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);
bless $self, $class;
}
$self->{ibx}->with_umask(\&_add, $self, $eml, $check_cb);
}
+sub batch_bytes ($) {
+ my ($self) = @_;
+ ($self->{parallel} ? $self->{shards} : 1) *
+ $PublicInbox::SearchIdx::BATCH_BYTES;
+}
+
# indexes a message, returns true if checkpointing is needed
sub do_idx ($$$$) {
my ($self, $msgref, $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 >= batch_bytes($self);
}
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);
}
# 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;
}
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($new),
'References/In-Reply-To');
# public
sub done {
my ($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 { $_->remote_close };
+ $err .= "shard close: $@\n" if $@;
+ }
}
- $self->{over}->disconnect;
+ eval { $self->{over}->disconnect };
+ $err .= "over disconnect: $@\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 ($$) {
$self->{ibx}->git->cleanup; # *async_wait
${$sync->{need_checkpoint}} = 0;
- $sync->{mm_tmp}->atfork_prepare;
+ my $mm_tmp = $sync->{mm_tmp};
+ $mm_tmp->atfork_prepare if $mm_tmp;
$self->done; # release lock
if (my $pr = $sync->{-opt}->{-progress}) {
# allow -watch or -mda to write...
$self->idx_init; # reacquire lock
- $sync->{mm_tmp}->atfork_parent;
+ $mm_tmp->atfork_parent if $mm_tmp;
}
sub index_oid { # cat_async callback
my ($bref, $oid, $type, $size, $arg) = @_;
return if $size == 0; # purged
my ($num, $mid0);
- my $mime = PublicInbox::Eml->new($$bref);
- my $mids = mids($mime->header_obj);
- my $chash = content_hash($mime);
+ my $eml = PublicInbox::Eml->new($$bref);
+ my $mids = mids($eml);
+ my $chash = content_hash($eml);
my $self = $arg->{v2w};
if (scalar(@$mids) == 0) {
blob => $oid,
mid => $mid0,
}, 'PublicInbox::Smsg';
- $smsg->populate($mime, $arg);
- if (do_idx($self, $bref, $mime, $smsg)) {
+ $smsg->populate($eml, $arg);
+ if (do_idx($self, $bref, $eml, $smsg)) {
${$arg->{need_checkpoint}} = 1;
}
}
}
$all->cat_async_wait;
}
- return 0 if (!$regen_max && !keys(%{$self->{unindex_range}}));
+ if (!$regen_max && !keys(%{$self->{unindex_range}})) {
+ $sync->{-regen_fmt} = "%u/?\n";
+ return 0;
+ }
# reindex should NOT see new commits anymore, if we do,
# it's a problem and we need to notice it via die()
my $self = $sync->{v2w};
my $unindexed = $sync->{in_unindex} ? $sync->{unindexed} : undef;
my $mm = $self->{mm};
- my $mids = mids(PublicInbox::Eml->new($bref)->header_obj);
+ my $mids = mids(PublicInbox::Eml->new($bref));
undef $$bref;
my $over = $self->{over};
foreach my $mid (@$mids) {
$ranges;
}
+sub index_xap_only { # git->cat_async callback
+ my ($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 ($$$;$) {
+ my ($self, $sync, $beg, $step) = @_;
+ my $ibx = $self->{ibx};
+ my $all = $ibx->git;
+ my $over = $ibx->over;
+ my $batch_bytes = batch_bytes($self);
+ $step //= $self->{shards};
+ my $end = $sync->{art_end};
+ if (my $pr = $sync->{-opt}->{-progress}) {
+ $pr->("Xapian indexlevel=$ibx->{indexlevel} ".
+ "$beg..$end (% $step)\n");
+ }
+ for (my $num = $beg; $num <= $end; $num += $step) {
+ my $smsg = $over->get_art($num) or next;
+ $smsg->{v2w} = $self;
+ $all->cat_async($smsg->{blob}, \&index_xap_only, $smsg);
+ if ($self->{transact_bytes} >= $batch_bytes) {
+ ${$sync->{nr}} = $num;
+ reindex_checkpoint($self, $sync);
+ }
+ }
+}
+
sub index_epoch ($$$) {
my ($self, $sync, $i) = @_;
update_last_commit($self, $git, $i, $stk->{latest_cmt});
}
+sub xapian_only {
+ my ($self, $opt, $sync) = @_;
+ my $seq = $opt->{sequentialshard};
+ 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 = $self->{shards} - 1;
+ index_xap_step($self, $sync, $_) for (0..$shard_end);
+ } else { # parallel (maybe)
+ index_xap_step($self, $sync, 0, 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->{xapianonly};
+
my $pr = $opt->{-progress};
my $epoch_max;
my $latest = git_dir_latest($self, \$epoch_max);
return unless defined $latest;
+
+ my $seq = $opt->{sequentialshard};
+ 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);
}
# 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;
}
- $self->{over}->rethread_done($opt);
+
+ if ($seq) { # deal with Xapian shards sequentially
+ $self->{ibx}->{indexlevel} = $idxlevel;
+ delete $sync->{mm_tmp};
+ xapian_only($self, $opt, $sync);
+ }
# reindex does not pick up new changes, so we rerun w/o it:
if ($opt->{reindex}) {