X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=b1d29ec14546056759e813f84ae3ff93a96497ab;hb=6a7e3c6f870d0555184b68940eb373fa102d4102;hp=52d6ba70af7a8401db7311ca89a66406de4b34a1;hpb=4c5fa84eec85cf406cbcd900f92dc478ed14ea30;p=public-inbox.git diff --git a/script/public-inbox-index b/script/public-inbox-index index 52d6ba70..b1d29ec1 100755 --- a/script/public-inbox-index +++ b/script/public-inbox-index @@ -1,132 +1,125 @@ -#!/usr/bin/perl -w -# Copyright (C) 2015-2018 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 REPO_DIR +# 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); -use Cwd 'abs_path'; -my $usage = "public-inbox-index REPO_DIR"; -use PublicInbox::Config; -my $config = eval { PublicInbox::Config->new } || eval { - warn "public-inbox unconfigured for serving, indexing anyways...\n"; - {} -}; -eval { require PublicInbox::SearchIdx }; -if ($@) { - print STDERR "Search::Xapian required for $0\n"; - exit 1; -} +my $usage = 'public-inbox-index [options] INBOX_DIR'; +my $help = < \$reindex, - '--regenerate' => \$regen, - '--jobs|j=i' => \$jobs, -); -GetOptions(%opts) or die "bad command-line args\n$usage"; -die "--jobs must be positive\n" if defined $jobs && $jobs <= 0; + Create and update search indices -my @dirs; +options: -sub resolve_repo_dir { - my ($cd) = @_; - my $prefix = defined $cd ? $cd : './'; - if (-d $prefix && -f "$prefix/inbox.lock") { # v2 - return abs_path($prefix); - } + --no-fsync speed up indexing, risk corruption on power outage + -L 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 $opt = { quiet => -1, compact => 0, max_size => undef, fsync => 1 }; +GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune + fsync|sync! xapian_only|xapian-only + indexlevel|index-level|L=s max_size|max-size=s + batch_size|batch-size=s + sequential_shard|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->{xapian_only} && !$opt->{reindex}) { + die "--xapian-only requires --reindex\n"; +} + +# require lazily to speed up --help +require PublicInbox::Admin; +PublicInbox::Admin::require_or_die('-index'); - my @cmd = qw(git rev-parse --git-dir); - my $cmd = join(' ', @cmd); - my $pid = open my $fh, '-|'; - defined $pid or die "forking $cmd failed: $!\n"; - if ($pid == 0) { - if (defined $cd) { - chdir $cd or die "chdir $cd failed: $!\n"; - } - exec @cmd; - die "Failed to exec $cmd: $!\n"; - } else { - my $dir = eval { - local $/; - <$fh>; - }; - close $fh or die "error in $cmd: $!\n"; - chomp $dir; - return abs_path($cd) if ($dir eq '.' && defined $cd); - abs_path($dir); +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} = $jobs; } } -if (@ARGV) { - @dirs = map { resolve_repo_dir($_) } @ARGV; -} else { - @dirs = (resolve_repo_dir()); +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 } + +my $max_size = $opt->{max_size} // $cfg->{lc('publicInbox.indexMaxSize')}; +if (defined $max_size) { + PublicInbox::Admin::parse_unsigned(\$max_size) or + die "`publicInbox.indexMaxSize=$max_size' not parsed\n"; + $opt->{max_size} = $max_size; } -sub usage { print STDERR "Usage: $usage\n"; exit 1 } -usage() unless @dirs; +my $bs = $opt->{batch_size} // $cfg->{lc('publicInbox.indexBatchSize')}; +if (defined $bs) { + PublicInbox::Admin::parse_unsigned(\$bs) or + die "`publicInbox.indexBatchSize=$bs' not parsed\n"; + $opt->{batch_size} = $bs; +} -foreach my $k (keys %$config) { - $k =~ /\Apublicinbox\.([^\.]+)\.mainrepo\z/ or next; - my $name = $1; - my $v = $config->{$k}; - for my $i (0..$#dirs) { - next if $dirs[$i] ne $v; - my $ibx = $config->lookup_name($name); - $dirs[$i] = $ibx if $ibx; - } +# 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->{sequential_shard} // + $cfg->{lc('publicInbox.indexSequentialShard')}; +if (defined $s) { + my $v = $cfg->git_bool($s); + defined($v) or + die "`publicInbox.indexSequentialShard=$s' not boolean\n"; + $opt->{sequential_shard} = $v; } -foreach my $dir (@dirs) { - if (!ref($dir) && -f "$dir/inbox.lock") { # v2 - my $ibx = { mainrepo => $dir, name => 'unnamed' }; - $dir = PublicInbox::Inbox->new($ibx); - } - index_dir($dir); +my $mods = {}; +foreach my $ibx (@ibxs) { + # XXX: users can shoot themselves in the foot, with opt->{indexlevel} + $ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapian_only} ? + 'full' : PublicInbox::Admin::detect_indexlevel($ibx)); + PublicInbox::Admin::scan_ibx_modules($mods, $ibx); } -sub index_dir { - my ($repo) = @_; - if (!ref $repo && ! -d $repo) { - die "$repo does not appear to be an inbox repository\n"; +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', $compact_opt); } - if (ref($repo) && ($repo->{version} || 1) == 2) { - eval { require PublicInbox::V2Writable }; - die "v2 requirements not met: $@\n" if $@; - my $v2w = eval { - local $ENV{NPROC} = $jobs; - PublicInbox::V2Writable->new($repo); - }; - if (defined $jobs) { - if ($jobs == 1) { - $v2w->{parallel} = 0; - } else { - my $n = $v2w->{partitions}; - if ($jobs != $n) { - warn -"Unable to respect --jobs=$jobs, inbox was created with $n partitions\n"; - } - } - } - my $mm = $repo->mm; - my (undef, $max) = $mm->minmax if $mm; - if (defined($max) && !$reindex && !$regen) { - die -"v2 inboxes may only use --reindex and/or --regenerate once\n". -"msgmap.sqlite3 is initialized\n"; - } + $ibx->{-no_fsync} = 1 if !$opt->{fsync}; - $v2w->reindex($regen); - $v2w->done; - } else { - my $s = PublicInbox::SearchIdx->new($repo, 1); - $s->index_sync({ reindex => $reindex }); + my $ibx_opt = $opt; + if (defined(my $s = $ibx->{lc('indexSequentialShard')})) { + defined(my $v = $cfg->git_bool($s)) or die <{name}.indexSequentialShard not boolean +EOL + $ibx_opt = { %$opt, sequential_shard => $v }; + } + PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt); + if ($compact_opt) { + local $compact_opt->{jobs} = 0 if $ibx_opt->{sequential_shard}; + PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt); } }