X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FXapcmd.pm;h=8de516ef5ace4f2c52ca840f52f7fe6ec3979944;hb=af0b0fb7a454470a32c452119d0392e0dedb3fe1;hp=4ee3fc79195d5f59e3ff18b29761dd875675fdf6;hpb=9dd7f90d71ee6d4ba533aee341c9dc44b06fcc6e;p=public-inbox.git

diff --git a/lib/PublicInbox/Xapcmd.pm b/lib/PublicInbox/Xapcmd.pm
index 4ee3fc79..8de516ef 100644
--- a/lib/PublicInbox/Xapcmd.pm
+++ b/lib/PublicInbox/Xapcmd.pm
@@ -1,15 +1,15 @@
-# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2021 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::Spawn qw(which popen_rd nodatacow_dir);
+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);
 
 # support testing with dev versions of Xapian which installs
 # commands with a version number suffix (e.g. "xapian-compact-1.5")
@@ -19,7 +19,6 @@ our @COMPACT_OPT = qw(jobs|j=i quiet|q blocksize|b=s no-full|n fuller|F);
 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;
@@ -38,7 +37,7 @@ sub commit_changes ($$$$) {
 			defined $new or die "BUG: $over exists when culling v2";
 			$over = PublicInbox::Over->new($over);
 			my $tmp_over = "$new/over.sqlite3";
-			$over->connect->sqlite_backup_to_file($tmp_over);
+			$over->dbh->sqlite_backup_to_file($tmp_over);
 			$over = undef;
 			$over_chg = 1;
 		}
@@ -53,7 +52,6 @@ sub commit_changes ($$$$) {
 			rename($old, "$new/old") or
 					die "rename $old => $new/old: $!\n";
 		}
-		# Xtmpdir->DESTROY won't remove $new after this:
 		rename($new, $old) or die "rename $new => $old: $!\n";
 		if (@st) {
 			my $prev = "$old/old";
@@ -83,7 +81,8 @@ sub commit_changes ($$$$) {
 				$im->{shards} = $n;
 			}
 		}
-
+		my $env = $opt->{-idx_env};
+		local %ENV = (%ENV, %$env) if $env;
 		PublicInbox::Admin::index_inbox($ibx, $im, $opt);
 	}
 }
@@ -102,17 +101,16 @@ sub runnable_or_die ($) {
 }
 
 sub prepare_reindex ($$$) {
-	my ($ibx, $im, $reindex) = @_;
+	my ($ibx, $im, $opt) = @_;
 	if ($ibx->version == 1) {
 		my $dir = $ibx->search->xdir(1);
 		my $xdb = $PublicInbox::Search::X{Database}->new($dir);
 		if (my $lc = $xdb->get_metadata('last_commit')) {
-			$reindex->{from} = $lc;
+			$opt->{reindex}->{from} = $lc;
 		}
 	} else { # v2
-		my $max;
-		$im->git_dir_latest(\$max) or return;
-		my $from = $reindex->{from};
+		my $max = $ibx->max_git_epoch // return;
+		my $from = $opt->{reindex}->{from};
 		my $mm = $ibx->mm;
 		my $v = PublicInbox::Search::SCHEMA_VERSION();
 		foreach my $i (0..$max) {
@@ -127,9 +125,14 @@ sub same_fs_or_die ($$) {
 	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);
+	my $max = $opt->{jobs} // scalar(@$queue);
 	if ($max <= 1) {
 		while (defined(my $args = shift @$queue)) {
 			$cb->($args, $opt);
@@ -139,37 +142,38 @@ sub process_queue {
 
 	# run in parallel:
 	my %pids;
+	local %SIG = %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;
+	if (my $srch = $ibx->search) {
+		$old = $srch->xdir(1);
+		-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";
@@ -177,7 +181,7 @@ sub prepare_run {
 
 	# 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 ($old && $ibx->version == 1) {
 		if (defined $reshard) {
 			warn
 "--reshard=$reshard ignored for v1 $ibx->{inboxdir}\n";
@@ -187,8 +191,9 @@ sub prepare_run {
 		my $v = PublicInbox::Search::SCHEMA_VERSION();
 		my $wip = File::Temp->newdir("xapian$v-XXXXXXXX", DIR => $dir);
 		$tmp->{$old} = $wip;
+		nodatacow_dir($wip->dirname);
 		push @queue, [ $old, $wip ];
-	} else {
+	} elsif ($old) {
 		opendir my $dh, $old or die "Failed to opendir $old: $!\n";
 		my @old_shards;
 		while (defined(my $dn = readdir($dh))) {
@@ -217,6 +222,7 @@ sub prepare_run {
 			same_fs_or_die($old, $wip->dirname);
 			my $cur = "$old/$dn";
 			push @queue, [ $src // $cur , $wip ];
+			nodatacow_dir($wip->dirname);
 			$tmp->{$cur} = $wip;
 		}
 		# mark old shards to be unlinked
@@ -230,14 +236,14 @@ sub prepare_run {
 sub check_compact () { runnable_or_die($XAPIAN_COMPACT) }
 
 sub _run {
-	my ($ibx, $cb, $opt, $reindex) = @_;
+	my ($ibx, $cb, $opt) = @_;
 	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, $reindex);
+		prepare_reindex($ibx, $im, $opt);
 		$im->lock_release;
 	}
 
@@ -249,25 +255,22 @@ sub _run {
 
 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, .. ] } }
+	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;
+		# 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;
 	setup_signals();
-	$ibx->umask_prepare;
-	$ibx->with_umask(\&_run, $ibx, $cb, $opt, $reindex);
+	$ibx->with_umask(\&_run, $ibx, $cb, $opt);
 }
 
 sub cpdb_retryable ($$) {
@@ -292,6 +295,11 @@ sub progress_pfx ($) {
 	($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 ($$) {
 	my ($args, $opt) = @_;
@@ -317,14 +325,18 @@ sub compact ($$) {
 	}
 	$pr->("$pfx `".join(' ', @$cmd)."'\n") if $pr;
 	push @$cmd, $src, $dst;
-	my $rd = popen_rd($cmd, undef, $rdr);
+	my ($rd, $pid);
+	local %SIG = %SIG;
+	setup_signals(\&kill_compact, \$pid);
+	($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 ($$$;$$) {
@@ -406,16 +418,18 @@ sub cpdb ($$) {
 		$ft = File::Temp->newdir("$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->{fsync};
+	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;