-# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
package PublicInbox::Xapcmd;
use strict;
use warnings;
-use PublicInbox::Spawn qw(which spawn);
+use PublicInbox::Spawn qw(which popen_rd);
use PublicInbox::Over;
-use PublicInbox::SearchIdx;
-use File::Temp ();
+use PublicInbox::SearchIdx qw(nodatacow_dir);
+use File::Temp 0.19 (); # ->newdir
use File::Path qw(remove_tree);
use File::Basename qw(dirname);
use POSIX ();
$SIG{INT} or die 'BUG: $SIG{INT} not handled';
my @old_shard;
+ my $over_chg;
while (my ($old, $newdir) = each %$tmp) {
next if $old eq ''; # no invalid paths
my $tmp_over = "$new/over.sqlite3";
$over->connect->sqlite_backup_to_file($tmp_over);
$over = undef;
+ $over_chg = 1;
}
if (!defined($new)) { # culled shard
die "failed to remove $prev: $!\n";
}
}
+
+ # trigger ->check_inodes in read-only daemons
+ syswrite($im->{lockfh}, '.') if $over_chg;
+
remove_tree(@old_shard);
$tmp = undef;
if (!$opt->{-coarse_lock}) {
sub prepare_reindex ($$$) {
my ($ibx, $im, $reindex) = @_;
- if ($ibx->{version} == 1) {
+ if ($ibx->version == 1) {
my $dir = $ibx->search->xdir(1);
my $xdb = $PublicInbox::Search::X{Database}->new($dir);
if (my $lc = $xdb->get_metadata('last_commit')) {
}
sub process_queue {
- my ($queue, $cb, $max, $opt) = @_;
+ my ($queue, $cb, $opt) = @_;
+ my $max = $opt->{jobs} // scalar(@$queue);
if ($max <= 1) {
while (defined(my $args = shift @$queue)) {
$cb->($args, $opt);
while (scalar keys %pids) {
my $pid = waitpid(-1, 0);
my $args = delete $pids{$pid};
- die join(' ', @$args)." failed: $?\n" if $?;
+ if ($args) {
+ die join(' ', @$args)." failed: $?\n" if $?;
+ } else {
+ warn "unknown PID($pid) reaped: $?\n";
+ }
}
}
}
$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->{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
-
- if (!$opt->{-coarse_lock}) {
- $reindex = $opt->{reindex} = {};
- $from = $reindex->{from} = [];
- require PublicInbox::SearchIdx;
- PublicInbox::SearchIdx::load_xapian_writable();
+sub prepare_run {
+ my ($ibx, $opt) = @_;
+ my $tmp = {}; # old shard dir => File::Temp->newdir object or undef
+ my @queue; # ([old//src,newdir]) - list of args for cpdb() or compact()
+ my $old;
+ if (my $srch = $ibx->search) {
+ $old = $srch->xdir(1);
+ -d $old or die "$old does not exist\n";
}
-
- $ibx->umask_prepare;
- my $old = $ibx->search->xdir(1);
- -d $old or die "$old does not exist\n";
-
- my $tmp = {};
- my $v = $ibx->{version} ||= 1;
- my @q;
my $reshard = $opt->{reshard};
if (defined $reshard && $reshard <= 0) {
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 ($old && $ibx->version == 1) {
if (defined $reshard) {
warn
"--reshard=$reshard ignored for v1 $ibx->{inboxdir}\n";
my $v = PublicInbox::Search::SCHEMA_VERSION();
my $wip = File::Temp->newdir("xapian$v-XXXXXXXX", DIR => $dir);
$tmp->{$old} = $wip;
- push @q, [ $old, $wip ];
- } else {
+ nodatacow_dir($wip->dirname);
+ push @queue, [ $old, $wip ];
+ } elsif ($old) {
opendir my $dh, $old or die "Failed to opendir $old: $!\n";
my @old_shards;
while (defined(my $dn = readdir($dh))) {
my $wip = File::Temp->newdir($tmpl, DIR => $old);
