* [PATCH 06/26] admin: hoist out resolve_inboxes for -compact and -index
2019-05-23 9:36 7% [PATCH 00/26] xcpdb: ease Xapian DB format migrations Eric Wong
@ 2019-05-23 9:36 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2019-05-23 9:36 UTC (permalink / raw)
To: meta
Both of these index-affecting commands should work similarly
on the command-line.
public-inbox-index no longer complains about unconfigured
~/.public-inbox/config; but often I found myself being
annoyed by that, anyways...
---
lib/PublicInbox/Admin.pm | 34 ++++++++++++++++++++++++
script/public-inbox-compact | 35 ++++++------------------
script/public-inbox-index | 53 +++++++------------------------------
3 files changed, 52 insertions(+), 70 deletions(-)
diff --git a/lib/PublicInbox/Admin.pm b/lib/PublicInbox/Admin.pm
index 3eff5cd..2784820 100644
--- a/lib/PublicInbox/Admin.pm
+++ b/lib/PublicInbox/Admin.pm
@@ -41,6 +41,40 @@ sub resolve_repo_dir {
}
}
+sub resolve_inboxes {
+ my ($argv, $warn_on_unconfigured) = @_;
+ require PublicInbox::Config;
+ require PublicInbox::Inbox;
+
+ my @ibxs = map { resolve_repo_dir($_) } @$argv;
+ push(@ibxs, resolve_repo_dir()) unless @ibxs;
+
+ my %dir2ibx;
+ if (my $config = eval { PublicInbox::Config->new }) {
+ $config->each_inbox(sub {
+ my ($ibx) = @_;
+ $dir2ibx{abs_path($ibx->{mainrepo})} = $ibx;
+ });
+ } elsif ($warn_on_unconfigured) {
+ # do we really care about this? It's annoying...
+ warn $warn_on_unconfigured, "\n";
+ }
+ for my $i (0..$#ibxs) {
+ my $dir = $ibxs[$i];
+ $ibxs[$i] = $dir2ibx{$dir} ||= do {
+ my $name = "unconfigured-$i";
+ PublicInbox::Inbox->new({
+ name => $name,
+ address => [ "$name\@example.com" ],
+ mainrepo => $dir,
+ # TODO: consumers may want to warn on this:
+ #-unconfigured => 1,
+ });
+ };
+ }
+ @ibxs;
+}
+
# TODO: make Devel::Peek optional, only used for daemon
my @base_mod = qw(Email::MIME Date::Parse Devel::Peek);
my @over_mod = qw(DBD::SQLite DBI);
diff --git a/script/public-inbox-compact b/script/public-inbox-compact
index 4aa6273..709fb92 100755
--- a/script/public-inbox-compact
+++ b/script/public-inbox-compact
@@ -1,35 +1,16 @@
#!/usr/bin/perl -w
-# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
use strict;
use warnings;
-use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
-use PublicInbox::Search;
-use PublicInbox::Config;
use PublicInbox::InboxWritable;
-use Cwd 'abs_path';
use PublicInbox::Xapcmd;
+use PublicInbox::Admin;
+PublicInbox::Admin::require_or_die('-index');
my $usage = "Usage: public-inbox-compact REPO_DIR\n";
-my $dir = shift or die $usage;
-my $config = eval { PublicInbox::Config->new };
-my $ibx;
-$dir = abs_path($dir);
-if ($config) {
- $config->each_inbox(sub {
- $ibx = $_[0] if abs_path($_[0]->{mainrepo}) eq $dir
- });
+my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV) or die $usage;
+foreach (@ibxs) {
+ my $ibx = PublicInbox::InboxWritable->new($_);
+ # we rely on --no-renumber to keep docids synched to NNTP
+ PublicInbox::Xapcmd::run($ibx, [qw(xapian-compact --no-renumber)]);
}
-unless ($ibx) {
- warn "W: $dir not configured in ".
- PublicInbox::Config::default_file() . "\n";
- $ibx = {
- mainrepo => $dir,
- name => 'ignored',
- address => [ 'old@example.com' ],
- };
- $ibx = PublicInbox::Inbox->new($ibx);
-}
-$ibx = PublicInbox::InboxWritable->new($ibx);
-
-# we rely on --no-renumber to keep docids synched to NNTP
-PublicInbox::Xapcmd::run($ibx, [qw(xapian-compact --no-renumber)]);
diff --git a/script/public-inbox-index b/script/public-inbox-index
index cf001cc..9399c27 100755
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -1,5 +1,5 @@
#!/usr/bin/perl -w
-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2019 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 git repository
# configured for public-inbox.
@@ -10,14 +10,8 @@ use strict;
use warnings;
use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
my $usage = "public-inbox-index REPO_DIR";
-use PublicInbox::Admin qw(resolve_repo_dir);
+use PublicInbox::Admin;
PublicInbox::Admin::require_or_die('-index');
-require PublicInbox::Config;
-
-my $config = eval { PublicInbox::Config->new } || eval {
- warn "public-inbox unconfigured for serving, indexing anyways...\n";
- undef;
-};
my $reindex;
my $prune;
@@ -32,53 +26,26 @@ my %opts = (
GetOptions(%opts) or die "bad command-line args\n$usage";
die "--jobs must be positive\n" if defined $jobs && $jobs < 0;
-my @dirs;
-
-if (@ARGV) {
- @dirs = map { resolve_repo_dir($_) } @ARGV;
-} else {
- @dirs = (resolve_repo_dir());
-}
-
sub usage { print STDERR "Usage: $usage\n"; exit 1 }
-usage() unless @dirs;
-
-defined($config) and $config->each_inbox(sub {
- my ($ibx) = @_;
- for my $i (0..$#dirs) {
- next if $dirs[$i] ne $ibx->{mainrepo};
- $dirs[$i] = $ibx;
- }
-});
-
-my @inboxes;
+# 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);
+PublicInbox::Admin::require_or_die('-index');
+usage() unless @ibxs;
my $mods = {};
-
-foreach my $dir (@dirs) {
- my $ibx = $dir;
- if (!ref($ibx)) {
- unless (-d $dir) {
- die "$dir does not appear to be an inbox repository\n";
- }
- $ibx = PublicInbox::Inbox->new({
- mainrepo => $dir,
- name => 'unnamed',
- indexlevel => $indexlevel,
- version => -f "$dir/inbox.lock" ? 2 : 1,
- });
