# 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 ($$$) {
my ($ibx, $tmp, $opt) = @_;
my $reindex = $opt->{reindex};
my $im = $ibx->importer(0);
- $im->lock_acquire if $reindex;
+ $im->lock_acquire if !$opt->{-coarse_lock};
+
+ $SIG{INT} or die 'BUG: $SIG{INT} not handled';
while (my ($old, $new) = each %$tmp) {
my @st = stat($old) or die "failed to stat($old): $!\n";
remove_tree($prev) or die "failed to remove $prev: $!\n";
}
$tmp->done;
- if ($reindex) {
+ if (!$opt->{-coarse_lock}) {
$opt->{-skip_lock} = 1;
PublicInbox::Admin::index_inbox($ibx, $opt);
# implicit lock_release
}
}
-sub xspawn {
- my ($cmd, $env, $opt) = @_;
- if (ref($cmd->[0]) eq 'CODE') {
- my $cb = shift(@$cmd); # $cb = cpdb()
- defined(my $pid = fork) or die "fork: $!";
- return $pid if $pid > 0;
- eval { $cb->($cmd, $env, $opt) };
- die $@ if $@;
- exit 0;
- } else {
- spawn($cmd, $env, $opt);
- }
+sub cb_spawn {
+ my ($cb, $args, $opt) = @_; # $cb = cpdb() or compact()
+ defined(my $pid = fork) or die "fork: $!";
+ return $pid if $pid > 0;
+ $cb->($args, $opt);
+ exit 0;
}
sub runnable_or_die ($) {
}
}
-sub progress_prepare ($) {
- my ($opt) = @_;
- if ($opt->{quiet}) {
- open my $null, '>', '/dev/null' or
- die "failed to open /dev/null: $!\n";
- $opt->{1} = fileno($null);
- $opt->{-dev_null} = $null;
- } else {
- $opt->{-progress} = sub { print STDERR @_ };
- }
-}
-
sub same_fs_or_die ($$) {
my ($x, $y) = @_;
return if ((stat($x))[0] == (stat($y))[0]); # 0 - st_dev
die "$x and $y reside on different filesystems\n";
}
+sub process_queue {
+ my ($queue, $cb, $max, $opt) = @_;
+ if ($max <= 1) {
+ while (defined(my $args = shift @$queue)) {
+ $cb->($args, $opt);
+ }
+ return;
+ }
+
+ # run in parallel:
+ my %pids;
+ while (@$queue) {
+ while (scalar(keys(%pids)) < $max && scalar(@$queue)) {
+ my $args = shift @$queue;
+ $pids{cb_spawn($cb, $args, $opt)} = $args;
+ }
+
+ while (scalar keys %pids) {
+ my $pid = waitpid(-1, 0);
+ my $args = delete $pids{$pid};
+ die join(' ', @$args)." failed: $?\n" if $?;
+ }
+ }
+}
+
sub run {
- my ($ibx, $cmd, $env, $opt) = @_;
- progress_prepare($opt ||= {});
+ 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 $exe = $cmd->[0];
runnable_or_die($XAPIAN_COMPACT) if $opt->{compact};
-
my $reindex; # v1:{ from => $x40 }, v2:{ from => [ $x40, $x40, .. ] } }
my $from; # per-epoch ranges
- if (ref($exe) eq 'CODE') {
+ if (!$opt->{-coarse_lock}) {
$reindex = $opt->{reindex} = {};
$from = $reindex->{from} = [];
require Search::Xapian::WritableDatabase;
- } else {
- runnable_or_die($exe);
}
+
$ibx->umask_prepare;
my $old = $ibx->search->xdir(1);
-d $old or die "$old does not exist\n";
my $tmp = PublicInbox::Xtmpdirs->new;
my $v = $ibx->{version} ||= 1;
- my @cmds;
+ my @q;
# we want temporary directories to be as deep as possible,
# so v2 partitions can keep "xap$SCHEMA_VERSION" on a separate FS.
my $old_parent = dirname($old);
same_fs_or_die($old_parent, $old);
$tmp->{$old} = tempdir('xapcmd-XXXXXXXX', DIR => $old_parent);
- push @cmds, [ @$cmd, $old, $tmp->{$old} ];
+ push @q, [ $old, $tmp->{$old} ];
} else {
opendir my $dh, $old or die "Failed to opendir $old: $!\n";
while (defined(my $dn = readdir($dh))) {
my $dst = tempdir($tmpl, DIR => $old);
same_fs_or_die($old, $dst);
my $cur = "$old/$dn";
- push @cmds, [@$cmd, $cur, $dst ];
+ push @q, [ $cur, $dst ];
$tmp->{$cur} = $dst;
} elsif ($dn eq '.' || $dn eq '..') {
} elsif ($dn =~ /\Aover\.sqlite3/) {
warn "W: skipping unknown dir: $old/$dn\n"
}
}
- die "No Xapian parts found in $old\n" unless @cmds;
+ die "No Xapian parts found in $old\n" unless @q;
}
my $im = $ibx->importer(0);
- my $max = $opt->{jobs} || scalar(@cmds);
+ my $max = $opt->{jobs} || scalar(@q);
$ibx->with_umask(sub {
$im->lock_acquire;
# fine-grained locking if we prepare for reindex
- if ($reindex) {
+ if (!$opt->{-coarse_lock}) {
prepare_reindex($ibx, $reindex);
$im->lock_release;
}
- delete($ibx->{$_}) for (qw(mm over search)); # cleanup
- my %pids;
- while (@cmds) {
