use v5.10.1;
use parent qw(PublicInbox::Lock);
use PublicInbox::SearchIdxShard;
-use PublicInbox::IdxStack;
use PublicInbox::Eml;
use PublicInbox::Git;
use PublicInbox::Import;
use PublicInbox::Spawn qw(spawn popen_rd);
use PublicInbox::SearchIdx qw(log2stack crlf_adjust is_ancestor check_size);
use IO::Handle; # ->autoflush
-use File::Temp qw(tempfile);
+use File::Temp ();
my $OID = qr/[a-f0-9]{40,}/;
# an estimate of the post-packed size to the raw uncompressed size
our $NPROC_MAX_DEFAULT = 4;
sub detect_nproc () {
- for my $nproc (qw(nproc gnproc)) { # GNU coreutils nproc
- `$nproc 2>/dev/null` =~ /^(\d+)$/ and return $1;
- }
-
# getconf(1) is POSIX, but *NPROCESSORS* vars are not
for (qw(_NPROCESSORS_ONLN NPROCESSORS_ONLN)) {
`getconf $_ 2>/dev/null` =~ /^(\d+)$/ and return $1;
}
+ for my $nproc (qw(nproc gnproc)) { # GNU coreutils nproc
+ `$nproc 2>/dev/null` =~ /^(\d+)$/ and return $1;
+ }
# should we bother with `sysctl hw.ncpu`? Those only give
# us total processor count, not online processor count.
total_bytes => 0,
current_info => '',
xpfx => $xpfx,
- over => PublicInbox::OverIdx->new("$xpfx/over.sqlite3"),
+ oidx => PublicInbox::OverIdx->new("$xpfx/over.sqlite3"),
lock_path => "$dir/inbox.lock",
# limit each git repo (epoch) to 1GB or so
rotate_bytes => int((1024 * 1024 * 1024) / $PACKING_FACTOR),
last_commit => [], # git epoch -> commit
};
- $self->{over}->{-no_sync} = 1 if $v2ibx->{-no_sync};
+ $self->{oidx}->{-no_fsync} = 1 if $v2ibx->{-no_fsync};
$self->{shards} = count_shards($self) || nproc_shards($creat);
bless $self, $class;
}
sub do_idx ($$$$) {
my ($self, $msgref, $mime, $smsg) = @_;
$smsg->{bytes} = $smsg->{raw_bytes} + crlf_adjust($$msgref);
- $self->{over}->add_overview($mime, $smsg);
+ $self->{oidx}->add_overview($mime, $smsg);
my $idx = idx_shard($self, $smsg->{num} % $self->{shards});
$idx->index_raw($msgref, $mime, $smsg);
my $n = $self->{transact_bytes} += $smsg->{raw_bytes};
- $n >= ($PublicInbox::SearchIdx::BATCH_BYTES * $self->{shards});
+ $n >= $self->{batch_bytes};
}
sub _add {
sub v2_num_for {
my ($self, $mime) = @_;
- my $mids = mids($mime->header_obj);
+ my $mids = mids($mime);
if (@$mids) {
my $mid = $mids->[0];
my $num = $self->{mm}->mid_insert($mid);
if ($altid && grep(/:file=msgmap\.sqlite3\z/, @$altid)) {
my $num = $self->{mm}->num_for($mid);
- if (defined $num && !$self->{over}->get_art($num)) {
+ if (defined $num && !$self->{oidx}->get_art($num)) {
return ($num, $mid);
}
}
}
sub v2_num_for_harder {
- my ($self, $mime) = @_;
+ my ($self, $eml) = @_;
- my $hdr = $mime->header_obj;
- my $dig = content_digest($mime);
- my $mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
+ my $dig = content_digest($eml);
+ my $mid0 = PublicInbox::Import::digest2mid($dig, $eml);
my $num = $self->{mm}->mid_insert($mid0);
unless (defined $num) {
# it's hard to spoof the last Received: header
- my @recvd = $hdr->header_raw('Received');
+ my @recvd = $eml->header_raw('Received');
$dig->add("Received: $_") foreach (@recvd);
