sub commit_changes ($$$) {
my ($ibx, $tmp, $opt) = @_;
- my $new_parts = $opt->{reshard};
+ my $reshard = $opt->{reshard};
my $reindex = $opt->{reindex};
my $im = $ibx->importer(0);
$im->lock_acquire if !$opt->{-coarse_lock};
$SIG{INT} or die 'BUG: $SIG{INT} not handled';
- my @old_part;
+ my @old_shard;
while (my ($old, $new) = each %$tmp) {
my @st = stat($old);
$over = undef;
}
- if (!defined($new)) { # culled partition
- push @old_part, $old;
+ if (!defined($new)) { # culled shard
+ push @old_shard, $old;
next;
}
die "failed to remove $prev: $!\n";
}
}
- remove_tree(@old_part);
+ remove_tree(@old_shard);
$tmp->done;
if (!$opt->{-coarse_lock}) {
$opt->{-skip_lock} = 1;
- if ($im->can('count_partitions')) {
+ if ($im->can('count_shards')) {
my $pr = $opt->{-progress};
- my $n = $im->count_partitions;
- if (defined $new_parts && $n != $new_parts) {
+ my $n = $im->count_shards;
+ if (defined $reshard && $n != $reshard) {
die
-"BUG: counted $n partitions after repartioning to $new_parts";
+"BUG: counted $n shards after resharding to $reshard";
}
- my $prev = $im->{partitions};
+ my $prev = $im->{shards};
if ($pr && $prev != $n) {
- $pr->("partition count changed: $prev => $n\n");
- $im->{partitions} = $n;
+ $pr->("shard count changed: $prev => $n\n");
+ $im->{shards} = $n;
}
}
my ($ibx, $task, $opt) = @_; # task = 'cpdb' or 'compact'
my $cb = \&${\"PublicInbox::Xapcmd::$task"};
PublicInbox::Admin::progress_prepare($opt ||= {});
- my $dir = $ibx->{mainrepo} or die "no mainrepo in inbox\n";
+ my $dir = $ibx->{inboxdir} or die "no inboxdir in inbox\n";
runnable_or_die($XAPIAN_COMPACT) if $opt->{compact};
my $reindex; # v1:{ from => $x40 }, v2:{ from => [ $x40, $x40, .. ] } }
my $from; # per-epoch ranges
my $tmp = PublicInbox::Xtmpdirs->new;
my $v = $ibx->{version} ||= 1;
my @q;
- my $new_parts = $opt->{reshard};
- if (defined $new_parts && $new_parts <= 0) {
+ my $reshard = $opt->{reshard};
+ if (defined $reshard && $reshard <= 0) {
die "--reshard must be a positive number\n";
}
# we want temporary directories to be as deep as possible,
- # so v2 partitions can keep "xap$SCHEMA_VERSION" on a separate FS.
+ # so v2 shards can keep "xap$SCHEMA_VERSION" on a separate FS.
if ($v == 1) {
- if (defined $new_parts) {
+ if (defined $reshard) {
warn
-"--reshard=$new_parts ignored for v1 $ibx->{mainrepo}\n";
+"--reshard=$reshard ignored for v1 $ibx->{inboxdir}\n";
}
my $old_parent = dirname($old);
same_fs_or_die($old_parent, $old);
push @q, [ $old, $wip ];
} else {
opendir my $dh, $old or die "Failed to opendir $old: $!\n";
- my @old_parts;
+ my @old_shards;
while (defined(my $dn = readdir($dh))) {
if ($dn =~ /\A[0-9]+\z/) {
- push @old_parts, $dn;
+ push @old_shards, $dn;
} elsif ($dn eq '.' || $dn eq '..') {
} elsif ($dn =~ /\Aover\.sqlite3/) {
} else {
warn "W: skipping unknown dir: $old/$dn\n"
}
}
- die "No Xapian parts found in $old\n" unless @old_parts;
+ die "No Xapian shards found in $old\n" unless @old_shards;
- my ($src, $max_part);
- if (!defined($new_parts) || $new_parts == scalar(@old_parts)) {
+ my ($src, $max_shard);
+ if (!defined($reshard) || $reshard == scalar(@old_shards)) {
# 1:1 copy
- $max_part = scalar(@old_parts) - 1;
+ $max_shard = scalar(@old_shards) - 1;
} else {
# M:N copy
- $max_part = $new_parts - 1;
- $src = [ map { "$old/$_" } @old_parts ];
+ $max_shard = $reshard - 1;
+ $src = [ map { "$old/$_" } @old_shards ];
}
- foreach my $dn (0..$max_part) {
+ foreach my $dn (0..$max_shard) {
