X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=PVE%2FQemuMigrate.pm;h=36f6fda54bfdadfa4baf267fc056da31612192e8;hb=d652f7b1ab64bef3972b70d4ae14e1e05e07db5e;hp=5da62eb53db6682b13ba9f1a95a3f81cc2e55f52;hpb=386c6ba7f5dc7de2a6e48d0520cda72f4b2a8bf3;p=qemu-server.git

diff --git a/PVE/QemuMigrate.pm b/PVE/QemuMigrate.pm
index 5da62eb..36f6fda 100644
--- a/PVE/QemuMigrate.pm
+++ b/PVE/QemuMigrate.pm
@@ -5,6 +5,7 @@ use warnings;
 use PVE::AbstractMigrate;
 use IO::File;
 use IPC::Open2;
+use POSIX qw( WNOHANG );
 use PVE::INotify;
 use PVE::Tools;
 use PVE::Cluster;
@@ -12,6 +13,9 @@ use PVE::Storage;
 use PVE::QemuServer;
 use Time::HiRes qw( usleep );
 use PVE::RPCEnvironment;
+use PVE::ReplicationConfig;
+use PVE::ReplicationState;
+use JSON;
 
 use base qw(PVE::AbstractMigrate);
 
@@ -44,17 +48,28 @@ sub fork_command_pipe {
 sub finish_command_pipe {
     my ($self, $cmdpipe, $timeout) = @_;
 
+    my $cpid = $cmdpipe->{pid};
+    return if !defined($cpid);
+
     my $writer = $cmdpipe->{writer};
     my $reader = $cmdpipe->{reader};
 
     $writer->close();
     $reader->close();
 
-    my $cpid = $cmdpipe->{pid};
+    my $collect_child_process = sub {
+	my $res = waitpid($cpid, WNOHANG);
+	if (defined($res) && ($res == $cpid)) {
+	    delete $cmdpipe->{cpid};
+	    return 1;
+	} else {
+	    return 0;
+	}
+     };
 
     if ($timeout) {
 	for (my $i = 0; $i < $timeout; $i++) {
-	    return if !PVE::ProcFSTools::check_process_running($cpid);
+	    return if &$collect_child_process();
 	    sleep(1);
 	}
     }
@@ -64,21 +79,24 @@ sub finish_command_pipe {
 
     # wait again
     for (my $i = 0; $i < 10; $i++) {
-	return if !PVE::ProcFSTools::check_process_running($cpid);
+	return if &$collect_child_process();
 	sleep(1);
     }
 
     $self->log('info', "ssh tunnel still running - terminating now with SIGKILL\n");
     kill 9, $cpid;
     sleep 1;
+
+    $self->log('err', "ssh tunnel child process (PID $cpid) couldn't be collected\n")
+	if !&$collect_child_process();
 }
 
 sub fork_tunnel {
-    my ($self, $nodeip, $lport, $rport) = @_;
+    my ($self, $tunnel_addr) = @_;
 
-    my @localtunnelinfo = $lport ? ('-L' , "$lport:localhost:$rport" ) : ();
+    my @localtunnelinfo = defined($tunnel_addr) ? ('-L' , $tunnel_addr ) : ();
 
-    my $cmd = [@{$self->{rem_ssh}}, @localtunnelinfo, 'qm', 'mtunnel' ];
+    my $cmd = [@{$self->{rem_ssh}}, '-o ExitOnForwardFailure=yes', @localtunnelinfo, 'qm', 'mtunnel' ];
 
     my $tunnel = $self->fork_command_pipe($cmd);
 
@@ -116,13 +134,23 @@ sub finish_tunnel {
 
     $self->finish_command_pipe($tunnel, 30);
 
