From feabfb1809b911fc97538282234c8b1f087ddb6a Mon Sep 17 00:00:00 2001 From: "Eric Wong (Contractor, The Linux Foundation)" Date: Tue, 20 Feb 2018 21:00:21 +0000 Subject: v2: support Xapian + SQLite indexing This is too slow, currently. Working with only 2017 LKML archives: git-only: ~1 minute git + SQLite: ~12 minutes git+Xapian+SQlite: ~45 minutes So yes, it looks like we'll need to parallelize Xapian indexing, at least. --- lib/PublicInbox/Import.pm | 1 + 1 file changed, 1 insertion(+) (limited to 'lib/PublicInbox/Import.pm') diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm index 364ab602..1a2698a7 100644 --- a/lib/PublicInbox/Import.pm +++ b/lib/PublicInbox/Import.pm @@ -285,6 +285,7 @@ sub add { # v2: we need this for Xapian if ($self->{want_object_id}) { chomp($self->{last_object_id} = $self->get_mark(":$blob")); + $self->{last_object_size} = $n; } my $ref = $self->{ref}; -- cgit v1.2.3-24-ge0c7