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);
};
$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;
}
# 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($$msgref);
$self->{over}->add_overview($mime, $smsg);
my $idx = idx_shard($self, $smsg->{num} % $self->{shards});
$idx->index_raw($msgref, $mime, $smsg);
# do not leak read-only FDs to child processes, we only have these
# FDs for duplicate detection so they should not be
# frequently activated.
- # delete @$ibx{qw(git mm search)};
- delete $ibx->{$_} foreach (qw(git mm search));
+ delete @$ibx{qw(mm search)};
+ $ibx->git->cleanup;
$self->{parallel} = 0 if ($ibx->{indexlevel}//'') eq 'basic';
if ($self->{parallel}) {
sub reindex_checkpoint ($$) {
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 ($$$) {
- my ($self, $sync, $oid) = @_;
- return if PublicInbox::SearchIdx::too_big($self, $oid);
- my ($num, $mid0, $len);
- my $msgref = $self->{ibx}->git->cat_file($oid, \$len);
- return if $len == 0; # purged
- my $mime = PublicInbox::Eml->new($$msgref);
+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($$bref);
my $mids = mids($mime->header_obj);
my $chash = content_hash($mime);
+ my $self = $arg->{v2w};
if (scalar(@$mids) == 0) {
warn "E: $oid has no Message-ID, skipping\n";
}
# {unindexed} is unlikely
- if ((my $unindexed = $self->{unindexed}) && scalar(@$mids) == 1) {
+ if ((my $unindexed = $arg->{unindexed}) && scalar(@$mids) == 1) {
$num = delete($unindexed->{$mids->[0]});
if (defined $num) {
$mid0 = $mids->[0];
$self->{mm}->mid_set($num, $mid0);
- delete($self->{unindexed}) if !keys(%$unindexed);
+ delete($arg->{unindexed}) if !keys(%$unindexed);
}
}
if (!defined($num)) { # reuse if reindexing (or duplicates)
}
}
$mid0 //= do { # is this a number we got before?
- $num = $sync->{mm_tmp}->num_for($mids->[0]);
+ $num = $arg->{mm_tmp}->num_for($mids->[0]);
defined($num) ? $mids->[0] : undef;
};
if (!defined($num)) {
for (my $i = $#$mids; $i >= 1; $i--) {
- $num = $sync->{mm_tmp}->num_for($mids->[$i]);
+ $num = $arg->{mm_tmp}->num_for($mids->[$i]);
if (defined($num)) {
$mid0 = $mids->[$i];
last;
}
}
if (defined($num)) {
- $sync->{mm_tmp}->num_delete($num);
+ $arg->{mm_tmp}->num_delete($num);
} else { # never seen
$num = $self->{mm}->mid_insert($mids->[0]);
if (defined($num)) {
warn "E: $oid <", join('> <', @$mids), "> is a duplicate\n";
return;
}
- $sync->{nr}++;
+ ++${$arg->{nr}};
my $smsg = bless {
- raw_bytes => $len,
+ raw_bytes => $size,
num => $num,
blob => $oid,
mid => $mid0,
}, 'PublicInbox::Smsg';
- $smsg->populate($mime, $sync);
- if (do_idx($self, $msgref, $mime, $smsg)) {
- reindex_checkpoint($self, $sync);
+ $smsg->populate($mime, $arg);
+ if (do_idx($self, $bref, $mime, $smsg)) {
+ ${$arg->{need_checkpoint}} = 1;
}
}
$heads;
}
-*is_ancestor = *PublicInbox::SearchIdx::is_ancestor;
-
# returns a revision range for git-log(1)
sub log_range ($$$$$) {
my ($self, $sync, $git, $i, $tip) = @_;
$range;
}
-sub prepare_range_stack {
- my ($git, $sync, $range) = @_;
- # Don't bump num_highwater on --reindex by using {D}.
- # We intentionally do NOT use {D} in the non-reindex case because
- # we want NNTP article number gaps from unindexed messages to
- # show up in mirrors, too.
- my $D = $sync->{D} //= $sync->{reindex} ? {} : undef; # OID_BIN => NR
-
- my $fh = $git->popen(qw(log --raw -r --pretty=tformat:%at-%ct-%H
- --no-notes --no-color --no-renames --no-abbrev),
- $range);
- my ($at, $ct, $stk);
- while (<$fh>) {
- if (/\A([0-9]+)-([0-9]+)-($OID)$/o) {
- ($at, $ct) = ($1 + 0, $2 + 0);
- $stk //= PublicInbox::IdxStack->new($3);
- } elsif (/\A:\d{6} 100644 $OID ($OID) [AM]\td$/o) {
- my $oid = $1;
- if ($D) { # reindex case
- $D->{pack('H*', $oid)}++;
- } else { # non-reindex case:
- $stk->push_rec('d', $at, $ct, $oid);
- }
- } elsif (/\A:\d{6} 100644 $OID ($OID) [AM]\tm$/o) {
- my $oid = $1;
- if ($D) {
- my $oid_bin = pack('H*', $oid);
- my $nr = --$D->{$oid_bin};
- delete($D->{$oid_bin}) if $nr <= 0;
-
- # nr < 0 (-1) means it never existed
- $stk->push_rec('m', $at, $ct, $oid) if $nr < 0;
- } else {
- $stk->push_rec('m', $at, $ct, $oid);
- }
- }
- }
- close $fh or die "git log failed: \$?=$?";
- $stk ? $stk->read_prepare : undef;
-}
-
sub sync_prepare ($$$) {
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);
}
+ $all->cat_async_wait;
}
return 0 if (!$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)->header_obj);
+ 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;
}
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)) {
$self->{mm}->{dbh}->begin_work;
$sync->{mm_tmp} = $self->{mm}->tmp_clone;
}
-
+ if ($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->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);