same_fs_or_die($old, $wip->dirname);
my $cur = "$old/$dn";
- push @q, [ $src // $cur , $wip ];
+ push @queue, [ $src // $cur , $wip ];
+ nodatacow_dir($wip->dirname);
$tmp->{$cur} = $wip;
}
# mark old shards to be unlinked
$tmp->{$_} ||= undef for @$src;
}
}
- 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, $im, $reindex);
- $im->lock_release;
- }
+ ($tmp, \@queue);
+}
+
+sub check_compact () { runnable_or_die($XAPIAN_COMPACT) }
- $ibx->cleanup;
- process_queue(\@q, $cb, $max, $opt);
- $im->lock_acquire if !$opt->{-coarse_lock};
- commit_changes($ibx, $im, $tmp, $opt);
- });
+sub _run {
+ my ($ibx, $cb, $opt, $reindex) = @_;
+ my $im = $ibx->importer(0);
+ $im->lock_acquire;
+ my ($tmp, $queue) = prepare_run($ibx, $opt);
+
+ # fine-grained locking if we prepare for reindex
+ if (!$opt->{-coarse_lock}) {
+ prepare_reindex($ibx, $im, $reindex);
+ $im->lock_release;
+ }
+
+ $ibx->cleanup;
+ process_queue($queue, $cb, $opt);
+ $im->lock_acquire if !$opt->{-coarse_lock};
+ commit_changes($ibx, $im, $tmp, $opt);
+}
+
+sub run {
+ my ($ibx, $task, $opt) = @_; # task = 'cpdb' or 'compact'
+ my $cb = \&${\"PublicInbox::Xapcmd::$task"};
+ PublicInbox::Admin::progress_prepare($opt ||= {});
+ defined(my $dir = $ibx->{inboxdir}) or die "no inboxdir defined\n";
+ -d $dir or die "inboxdir=$dir does not exist\n";
+ check_compact() if $opt->{compact} && $ibx->search;
+ my $reindex; # v1:{ from => $x40 }, v2:{ from => [ $x40, $x40, .. ] } }
+
+ if (!$opt->{-coarse_lock}) {
+ $reindex = $opt->{reindex} = { # per-epoch ranges for v2
+ from => $ibx->version == 1 ? '' : [],
+ };
+ PublicInbox::SearchIdx::load_xapian_writable();
+ }
+
+ local %SIG = %SIG;
+ setup_signals();
+ $ibx->umask_prepare;
+ $ibx->with_umask(\&_run, $ibx, $cb, $opt, $reindex);
}
sub cpdb_retryable ($$) {
my ($args, $opt) = @_;
my ($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};
my $rdr = {};
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' ];
}
$pr->("$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>) {
+ my $rd = popen_rd($cmd, undef, $rdr);
+ while (<$rd>) {
+ if ($pr) {
s/\r/\r$pfx /g;
$pr->("$pfx $_");
}
}
- my $rp = waitpid($pid, 0);
- if ($? || $rp != $pid) {
- die join(' ', @$cmd)." failed: $? (pid=$pid, reaped=$rp)\n";
- }
+ close $rd or die join(' ', @$cmd)." failed: $?n";
}
sub cpdb_loop ($$$;$$) {
$ft = File::Temp->newdir("$new.compact-XXXXXX", DIR => $dir);
setup_signals();
$tmp = $ft->dirname;
+ nodatacow_dir($tmp);
} else {
$tmp = $new;
}
# like copydatabase(1), be sure we don't overwrite anything in case
# of other bugs:
- my $creat = eval($PublicInbox::Search::Xap.'::DB_CREATE()');
+ my $flag = eval($PublicInbox::Search::Xap.'::DB_CREATE()');
die if $@;
my $XapianWritableDatabase = $PublicInbox::Search::X{WritableDatabase};
- my $dst = $XapianWritableDatabase->new($tmp, $creat);
+ $flag |= $PublicInbox::SearchIdx::DB_NO_SYNC if !$opt->{sync};
+ my $dst = $XapianWritableDatabase->new($tmp, $flag);
my $pr = $opt->{-progress};
my $pfx = $opt->{-progress_pfx} = progress_pfx($new);
my $pr_data = { pr => $pr, pfx => $pfx, nr => 0 } if $pr;