-# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 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 popen_rd);
+use PublicInbox::Syscall;
+use PublicInbox::Admin qw(setup_signals);
use PublicInbox::Over;
use PublicInbox::SearchIdx;
use File::Temp 0.19 (); # ->newdir
use File::Path qw(remove_tree);
-use File::Basename qw(dirname);
-use POSIX ();
+use POSIX qw(WNOHANG _exit);
# support testing with dev versions of Xapian which installs
# commands with a version number suffix (e.g. "xapian-compact-1.5")
sub commit_changes ($$$$) {
my ($ibx, $im, $tmp, $opt) = @_;
my $reshard = $opt->{reshard};
- my $reindex = $opt->{reindex};
$SIG{INT} or die 'BUG: $SIG{INT} not handled';
- my @old_shard;
- my $over_chg;
-
- while (my ($old, $newdir) = each %$tmp) {
+ my (@old_shard, $over_chg);
+
+ # Sort shards highest-to-lowest, since ->xdb_shards_flat
+ # determines the number of shards to load based on the max;
+ # and we'd rather xdb_shards_flat to momentarily fail rather
+ # than load out-of-date shards
+ my @order = sort {
+ my ($x) = ($a =~ m!/([0-9]+)/*\z!);
+ my ($y) = ($b =~ m!/([0-9]+)/*\z!);
+ ($y // -1) <=> ($x // -1) # we may have non-shards
+ } keys %$tmp;
+
+ my ($dname) = ($order[0] =~ m!(.*/)[^/]+/*\z!);
+ my $mode = (stat($dname))[2];
+ for my $old (@order) {
next if $old eq ''; # no invalid paths
- my @st = stat($old);
- if (!@st && !defined($opt->{reshard})) {
+ my $newdir = $tmp->{$old};
+ my $have_old = -e $old;
+ if (!$have_old && !defined($opt->{reshard})) {
die "failed to stat($old): $!";
}
defined $new or die "BUG: $over exists when culling v2";
$over = PublicInbox::Over->new($over);
my $tmp_over = "$new/over.sqlite3";
- $over->connect->sqlite_backup_to_file($tmp_over);
+ $over->dbh->sqlite_backup_to_file($tmp_over);
$over = undef;
$over_chg = 1;
}
next;
}
- if (@st) {
- chmod($st[2] & 07777, $new) or die "chmod $old: $!\n";
+ chmod($mode & 07777, $new) or die "chmod($new): $!\n";
+ if ($have_old) {
rename($old, "$new/old") or
die "rename $old => $new/old: $!\n";
}
- # Xtmpdir->DESTROY won't remove $new after this:
rename($new, $old) or die "rename $new => $old: $!\n";
- if (@st) {
- my $prev = "$old/old";
- remove_tree($prev) or
- die "failed to remove $prev: $!\n";
- }
+ push @old_shard, "$old/old" if $have_old;
}
# trigger ->check_inodes in read-only daemons
- syswrite($im->{lockfh}, '.') if $over_chg;
+ syswrite($im->{lockfh}, '.') if $over_chg && $im;
remove_tree(@old_shard);
$tmp = undef;
if (!$opt->{-coarse_lock}) {
$opt->{-skip_lock} = 1;
-
- if ($im->can('count_shards')) {
+ $im //= $ibx if $ibx->can('eidx_sync');
+ if ($im->can('count_shards')) { # v2w or eidx
my $pr = $opt->{-progress};
my $n = $im->count_shards;
if (defined $reshard && $n != $reshard) {
$im->{shards} = $n;
}
}
-
- PublicInbox::Admin::index_inbox($ibx, $im, $opt);
+ my $env = $opt->{-idx_env};
+ local %ENV = (%ENV, %$env) if $env;
+ if ($ibx->can('eidx_sync')) {
+ $ibx->eidx_sync($opt);
+ } else {
+ PublicInbox::Admin::index_inbox($ibx, $im, $opt);
+ }
}
}
sub cb_spawn {
my ($cb, $args, $opt) = @_; # $cb = cpdb() or compact()
- defined(my $pid = fork) or die "fork: $!";
+ my $seed = rand(0xffffffff);
+ my $pid = fork // die "fork: $!";
return $pid if $pid > 0;
+ srand($seed);
+ $SIG{__DIE__} = sub { warn @_; _exit(1) }; # don't jump up stack
$cb->($args, $opt);
- POSIX::_exit(0);
+ _exit(0);
}
sub runnable_or_die ($) {
which($exe) or die "$exe not found in PATH\n";
}
-sub prepare_reindex ($$$) {
- my ($ibx, $im, $reindex) = @_;
- if ($ibx->version == 1) {
+sub prepare_reindex ($$) {
+ my ($ibx, $opt) = @_;
+ if ($ibx->can('eidx_sync')) { # no prep needed for ExtSearchIdx
