {new_smsg} unset';
- $new_smsg->populate($req->{eml}, $req);
- my $self = $req->{eidx};
+ my $eml = delete $req->{eml};
+ $new_smsg->populate($eml, $req);
+ my $self = $req->{self};
my $docid = $self->{oidx}->adj_counter('eidx_docid', '+');
$new_smsg->{num} = $docid;
my $idx = $self->idx_shard($docid);
- my $eml = delete $req->{eml};
$self->{oidx}->add_overview($eml, $new_smsg);
- $idx->index_raw(undef, $eml, $new_smsg, delete $new_smsg->{ibx});
+ my $oid = $new_smsg->{blob};
+ my $ibx = delete $req->{ibx} or die 'BUG: {ibx} unset';
+ $self->{oidx}->add_xref3($docid, $req->{xnum}, $oid, $ibx->eidx_key);
+ $idx->index_raw(undef, $eml, $new_smsg, $ibx);
+ check_batch_limit($req);
}
sub do_finalize ($) {
} elsif (exists $req->{new_smsg}) { # totally unseen messsage
index_unseen($req);
} else {
- warn "W: ignoring delete $req->{oid} (not found)\n";
+ # `d' message was already unindexed in the v1/v2 inboxes,
+ # so it's too noisy to warn, here.
+ }
+ # cur_cmt may be undef for unindex_oid, set by V2Writable::index_todo
+ if (defined(my $cur_cmt = $req->{cur_cmt})) {
+ ${$req->{latest_cmt}} = $cur_cmt;
}
}
sub do_step ($) { # main iterator for adding messages to the index
my ($req) = @_;
- my $self = $req->{eidx};
+ my $self = $req->{self};
while (1) {
if (my $next_arg = $req->{next_arg}) {
if (my $smsg = $self->{oidx}->next_by_mid(@$next_arg)) {
do_finalize($req);
}
+sub _blob_missing ($) { # called when req->{cur_smsg}->{blob} is bad
+ my ($req) = @_;
+ my $smsg = $req->{cur_smsg} or die 'BUG: {cur_smsg} missing';
+ 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});
+ }
+}
+
sub ck_existing { # git->cat_async callback
my ($bref, $oid, $type, $size, $req) = @_;
my $smsg = $req->{cur_smsg} or die 'BUG: {cur_smsg} missing';
- return if is_bad_blob($oid, $type, $size, $smsg->{blob});
- my $cur = PublicInbox::Eml->new($bref);
- if (content_digest($cur) eq $req->{chash}) {
- push @{$req->{indexed}}, $smsg; # for do_xpost
- } # else { index_unseen later }
+ if ($type eq 'missing') {
+ _blob_missing($req);
+ } elsif (!is_bad_blob($oid, $type, $size, $smsg->{blob})) {
+ my $cur = PublicInbox::Eml->new($bref);
+ if (content_hash($cur) eq $req->{chash}) {
+ push @{$req->{indexed}}, $smsg; # for do_xpost
+ } # else { index_unseen later }
+ }
do_step($req);
}
# return the number if so
sub cur_ibx_xnum ($$) {
my ($req, $bref) = @_;
- my $ibx = $req->{sync}->{ibx} or die 'BUG: current {ibx} missing';
+ my $ibx = $req->{ibx} or die 'BUG: current {ibx} missing';
