user/dev discussion of public-inbox itself
 help / color / mirror / Atom feed
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 11/14] convert: support new -index options
Date: Mon, 10 Aug 2020 02:12:02 +0000
Message-ID: <20200810021205.18909-12-e@yhbt.net> (raw)
In-Reply-To: <20200810021205.18909-1-e@yhbt.net>

Converting v1 inboxes from v2 can be a painful experience
on HDD.  Some of the new options in the CLI or config
file make it less painful.
---
 Documentation/public-inbox-convert.pod | 19 +++++++
 lib/PublicInbox/Admin.pm               | 36 ++++++++++++
 script/public-inbox-convert            | 77 +++++++++++++++++++-------
 script/public-inbox-index              | 47 ++--------------
 4 files changed, 117 insertions(+), 62 deletions(-)

diff --git a/Documentation/public-inbox-convert.pod b/Documentation/public-inbox-convert.pod
index a8a5658c..a7958cf8 100644
--- a/Documentation/public-inbox-convert.pod
+++ b/Documentation/public-inbox-convert.pod
@@ -33,6 +33,25 @@ at 4 due to various bottlenecks.  The number of Xapian shards
 will be 1 less than the JOBS value, since there is a single
 process which distributes work to the Xapian shards.
 
+=item -L LEVEL, --index-level=LEVEL
+
+=item -c, --compact
+
+=item -v, --verbose
+
+=item --no-fsync
+
+=item --sequential-shard
+
+=item --batch-size=BYTES
+
+=item --max-size=BYTES
+
+These options affect indexing.  They have no effect if
+L</--no-index> is specified
+
+See L<public-inbox-index(1)> for a description of these options.
+
 =back
 
 =head1 ENVIRONMENT
diff --git a/lib/PublicInbox/Admin.pm b/lib/PublicInbox/Admin.pm
index 8a9a81c9..ce720beb 100644
--- a/lib/PublicInbox/Admin.pm
+++ b/lib/PublicInbox/Admin.pm
@@ -265,4 +265,40 @@ sub parse_unsigned ($) {
 	1;
 }
 
+sub index_prepare ($$) {
+	my ($opt, $cfg) = @_;
+	my $env;
+	if ($opt->{compact}) {
+		require PublicInbox::Xapcmd;
+		PublicInbox::Xapcmd::check_compact();
+		$opt->{compact_opt} = { -coarse_lock => 1, compact => 1 };
+		if (defined(my $jobs = $opt->{jobs})) {
+			$opt->{compact_opt}->{jobs} = $jobs;
+		}
+	}
+	for my $k (qw(max_size batch_size)) {
+		my $git_key = "publicInbox.index".ucfirst($k);
+		$git_key =~ s/_([a-z])/\U$1/g;
+		defined(my $v = $opt->{$k} // $cfg->{lc($git_key)}) or next;
+		parse_unsigned(\$v) or die "`$git_key=$v' not parsed\n";
+		$v > 0 or die "`$git_key=$v' must be positive\n";
+		$opt->{$k} = $v;
+	}
+
+	# 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
+	$opt->{batch_size} and
+		$env = { XAPIAN_FLUSH_THRESHOLD => '4294967295' };
+
+	for my $k (qw(sequential_shard)) {
+		my $git_key = "publicInbox.index".ucfirst($k);
+		$git_key =~ s/_([a-z])/\U$1/g;
+		defined(my $s = $opt->{$k} // $cfg->{lc($git_key)}) or next;
+		defined(my $v = $cfg->git_bool($s))
+					or die "`$git_key=$s' not boolean\n";
+		$opt->{$k} = $v;
+	}
+	$env;
+}
+
 1;
diff --git a/script/public-inbox-convert b/script/public-inbox-convert
index dbb2bd38..ca16b0dc 100755
--- a/script/public-inbox-convert
+++ b/script/public-inbox-convert
@@ -12,26 +12,57 @@ use PublicInbox::Git;
 use PublicInbox::Spawn qw(spawn);
 use Cwd 'abs_path';
 use File::Copy 'cp'; # preserves permissions:
-my $usage = "Usage: public-inbox-convert OLD NEW\n";
-my $jobs;
-my $index = 1;
-my %opts = (
-	'--jobs|j=i' => \$jobs,
-	'--index!' => \$index,
-);
-GetOptions(%opts) or die "bad command-line args\n$usage";
+my $usage = 'Usage: public-inbox-convert [options] OLD NEW';
+my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
+usage: $usage
+
+  convert v1 format inboxes to v2
+
+options:
+
+  --no-index          do not index after conversion
+  --jobs=NUM          set shards (NUM=0)
+  --verbose | -v      increase verbosity (may be repeated)
+  --help | -?         show this help
+
+index options (see public-inbox-index(1) manpage for full description):
+
+  --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
+  --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
+
+See public-inbox-convert(1) man page for full documentation.
+EOF
+
+my $opt = {
+	index => 1,
+	# index defaults:
+	quiet => -1, compact => 0, maxsize => undef, fsync => 1,
+	reindex => 1, # we always reindex
+};
+GetOptions($opt, qw(jobs|j=i index! help|?),
+		# index options
+		qw(verbose|v+ rethread compact|c+ fsync|sync!
+		indexlevel|index-level|L=s max_size|max-size=s
+		batch_size|batch-size=s
+		sequential_shard|sequential-shard|seq-shard
+		)) or die <<EOF;
+bad command-line args\n$usage
+EOF
+if ($opt->{help}) { print $help; exit 0 };
 my $old_dir = shift(@ARGV) or die $usage;
 my $new_dir = shift(@ARGV) or die $usage;
 die "$new_dir exists\n" if -d $new_dir;
 die "$old_dir not a directory\n" unless -d $old_dir;
-my $config = PublicInbox::Config->new;
+my $cfg = PublicInbox::Config->new;
 $old_dir = abs_path($old_dir);
 my $old;
-if ($config) {
-	$config->each_inbox(sub {
-		$old = $_[0] if abs_path($_[0]->{inboxdir}) eq $old_dir;
-	});
-}
+$cfg->each_inbox(sub {
+	$old = $_[0] if abs_path($_[0]->{inboxdir}) eq $old_dir;
+});
 unless ($old) {
 	warn "W: $old_dir not configured in " .
 		PublicInbox::Config::default_file() . "\n";
@@ -48,16 +79,20 @@ if ($old->version >= 2) {
 }
 
