use PublicInbox::OverIdx;
use PublicInbox::Msgmap;
use PublicInbox::Spawn qw(spawn popen_rd);
-use PublicInbox::SearchIdx qw(too_big log2stack crlf_adjust is_ancestor);
+use PublicInbox::SearchIdx qw(log2stack crlf_adjust is_ancestor check_size);
use IO::Handle; # ->autoflush
use File::Temp qw(tempfile);
};
$self->{over}->{-no_sync} = 1 if $v2ibx->{-no_sync};
$self->{shards} = count_shards($self) || nproc_shards($creat);
- $self->{index_max_size} = $v2ibx->{index_max_size};
bless $self, $class;
}
sub v2_num_for {
my ($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, $mid0);
}
# do not leak read-only FDs to child processes, we only have these
# FDs for duplicate detection so they should not be
# frequently activated.
- # delete @$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 ($$) {
- my ($old_mime, $new_mime) = @_;
- my $old = $old_mime->header_obj;
- my $new = $new_mime->header_obj;
+ my ($old, $new) = @_;
_check_mids_match(mids($old), mids($new), 'Message-ID(s)');
_check_mids_match(references($old), references($new),
'References/In-Reply-To');
# public
sub done {
my ($self) = @_;
- my $im = delete $self->{im};
- $im->done if $im; # PublicInbox::Import::done
- checkpoint($self);
- my $mm = delete $self->{mm};
- $mm->{dbh}->commit if $mm;
+ my $err = '';
+ if (my $im = delete $self->{im}) {
+ eval { $im->done }; # PublicInbox::Import::done
+ $err .= "import done: $@\n" if $@;
+ }
+ if (!$err) {
+ eval { checkpoint($self) };
+ $err .= "checkpoint: $@\n" if $@;
+ }
+ if (my $mm = delete $self->{mm}) {
+ my $m = $err ? 'rollback' : 'commit';
+ eval { $mm->{dbh}->$m };
+ $err .= "msgmap $m: $@\n" if $@;
+ }
my $shards = delete $self->{idx_shards};
if ($shards) {
- $_->remote_close for @$shards;
+ for (@$shards) {
+ eval { $_->remote_close };
+ $err .= "shard close: $@\n" if $@;
+ }
}
- $self->{over}->disconnect;
+ eval { $self->{over}->disconnect };
+ $err .= "over disconnect: $@\n" if $@;
delete $self->{bnote};
my $nbytes = $self->{total_bytes};
$self->{total_bytes} = 0;
$self->lock_release(!!$nbytes) if $shards;
$self->{ibx}->git->cleanup;
+ die $err if $err;
}
sub fill_alternates ($$) {
sub reindex_checkpoint ($$) {
my ($self, $sync) = @_;
+ $self->{ibx}->git->cleanup; # *async_wait
+ ${$sync->{need_checkpoint}} = 0;
$sync->{mm_tmp}->atfork_prepare;
$self->done; # release lock
if (my $pr = $sync->{-opt}->{-progress}) {
- $pr->(sprintf($sync->{-regen_fmt}, $sync->{nr}));
+ $pr->(sprintf($sync->{-regen_fmt}, ${$sync->{nr}}));
}
# allow -watch or -mda to write...
$sync->{mm_tmp}->atfork_parent;
}
-sub reindex_oid ($$$) {
- my ($self, $sync, $oid) = @_;
- return if too_big($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 = $sync->{unindexed}) && scalar(@$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, $mid0);
- delete($sync->{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;
}
}
# 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);
}
+ $all->cat_async_wait;
}
return 0 if (!$regen_max && !keys(%{$self->{unindex_range}}));
# 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;
}
}
}
-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 = $sync->{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;
}
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->{index_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, $stk->{latest_cmt});
}
fill_alternates($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});
+ }
+ if ($sync->{index_max_size} = $self->{ibx}->{index_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;
}
- $self->{over}->rethread_done($opt);
# reindex does not pick up new changes, so we rerun w/o it:
if ($opt->{reindex}) {