X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=9e0907be554815c7fe5bd6b1703721781bfe93ab;hb=03d2ebbcde99903bd84d3fd0c2815edc28ee3acf;hp=2e1934b0833110d58ca0b2ccaba47cd6249419ff;hpb=b02c7a346bd36f1325518ca110a781c619082da1;p=public-inbox.git

diff --git a/script/public-inbox-index b/script/public-inbox-index
index 2e1934b0..9e0907be 100755
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -1,4 +1,4 @@
-#!/usr/bin/perl -w
+#!perl -w
 # Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 # Basic tool to create a Xapian search index for a public-inbox.
@@ -6,27 +6,60 @@
 # highly recommended: eatmydata public-inbox-index INBOX_DIR
 
 use strict;
-use warnings;
+use v5.10.1;
 use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
-my $usage = "public-inbox-index INBOX_DIR";
-use PublicInbox::Admin;
-PublicInbox::Admin::require_or_die('-index');
-use PublicInbox::Xapcmd;
+my $usage = 'public-inbox-index [options] INBOX_DIR';
+my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
+usage: $usage
+
+  Create and update search indices
+
+options:
+
+  --no-fsync          speed up indexing, risk corruption on power outage
+  --indexlevel=LEVEL  `basic', 'medium', or `full' (default: full)
+  --compact | -c      run public-inbox-compact(1) after indexing
+  --sequential-shard  index Xapian shards sequentially for slow storage
+  --jobs=NUM          set or disable parallelization (NUM=0)
+  --batch-size=BYTES  flush changes to OS after a given number of bytes
+  --max-size=BYTES    do not index messages larger than the given size
+  --reindex           index previously indexed data (if upgrading)
+  --rethread          regenerate thread IDs (if upgrading, use sparingly)
+  --prune             prune git storage on discontiguous history
+  --verbose | -v      increase verbosity (may be repeated)
+  --help | -?         show this help
 
+BYTES may use `k', `m', and `g' suffixes (e.g. `10m' for 10 megabytes)
+See public-inbox-index(1) man page for full documentation.
+EOF
 my $compact_opt;
-my $opt = { quiet => -1, compact => 0, maxsize => undef };
+my $opt = { quiet => -1, compact => 0, maxsize => undef, fsync => 1 };
 GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune
-		indexlevel|L=s maxsize|max-size=s batchsize|batch-size=s))
+		fsync|sync! xapianonly|xapian-only
+		indexlevel|L=s maxsize|max-size=s batchsize|batch-size=s
+		sequentialshard|seq-shard|sequential-shard
+		help|?))
 	or die "bad command-line args\n$usage";
+if ($opt->{help}) { print $help; exit 0 };
 die "--jobs must be >= 0\n" if defined $opt->{jobs} && $opt->{jobs} < 0;
+if ($opt->{xapianonly} && !$opt->{reindex}) {
+	die "--xapian-only requires --reindex\n";
+}
+
+# require lazily to speed up --help
+require PublicInbox::Admin;
+PublicInbox::Admin::require_or_die('-index');
 
 if ($opt->{compact}) {
 	require PublicInbox::Xapcmd;
 	PublicInbox::Xapcmd::check_compact();
 	$compact_opt = { -coarse_lock => 1, compact => 1 };
+	if (defined(my $jobs = $opt->{jobs})) {
+		$compact_opt->{jobs} = $jobs;
+	}
 }
 
-my $cfg = PublicInbox::Config->new;
+my $cfg = PublicInbox::Config->new; # Config is loaded by Admin
 my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, undef, $cfg);
 PublicInbox::Admin::require_or_die('-index');
 unless (@ibxs) { print STDERR "Usage: $usage\n"; exit 1 }
@@ -37,28 +70,57 @@ if (defined $max_size) {
 		die "`publicInbox.indexMaxSize=$max_size' not parsed\n";
 }
 
-if (my $bs = $opt->{batchsize} // $cfg->{lc('publicInbox.indexBatchSize')}) {
+my $bs = $opt->{batchsize} // $cfg->{lc('publicInbox.indexBatchSize')};
+if (defined $bs) {
 	PublicInbox::Admin::parse_unsigned(\$bs) or
 		die "`publicInbox.indexBatchSize=$bs' not parsed\n";
-	$PublicInbox::SearchIdx::BATCH_BYTES = $bs;
+}
+no warnings 'once';
+local $PublicInbox::SearchIdx::BATCH_BYTES = $bs if defined($bs);
+use warnings 'once';
+
+# out-of-the-box builds of Xapian 1.4.x are still limited to 32-bit
+# https://getting-started-with-xapian.readthedocs.io/en/latest/concepts/indexing/limitations.html
+local $ENV{XAPIAN_FLUSH_THRESHOLD} ||= '4294967295' if defined($bs);
+
+my $s = $opt->{sequentialshard} //
+			$cfg->{lc('publicInbox.indexSequentialShard')};
+if (defined $s) {
+	my $v = $cfg->git_bool($s);
+	defined($v) or
+		die "`publicInbox.indexSequentialShard=$s' not boolean\n";
+	$opt->{sequentialshard} = $v;
 }
 
 my $mods = {};
 foreach my $ibx (@ibxs) {
 	# XXX: users can shoot themselves in the foot, with opt->{indexlevel}
-	$ibx->{indexlevel} //= $opt->{indexlevel} //
-			PublicInbox::Admin::detect_indexlevel($ibx);
+	$ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapianonly} ?
+			'full' : PublicInbox::Admin::detect_indexlevel($ibx));
 	$ibx->{index_max_size} = $max_size;
 	PublicInbox::Admin::scan_ibx_modules($mods, $ibx);
 }
 
 PublicInbox::Admin::require_or_die(keys %$mods);
+require PublicInbox::InboxWritable;
 PublicInbox::Admin::progress_prepare($opt);
 for my $ibx (@ibxs) {
 	$ibx = PublicInbox::InboxWritable->new($ibx);
 	if ($opt->{compact} >= 2) {
 		PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt);
 	}
-	PublicInbox::Admin::index_inbox($ibx, undef, $opt);
-	PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt) if $compact_opt;
+	$ibx->{-no_fsync} = 1 if !$opt->{fsync};
+
+	my $ibx_opt = $opt;
+	if (defined(my $s = $ibx->{indexsequentialshard})) {
+		defined(my $v = $cfg->git_bool($s)) or die <<EOL;
+publicInbox.$ibx->{name}.indexSequentialShard not boolean
+EOL
+		$ibx_opt = { %$opt, sequentialshard => $v };
+	}
+	PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt);
+	if ($compact_opt) {
+		local $compact_opt->{jobs} = 0 if $ibx_opt->{sequentialshard};
+		PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt);
+	}
 }