- $mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
+ $mid0 = PublicInbox::Import::digest2mid($dig, $eml);
$num = $self->{mm}->mid_insert($mid0);
# fall back to a random Message-ID and give up determinism:
until (defined($num)) {
$dig->add(rand);
- $mid0 = PublicInbox::Import::digest2mid($dig, $hdr);
+ $mid0 = PublicInbox::Import::digest2mid($dig, $eml);
warn "using random Message-ID <$mid0> as fallback\n";
$num = $self->{mm}->mid_insert($mid0);
}
}
- PublicInbox::Import::append_mid($hdr, $mid0);
+ PublicInbox::Import::append_mid($eml, $mid0);
($num, $mid0);
}
sub _idx_init { # with_umask callback
my ($self, $opt) = @_;
$self->lock_acquire unless $opt && $opt->{-skip_lock};
- $self->{over}->create;
+ $self->{oidx}->create;
# xcpdb can change shard count while -watch is idle
my $nshards = count_shards($self);
$self->{shards} = $nshards if $nshards && $nshards != $self->{shards};
+ $self->{batch_bytes} = $opt->{batch_size} //
+ $PublicInbox::SearchIdx::BATCH_BYTES;
+ $self->{batch_bytes} *= $self->{shards} if $self->{parallel};
# need to create all shards before initializing msgmap FD
# idx_shards must be visible to all forked processes
# for SQLite:
my $mm = $self->{mm} = PublicInbox::Msgmap->new_file(
"$self->{ibx}->{inboxdir}/msgmap.sqlite3",
- $self->{ibx}->{-no_sync} ? 2 : 1);
+ $self->{ibx}->{-no_fsync} ? 2 : 1);
$mm->{dbh}->begin_work;
}
} else {
$im = $self->importer;
}
- my $over = $self->{over};
+ my $oidx = $self->{oidx};
my $chashes = content_hashes($old_eml);
my $removed = [];
- my $mids = mids($old_eml->header_obj);
+ my $mids = mids($old_eml);
# We avoid introducing new blobs into git since the raw content
# can be slightly different, so we do not need the user-supplied
foreach my $mid (@$mids) {
my %gone; # num => [ smsg, $mime, raw ]
my ($id, $prev);
- while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
+ while (my $smsg = $oidx->next_by_mid($mid, \$id, \$prev)) {
my $msg = get_blob($self, $smsg);
if (!defined($msg)) {
warn "broken smsg for $mid\n";
# Message-IDs are pretty complex and rethreading hasn't been fully
# implemented, yet.
sub check_mids_match ($$) {
- my ($old_mime, $new_mime) = @_;
- my $old = $old_mime->header_obj;
- my $new = $new_mime->header_obj;
+ my ($old, $new) = @_;
_check_mids_match(mids($old), mids($new), 'Message-ID(s)');
_check_mids_match(references($old), references($new),
'References/In-Reply-To');
$dbh->commit;
# SQLite overview is third
- $self->{over}->commit_lazy;
+ $self->{oidx}->commit_lazy;
# Now deal with Xapian
if ($wait) {
my $barrier = $self->barrier_init(scalar @$shards);
# each shard needs to issue a barrier command
- $_->remote_barrier for @$shards;
+ $_->shard_barrier for @$shards;
# wait for each Xapian shard
$self->barrier_wait($barrier);
} else {
- $_->remote_commit for @$shards;
+ $_->shard_commit for @$shards;
}
# last_commit is special, don't commit these until
# public
sub barrier { checkpoint($_[0], 1) };
+# true if locked and active
