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::OverIdx;
use PublicInbox::Msgmap;
use PublicInbox::Spawn qw(spawn popen_rd);
-use PublicInbox::SearchIdx;
+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.
rotate_bytes => int((1024 * 1024 * 1024) / $PACKING_FACTOR),
last_commit => [], # git epoch -> commit
};
- $self->{over}->{-no_sync} = 1 if $v2ibx->{-no_sync};
+ $self->{over}->{-no_fsync} = 1 if $v2ibx->{-no_fsync};
$self->{shards} = count_shards($self) || nproc_shards($creat);
- $self->{index_max_size} = $v2ibx->{index_max_size};
bless $self, $class;
}
# indexes a message, returns true if checkpointing is needed
sub do_idx ($$$$) {
my ($self, $msgref, $mime, $smsg) = @_;
- $smsg->{bytes} = $smsg->{raw_bytes} +
- PublicInbox::SearchIdx::crlf_adjust($$msgref);
+ $smsg->{bytes} = $smsg->{raw_bytes} + crlf_adjust($$msgref);
$self->{over}->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);
}
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);
}
# 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;
}
# do not leak read-only FDs to child processes, we only have these
# FDs for duplicate detection so they should not be
# frequently activated.
- # delete @$ibx{qw(git mm search)};
- delete $ibx->{$_} foreach (qw(git mm search));
+ delete @$ibx{qw(mm search)};
+ $ibx->git->cleanup;
$self->{parallel} = 0 if ($ibx->{indexlevel}//'') eq 'basic';
if ($self->{parallel}) {
my $over = $self->{over};
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
# 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');
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->{over}->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 ($$) {
sub reindex_checkpoint ($$) {
my ($self, $sync) = @_;
- $sync->{mm_tmp}->atfork_prepare;
+ $self->{ibx}->git->cleanup; # *async_wait
+ ${$sync->{need_checkpoint}} = 0;
+ my $mm_tmp = $sync->{mm_tmp};
+ $mm_tmp->atfork_prepare if $mm_tmp;
$self->done; # release lock
if (my $pr = $sync->{-opt}->{-progress}) {
- $pr->(sprintf($sync->{-regen_fmt}, $sync->{nr}));
+ $pr->(sprintf($sync->{-regen_fmt}, ${$sync->{nr}}));
}
# 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 reindex_oid ($$$) {
- my ($self, $sync, $oid) = @_;
- return if PublicInbox::SearchIdx::too_big($self, $oid);
- my ($num, $mid0, $len);
- my $msgref = $self->{ibx}->git->cat_file($oid, \$len);
- return if $len == 0; # purged
- my $mime = PublicInbox::Eml->new($$msgref);
- my $mids = mids($mime->header_obj);
- my $chash = content_hash($mime);
+sub index_oid { # cat_async callback
+ my ($bref, $oid, $type, $size, $arg) = @_;
+ return if $size == 0; # purged
+ my ($num, $mid0);
+ my $eml = PublicInbox::Eml->new($$bref);
+ my $mids = mids($eml);
+ my $chash = content_hash($eml);
+ my $self = $arg->{v2w};
if (scalar(@$mids) == 0) {
warn "E: $oid has no Message-ID, skipping\n";
}
# {unindexed} is unlikely
- if ((my $unindexed = $self->{unindexed}) && scalar(@$mids) == 1) {
+ if ((my $unindexed = $arg->{unindexed}) && scalar(@$mids) == 1) {
$num = delete($unindexed->{$mids->[0]});
if (defined $num) {
$mid0 = $mids->[0];
$self->{mm}->mid_set($num, $mid0);
- delete($self->{unindexed}) if !keys(%$unindexed);
+ delete($arg->{unindexed}) if !keys(%$unindexed);
}
}
if (!defined($num)) { # reuse if reindexing (or duplicates)
}
}
$mid0 //= do { # is this a number we got before?