 $old->{indexlevel} //= PublicInbox::Admin::detect_indexlevel($old);
-if ($index) {
+my $env;
+if ($opt->{'index'}) {
 	my $mods = {};
 	PublicInbox::Admin::scan_ibx_modules($mods, $old);
 	PublicInbox::Admin::require_or_die(keys %$mods);
+	PublicInbox::Admin::progress_prepare($opt);
+	$env = PublicInbox::Admin::index_prepare($opt, $cfg);
 }
-
+local %ENV = (%$env, %ENV) if $env;
 my $new = { %$old };
 $new->{inboxdir} = abs_path($new_dir);
 $new->{version} = 2;
-$new = PublicInbox::InboxWritable->new($new);
+$new = PublicInbox::InboxWritable->new($new, { nproc => $opt->{jobs} });
+$new->{-no_fsync} = 1 if !$opt->{fsync};
 my $v2w;
 $old->umask_prepare;
 
@@ -73,7 +108,7 @@ $old->with_umask(sub {
 	local $ENV{GIT_CONFIG} = $old_cfg;
 	my $new_cfg = "$new->{inboxdir}/all.git/config";
 	$v2w = PublicInbox::V2Writable->new($new, 1);
-	$v2w->init_inbox($jobs);
+	$v2w->init_inbox(delete $opt->{jobs});
 	unlink $new_cfg;
 	link_or_copy($old_cfg, $new_cfg);
 	if (my $alt = $new->{altid}) {
@@ -98,7 +133,7 @@ $clone may not be valid after migrating to v2, not copying
 my $state = '';
 my $head = $old->{ref_head} || 'HEAD';
 my ($rd, $pid) = $old->git->popen(qw(fast-export --use-done-feature), $head);
-$v2w->idx_init;
+$v2w->idx_init($opt);
 my $im = $v2w->importer;
 my ($r, $w) = $im->gfi_start;
 my $h = '[0-9a-f]';
@@ -155,10 +190,10 @@ if (my $mm = $old->mm) {
 
