xpfx => $xpfx,
over => PublicInbox::OverIdxFork->new("$xpfx/over.sqlite3"),
lock_path => "$dir/inbox.lock",
- # limit each repo to 1GB or so
+ # limit each git repo (epoch) to 1GB or so
rotate_bytes => int((1024 * 1024 * 1024) / $PACKING_FACTOR),
- last_commit => [],
+ last_commit => [], # git repo -> commit
};
$self->{partitions} = count_partitions($self) || nproc();
bless $self, $class;
my ($self, $parallel) = @_;
$self->{parallel} = $parallel;
$self->idx_init;
- my $max_git = -1;
- git_dir_latest($self, \$max_git);
- $self->git_init($max_git >= 0 ? $max_git : 0);
+ my $epoch_max = -1;
+ git_dir_latest($self, \$epoch_max);
+ $self->git_init($epoch_max >= 0 ? $epoch_max : 0);
$self->done;
}
my $nparts = $self->{partitions};
my $part = $num % $nparts;
- $self->{last_commit}->[$self->{max_git}] = $cmt;
+ $self->{last_commit}->[$self->{epoch_max}] = $cmt;
my $idx = $self->idx_part($part);
$idx->index_raw($len, $msgref, $num, $oid, $mid0, $mime);
my $n = $self->{transact_bytes} += $len;
$self->done;
my $pfx = "$self->{-inbox}->{mainrepo}/git";
my $purges = [];
- foreach my $i (0..$self->{max_git}) {
+ foreach my $i (0..$self->{epoch_max}) {
my $git = PublicInbox::Git->new("$pfx/$i.git");
my $im = $self->import_init($git, 0, 1);
$purges->[$i] = $im->purge_oids($purge);
foreach my $mid (@$mids) {
my %gone;
- $srch->reopen->each_smsg_by_mid($mid, sub {
- my ($smsg) = @_;
- $smsg->load_expand;
+ my ($id, $prev);
+ while (my $smsg = $srch->next_by_mid($mid, \$id, \$prev)) {
my $msg = $ibx->msg_by_smsg($smsg);
if (!defined($msg)) {
warn "broken smsg for $mid\n";
- return 1; # continue
+ next; # continue
}
my $orig = $$msg;
my $cur = PublicInbox::MIME->new($msg);
if (content_id($cur) eq $cid) {
$smsg->{mime} = $cur;
- $gone{$smsg->num} = [ $smsg, \$orig ];
+ $gone{$smsg->{num}} = [ $smsg, \$orig ];
}
- 1; # continue
- });
+ }
my $n = scalar keys %gone;
next unless $n;
if ($n > 1) {
foreach my $idx (@$parts) {
$idx->remote_remove($oid, $mid);
}
- $self->{over}->remove_oid($oid, $mid);
}
$self->barrier;
}
if (defined $mark) {
my $cmt = $im->get_mark($mark);
- $self->{last_commit}->[$self->{max_git}] = $cmt;
+ $self->{last_commit}->[$self->{epoch_max}] = $cmt;
}
if ($purge && scalar keys %$purge) {
return purge_oids($self, $purge);
$purges;
}
+sub last_commit_part ($$;$) {
+ my ($self, $i, $cmt) = @_;
+ my $v = PublicInbox::Search::SCHEMA_VERSION();
+ $self->{mm}->last_commit_xap($v, $i, $cmt);
+}
+
sub set_last_commits ($) {
my ($self) = @_;
- defined(my $max_git = $self->{max_git}) or return;
- my $mm = $self->{mm};
+ defined(my $epoch_max = $self->{epoch_max}) or return;
my $last_commit = $self->{last_commit};
- foreach my $i (0..$max_git) {
+ foreach my $i (0..$epoch_max) {
defined(my $cmt = $last_commit->[$i]) or next;
$last_commit->[$i] = undef;
- $mm->last_commit_n($i, $cmt);
+ last_commit_part($self, $i, $cmt);
}
}
# issue a write barrier to ensure all data is visible to other processes
# and read-only ops. Order of data importance is: git > SQLite > Xapian
sub barrier {
- my ($self, $fsync) = @_;
+ my ($self) = @_;
if (my $im = $self->{im}) {
$im->barrier;
$_->remote_barrier foreach @$parts;
$over->barrier_wait; # wait for each Xapian partition
- $over->commit_fsync if $fsync;
# last_commit is special, don't commit these until
# remote partitions are done:
}
sub git_init {
- my ($self, $new) = @_;
+ my ($self, $epoch) = @_;
my $pfx = "$self->{-inbox}->{mainrepo}/git";
- my $git_dir = "$pfx/$new.git";
+ my $git_dir = "$pfx/$epoch.git";
my @cmd = (qw(git init --bare -q), $git_dir);
PublicInbox::Import::run_die(\@cmd);
PublicInbox::Import::run_die(\@cmd);
my $alt = "$all/objects/info/alternates";
- my $new_obj_dir = "../../git/$new.git/objects";
+ my $new_obj_dir = "../../git/$epoch.git/objects";
my %alts;
if (-e $alt) {
open(my $fh, '<', $alt) or die "open < $alt: $!\n";
$im->done;
$self->barrier(1);
$im = undef;
- my $git_dir = $self->git_init(++$self->{max_git});
+ my $git_dir = $self->git_init(++$self->{epoch_max});