- $num = $sync->{mm_tmp}->num_for($mids->[0]);
+ $num = $arg->{mm_tmp}->num_for($mids->[0]);
defined($num) ? $mids->[0] : undef;
};
if (!defined($num)) {
for (my $i = $#$mids; $i >= 1; $i--) {
- $num = $sync->{mm_tmp}->num_for($mids->[$i]);
+ $num = $arg->{mm_tmp}->num_for($mids->[$i]);
if (defined($num)) {
$mid0 = $mids->[$i];
last;
}
}
if (defined($num)) {
- $sync->{mm_tmp}->num_delete($num);
+ $arg->{mm_tmp}->num_delete($num);
} else { # never seen
$num = $self->{mm}->mid_insert($mids->[0]);
if (defined($num)) {
warn "E: $oid <", join('> <', @$mids), "> is a duplicate\n";
return;
}
- $sync->{nr}++;
+ ++${$arg->{nr}};
my $smsg = bless {
- raw_bytes => $len,
+ raw_bytes => $size,
num => $num,
blob => $oid,
mid => $mid0,
}, 'PublicInbox::Smsg';
- $smsg->populate($mime, $sync);
- if (do_idx($self, $msgref, $mime, $smsg)) {
- reindex_checkpoint($self, $sync);
+ $smsg->populate($eml, $arg);
+ if (do_idx($self, $bref, $eml, $smsg)) {
+ ${$arg->{need_checkpoint}} = 1;
}
}
$heads;
}
-*is_ancestor = *PublicInbox::SearchIdx::is_ancestor;
-
# returns a revision range for git-log(1)
sub log_range ($$$$$) {
my ($self, $sync, $git, $i, $tip) = @_;
my $opt = $sync->{-opt};
my $pr = $opt->{-progress} if (($opt->{verbose} || 0) > 1);
my $cur = $sync->{ranges}->[$i] or do {
- $pr->("$i.git indexing all of $tip") if $pr;
+ $pr->("$i.git indexing all of $tip\n") if $pr;
return $tip; # all of it
};
$range;
}
-sub prepare_range_stack {
- my ($git, $sync, $range) = @_;
- # Don't bump num_highwater on --reindex by using {D}.
- # We intentionally do NOT use {D} in the non-reindex case because
- # we want NNTP article number gaps from unindexed messages to
- # show up in mirrors, too.
- my $D = $sync->{D} //= $sync->{reindex} ? {} : undef; # OID_BIN => NR
-
- my $fh = $git->popen(qw(log --raw -r --pretty=tformat:%at-%ct-%H
- --no-notes --no-color --no-renames --no-abbrev),
- $range);
- my ($at, $ct, $stk);
- while (<$fh>) {
- if (/\A([0-9]+)-([0-9]+)-($OID)$/o) {
- ($at, $ct) = ($1 + 0, $2 + 0);
- $stk //= PublicInbox::IdxStack->new($3);
- } elsif (/\A:\d{6} 100644 $OID ($OID) [AM]\td$/o) {
- my $oid = $1;
- if ($D) { # reindex case
- $D->{pack('H*', $oid)}++;
- } else { # non-reindex case:
- $stk->push_rec('d', $at, $ct, $oid);
- }
- } elsif (/\A:\d{6} 100644 $OID ($OID) [AM]\tm$/o) {
- my $oid = $1;
- if ($D) {
- my $oid_bin = pack('H*', $oid);
- my $nr = --$D->{$oid_bin};
- delete($D->{$oid_bin}) if $nr <= 0;
-
- # nr < 0 (-1) means it never existed
- $stk->push_rec('m', $at, $ct, $oid) if $nr < 0;
- } else {
- $stk->push_rec('m', $at, $ct, $oid);
- }
- }
- }
- close $fh or die "git log failed: \$?=$?";
- $stk ? $stk->read_prepare : undef;
-}
-
sub sync_prepare ($$$) {
my ($self, $sync, $epoch_max) = @_;
my $pr = $sync->{-opt}->{-progress};
my $range = log_range($self, $sync, $git, $i, $tip) or next;
# can't use 'rev-list --count' if we use --diff-filter
$pr->("$i.git counting $range ... ") if $pr;
- my $stk = prepare_range_stack($git, $sync, $range);
+ # Don't bump num_highwater on --reindex by using {D}.
+ # We intentionally do NOT use {D} in the non-reindex case
+ # because we want NNTP article number gaps from unindexed
+ # messages to show up in mirrors, too.
+ $sync->{D} //= $sync->{reindex} ? {} : undef; # OID_BIN => NR
+ my $stk = log2stack($sync, $git, $range, $self->{ibx});
my $nr = $stk ? $stk->num_records : 0;
$pr->("$nr\n") if $pr;
$sync->{stacks}->[$i] = $stk if $stk;
# our code and blindly injects "d" file history into git repos
if (my @leftovers = keys %{delete($sync->{D}) // {}}) {
warn('W: unindexing '.scalar(@leftovers)." leftovers\n");
+ my $arg = { v2w => $self };
+ my $all = $self->{ibx}->git;
for my $oid (@leftovers) {
$oid = unpack('H*', $oid);
$self->{current_info} = "leftover $oid";
- unindex_oid($self, $oid);
+ $all->cat_async($oid, \&unindex_oid, $arg);
}
+ $all->cat_async_wait;
+ }
+ if (!$regen_max && !keys(%{$self->{unindex_range}})) {
+ $sync->{-regen_fmt} = "%u/?\n";
+ return 0;
}
- return 0 if (!$regen_max && !keys(%{$self->{unindex_range}}));