my $tmpl = "$dn-XXXXXXXX";
my $wip = tempdir($tmpl, DIR => $old);
same_fs_or_die($old, $wip);
push @q, [ $src // $cur , $wip ];
$tmp->{$cur} = $wip;
}
- # mark old parts to be unlinked
+ # mark old shards to be unlinked
if ($src) {
$tmp->{$_} ||= undef for @$src;
}
}
sub cpdb_loop ($$$;$$) {
- my ($src, $dst, $pr_data, $cur_part, $new_parts) = @_;
+ my ($src, $dst, $pr_data, $cur_shard, $reshard) = @_;
my ($pr, $fmt, $nr, $pfx);
if ($pr_data) {
$pr = $pr_data->{pr};
eval {
for (; $it != $end; $it++) {
my $docid = $it->get_docid;
- if (defined $new_parts) {
- my $dst_part = $docid % $new_parts;
- next if $dst_part != $cur_part;
+ if (defined $reshard) {
+ my $dst_shard = $docid % $reshard;
+ next if $dst_shard != $cur_shard;
}
my $doc = $src->get_document($docid);
$dst->replace_document($docid, $doc);
sub cpdb ($$) {
my ($args, $opt) = @_;
my ($old, $new) = @$args;
- my ($src, $cur_part);
- my $new_parts;
+ my ($src, $cur_shard);
+ my $reshard;
if (ref($old) eq 'ARRAY') {
- ($cur_part) = ($new =~ m!xap[0-9]+/([0-9]+)\b!);
- defined $cur_part or
- die "BUG: could not extract partition # from $new";
- $new_parts = $opt->{reshard};
- defined $new_parts or die 'BUG: got array src w/o --partition';
+ ($cur_shard) = ($new =~ m!xap[0-9]+/([0-9]+)\b!);
+ defined $cur_shard or
+ die "BUG: could not extract shard # from $new";
+ $reshard = $opt->{reshard};
+ defined $reshard or die 'BUG: got array src w/o --reshard';
- # repartitioning, M:N copy means have full read access
+ # resharding, M:N copy means have full read access
foreach (@$old) {
if ($src) {
my $sub = Search::Xapian::Database->new($_);
my $lc = $src->get_metadata('last_commit');
$dst->set_metadata('last_commit', $lc) if $lc;
- # only the first xapian partition (0) gets 'indexlevel'
+ # only the first xapian shard (0) gets 'indexlevel'
if ($new =~ m!(?:xapian[0-9]+|xap[0-9]+/0)\b!) {
my $l = $src->get_metadata('indexlevel');
if ($l eq 'medium') {
if ($pr_data) {
my $tot = $src->get_doccount;
- # we can only estimate when repartitioning,
+ # we can only estimate when resharding,
# because removed spam causes slight imbalance
my $est = '';
- if (defined $cur_part && $new_parts > 1) {
- $tot = int($tot/$new_parts);
+ if (defined $cur_shard && $reshard > 1) {
+ $tot = int($tot/$reshard);
$est = 'around ';
}
my $fmt = "$pfx % ".length($tot)."u/$tot\n";
};
} while (cpdb_retryable($src, $pfx));
- if (defined $new_parts) {
+ if (defined $reshard) {
# we rely on document IDs matching NNTP article number,
- # so we can't have the combined DB support rewriting
+ # so we can't have the Xapian sharding DB support rewriting
# document IDs. Thus we iterate through each shard
# individually.
$src = undef;
foreach (@$old) {
my $old = Search::Xapian::Database->new($_);
- cpdb_loop($old, $dst, $pr_data, $cur_part, $new_parts);
+ cpdb_loop($old, $dst, $pr_data, $cur_shard, $reshard);
}
} else {
cpdb_loop($src, $dst, $pr_data);
# http://www.tldp.org/LDP/abs/html/exitcodes.html
$SIG{INT} = sub { exit(130) };
$SIG{HUP} = $SIG{PIPE} = $SIG{TERM} = sub { exit(1) };
- my $self = bless {}, $_[0]; # old partition => new (tmp) partition
+ my $self = bless {}, $_[0]; # old shard => new (WIP) shard
$owner{"$self"} = $$;
$self;
}
my $owner_pid = delete $owner{"$self"} or return;
return if $owner_pid != $$;
foreach my $new (values %$self) {
- defined $new or next; # may be undef if repartitioning
+ defined $new or next; # may be undef if resharding
remove_tree($new) unless -d "$new/old";
}
done($self);