+    if ($tunnel->{sock_addr}) {
+	# ssh does not clean up on local host
+	my $cmd = ['rm', '-f', $tunnel->{sock_addr}]; #
+	PVE::Tools::run_command($cmd);
+
+	# .. and just to be sure check on remote side
+	unshift @{$cmd}, @{$self->{rem_ssh}};
+	PVE::Tools::run_command($cmd);
+    }
+
     die $err if $err;
 }
 
 sub lock_vm {
     my ($self, $vmid, $code, @param) = @_;
 
-    return PVE::QemuServer::lock_config($vmid, $code, @param);
+    return PVE::QemuConfig->lock_config($vmid, $code, @param);
 }
 
 sub prepare {
@@ -132,14 +160,14 @@ sub prepare {
 
     $self->{storecfg} = PVE::Storage::config();
 
-    # test is VM exist
-    my $conf = $self->{vmconf} = PVE::QemuServer::load_config($vmid);
+    # test if VM exists
+    my $conf = $self->{vmconf} = PVE::QemuConfig->load_config($vmid);
 
-    PVE::QemuServer::check_lock($conf);
+    PVE::QemuConfig->check_lock($conf);
 
     my $running = 0;
     if (my $pid = PVE::QemuServer::check_running($vmid)) {
-	die "cant migrate running VM without --online\n" if !$online;
+	die "can't migrate running VM without --online\n" if !$online;
 	$running = $pid;
 
 	$self->{forcemachine} = PVE::QemuServer::qemu_machine_pxe($vmid, $conf);
@@ -154,11 +182,31 @@ sub prepare {
 	}
     }
 
-    # activate volumes
     my $vollist = PVE::QemuServer::get_vm_volumes($conf);
-    PVE::Storage::activate_volumes($self->{storecfg}, $vollist);
 
-    # fixme: check if storage is available on both nodes
+    my $need_activate = [];
+    foreach my $volid (@$vollist) {
+	my ($sid, $volname) = PVE::Storage::parse_volume_id($volid, 1);
+
+	# check if storage is available on both nodes
+	my $targetsid = $self->{opts}->{targetstorage} ? $self->{opts}->{targetstorage} : $sid;
+
+	my $scfg = PVE::Storage::storage_check_node($self->{storecfg}, $sid);
+	PVE::Storage::storage_check_node($self->{storecfg}, $targetsid, $self->{node});
+
+	if ($scfg->{shared}) {
+	    # PVE::Storage::activate_storage checks this for non-shared storages
+	    my $plugin = PVE::Storage::Plugin->lookup($scfg->{type});
+	    warn "Used shared storage '$sid' is not online on source node!\n"
+		if !$plugin->check_connection($sid, $scfg);
+	} else {
+	    # only activate if not shared
+	    push @$need_activate, $volid;
+	}
+    }
+
+    # activate volumes
+    PVE::Storage::activate_volumes($self->{storecfg}, $need_activate);
 
     # test ssh connection
     my $cmd = [ @{$self->{rem_ssh}}, '/bin/true' ];
@@ -171,103 +219,218 @@ sub prepare {
 sub sync_disks {
     my ($self, $vmid) = @_;
 
-    $self->log('info', "copying disk images");
-
     my $conf = $self->{vmconf};
 
+    # local volumes which have been copied
     $self->{volumes} = [];
 
     my $res = [];
 
     eval {
 
-	my $volhash = {};
-	my $cdromhash = {};
+	# found local volumes and their origin
+	my $local_volumes = {};
+	my $local_volumes_errors = {};
+	my $other_errors = [];
+	my $abort = 0;
 
 	my $sharedvm = 1;
 
+	my $log_error = sub {
+	    my ($msg, $volid) = @_;
+
+	    if (defined($volid)) {
+		$local_volumes_errors->{$volid} = $msg;
+	    } else {
+		push @$other_errors, $msg;
+	    }
+	    $abort = 1;
+	};
+
 	my @sids = PVE::Storage::storage_ids($self->{storecfg});
-        foreach my $storeid (@sids) {
+	foreach my $storeid (@sids) {
 	    my $scfg = PVE::Storage::storage_config($self->{storecfg}, $storeid);
-            next if $scfg->{shared};
+	    next if $scfg->{shared};
 	    next if !PVE::Storage::storage_check_enabled($self->{storecfg}, $storeid, undef, 1);
 