+sub active { !!$_[0]->{im} }
+
# public
sub done {
my ($self) = @_;
- my $im = delete $self->{im};
- $im->done if $im; # PublicInbox::Import::done
- checkpoint($self);
- my $mm = delete $self->{mm};
- $mm->{dbh}->commit if $mm;
+ my $err = '';
+ if (my $im = delete $self->{im}) {
+ eval { $im->done }; # PublicInbox::Import::done
+ $err .= "import done: $@\n" if $@;
+ }
+ if (!$err) {
+ eval { checkpoint($self) };
+ $err .= "checkpoint: $@\n" if $@;
+ }
+ if (my $mm = delete $self->{mm}) {
+ my $m = $err ? 'rollback' : 'commit';
+ eval { $mm->{dbh}->$m };
+ $err .= "msgmap $m: $@\n" if $@;
+ }
my $shards = delete $self->{idx_shards};
if ($shards) {
- $_->remote_close for @$shards;
+ for (@$shards) {
+ eval { $_->shard_close };
+ $err .= "shard close: $@\n" if $@;
+ }
}
- $self->{over}->disconnect;
+ eval { $self->{oidx}->dbh_close };
+ $err .= "over close: $@\n" if $@;
delete $self->{bnote};
my $nbytes = $self->{total_bytes};
$self->{total_bytes} = 0;
$self->lock_release(!!$nbytes) if $shards;
$self->{ibx}->git->cleanup;
+ die $err if $err;
}
sub fill_alternates ($$) {
}
return unless $new;
- my ($fh, $tmp) = tempfile('alt-XXXXXXXX', DIR => $info_dir);
+ my $fh = File::Temp->new(TEMPLATE => 'alt-XXXXXXXX', DIR => $info_dir);
+ my $tmp = $fh->filename;
print $fh join("\n", sort { $alt{$b} <=> $alt{$a} } keys %alt), "\n"
or die "print $tmp: $!\n";
chmod($mode, $fh) or die "fchmod $tmp: $!\n";
close $fh or die "close $tmp $!\n";
rename($tmp, $alt) or die "rename $tmp => $alt: $!\n";
+ $fh->unlink_on_destroy(0);
}
sub git_init {
sub diff ($$$) {
my ($mid, $cur, $new) = @_;
- my ($ah, $an) = tempfile('email-cur-XXXXXXXX', TMPDIR => 1);
+ my $ah = File::Temp->new(TEMPLATE => 'email-cur-XXXXXXXX', TMPDIR => 1);
print $ah $cur->as_string or die "print: $!";
- close $ah or die "close: $!";
- my ($bh, $bn) = tempfile('email-new-XXXXXXXX', TMPDIR => 1);
+ $ah->flush or die "flush: $!";
PublicInbox::Import::drop_unwanted_headers($new);
+ my $bh = File::Temp->new(TEMPLATE => 'email-new-XXXXXXXX', TMPDIR => 1);
print $bh $new->as_string or die "print: $!";
- close $bh or die "close: $!";
- my $cmd = [ qw(diff -u), $an, $bn ];
+ $bh->flush or die "flush: $!";
+ my $cmd = [ qw(diff -u), $ah->filename, $bh->filename ];
print STDERR "# MID conflict <$mid>\n";
my $pid = spawn($cmd, undef, { 1 => 2 });
waitpid($pid, 0) == $pid or die "diff did not finish";
- unlink($an, $bn);
}
sub get_blob ($$) {
sub content_exists ($$$) {
my ($self, $mime, $mid) = @_;
- my $over = $self->{over};
+ my $oidx = $self->{oidx};
my $chashes = content_hashes($mime);
my ($id, $prev);
- while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
+ while (my $smsg = $oidx->next_by_mid($mid, \$id, \$prev)) {
my $msg = get_blob($self, $smsg);
if (!defined($msg)) {
warn "broken smsg for $mid\n";
$self->{ibx}->git->cleanup; # *async_wait
${$sync->{need_checkpoint}} = 0;
- $sync->{mm_tmp}->atfork_prepare;
+ my $mm_tmp = $sync->{mm_tmp};
+ $mm_tmp->atfork_prepare if $mm_tmp;