- } elsif (defined $indexlevel && !defined($ibx->{indexlevel})) {
+foreach my $ibx (@ibxs) {
+ if (defined $indexlevel && !defined($ibx->{indexlevel})) {
# XXX: users can shoot themselves in the foot, with this...
$ibx->{indexlevel} = $indexlevel;
}
- push @inboxes, $ibx;
PublicInbox::Admin::scan_ibx_modules($mods, $ibx);
}
PublicInbox::Admin::require_or_die(keys %$mods);
require PublicInbox::SearchIdx;
-index_inbox($_) for @inboxes;
+index_inbox($_) for @ibxs;
sub index_inbox {
my ($repo) = @_;
--
EW
^ permalink raw reply related [relevance 5%]
* [PATCH 00/26] xcpdb: ease Xapian DB format migrations
@ 2019-05-23 9:36 7% Eric Wong
2019-05-23 9:36 5% ` [PATCH 06/26] admin: hoist out resolve_inboxes for -compact and -index Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2019-05-23 9:36 UTC (permalink / raw)
To: meta
I've noticed performance problems in Xapian's old chert
backend which seem alleviated with the new glass backend;
particularly related to phrase searches.
Unfortunately, the tool distributed with Xapian for updating DB
formats, copydatabase(1), is extremely slow and blocking updates
for hours at a time to perform the migration is not acceptable.
(That's right, "copydatabase" is NOT a Postgres command!)
So, I've written "public-inbox-xcpdb" and gotten it to perform
the bulk copy operation without holding inbox.lock and have it
deal gracefully with Xapian DB modifications. xcpdb is still
slow, but I've (finally!) implemented partial reindexing to
allow it to minimize the lock time and not stall -mda or -watch
processes while it is working.
There's a bunch of cleanups along the way, too; and it should
make future changes to repartition the Xapian DB on existing v2
inboxes easier.
Eric Wong (26):
t/convert-compact: skip on missing xapian-compact(1)
v1writable: retire in favor of InboxWritable
doc: document the reason for --no-renumber
search: reenable phrase search on non-chert Xapian
xapcmd: new module for wrapping Xapian commands
admin: hoist out resolve_inboxes for -compact and -index
xapcmd: support spawn options
xcpdb: new tool which wraps Xapian's copydatabase(1)
xapcmd: do not cleanup on errors
admin: move index_inbox over
xcpdb: implement using Perl bindings
xapcmd: xcpdb supports compaction
v2writable: hoist out log_range sub for readability
xcpdb: use fine-grained locking
xcpdb: implement progress reporting
xcpdb: cleanup error handling and diagnosis
xapcmd: avoid EXDEV when finalizing changes
doc: xcpdb: update to reflect the current state
xapcmd: use "print STDERR" for progress reporting
xcpdb: show re-indexing progress
xcpdb: remove temporary directories on aborts
compact: reuse infrastructure from xcpdb
xcpdb|compact: support some xapian-compact switches
xapcmd: cleanup on interrupted xcpdb "--compact"
xcpdb|compact: support --jobs/-j flag like gmake(1)
xapcmd: do not reset %SIG until last Xtmpdir is done
Documentation/include.mk | 6 +-
Documentation/public-inbox-v1-format.pod | 4 +
Documentation/public-inbox-v2-format.pod | 4 +
Documentation/public-inbox-xcpdb.pod | 57 ++++
MANIFEST | 4 +-
lib/PublicInbox/Admin.pm | 66 ++++
lib/PublicInbox/InboxWritable.pm | 35 ++-
lib/PublicInbox/Search.pm | 48 +--
lib/PublicInbox/SearchIdx.pm | 34 ++-
lib/PublicInbox/V1Writable.pm | 34 ---
lib/PublicInbox/V2Writable.pm | 109 ++++---
lib/PublicInbox/Xapcmd.pm | 370 +++++++++++++++++++++++
script/public-inbox-compact | 102 +------
script/public-inbox-index | 102 +------
script/public-inbox-init | 13 +-
script/public-inbox-xcpdb | 19 ++
t/cgi.t | 4 +-
t/convert-compact.t | 4 +
t/indexlevels-mirror.t | 27 +-
t/init.t | 4 +-
t/nntpd.t | 15 +-
t/search.t | 1 +
t/v2mirror.t | 1 +
23 files changed, 740 insertions(+), 323 deletions(-)
create mode 100644 Documentation/public-inbox-xcpdb.pod
delete mode 100644 lib/PublicInbox/V1Writable.pm
create mode 100644 lib/PublicInbox/Xapcmd.pm
create mode 100755 script/public-inbox-xcpdb
--
EW
^ permalink raw reply [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2019-05-23 9:36 7% [PATCH 00/26] xcpdb: ease Xapian DB format migrations Eric Wong
2019-05-23 9:36 5% ` [PATCH 06/26] admin: hoist out resolve_inboxes for -compact and -index Eric Wong
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).