# XXX overkill?
git_blob_digest($bref)->hexdigest eq $req->{oid} or die
undef;
}
-sub m_start { # git->cat_async callback for 'm'
+sub index_oid { # git->cat_async callback for 'm'
my ($bref, $oid, $type, $size, $req) = @_;
+ my $self = $req->{self};
+ local $self->{current_info} = "$self->{current_info} $oid";
return if is_bad_blob($oid, $type, $size, $req->{oid});
my $new_smsg = $req->{new_smsg} = bless {
blob => $oid,
- raw_bytes => $size,
}, 'PublicInbox::Smsg';
- $new_smsg->{bytes} = $new_smsg->{raw_bytes} + crlf_adjust($$bref);
+ $new_smsg->{bytes} = $size + crlf_adjust($$bref);
defined($req->{xnum} = cur_ibx_xnum($req, $bref)) or return;
- $new_smsg->{ibx} = $req->{sync}->{ibx};
+ ++${$req->{nr}};
do_step($req);
}
-sub d_start { # git->cat_async callback for 'd'
+sub unindex_oid { # git->cat_async callback for 'd'
my ($bref, $oid, $type, $size, $req) = @_;
+ my $self = $req->{self};
+ local $self->{current_info} = "$self->{current_info} $oid";
return if is_bad_blob($oid, $type, $size, $req->{oid});
return if defined(cur_ibx_xnum($req, $bref)); # was re-added
do_step($req);
}
-sub eidx_last_epoch_commit ($$$) {
- my ($self, $sync, $epoch) = @_;
- my $key = $sync->{ibx}->eidx_key;
- my $uidvalidity = $sync->{ibx}->uidvalidity;
- $self->{oidx}->eidx_meta("lc-v2:$key//$uidvalidity;$epoch");
+# overrides V2Writable::last_commits, called by sync_ranges via sync_prepare
+sub last_commits {
+ my ($self, $sync) = @_;
+ my $heads = [];
+ my $ekey = $sync->{ibx}->eidx_key;
+ my $uv = $sync->{ibx}->uidvalidity;
+ for my $i (0..$sync->{epoch_max}) {
+ $heads->[$i] = $self->{oidx}->eidx_meta("lc-v2:$ekey//$uv;$i");
+ }
+ $heads;
}
sub _sync_inbox ($$$) {
- my ($self, $opt, $ibx) = @_;
- my $sync = {
- need_checkpoint => \(my $bool = 0),
- unindex_range => {}, # EPOCH => oid_old..oid_new
- reindex => $opt->{reindex},
- -opt => $opt,
- eidx => $self,
- ibx => $ibx,
- };
- my $key = $ibx->eidx_key;
- my $u = $ibx->uidvalidity;
- my $oidx = $self->{oidx};
+ my ($self, $sync, $ibx) = @_;
+ $sync->{ibx} = $ibx;
+ $sync->{nr} = \(my $nr = 0);
my $v = $ibx->version;
+ my $ekey = $ibx->eidx_key;
if ($v == 2) {
my $epoch_max;
defined($ibx->git_dir_latest(\$epoch_max)) or return;
- my $heads = $sync->{ranges} = [];
- for my $i (0..$epoch_max) {
- $heads->[$i] = $oidx->eidx_meta("lc-v2:$key//$u;$i");
- }
-
-
+ $sync->{epoch_max} = $epoch_max;
+ sync_prepare($self, $sync); # or return # TODO: once MiscIdx is stable
} elsif ($v == 1) {
- my $lc = $oidx->eidx_meta("lc-v1:$key//$u");
- prepare_stack($sync, $lc ? "$lc..HEAD" : 'HEAD');
+ my $uv = $ibx->uidvalidity;
+ my $lc = $self->{oidx}->eidx_meta("lc-v1:$ekey//$uv");
+ my $stk = prepare_stack($sync, $lc ? "$lc..HEAD" : 'HEAD');
+ my $unit = { stack => $stk, git => $ibx->git };
+ push @{$sync->{todo}}, $unit;
} else {
- warn "E: $key unsupported inbox version (v$v)\n";
+ warn "E: $ekey unsupported inbox version (v$v)\n";
return;
}
+ unless ($sync->{quit}) {
+ index_todo($self, $sync, $_) for @{delete($sync->{todo}) // []};
+ $self->{midx}->index_ibx($ibx) unless $sync->{quit};
+ }
+ $ibx->git->cleanup; # done with this inbox, now
}
sub eidx_sync { # main entry point
$self->idx_init($opt); # acquire lock via V2Writable::_idx_init
$self->{oidx}->rethread_prepare($opt);
- _sync_inbox($self, $opt, $_) for (@{$self->{ibx_list}});
+ my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
+ local $self->{current_info} = '';
+ local $SIG{__WARN__} = sub {
+ $warn_cb->($self->{current_info}, ': ', @_);
+ };
+ my $sync = {