$self->done; # release lock
if (my $pr = $sync->{-opt}->{-progress}) {
}
# allow -watch or -mda to write...
- $self->idx_init; # reacquire lock
- $sync->{mm_tmp}->atfork_parent;
+ $self->idx_init($sync->{-opt}); # reacquire lock
+ $mm_tmp->atfork_parent if $mm_tmp;
}
sub index_oid { # cat_async callback
my ($bref, $oid, $type, $size, $arg) = @_;
return if $size == 0; # purged
my ($num, $mid0);
- my $mime = PublicInbox::Eml->new($$bref);
- my $mids = mids($mime->header_obj);
- my $chash = content_hash($mime);
+ my $eml = PublicInbox::Eml->new($$bref);
+ my $mids = mids($eml);
+ my $chash = content_hash($eml);
my $self = $arg->{v2w};
if (scalar(@$mids) == 0) {
}
}
if (!defined($num)) { # reuse if reindexing (or duplicates)
- my $over = $self->{over};
+ my $oidx = $self->{oidx};
for my $mid (@$mids) {
- ($num, $mid0) = $over->num_mid0_for_oid($oid, $mid);
+ ($num, $mid0) = $oidx->num_mid0_for_oid($oid, $mid);
last if defined $num;
}
}
blob => $oid,
mid => $mid0,
}, 'PublicInbox::Smsg';
- $smsg->populate($mime, $arg);
- if (do_idx($self, $bref, $mime, $smsg)) {
+ $smsg->populate($eml, $arg);
+ if (do_idx($self, $bref, $eml, $smsg)) {
${$arg->{need_checkpoint}} = 1;
}
}
my $opt = $sync->{-opt};
my $pr = $opt->{-progress} if (($opt->{verbose} || 0) > 1);
my $cur = $sync->{ranges}->[$i] or do {
- $pr->("$i.git indexing all of $tip") if $pr;
+ $pr->("$i.git indexing all of $tip\n") if $pr;
return $tip; # all of it
};
}
$all->cat_async_wait;
}
- return 0 if (!$regen_max && !keys(%{$self->{unindex_range}}));
+ if (!$regen_max && !keys(%{$self->{unindex_range}})) {
+ $sync->{-regen_fmt} = "%u/?\n";
+ return 0;
+ }
# reindex should NOT see new commits anymore, if we do,
# it's a problem and we need to notice it via die()
sub unindex_oid_remote ($$$) {
my ($self, $oid, $mid) = @_;
- my @removed = $self->{over}->remove_oid($oid, $mid);
+ my @removed = $self->{oidx}->remove_oid($oid, $mid);
for my $num (@removed) {
my $idx = idx_shard($self, $num % $self->{shards});
- $idx->remote_remove($oid, $num);
+ $idx->shard_remove($oid, $num);
}
}
my $self = $sync->{v2w};
my $unindexed = $sync->{in_unindex} ? $sync->{unindexed} : undef;
my $mm = $self->{mm};
- my $mids = mids(PublicInbox::Eml->new($bref)->header_obj);
+ my $mids = mids(PublicInbox::Eml->new($bref));
undef $$bref;
- my $over = $self->{over};
+ my $oidx = $self->{oidx};
foreach my $mid (@$mids) {
my %gone;
my ($id, $prev);
- while (my $smsg = $over->next_by_mid($mid, \$id, \$prev)) {
+ while (my $smsg = $oidx->next_by_mid($mid, \$id, \$prev)) {
$gone{$smsg->{num}} = 1 if $oid eq $smsg->{blob};
}
my $n = scalar(keys(%gone)) or next;
$ranges;
}
+sub index_xap_only { # git->cat_async callback
+ my ($bref, $oid, $type, $size, $smsg) = @_;
+ my $self = $smsg->{v2w};
+ my $idx = idx_shard($self, $smsg->{num} % $self->{shards});
+ $smsg->{raw_bytes} = $size;
+ $idx->index_raw($bref, undef, $smsg);
+ $self->{transact_bytes} += $size;
+}
+
+sub index_xap_step ($$$;$) {
+ my ($self, $sync, $beg, $step) = @_;
+ my $end = $sync->{art_end};
+ return if $beg > $end; # nothing to do
+
+ $step //= $self->{shards};
+ my $ibx = $self->{ibx};
+ if (my $pr = $sync->{-opt}->{-progress}) {
+ $pr->("Xapian indexlevel=$ibx->{indexlevel} ".
