int($ENV{NPROC} || `nproc 2>/dev/null` || 2);
}
-sub new {
- my ($class, $v2ibx, $creat) = @_;
- my $dir = $v2ibx->{mainrepo} or die "no mainrepo in inbox\n";
- unless (-d $dir) {
- if ($creat) {
- require File::Path;
- File::Path::mkpath($dir);
- } else {
- die "$dir does not exist\n";
- }
- }
-
+sub count_partitions ($) {
+ my ($self) = @_;
my $nparts = 0;
- my $xpfx = "$dir/xap" . PublicInbox::Search::SCHEMA_VERSION;
+ my $xpfx = $self->{xpfx};
# always load existing partitions in case core count changes:
+ # Also, partition count may change while -watch is running
+ # due to -compact
if (-d $xpfx) {
foreach my $part (<$xpfx/*>) {
-d $part && $part =~ m!/\d+\z! or next;
};
}
}
- $nparts = nproc() if ($nparts == 0);
+ $nparts;
+}
+
+sub new {
+ my ($class, $v2ibx, $creat) = @_;
+ my $dir = $v2ibx->{mainrepo} or die "no mainrepo in inbox\n";
+ unless (-d $dir) {
+ if ($creat) {
+ require File::Path;
+ File::Path::mkpath($dir);
+ } else {
+ die "$dir does not exist\n";
+ }
+ }
$v2ibx = PublicInbox::InboxWritable->new($v2ibx);
+
+ my $xpfx = "$dir/xap" . PublicInbox::Search::SCHEMA_VERSION;
my $self = {
-inbox => $v2ibx,
im => undef, # PublicInbox::Import
- partitions => $nparts,
parallel => 1,
transact_bytes => 0,
+ xpfx => $xpfx,
over => PublicInbox::OverIdxFork->new("$xpfx/over.sqlite3"),
lock_path => "$dir/inbox.lock",
# limit each repo 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;
}
$self->lock_acquire;
$over->create($self);
+ # -compact can change partition count while -watch is idle
+ my $nparts = count_partitions($self);
+ if ($nparts && $nparts != $self->{partitions}) {
+ $self->{partitions} = $nparts;
+ }
+
# need to create all parts before initializing msgmap FD
my $max = $self->{partitions} - 1;
my $mark;
foreach my $mid (@$mids) {
+ my %gone;
$srch->reopen->each_smsg_by_mid($mid, sub {
my ($smsg) = @_;
$smsg->load_expand;
my $orig = $$msg;
my $cur = PublicInbox::MIME->new($msg);
if (content_id($cur) eq $cid) {
- $mm->num_delete($smsg->num);
- # $removed should only be set once assuming
- # no bugs in our deduplication code:
- $removed = $smsg;
- $removed->{mime} = $cur;
- my $oid = $smsg->{blob};
- if ($purge) {
- $purge->{$oid} = 1;
- } else {
- ($mark, undef) =
- $im->remove(\$orig, $cmt_msg);
- }
- $orig = undef;
- $removed->num; # memoize this for callers
-
- foreach my $idx (@$parts) {
- $idx->remote_remove($oid, $mid);
- }
- $self->{over}->remove_oid($oid, $mid);
+ $smsg->{mime} = $cur;
+ $gone{$smsg->num} = [ $smsg, \$orig ];
}
1; # continue
});
+ my $n = scalar keys %gone;
+ next unless $n;
+ if ($n > 1) {
+ warn "BUG: multiple articles linked to <$mid>\n",
+ join(',', sort keys %gone), "\n";
+ }
+ foreach my $num (keys %gone) {
+ my ($smsg, $orig) = @{$gone{$num}};
+ $mm->num_delete($num);
+ # $removed should only be set once assuming
+ # no bugs in our deduplication code:
+ $removed = $smsg;
+ my $oid = $smsg->{blob};
+ if ($purge) {
+ $purge->{$oid} = 1;
+ } else {
+ ($mark, undef) = $im->remove($orig, $cmt_msg);
+ }
+ $orig = undef;
+ foreach my $idx (@$parts) {
+ $idx->remote_remove($oid, $mid);
+ }
+ }
$self->barrier;
}
$purges;
}
+sub last_commit_part ($$;$) {
+ my ($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};
my $last_commit = $self->{last_commit};
foreach my $i (0..$max_git) {
defined(my $cmt = $last_commit->[$i]) or next;
$last_commit->[$i] = undef;
- $mm->last_commit_n($i, $cmt);
+ last_commit_part($self, $i, $cmt);
}
}
# 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" }
my ($self, $max_git) = @_;
my $heads = [];
for (my $i = $max_git; $i >= 0; $i--) {
- $heads->[$i] = $self->{mm}->last_commit_n($i);
+ $heads->[$i] = last_commit_part($self, $i);
}
$heads;
}