use PublicInbox::Spawn qw(which spawn);
use PublicInbox::Over;
use PublicInbox::Search;
-use File::Temp qw(tempdir);
+use File::Temp ();
use File::Path qw(remove_tree);
use File::Basename qw(dirname);
+use POSIX ();
# support testing with dev versions of Xapian which installs
# commands with a version number suffix (e.g. "xapian-compact-1.5")
our $XAPIAN_COMPACT = $ENV{XAPIAN_COMPACT} || 'xapian-compact';
our @COMPACT_OPT = qw(jobs|j=i quiet|q blocksize|b=s no-full|n fuller|F);
-sub commit_changes ($$$) {
- my ($ibx, $tmp, $opt) = @_;
+sub commit_changes ($$$$) {
+ my ($ibx, $im, $tmp, $opt) = @_;
my $reshard = $opt->{reshard};
my $reindex = $opt->{reindex};
- my $im = $ibx->importer(0);
- $im->lock_acquire if !$opt->{-coarse_lock};
$SIG{INT} or die 'BUG: $SIG{INT} not handled';
my @old_shard;
- while (my ($old, $new) = each %$tmp) {
+ while (my ($old, $newdir) = each %$tmp) {
+ next if $old eq ''; # no invalid paths
my @st = stat($old);
if (!@st && !defined($opt->{reshard})) {
die "failed to stat($old): $!";
}
+ my $new = $newdir->dirname if defined($newdir);
my $over = "$old/over.sqlite3";
if (-f $over) { # only for v1, v2 over is untouched
defined $new or die "BUG: $over exists when culling v2";
}
}
remove_tree(@old_shard);
- $tmp->done;
+ $tmp = undef;
if (!$opt->{-coarse_lock}) {
$opt->{-skip_lock} = 1;
}
}
- PublicInbox::Admin::index_inbox($ibx, $opt);
- # implicit lock_release
- } else {
- $im->lock_release;
+ PublicInbox::Admin::index_inbox($ibx, $im, $opt);
}
}
defined(my $pid = fork) or die "fork: $!";
return $pid if $pid > 0;
$cb->($args, $opt);
- exit 0;
+ POSIX::_exit(0);
}
sub runnable_or_die ($) {
which($exe) or die "$exe not found in PATH\n";
}
-sub prepare_reindex ($$) {
- my ($ibx, $reindex) = @_;
+sub prepare_reindex ($$$) {
+ my ($ibx, $im, $reindex) = @_;
if ($ibx->{version} == 1) {
my $dir = $ibx->search->xdir(1);
my $xdb = Search::Xapian::Database->new($dir);
$reindex->{from} = $lc;
}
} else { # v2
- my $v2w = $ibx->importer(0);
my $max;
- $v2w->git_dir_latest(\$max) or return;
+ $im->git_dir_latest(\$max) or return;
my $from = $reindex->{from};
my $mm = $ibx->mm;
my $v = PublicInbox::Search::SCHEMA_VERSION();
}
}
+sub setup_signals () {
+ # http://www.tldp.org/LDP/abs/html/exitcodes.html
+ $SIG{INT} = sub { exit(130) };
+ $SIG{HUP} = $SIG{PIPE} = $SIG{TERM} = sub { exit(1) };
+}
+
sub run {
my ($ibx, $task, $opt) = @_; # task = 'cpdb' or 'compact'
my $cb = \&${\"PublicInbox::Xapcmd::$task"};
PublicInbox::Admin::progress_prepare($opt ||= {});
- my $dir = $ibx->{mainrepo} or die "no mainrepo in inbox\n";
+ my $dir = $ibx->{inboxdir} or die "no inboxdir in inbox\n";
runnable_or_die($XAPIAN_COMPACT) if $opt->{compact};
my $reindex; # v1:{ from => $x40 }, v2:{ from => [ $x40, $x40, .. ] } }
my $from; # per-epoch ranges
my $old = $ibx->search->xdir(1);
-d $old or die "$old does not exist\n";
- my $tmp = PublicInbox::Xtmpdirs->new;
+ my $tmp = {};
my $v = $ibx->{version} ||= 1;
my @q;
my $reshard = $opt->{reshard};
die "--reshard must be a positive number\n";
}
+ local %SIG = %SIG;
+ setup_signals();