+ } elsif ($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')) {
- $reindex->{from} = $lc;
+ $opt->{reindex}->{from} = $lc;
}
} else { # v2
- my $max;
- $im->git_dir_latest(\$max) or return;
- my $from = $reindex->{from};
+ my $max = $ibx->max_git_epoch // return;
+ my $from = $opt->{reindex}->{from};
my $mm = $ibx->mm;
my $v = PublicInbox::Search::SCHEMA_VERSION();
foreach my $i (0..$max) {
die "$x and $y reside on different filesystems\n";
}
+sub kill_pids {
+ my ($sig, $pids) = @_;
+ kill($sig, keys %$pids); # pids may be empty
+}
+
sub process_queue {
my ($queue, $cb, $opt) = @_;
my $max = $opt->{jobs} // scalar(@$queue);
# run in parallel:
my %pids;
+ local @SIG{keys %SIG} = values %SIG;
+ setup_signals(\&kill_pids, \%pids);
while (@$queue) {
while (scalar(keys(%pids)) < $max && scalar(@$queue)) {
my $args = shift @$queue;
$pids{cb_spawn($cb, $args, $opt)} = $args;
}
+ my $flags = 0;
while (scalar keys %pids) {
- my $pid = waitpid(-1, 0);
+ my $pid = waitpid(-1, $flags) or last;
+ last if $pid < 0;
my $args = delete $pids{$pid};
if ($args) {
die join(' ', @$args)." failed: $?\n" if $?;
} else {
warn "unknown PID($pid) reaped: $?\n";
}
+ $flags = WNOHANG if scalar(@$queue);
}
}
}
-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 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 = $ibx->search->xdir(1);
- -d $old or die "$old does not exist\n";
+ my ($old, $misc_ok);
+ if ($ibx->can('eidx_sync')) {
+ $misc_ok = 1;
+ $old = $ibx->xdir(1);
+ } elsif (my $srch = $ibx->search) {
+ $old = $srch->xdir(1);
+ }
+ if (defined $old) {
+ -d $old or die "$old does not exist\n";
+ }
my $reshard = $opt->{reshard};
if (defined $reshard && $reshard <= 0) {
die "--reshard must be a positive number\n";
# we want temporary directories to be as deep as possible,
# so v2 shards can keep "xap$SCHEMA_VERSION" on a separate FS.
- if ($ibx->version == 1) {
+ if (defined($old) && $ibx->can('version') && $ibx->version == 1) {
if (defined $reshard) {
warn
"--reshard=$reshard ignored for v1 $ibx->{inboxdir}\n";
}
- my $dir = dirname($old);
+ my ($dir) = ($old =~ m!(.*?/)[^/]+/*\z!);
same_fs_or_die($dir, $old);
my $v = PublicInbox::Search::SCHEMA_VERSION();
- my $wip = File::Temp->newdir("xapian$v-XXXXXXXX", DIR => $dir);
+ my $wip = File::Temp->newdir("xapian$v-XXXX", DIR => $dir);
$tmp->{$old} = $wip;
+ PublicInbox::Syscall::nodatacow_dir($wip->dirname);
push @queue, [ $old, $wip ];
- } else {
+ } elsif (defined $old) {
opendir my $dh, $old or die "Failed to opendir $old: $!\n";
my @old_shards;
while (defined(my $dn = readdir($dh))) {
push @old_shards, $dn;
} elsif ($dn eq '.' || $dn eq '..') {
} elsif ($dn =~ /\Aover\.sqlite3/) {
+ } elsif ($dn eq 'misc' && $misc_ok) {
} else {
warn "W: skipping unknown dir: $old/$dn\n"
}
$src = [ map { "$old/$_" } @old_shards ];
}
foreach my $dn (0..$max_shard) {
- my $tmpl = "$dn-XXXXXXXX";
- my $wip = File::Temp->newdir($tmpl, DIR => $old);
+ my $wip = File::Temp->newdir("$dn-XXXX", DIR => $old);
same_fs_or_die($old, $wip->dirname);
my $cur = "$old/$dn";
push @queue, [ $src // $cur , $wip ];
+ PublicInbox::Syscall::nodatacow_dir($wip->dirname);
$tmp->{$cur} = $wip;
}
# mark old shards to be unlinked
sub check_compact () { runnable_or_die($XAPIAN_COMPACT) }
-sub _run {
- my ($ibx, $cb, $opt, $reindex) = @_;
- my $im = $ibx->importer(0);
- $im->lock_acquire;
+sub _run { # with_umask callback
+ my ($ibx, $cb, $opt) = @_;
+ my $im = $ibx->can('importer') ? $ibx->importer(0) : undef;
+ ($im // $ibx)->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;
+ prepare_reindex($ibx, $opt);
+ ($im // $ibx)->lock_release;
}
- $ibx->cleanup;
+ $ibx->cleanup if $ibx->can('cleanup');
process_queue($queue, $cb, $opt);