my $git = PublicInbox::Git->new($git_dir);
return $self->import_init($git, 0);
}
}
- my $new = 0;
+ my $epoch = 0;
my $max;
my $latest = git_dir_latest($self, \$max);
if (defined $latest) {
my $git = PublicInbox::Git->new($latest);
my $packed_bytes = $git->packed_bytes;
if ($packed_bytes >= $self->{rotate_bytes}) {
- $new = $max + 1;
+ $epoch = $max + 1;
} else {
- $self->{max_git} = $max;
+ $self->{epoch_max} = $max;
return $self->import_init($git, $packed_bytes);
}
}
- $self->{max_git} = $new;
- $latest = $self->git_init($new);
+ $self->{epoch_max} = $epoch;
+ $latest = $self->git_init($epoch);
$self->import_init(PublicInbox::Git->new($latest), 0);
}
my $srch = $ibx->search->reopen;
my $cid = content_id($mime);
my $found;
- $srch->each_smsg_by_mid($mid, sub {
- my ($smsg) = @_;
- $smsg->load_expand;
+ my ($id, $prev);
+ while (my $smsg = $srch->next_by_mid($mid, \$id, \$prev)) {
my $msg = $ibx->msg_by_smsg($smsg);
if (!defined($msg)) {
warn "broken smsg for $mid\n";
- return 1; # continue
+ next;
}
my $cur = PublicInbox::MIME->new($msg);
if (content_id($cur) eq $cid) {
$smsg->{mime} = $cur;
$found = $smsg;
- return 0; # break out of loop
+ last;
}
# XXX DEBUG_DIFF is experimental and may be removed
diff($mid, $cur, $mime) if $ENV{DEBUG_DIFF};
-
- 1; # continue
- });
+ }
$found;
}
# only update last_commit for $i on reindex iff newer than current
sub update_last_commit {
my ($self, $git, $i, $cmt) = @_;
- my $last = $self->{mm}->last_commit_n($i);
+ my $last = last_commit_part($self, $i);
if (defined $last && is_ancestor($git, $last, $cmt)) {
my @cmd = (qw(rev-list --count), "$last..$cmt");
chomp(my $n = $git->qx(@cmd));
return if $n ne '' && $n == 0;
}
- $self->{mm}->last_commit_n($i, $cmt);
+ last_commit_part($self, $i, $cmt);
}
sub git_dir_n ($$) { "$_[0]->{-inbox}->{mainrepo}/git/$_[1].git" }
sub last_commits {
- my ($self, $max_git) = @_;
+ my ($self, $epoch_max) = @_;
my $heads = [];
- for (my $i = $max_git; $i >= 0; $i--) {
- $heads->[$i] = $self->{mm}->last_commit_n($i);
+ for (my $i = $epoch_max; $i >= 0; $i--) {
+ $heads->[$i] = last_commit_part($self, $i);
}
$heads;
}
}
sub index_prepare {
- my ($self, $opts, $max_git, $ranges) = @_;
+ my ($self, $opts, $epoch_max, $ranges) = @_;
my $regen_max = 0;
my $head = $self->{-inbox}->{ref_head} || 'refs/heads/master';
- for (my $i = $max_git; $i >= 0; $i--) {
+ for (my $i = $epoch_max; $i >= 0; $i--) {
die "already indexing!\n" if $self->{index_pipe};
my $git_dir = git_dir_n($self, $i);
-d $git_dir or next; # missing parts are fine
my $mime = PublicInbox::MIME->new($msgref);
my $mids = mids($mime->header_obj);
$mime = $msgref = undef;
-
+ my $srch = $self->{-inbox}->search;
foreach my $mid (@$mids) {
my %gone;
- $self->{-inbox}->search->reopen->each_smsg_by_mid($mid, sub {
- my ($smsg) = @_;
- $smsg->load_expand;
+ my ($id, $prev);
+ while (my $smsg = $srch->next_by_mid($mid, \$id, \$prev)) {
$gone{$smsg->num} = 1 if $oid eq $smsg->{blob};
1; # continue
- });
+ }
my $n = scalar keys %gone;
next unless $n;
if ($n > 1) {
my ($self, $opts) = @_;
$opts ||= {};
my $ibx = $self->{-inbox};
- my $max_git;
- my $latest = git_dir_latest($self, \$max_git);
+ my $epoch_max;
+ my $latest = git_dir_latest($self, \$epoch_max);
return unless defined $latest;
$self->idx_init; # acquire lock
my $mm_tmp = $self->{mm}->tmp_clone;
- my $ranges = $opts->{reindex} ? [] : $self->last_commits($max_git);
+ my $ranges = $opts->{reindex} ? [] : $self->last_commits($epoch_max);
my ($min, $max) = $mm_tmp->minmax;
- my $regen = $self->index_prepare($opts, $max_git, $ranges);
+ my $regen = $self->index_prepare($opts, $epoch_max, $ranges);
$$regen += $max if $max;
my $D = {};
my @cmd = qw(log --raw -r --pretty=tformat:%h
# work backwards through history
my $last_commit = [];
- for (my $i = $max_git; $i >= 0; $i--) {
+ for (my $i = $epoch_max; $i >= 0; $i--) {
my $git_dir = git_dir_n($self, $i);
die "already reindexing!\n" if delete $self->{reindex_pipe};
-d $git_dir or next; # missing parts are fine