-            # get list from PVE::Storage (for unused volumes)
-            my $dl = PVE::Storage::vdisk_list($self->{storecfg}, $storeid, $vmid);
-            PVE::Storage::foreach_volid($dl, sub {
-                my ($volid, $sid, $volname) = @_;
+	    # get list from PVE::Storage (for unused volumes)
+	    my $dl = PVE::Storage::vdisk_list($self->{storecfg}, $storeid, $vmid);
 
-                # check if storage is available on target node
-                PVE::Storage::storage_check_node($self->{storecfg}, $sid, $self->{node});
+	    next if @{$dl->{$storeid}} == 0;
 
-                $volhash->{$volid} = 1;
-		$sharedvm = 0; # there is a non-shared disk
-            });
-        }
+	    my $targetsid = $self->{opts}->{targetstorage} ? $self->{opts}->{targetstorage} : $storeid;
 
-	# and add used, owned/non-shared disks (just to be sure we have all)
+	    # check if storage is available on target node
+	    PVE::Storage::storage_check_node($self->{storecfg}, $targetsid, $self->{node});
+	    $sharedvm = 0; # there is a non-shared disk
 
-	PVE::QemuServer::foreach_volid($conf, sub {
-	    my ($volid, $is_cdrom) = @_;
+	    PVE::Storage::foreach_volid($dl, sub {
+		my ($volid, $sid, $volname) = @_;
+
+		$local_volumes->{$volid} = 'storage';
+	    });
+	}
 
-	    return if !$volid;
+	my $test_volid = sub {
+	    my ($volid, $attr) = @_;
 
-	    die "cant migrate local file/device '$volid'\n" if $volid =~ m|^/|;
+	    if ($volid =~ m|^/|) {
+		$local_volumes->{$volid} = 'config';
+		die "local file/device\n";
+	    }
 
-	    if ($is_cdrom) {
-		die "cant migrate local cdrom drive\n" if $volid eq 'cdrom';
+	    my $snaprefs = $attr->{referenced_in_snapshot};
+
+	    if ($attr->{cdrom}) {
+		if ($volid eq 'cdrom') {
+		    my $msg = "can't migrate local cdrom drive";
+		    if (defined($snaprefs) && !$attr->{referenced_in_config}) {
+			my $snapnames = join(', ', sort keys %$snaprefs);
+			$msg .= " (referenced in snapshot - $snapnames)";
+		    }
+		    &$log_error("$msg\n");
+		    return;
+		}
 		return if $volid eq 'none';
-		$cdromhash->{$volid} = 1;
 	    }
 
 	    my ($sid, $volname) = PVE::Storage::parse_volume_id($volid);
 
+	    my $targetsid = $self->{opts}->{targetstorage} ? $self->{opts}->{targetstorage} : $sid;
 	    # check if storage is available on both nodes
 	    my $scfg = PVE::Storage::storage_check_node($self->{storecfg}, $sid);
-	    PVE::Storage::storage_check_node($self->{storecfg}, $sid, $self->{node});
+	    PVE::Storage::storage_check_node($self->{storecfg}, $targetsid, $self->{node});
 
 	    return if $scfg->{shared};
 
-	    die "can't migrate local cdrom '$volid'\n" if $cdromhash->{$volid};
-
 	    $sharedvm = 0;
 
+	    $local_volumes->{$volid} = $attr->{referenced_in_config} ? 'config' : 'snapshot';
+
+	    die "local cdrom image\n" if $attr->{cdrom};
+
 	    my ($path, $owner) = PVE::Storage::path($self->{storecfg}, $volid);
 
-	    die "can't migrate volume '$volid' - owned by other VM (owner = VM $owner)\n"
+	    die "owned by other VM (owner = VM $owner)\n"
 		if !$owner || ($owner != $self->{vmid});
 