- $im->lock_acquire if !$opt->{-coarse_lock};
+ ($im // $ibx)->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"};
+ my $cb = \&$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};
- my $reindex; # v1:{ from => $x40 }, v2:{ from => [ $x40, $x40, .. ] } }
+ my $dir;
+ for my $fld (qw(inboxdir topdir)) {
+ my $d = $ibx->{$fld} // next;
+ -d $d or die "$fld=$d does not exist\n";
+ $dir = $d;
+ last;
+ }
+ check_compact() if $opt->{compact} && $ibx->search;
- if (!$opt->{-coarse_lock}) {
- $reindex = $opt->{reindex} = { # per-epoch ranges for v2
- from => $ibx->version == 1 ? '' : [],
- };
- require PublicInbox::SearchIdx;
+ if (!$ibx->can('eidx_sync') && !$opt->{-coarse_lock}) {
+ # per-epoch ranges for v2
+ # v1:{ from => $OID }, v2:{ from => [ $OID, $OID, $OID ] } }
+ $opt->{reindex} = { from => $ibx->version == 1 ? '' : [] };
PublicInbox::SearchIdx::load_xapian_writable();
}
- local %SIG = %SIG;
+ local @SIG{keys %SIG} = values %SIG;
setup_signals();
- $ibx->umask_prepare;
- $ibx->with_umask(\&_run, $ibx, $cb, $opt, $reindex);
+ $ibx->with_umask(\&_run, $ibx, $cb, $opt);
}
sub cpdb_retryable ($$) {
}
sub progress_pfx ($) {
- my ($wip) = @_; # tempdir v2: ([0-9])+-XXXXXXXX
+ my ($wip) = @_; # tempdir v2: ([0-9])+-XXXX
my @p = split('/', $wip);
# return "xap15/0" for v2, or "xapian15" for v1:
($p[-1] =~ /\A([0-9]+)/) ? "$p[-2]/$1" : $p[-1];
}
+sub kill_compact { # setup_signals callback
+ my ($sig, $pidref) = @_;
+ kill($sig, $$pidref) if defined($$pidref);
+}
+
# xapian-compact wrapper
-sub compact ($$) {
+sub compact ($$) { # cb_spawn callback
my ($args, $opt) = @_;
my ($src, $newdir) = @$args;
my $dst = ref($newdir) ? $newdir->dirname : $newdir;
}
$pr->("$pfx `".join(' ', @$cmd)."'\n") if $pr;
push @$cmd, $src, $dst;
- my $rd = popen_rd($cmd, undef, $rdr);
+ my ($rd, $pid);
+ local @SIG{keys %SIG} = values %SIG;
+ setup_signals(\&kill_compact, \$pid);
+ ($rd, $pid) = popen_rd($cmd, undef, $rdr);
while (<$rd>) {
if ($pr) {
s/\r/\r$pfx /g;
$pr->("$pfx $_");
}
}
- close $rd or die join(' ', @$cmd)." failed: $?n";
+ waitpid($pid, 0);
+ die "@$cmd failed: \$?=$?\n" if $?;
}
sub cpdb_loop ($$$;$$) {
# Like copydatabase(1), this is horribly slow; and it doesn't seem due
# to the overhead of Perl.
-sub cpdb ($$) {
+sub cpdb ($$) { # cb_spawn callback
my ($args, $opt) = @_;
my ($old, $newdir) = @$args;
my $new = $newdir->dirname;
my ($src, $cur_shard);
my $reshard;
- PublicInbox::SearchIdx::load_xapian_writable() or die;
+ PublicInbox::SearchIdx::load_xapian_writable();
my $XapianDatabase = $PublicInbox::Search::X{Database};
if (ref($old) eq 'ARRAY') {
- ($cur_shard) = ($new =~ m!xap[0-9]+/([0-9]+)\b!);
+ ($cur_shard) = ($new =~ m!(?:xap|ei)[0-9]+/([0-9]+)\b!);
defined $cur_shard or
die "BUG: could not extract shard # from $new";
$reshard = $opt->{reshard};
}
my ($tmp, $ft);
- local %SIG = %SIG;
+ local @SIG{keys %SIG} = values %SIG;
if ($opt->{compact}) {
- my $dir = dirname($new);
+ my ($dir) = ($new =~ m!(.*?/)[^/]+/*\z!);
same_fs_or_die($dir, $new);
- $ft = File::Temp->newdir("$new.compact-XXXXXX", DIR => $dir);
+ $ft = File::Temp->newdir("$new.compact-XXXX", DIR => $dir);
setup_signals();
$tmp = $ft->dirname;
+ PublicInbox::Syscall::nodatacow_dir($tmp);
} else {
$tmp = $new;
}
my $flag = eval($PublicInbox::Search::Xap.'::DB_CREATE()');
die if $@;
my $XapianWritableDatabase = $PublicInbox::Search::X{WritableDatabase};
- $flag |= $PublicInbox::SearchIdx::DB_NO_SYNC if !$opt->{sync};
+ $flag |= $PublicInbox::SearchIdx::DB_NO_SYNC if !$opt->{fsync};
my $dst = $XapianWritableDatabase->new($tmp, $flag);
my $pr = $opt->{-progress};
my $pfx = $opt->{-progress_pfx} = progress_pfx($new);