 	# we want to trigger a reindex, not a from scratch index if
 	# we're reusing the msgmap from an existing v1 installation.
-	$v2w->idx_init;
+	$v2w->idx_init($opt);
 	my $epoch0 = PublicInbox::Git->new($v2w->git_init(0));
 	chop(my $cmt = $epoch0->qx(qw(rev-parse --verify), $head));
 	$v2w->last_epoch_commit(0, $cmt);
 }
-$v2w->index_sync({reindex => 1}) if $index;
+$v2w->index_sync($opt) if delete $opt->{'index'};
 $v2w->done;
diff --git a/script/public-inbox-index b/script/public-inbox-index
index b1d29ec1..14d3afd4 100755
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -32,7 +32,6 @@ options:
 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
@@ -51,47 +50,11 @@ if ($opt->{xapian_only} && !$opt->{reindex}) {
 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; # 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;
-}
-
-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;
-}
-
-# 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;
-}
-
 my $mods = {};
 foreach my $ibx (@ibxs) {
 	# XXX: users can shoot themselves in the foot, with opt->{indexlevel}
@@ -101,12 +64,14 @@ foreach my $ibx (@ibxs) {
 }
 
 PublicInbox::Admin::require_or_die(keys %$mods);
+my $env = PublicInbox::Admin::index_prepare($opt, $cfg);
+local %ENV = (%ENV, %$env) if $env;
 require PublicInbox::InboxWritable;
 PublicInbox::Admin::progress_prepare($opt);
 for my $ibx (@ibxs) {
 	$ibx = PublicInbox::InboxWritable->new($ibx);
 	if ($opt->{compact} >= 2) {
-		PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt);
+		PublicInbox::Xapcmd::run($ibx, 'compact', $opt->{compact_opt});
 	}
 	$ibx->{-no_fsync} = 1 if !$opt->{fsync};
 
@@ -118,8 +83,8 @@ 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);
+	if (my $copt = $opt->{compact_opt}) {
+		local $copt->{jobs} = 0 if $ibx_opt->{sequential_shard};
+		PublicInbox::Xapcmd::run($ibx, 'compact', $copt);
 	}
 }

  parent reply	other threads:[~2020-08-10  2:12 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-10  2:11 [PATCH 00/14] more indexing related improvements Eric Wong
2020-08-10  2:11 ` [PATCH 01/14] index: require --reindex when using --xapian-only Eric Wong
2020-08-10  2:11 ` [PATCH 02/14] index: --sequential-shard works incrementally Eric Wong
2020-08-10  2:11 ` [PATCH 03/14] doc: index: more notes about latest changes Eric Wong
2020-08-10  2:38   ` Kyle Meyer
2020-08-10  6:29     ` Eric Wong
2020-08-10  2:11 ` [PATCH 04/14] doc: add some notes around -xcpdb / -edit / -purge Eric Wong
2020-08-10  2:11 ` [PATCH 05/14] index+xcpdb: improve SIG{INT,TERM,HUP,PIPE} behavior Eric Wong
2020-08-10  2:11 ` [PATCH 06/14] msgmap: tmp_clone: simplify + meaningful filename Eric Wong
2020-08-10  2:11 ` [PATCH 07/14] avoid File::Temp::tempfile in more places Eric Wong
2020-08-10  2:11 ` [PATCH 08/14] admin: use a generic veriable name Eric Wong
2020-08-10  2:38   ` Kyle Meyer
2020-08-10  2:12 ` [PATCH 09/14] index: cleanup internal variables Eric Wong
2020-08-10  2:12 ` [PATCH 10/14] searchidx: use singular `$opt' for consistency with v2 Eric Wong
2020-08-10  2:12 ` Eric Wong [this message]
2020-08-10  2:12 ` [PATCH 12/14] convert: speed up --help Eric Wong
2020-08-10  2:12 ` [PATCH 13/14] convert: check ARGV more correctly Eric Wong
2020-08-10  2:12 ` [PATCH 14/14] convert: set No_COW on copied SQLite files Eric Wong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://public-inbox.org/README

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200810021205.18909-12-e@yhbt.net \
    --to=e@yhbt.net \
    --cc=meta@public-inbox.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

user/dev discussion of public-inbox itself

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://public-inbox.org/meta
	git clone --mirror http://czquwvybam4bgbro.onion/meta
	git clone --mirror http://hjrcffqmbrq6wope.onion/meta
	git clone --mirror http://ou63pmih66umazou.onion/meta

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V1 meta meta/ https://public-inbox.org/meta \
		meta@public-inbox.org
	public-inbox-index meta

Example config snippet for mirrors.
Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://ou63pmih66umazou.onion/inbox.comp.mail.public-inbox.meta
	nntp://czquwvybam4bgbro.onion/inbox.comp.mail.public-inbox.meta
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.io/gmane.mail.public-inbox.general
 note: .onion URLs require Tor: https://www.torproject.org/

code repositories for the project(s) associated with this inbox:

	https://80x24.org/public-inbox.git

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git