+ "$beg..$end (% $step)\n");
+ }
+ for (my $num = $beg; $num <= $end; $num += $step) {
+ my $smsg = $ibx->over->get_art($num) or next;
+ $smsg->{v2w} = $self;
+ $ibx->git->cat_async($smsg->{blob}, \&index_xap_only, $smsg);
+ if ($self->{transact_bytes} >= $self->{batch_bytes}) {
+ ${$sync->{nr}} = $num;
+ reindex_checkpoint($self, $sync);
+ }
+ }
+}
+
sub index_epoch ($$$) {
my ($self, $sync, $i) = @_;
$self->{current_info} = "$i.git $oid";
if ($f eq 'm') {
my $arg = { %$sync, autime => $at, cotime => $ct };
- if ($sync->{index_max_size}) {
+ if ($sync->{max_size}) {
$all->check_async($oid, \&check_size, $arg);
} else {
$all->cat_async($oid, \&index_oid, $arg);
update_last_commit($self, $git, $i, $stk->{latest_cmt});
}
+sub xapian_only {
+ my ($self, $opt, $sync, $art_beg) = @_;
+ my $seq = $opt->{sequential_shard};
+ $art_beg //= 0;
+ local $self->{parallel} = 0 if $seq;
+ $self->idx_init($opt); # acquire lock
+ if (my $art_end = $self->{ibx}->mm->max) {
+ $sync //= {
+ need_checkpoint => \(my $bool = 0),
+ -opt => $opt,
+ v2w => $self,
+ nr => \(my $nr = 0),
+ -regen_fmt => "%u/?\n",
+ };
+ $sync->{art_end} = $art_end;
+ if ($seq || !$self->{parallel}) {
+ my $shard_end = $self->{shards} - 1;
+ for my $i (0..$shard_end) {
+ index_xap_step($self, $sync, $art_beg + $i);
+ if ($i != $shard_end) {
+ reindex_checkpoint($self, $sync);
+ }
+ }
+ } else { # parallel (maybe)
+ index_xap_step($self, $sync, $art_beg, 1);
+ }
+ }
+ $self->{ibx}->git->cat_async_wait;
+ $self->done;
+}
+
# public, called by public-inbox-index
sub index_sync {
my ($self, $opt) = @_;
- $opt ||= {};
+ $opt //= $_[1] //= {};
+ goto \&xapian_only if $opt->{xapian_only};
+
my $pr = $opt->{-progress};
my $epoch_max;
my $latest = git_dir_latest($self, \$epoch_max);
return unless defined $latest;
+
+ my $seq = $opt->{sequential_shard};
+ my $art_beg; # the NNTP article number we start xapian_only at
+ my $idxlevel = $self->{ibx}->{indexlevel};
+ local $self->{ibx}->{indexlevel} = 'basic' if $seq;
+
$self->idx_init($opt); # acquire lock
fill_alternates($self, $epoch_max);
- $self->{over}->rethread_prepare($opt);
+ $self->{oidx}->rethread_prepare($opt);
my $sync = {
need_checkpoint => \(my $bool = 0),
unindex_range => {}, # EPOCH => oid_old..oid_new
# only for batch performance.
$self->{mm}->{dbh}->rollback;
$self->{mm}->{dbh}->begin_work;
- $sync->{mm_tmp} = $self->{mm}->tmp_clone;
+ $sync->{mm_tmp} =
+ $self->{mm}->tmp_clone($self->{ibx}->{inboxdir});
+
+ # xapian_only works incrementally w/o --reindex
+ if ($seq && !$opt->{reindex}) {
+ $art_beg = $sync->{mm_tmp}->max;
+ $art_beg++ if defined($art_beg);
+ }
}
- if ($sync->{index_max_size} = $self->{ibx}->{index_max_size}) {
+ if ($sync->{max_size} = $opt->{max_size}) {
$sync->{index_oid} = \&index_oid;
}
# work forwards through history
index_epoch($self, $sync, $_) for (0..$epoch_max);
+ $self->{oidx}->rethread_done($opt);
$self->done;
if (my $nr = $sync->{nr}) {
my $pr = $sync->{-opt}->{-progress};
$pr->('all.git '.sprintf($sync->{-regen_fmt}, $$nr)) if $pr;
}
- $self->{over}->rethread_done($opt);
+
+ # deal with Xapian shards sequentially
+ if ($seq && delete($sync->{mm_tmp})) {
+ $self->{ibx}->{indexlevel} = $idxlevel;
+ xapian_only($self, $opt, $sync, $art_beg);
+ }
+
+ # --reindex on the command-line
+ if ($opt->{reindex} && !ref($opt->{reindex}) && $idxlevel ne 'basic') {
+ $self->lock_acquire;
+ my $s0 = PublicInbox::SearchIdx->new($self->{ibx}, 0, 0);
+ if (my $xdb = $s0->idx_acquire) {
+ my $n = $xdb->get_metadata('has_threadid');
+ $xdb->set_metadata('has_threadid', '1') if $n ne '1';
+ }
+ $s0->idx_release;
+ $self->lock_release;
+ }
# reindex does not pick up new changes, so we rerun w/o it:
if ($opt->{reindex}) {