+ need_checkpoint => \(my $need_checkpoint = 0),
+ reindex => $opt->{reindex},
+ -opt => $opt,
+ self => $self,
+ -regen_fmt => "%u/?\n",
+ };
+ local $SIG{USR1} = sub { $need_checkpoint = 1 };
+ my $quit = sub { $sync->{quit} = 1; warn "gracefully quitting\n"; };
+ local $SIG{QUIT} = $quit;
+ local $SIG{INT} = $quit;
+ local $SIG{TERM} = $quit;
+
+ # don't use $_ here, it'll get clobbered by reindex_checkpoint
+ for my $ibx (@{$self->{ibx_list}}) {
+ _sync_inbox($self, $sync, $ibx);
+ last if $sync->{quit};
+ }
+
+ $self->{oidx}->rethread_done($opt) unless $sync->{quit};
+
+ PublicInbox::V2Writable::done($self);
+}
+
+sub update_last_commit { # overrides V2Writable
+ my ($self, $sync, $stk) = @_;
+ my $unit = $sync->{unit} // return;
+ my $latest_cmt = $stk ? $stk->{latest_cmt} : ${$sync->{latest_cmt}};
+ defined($latest_cmt) or return;
+ my $ibx = $sync->{ibx} or die 'BUG: {ibx} missing';
+ my $ekey = $ibx->eidx_key;
+ my $uv = $ibx->uidvalidity;
+ my $epoch = $unit->{epoch};
+ my $meta_key;
+ my $v = $ibx->version;
+ if ($v == 2) {
+ die 'No {epoch} for v2 unit' unless defined $epoch;
+ $meta_key = "lc-v2:$ekey//$uv;$epoch";
+ } elsif ($v == 1) {
+ die 'Unexpected {epoch} for v1 unit' if defined $epoch;
+ $meta_key = "lc-v1:$ekey//$uv";
+ } else {
+ die "Unsupported inbox version: $v";
+ }
+ my $last = $self->{oidx}->eidx_meta($meta_key);
+ if (defined $last && is_ancestor($self->git, $last, $latest_cmt)) {
+ my @cmd = (qw(rev-list --count), "$last..$latest_cmt");
+ chomp(my $n = $unit->{git}->qx(@cmd));
+ return if $n ne '' && $n == 0;
+ }
+ $self->{oidx}->eidx_meta($meta_key, $latest_cmt);
+}
+
+sub _idx_init { # with_umask callback
+ my ($self, $opt) = @_;
+ PublicInbox::V2Writable::_idx_init($self, $opt);
+ $self->{midx} = PublicInbox::MiscIdx->new($self);
}
sub idx_init { # similar to V2Writable
my $info_dir = "$ALL/objects/info";
my $alt = "$info_dir/alternates";
my $mode = 0644;
- my (%old, @old, %new, @new);
+ 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 (<$fh>) {
- push @old, $_ if !$old{$_}++;
+ while (my $line = <$fh>) {
+ chomp(my $d = $line);
+ if (my @st = stat($d)) {
+ next if $seen{"$st[0]\0$st[1]"}++;
+ } else {
+ warn "W: stat($d) failed (from $alt): $!\n";
+ }
+ push @old, $line;
}
}
for my $ibx (@{$self->{ibx_list}}) {
my $line = $ibx->git->{git_dir} . "/objects\n";
- next if $old{$line};
- $new{$line} = 1;
+ chomp(my $d = $line);
+ if (my @st = stat($d)) {
+ next if $seen{"$st[0]\0$st[1]"}++;
+ } else {
+ warn "W: stat($d) failed (from $ibx->{inboxdir}): $!\n";
+ }
push @new, $line;
}
- push @old, @new;
- PublicInbox::V2Writable::write_alternates($info_dir, $mode, \@old);
+ if (scalar @new) {
+ push @old, @new;
+ my $o = \@old;
+ PublicInbox::V2Writable::write_alternates($info_dir, $mode, $o);
+ }
$self->parallel_init($self->{indexlevel});
$self->umask_prepare;
- $self->with_umask(\&PublicInbox::V2Writable::_idx_init, $self, $opt);
+ $self->with_umask(\&_idx_init, $self, $opt);
$self->{oidx}->begin_lazy;
$self->{oidx}->eidx_prep;
+ $self->{midx}->begin_txn;
}
no warnings 'once';
*with_umask = \&PublicInbox::InboxWritable::with_umask;
*parallel_init = \&PublicInbox::V2Writable::parallel_init;
*nproc_shards = \&PublicInbox::V2Writable::nproc_shards;
+*sync_prepare = \&PublicInbox::V2Writable::sync_prepare;
+*index_todo = \&PublicInbox::V2Writable::index_todo;
+*count_shards = \&PublicInbox::V2Writable::count_shards;
+*atfork_child = \&PublicInbox::V2Writable::atfork_child;
+*idx_shard = \&PublicInbox::V2Writable::idx_shard;
1;