X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=9e0907be554815c7fe5bd6b1703721781bfe93ab;hb=03d2ebbcde99903bd84d3fd0c2815edc28ee3acf;hp=c0d637b109d886ecdd2c89424bf1cb488d3aa8d1;hpb=7187388231277606aaac3c00287f55ac7b604844;p=public-inbox.git
diff --git a/script/public-inbox-index b/script/public-inbox-index
index c0d637b1..9e0907be 100755
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -1,39 +1,126 @@
-#!/usr/bin/perl -w
-# Copyright (C) 2015-2019 all contributors
+#!perl -w
+# Copyright (C) 2015-2020 all contributors
# License: AGPL-3.0+
-# Basic tool to create a Xapian search index for a git repository
-# configured for public-inbox.
+# Basic tool to create a Xapian search index for a public-inbox.
# Usage with libeatmydata
# 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');
+my $usage = 'public-inbox-index [options] INBOX_DIR';
+my $help = < -1 };
-GetOptions($opt, qw(verbose|v+ reindex jobs|j=i prune indexlevel|L=s))
+ --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 $opt = { quiet => -1, compact => 0, maxsize => undef, fsync => 1 };
+GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune
+ 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";
-die "--jobs must be positive\n" if defined $opt->{jobs} && $opt->{jobs} <= 0;
+if ($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');
-sub usage { print STDERR "Usage: $usage\n"; exit 1 }
+if ($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;
+ }
+}
-# do we really care about this message? It's annoying...
-my $warn = 'public-inbox unconfigured for serving, indexing anyways...';
-my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $warn);
+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');
-usage() unless @ibxs;
+unless (@ibxs) { print STDERR "Usage: $usage\n"; exit 1 }
+
+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";
+}
+
+my $bs = $opt->{batchsize} // $cfg->{lc('publicInbox.indexBatchSize')};
+if (defined $bs) {
+ PublicInbox::Admin::parse_unsigned(\$bs) or
+ die "`publicInbox.indexBatchSize=$bs' not parsed\n";
+}
+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) {
- if (defined $opt->{indexlevel} && !defined($ibx->{indexlevel})) {
- # XXX: users can shoot themselves in the foot, with this...
- $ibx->{indexlevel} = $opt->{indexlevel};
- }
+ # XXX: users can shoot themselves in the foot, with opt->{indexlevel}
+ $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($opt);
-PublicInbox::Admin::index_inbox($_, $opt) for @ibxs;
+for my $ibx (@ibxs) {
+ $ibx = PublicInbox::InboxWritable->new($ibx);
+ if ($opt->{compact} >= 2) {
+ PublicInbox::Xapcmd::run($ibx, 'compact', $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 <{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);
+ }
+}