From b0372059b451c01fba1fdfe8a1879fbd5c7ca53d Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Sun, 21 Jun 2020 00:21:31 +0000 Subject: init: add -j / --jobs parameter On a powerful (by my standards) machine with 16GB RAM and an 7200 RPM HDD marketed for "enterprise" use, indexing a 8.1G (in git) LKML snapshot from Sep 2019 did not finish after 7 days with the default number (3) of Xapian shards (`--jobs=4') and `--batch-size=10m'. Indexing starts off fast, but progressively get slower as contents of the inbox (including Xapian + SQLite DBs) could no longer be cached by the kernel. Once the on-disk size increased, HDD seek contention between the Xapian shard workers slowed the process down to a crawl. With a single shard, it still took around 3.5 days to index on the HDD. That's not good, but it's far better than not finishing after 7 days. So allow unfortunate HDD users to easily specify a single shard on public-inbox-init. For reference, a freshly TRIM-ed low-end TLC SSD on the SATA II bus on the same machine indexes that same snapshot of LKML in ~7 hours with 3 shards and the same 10m batch size. In the past, a higher-end consumer grade MLC SSDs on similar hardware indexed a similarly sized-data set in ~4 hours. --- script/public-inbox-init | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'script/public-inbox-init') diff --git a/script/public-inbox-init b/script/public-inbox-init index 10d3ad45..00147db5 100755 --- a/script/public-inbox-init +++ b/script/public-inbox-init @@ -27,10 +27,12 @@ use Cwd qw/abs_path/; my $version = undef; my $indexlevel = undef; my $skip_epoch; +my $jobs; my %opts = ( 'V|version=i' => \$version, 'L|indexlevel=s' => \$indexlevel, 'S|skip|skip-epoch=i' => \$skip_epoch, + 'j|jobs=i' => \$jobs, ); GetOptions(%opts) or usage(); PublicInbox::Admin::indexlevel_ok_or_die($indexlevel) if defined $indexlevel; @@ -144,6 +146,12 @@ my $ibx = PublicInbox::Inbox->new({ }); my $creat_opt = {}; +if (defined $jobs) { + die "--jobs is only supported for -V2 inboxes\n" if $version == 1; + die "--jobs=$jobs must be >= 1\n" if $jobs <= 0; + $creat_opt->{nproc} = $jobs; +} + PublicInbox::InboxWritable->new($ibx, $creat_opt)->init_inbox(0, $skip_epoch); # needed for git prior to v2.1.0 -- cgit v1.2.3-24-ge0c7