+
# we want temporary directories to be as deep as possible,
# so v2 shards can keep "xap$SCHEMA_VERSION" on a separate FS.
if ($v == 1) {
if (defined $reshard) {
warn
-"--reshard=$reshard ignored for v1 $ibx->{mainrepo}\n";
+"--reshard=$reshard ignored for v1 $ibx->{inboxdir}\n";
}
- my $old_parent = dirname($old);
- same_fs_or_die($old_parent, $old);
+ my $dir = dirname($old);
+ same_fs_or_die($dir, $old);
my $v = PublicInbox::Search::SCHEMA_VERSION();
- my $wip = tempdir("xapian$v-XXXXXXXX", DIR => $old_parent);
+ my $wip = File::Temp->newdir("xapian$v-XXXXXXXX", DIR => $dir);
$tmp->{$old} = $wip;
push @q, [ $old, $wip ];
} else {
}
foreach my $dn (0..$max_shard) {
my $tmpl = "$dn-XXXXXXXX";
- my $wip = tempdir($tmpl, DIR => $old);
- same_fs_or_die($old, $wip);
+ my $wip = File::Temp->newdir($tmpl, DIR => $old);
+ same_fs_or_die($old, $wip->dirname);
my $cur = "$old/$dn";
push @q, [ $src // $cur , $wip ];
$tmp->{$cur} = $wip;
$tmp->{$_} ||= undef for @$src;
}
}
- my $im = $ibx->importer(0);
my $max = $opt->{jobs} || scalar(@q);
$ibx->with_umask(sub {
+ my $im = $ibx->importer(0);
$im->lock_acquire;
# fine-grained locking if we prepare for reindex
if (!$opt->{-coarse_lock}) {
- prepare_reindex($ibx, $reindex);
+ prepare_reindex($ibx, $im, $reindex);
$im->lock_release;
}
- delete($ibx->{$_}) for (qw(mm over search)); # cleanup
+ $ibx->cleanup;
process_queue(\@q, $cb, $max, $opt);
- commit_changes($ibx, $tmp, $opt);
+ $im->lock_acquire if !$opt->{-coarse_lock};
+ commit_changes($ibx, $im, $tmp, $opt);
});
}
# xapian-compact wrapper
sub compact ($$) {
my ($args, $opt) = @_;
- my ($src, $dst) = @$args;
+ my ($src, $newdir) = @$args;
+ my $dst = ref($newdir) ? $newdir->dirname : $newdir;
my ($r, $w);
my $pfx = $opt->{-progress_pfx} ||= progress_pfx($src);
my $pr = $opt->{-progress};
# to the overhead of Perl.
sub cpdb ($$) {
my ($args, $opt) = @_;
- my ($old, $new) = @$args;
+ my ($old, $newdir) = @$args;
+ my $new = $newdir->dirname;
my ($src, $cur_shard);
my $reshard;
if (ref($old) eq 'ARRAY') {
$src = Search::Xapian::Database->new($old);
}
- my ($xtmp, $tmp);
+ my ($tmp, $ft);
+ local %SIG = %SIG;
if ($opt->{compact}) {
- my $newdir = dirname($new);
- same_fs_or_die($newdir, $new);
- $tmp = tempdir("$new.compact-XXXXXX", DIR => $newdir);
- $xtmp = PublicInbox::Xtmpdirs->new;
- $xtmp->{$new} = $tmp;
+ my $dir = dirname($new);
+ same_fs_or_die($dir, $new);
+ $ft = File::Temp->newdir("$new.compact-XXXXXX", DIR => $dir);
+ setup_signals();
+ $tmp = $ft->dirname;
} else {
$tmp = $new;
}
}
$pr->(sprintf($pr_data->{fmt}, $pr_data->{nr})) if $pr;
- return unless $xtmp;
+ return unless $opt->{compact};
$src = $dst = undef; # flushes and closes
# since $dst isn't readable by HTTP or NNTP clients, yet:
compact([ $tmp, $new ], $opt);
remove_tree($tmp) or die "failed to remove $tmp: $!\n";
- $xtmp->done;
-}
-
-# slightly easier-to-manage manage than END{} blocks
-package PublicInbox::Xtmpdirs;
-use strict;
-use warnings;
-use File::Path qw(remove_tree);
-my %owner;
-
-sub new {
- # http://www.tldp.org/LDP/abs/html/exitcodes.html
- $SIG{INT} = sub { exit(130) };
- $SIG{HUP} = $SIG{PIPE} = $SIG{TERM} = sub { exit(1) };
- my $self = bless {}, $_[0]; # old shard => new (WIP) shard
- $owner{"$self"} = $$;
- $self;
-}
-
-sub done {
- my ($self) = @_;
- delete $owner{"$self"};
-
- my %known_pids;
- $known_pids{$_}++ foreach values %owner;
- if (!$known_pids{$$}) {
- $SIG{INT} = $SIG{HUP} = $SIG{PIPE} = $SIG{TERM} = 'DEFAULT';
- }
- %$self = ();
-}
-
-sub DESTROY {
- my ($self) = @_;
- my $owner_pid = delete $owner{"$self"} or return;
- return if $owner_pid != $$;
- foreach my $new (values %$self) {
- defined $new or next; # may be undef if resharding
- remove_tree($new) unless -d "$new/old";
- }
- done($self);
}
1;