- while (scalar(keys(%pids)) < $max && scalar(@cmds)) {
- my $x = shift @cmds;
- $pids{xspawn($x, $env, $opt)} = $x;
- }
- while (scalar keys %pids) {
- my $pid = waitpid(-1, 0);
- my $x = delete $pids{$pid};
- die join(' ', @$x)." failed: $?\n" if $?;
- }
- }
+ delete($ibx->{$_}) for (qw(mm over search)); # cleanup
+ process_queue(\@q, $cb, $max, $opt);
commit_changes($ibx, $tmp, $opt);
});
}
0;
}
+sub progress_pfx ($) {
+ my @p = split('/', $_[0]);
+
+ # return "xap15/0" for v2, or "xapian15" for v1:
+ ($p[-1] =~ /\A\d+\z/) ? "$p[-2]/$p[-1]" : $p[-1];
+}
+
+# xapian-compact wrapper
+sub compact ($$) {
+ my ($args, $opt) = @_;
+ my ($src, $dst) = @$args;
+ my ($r, $w);
+ my $pfx = $opt->{-progress_pfx} ||= progress_pfx($src);
+ my $pr = $opt->{-progress};
+ my $rdr = {};
+
+ foreach my $fd (0..2) {
+ defined(my $dfd = $opt->{$fd}) or next;
+ $rdr->{$fd} = $dfd;
+ }
+ $rdr->{1} = fileno($w) if $pr && pipe($r, $w);
+
+ # we rely on --no-renumber to keep docids synched to NNTP
+ my $cmd = [ $XAPIAN_COMPACT, '--no-renumber' ];
+ for my $sw (qw(no-full fuller)) {
+ push @$cmd, "--$sw" if $opt->{$sw};
+ }
+ for my $sw (qw(blocksize)) {
+ defined(my $v = $opt->{$sw}) or next;
+ push @$cmd, "--$sw", $v;
+ }
+ $pr->("$pfx `".join(' ', @$cmd)."'\n") if $pr;
+ push @$cmd, $src, $dst;
+ my $pid = spawn($cmd, undef, $rdr);
+ if ($pr) {
+ close $w or die "close: \$w: $!";
+ foreach (<$r>) {
+ s/\r/\r$pfx /g;
+ $pr->("$pfx $_");
+ }
+ }
+ my $rp = waitpid($pid, 0);
+ if ($? || $rp != $pid) {
+ die join(' ', @$cmd)." failed: $? (pid=$pid, reaped=$rp)\n";
+ }
+}
+
# Like copydatabase(1), this is horribly slow; and it doesn't seem due
# to the overhead of Perl.
-sub cpdb {
- my ($args, $env, $opt) = @_;
+sub cpdb ($$) {
+ my ($args, $opt) = @_;
my ($old, $new) = @$args;
my $src = Search::Xapian::Database->new($old);
- my $tmp = $opt->{compact} ? "$new.compact" : $new;
+ my ($xtmp, $tmp);
+ if ($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;
+ } else {
+ $tmp = $new;
+ }
# like copydatabase(1), be sure we don't overwrite anything in case
# of other bugs:
my $creat = Search::Xapian::DB_CREATE();
my $dst = Search::Xapian::WritableDatabase->new($tmp, $creat);
my ($it, $end);
- my $pfx = '';
my ($nr, $tot, $fmt); # progress output
my $pr = $opt->{-progress};
+ my $pfx = $opt->{-progress_pfx} = progress_pfx($old);
do {
eval {
if ($pr) {
$nr = 0;
$tot = $src->get_doccount;
- my @p = split('/', $old);
- $pfx = "$p[-2]/$p[-1]:";
$fmt = "$pfx % ".length($tot)."u/$tot\n";
$pr->("$pfx copying $tot documents\n");
}
} while (cpdb_retryable($src, $pfx));
$pr->(sprintf($fmt, $nr)) if $pr;
- return unless $opt->{compact};
+ return unless $xtmp;
$src = $dst = undef; # flushes and closes
- $pr->("$pfx compacting...\n") if $pr;
# this is probably the best place to do xapian-compact
# since $dst isn't readable by HTTP or NNTP clients, yet:
- my $cmd = [ $XAPIAN_COMPACT, '--no-renumber', $tmp, $new ];
- my $rdr = {};
- foreach my $fd (0..2) {
- defined(my $dst = $opt->{$fd}) or next;
- $rdr->{$fd} = $dst;
- }
-
- my ($r, $w);
- if ($pr && pipe($r, $w)) {
- $rdr->{1} = fileno($w);
- }
- my $pid = spawn($cmd, $env, $rdr);
- if ($pr) {
- close $w or die "close: \$w: $!";
- foreach (<$r>) {
- s/\r/\r$pfx /g;
- $pr->("$pfx $_");
- }
- }
- my $rp = waitpid($pid, 0);
- if ($? || $rp != $pid) {
- die join(' ', @$cmd)." failed: $? (pid=$pid, reaped=$rp)\n";
- }
+ compact([ $tmp, $new ], $opt);
remove_tree($tmp) or die "failed to remove $tmp: $!\n";
+ $xtmp->done;
}
# slightly easier-to-manage manage than END{} blocks
sub done {
my ($self) = @_;
delete $owner{"$self"};
- $SIG{INT} = $SIG{HUP} = $SIG{PIPE} = $SIG{TERM} = 'DEFAULT';
+
+ my %known_pids;
+ $known_pids{$_}++ foreach values %owner;
+ if (!$known_pids{$$}) {
+ $SIG{INT} = $SIG{HUP} = $SIG{PIPE} = $SIG{TERM} = 'DEFAULT';
+ }
%$self = ();
}
foreach my $new (values %$self) {
remove_tree($new) unless -d "$new/old";
}
- $SIG{INT} = $SIG{HUP} = $SIG{PIPE} = $SIG{TERM} = 'DEFAULT';
+ done($self);
}
1;