-	    $volhash->{$volid} = 1;
-	});
+	    if (defined($snaprefs)) {
+		# we cannot migrate shapshots on local storage
+		# exceptions: 'zfspool' or 'qcow2' files (on directory storage)
+
+		my $format = PVE::QemuServer::qemu_img_format($scfg, $volname);
+		die "online storage migration not possible if snapshot exists\n" if $self->{running};
+		if (!($scfg->{type} eq 'zfspool' || $format eq 'qcow2')) {
+		    die "non-migratable snapshot exists\n";
+		}
+	    }
+
+	    die "referenced by linked clone(s)\n"
+		if PVE::Storage::volume_is_base_and_used($self->{storecfg}, $volid);
+	};
+
+	PVE::QemuServer::foreach_volid($conf, sub {
+	    my ($volid, $attr) = @_;
+	    eval { $test_volid->($volid, $attr); };
+	    if (my $err = $@) {
+		&$log_error($err, $volid);
+	    }
+        });
+
+	foreach my $vol (sort keys %$local_volumes) {
+	    if ($local_volumes->{$vol} eq 'storage') {
+		$self->log('info', "found local disk '$vol' (via storage)\n");
+	    } elsif ($local_volumes->{$vol} eq 'config') {
+		&$log_error("can't live migrate attached local disks without with-local-disks option\n", $vol)
+		    if $self->{running} && !$self->{opts}->{"with-local-disks"};
+		$self->log('info', "found local disk '$vol' (in current VM config)\n");
+	    } elsif ($local_volumes->{$vol} eq 'snapshot') {
+		$self->log('info', "found local disk '$vol' (referenced by snapshot(s))\n");
+	    } else {
+		$self->log('info', "found local disk '$vol'\n");
+	    }
+	}
+
+	foreach my $vol (sort keys %$local_volumes_errors) {
+	    $self->log('warn', "can't migrate local disk '$vol': $local_volumes_errors->{$vol}");
+	}
+	foreach my $err (@$other_errors) {
+	    $self->log('warn', "$err");
+	}
+
+	if ($self->{running} && !$sharedvm && !$self->{opts}->{targetstorage}) {
+	    $self->{opts}->{targetstorage} = 1; #use same sid for remote local
+	}
 
-	if ($self->{running} && !$sharedvm) {
-	    die "can't do online migration - VM uses local disks\n";
+	if ($abort) {
+	    die "can't migrate VM - check log\n";
 	}
 
-	# do some checks first
-	foreach my $volid (keys %$volhash) {
+	# additional checks for local storage
+	foreach my $volid (keys %$local_volumes) {
 	    my ($sid, $volname) = PVE::Storage::parse_volume_id($volid);
 	    my $scfg =  PVE::Storage::storage_config($self->{storecfg}, $sid);
 
+	    my $migratable = ($scfg->{type} eq 'dir') || ($scfg->{type} eq 'zfspool') ||
+		($scfg->{type} eq 'lvmthin') || ($scfg->{type} eq 'lvm');
+
 	    die "can't migrate '$volid' - storage type '$scfg->{type}' not supported\n"
-		if (!($scfg->{type} eq 'dir' || $scfg->{type} eq 'zfspool') && (!$sharedvm));
+		if !$migratable;
 
-	    # if file, check if a backing file exist
-	    if (!($scfg->{type} eq 'dir' || $scfg->{type} eq 'zfspool') && (!$sharedvm)) {
-		my (undef, undef, undef, $parent) = PVE::Storage::volume_size_info($self->{storecfg}, $volid, 1);
-		die "can't migrate '$volid' as it's a clone of '$parent'" if $parent;
+	    # image is a linked clone on local storage, se we can't migrate.
+	    if (my $basename = (PVE::Storage::parse_volname($self->{storecfg}, $volid))[3]) {
+		die "can't migrate '$volid' as it's a clone of '$basename'";
 	    }
 	}
 
