index: v2: parallel by default

[public-inbox.git] / script / public-inbox-index

diff --git a/script/public-inbox-index b/script/public-inbox-index
index 2d0f0eca5be54505adc83663f3608874f5dfbe7d..6217fb86c4ee3cef46083e78a5d4d3440e4bad63 100755 (executable)
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -16,9 +16,9 @@ use PublicInbox::Xapcmd;
 my $compact_opt;
 my $opt = { quiet => -1, compact => 0, maxsize => undef };
 GetOptions($opt, qw(verbose|v+ reindex compact|c+ jobs|j=i prune
-               indexlevel|L=s maxsize|max-size=s))
+               indexlevel|L=s maxsize|max-size=s batchsize|batch-size=s))
        or die "bad command-line args\n$usage";
-die "--jobs must be positive\n" if defined $opt->{jobs} && $opt->{jobs} <= 0;
+die "--jobs must be >= 0\n" if defined $opt->{jobs} && $opt->{jobs} < 0;
 
 if ($opt->{compact}) {
        require PublicInbox::Xapcmd;
@@ -30,13 +30,20 @@ my $cfg = PublicInbox::Config->new;
 my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, undef, $cfg);
 PublicInbox::Admin::require_or_die('-index');
 unless (@ibxs) { print STDERR "Usage: $usage\n"; exit 1 }
-my $mods = {};
+
 my $max_size = $opt->{maxsize} // $cfg->{lc('publicInbox.indexMaxSize')};
 if (defined $max_size) {
        PublicInbox::Admin::parse_unsigned(\$max_size) or
                die "`publicInbox.indexMaxSize=$max_size' not parsed\n";
 }
 
+if (my $bs = $opt->{batchsize} // $cfg->{lc('publicInbox.indexBatchSize')}) {
+       PublicInbox::Admin::parse_unsigned(\$bs) or
+               die "`publicInbox.indexBatchSize=$bs' not parsed\n";
+       $PublicInbox::SearchIdx::BATCH_BYTES = $bs;
+}
+
+my $mods = {};
 foreach my $ibx (@ibxs) {
        # XXX: users can shoot themselves in the foot, with opt->{indexlevel}
        $ibx->{indexlevel} //= $opt->{indexlevel} //