# reindex should NOT see new commits anymore, if we do,
# it's a problem and we need to notice it via die()
my $pad = length($regen_max) + 1;
$sync->{-regen_fmt} = "% ${pad}u/$regen_max\n";
- $sync->{nr} = 0;
+ $sync->{nr} = \(my $nr = 0);
return -1 if $sync->{reindex};
$regen_max + $self->{mm}->num_highwater() || 0;
}
my @removed = $self->{over}->remove_oid($oid, $mid);
for my $num (@removed) {
my $idx = idx_shard($self, $num % $self->{shards});
- $idx->remote_remove($oid, $num);
+ $idx->shard_remove($oid, $num);
}
}
-sub unindex_oid ($$;$) {
- my ($self, $oid, $unindexed) = @_;
+sub unindex_oid ($$;$) { # git->cat_async callback
+ my ($bref, $oid, $type, $size, $sync) = @_;
+ my $self = $sync->{v2w};
+ my $unindexed = $sync->{in_unindex} ? $sync->{unindexed} : undef;
my $mm = $self->{mm};
- my $msgref = $self->{ibx}->git->cat_file($oid);
- my $mime = PublicInbox::Eml->new($msgref);
- my $mids = mids($mime->header_obj);
- $mime = $msgref = undef;
+ my $mids = mids(PublicInbox::Eml->new($bref));
+ undef $$bref;
my $over = $self->{over};
foreach my $mid (@$mids) {
my %gone;
# a mirror because the source used -purge or -edit
sub unindex ($$$$) {
my ($self, $sync, $git, $unindex_range) = @_;
- my $unindexed = $self->{unindexed} ||= {}; # $mid0 => $num
+ my $unindexed = $sync->{unindexed} //= {}; # $mid0 => $num
my $before = scalar keys %$unindexed;
# order does not matter, here:
my @cmd = qw(log --raw -r
--no-notes --no-color --no-abbrev --no-renames);
my $fh = $git->popen(@cmd, $unindex_range);
+ my $all = $self->{ibx}->git;
+ local $sync->{in_unindex} = 1;
while (<$fh>) {
/\A:\d{6} 100644 $OID ($OID) [AM]\tm$/o or next;
- unindex_oid($self, $1, $unindexed);
+ $all->cat_async($1, \&unindex_oid, $sync);
}
close $fh or die "git log failed: \$?=$?";
+ $all->cat_async_wait;
return unless $sync->{-opt}->{prune};
my $after = scalar keys %$unindexed;
$ranges;
}
+sub index_xap_only { # git->cat_async callback
+ my ($bref, $oid, $type, $size, $smsg) = @_;
+ my $self = $smsg->{v2w};
+ my $idx = idx_shard($self, $smsg->{num} % $self->{shards});
+ $smsg->{raw_bytes} = $size;
+ $idx->index_raw($bref, undef, $smsg);
+ $self->{transact_bytes} += $size;
+}
+
+sub index_xap_step ($$$;$) {
+ my ($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) = @_;
}
defined(my $stk = $sync->{stacks}->[$i]) or return;
$sync->{stacks}->[$i] = undef;
+ my $all = $self->{ibx}->git;
while (my ($f, $at, $ct, $oid) = $stk->pop_rec) {
$self->{current_info} = "$i.git $oid";
if ($f eq 'm') {
- $sync->{autime} = $at;
- $sync->{cotime} = $ct;
- reindex_oid($self, $sync, $oid);
+ my $arg = { %$sync, autime => $at, cotime => $ct };
+ if ($sync->{max_size}) {
+ $all->check_async($oid, \&check_size, $arg);
+ } else {
+ $all->cat_async($oid, \&index_oid, $arg);
+ }
} elsif ($f eq 'd') {
- unindex_oid($self, $oid);
+ $all->cat_async($oid, \&unindex_oid, $sync);
+ }
+ if (${$sync->{need_checkpoint}}) {
+ reindex_checkpoint($self, $sync);
}
}
- delete @$sync{qw(autime cotime)};
+ $all->check_async_wait;
+ $all->cat_async_wait;
update_last_commit($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);
my $sync = {
+ need_checkpoint => \(my $bool = 0),
unindex_range => {}, # EPOCH => oid_old..oid_new
reindex => $opt->{reindex},
- -opt => $opt
+ -opt => $opt,
+ v2w => $self,
};
$sync->{ranges} = sync_ranges($self, $sync, $epoch_max);
if (sync_prepare($self, $sync, $epoch_max)) {
# 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->{max_size} = $opt->{max_size}) {
+ $sync->{index_oid} = \&index_oid;
+ }
# work forwards through history
index_epoch($self, $sync, $_) for (0..$epoch_max);
+ $self->{over}->rethread_done($opt);
$self->done;
if (my $nr = $sync->{nr}) {
my $pr = $sync->{-opt}->{-progress};
- $pr->('all.git '.sprintf($sync->{-regen_fmt}, $nr)) if $pr;
+ $pr->('all.git '.sprintf($sync->{-regen_fmt}, $$nr)) if $pr;
+ }
+
+ # deal with Xapian shards sequentially
+ if ($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;
}
- $self->{over}->rethread_done($opt);
# reindex does not pick up new changes, so we rerun w/o it:
if ($opt->{reindex}) {