-	foreach my $volid (keys %$volhash) {
+	my $rep_volumes;
+
+	$self->log('info', "copying disk images");
+
+	my $rep_cfg = PVE::ReplicationConfig->new();
+
+	if (my $jobcfg = $rep_cfg->find_local_replication_job($vmid, $self->{node})) {
+	    die "can't live migrate VM with replicated volumes\n" if $self->{running};
+	    my $start_time = time();
+	    my $logfunc = sub { my ($msg) = @_;  $self->log('info', $msg); };
+	    $rep_volumes = PVE::Replication::run_replication(
+	       'PVE::QemuConfig', $jobcfg, $start_time, $start_time, $logfunc);
+	}
+
+	foreach my $volid (keys %$local_volumes) {
 	    my ($sid, $volname) = PVE::Storage::parse_volume_id($volid);
-	    push @{$self->{volumes}}, $volid;
-	    PVE::Storage::storage_migrate($self->{storecfg}, $volid, $self->{nodeip}, $sid);
+	    if ($self->{running} && $self->{opts}->{targetstorage} && $local_volumes->{$volid} eq 'config') {
+		push @{$self->{online_local_volumes}}, $volid;
+	    } else {
+		next if $rep_volumes->{$volid};
+		push @{$self->{volumes}}, $volid;
+		my $insecure = $self->{opts}->{migration_type} eq 'insecure';
+		PVE::Storage::storage_migrate($self->{storecfg}, $volid, $self->{ssh_info}, $sid,
+					      undef, undef, undef, undef, $insecure);
+	    }
 	}
     };
     die "Failed to sync data - $@" if $@;
 }
 
+sub cleanup_remotedisks {
+    my ($self) = @_;
+
+    foreach my $target_drive (keys %{$self->{target_drive}}) {
+
+	my $drive = PVE::QemuServer::parse_drive($target_drive, $self->{target_drive}->{$target_drive}->{volid});
+	my ($storeid, $volname) = PVE::Storage::parse_volume_id($drive->{file});
+
+	my $cmd = [@{$self->{rem_ssh}}, 'pvesm', 'free', "$storeid:$volname"];
+
+	eval{ PVE::Tools::run_command($cmd, outfunc => sub {}, errfunc => sub {}) };
+	if (my $err = $@) {
+	    $self->log('err', $err);
+	    $self->{errors} = 1;
+	}
+    }
+}
+
 sub phase1 {
     my ($self, $vmid) = @_;
 
@@ -277,7 +440,7 @@ sub phase1 {
 
     # set migrate lock in config file
     $conf->{lock} = 'migrate';
-    PVE::QemuServer::update_config_nolock($vmid, $conf, 1);
+    PVE::QemuConfig->write_config($vmid, $conf);
 
     sync_disks($self, $vmid);
 
@@ -290,7 +453,7 @@ sub phase1_cleanup {
 
     my $conf = $self->{vmconf};
     delete $conf->{lock};
-    eval { PVE::QemuServer::update_config_nolock($vmid, $conf, 1) };
+    eval { PVE::QemuConfig->write_config($vmid, $conf) };
     if (my $err = $@) {
 	$self->log('err', $err);
     }
@@ -312,6 +475,7 @@ sub phase2 {
 
     my $raddr;
     my $rport;
+    my $ruri; # the whole migration dst. URI (protocol:address[:port])
     my $nodename = PVE::INotify::nodename();
 
     ## start on remote node
@@ -323,12 +487,29 @@ sub phase2 {
 	$spice_ticket = $res->{ticket};
     }
 
-    push @$cmd , 'qm', 'start', $vmid, '--stateuri', 'tcp', '--skiplock', '--migratedfrom', $nodename;
+    push @$cmd , 'qm', 'start', $vmid, '--skiplock', '--migratedfrom', $nodename;
+
+    my $migration_type = $self->{opts}->{migration_type};
+
+    push @$cmd, '--migration_type', $migration_type;
+
+    push @$cmd, '--migration_network', $self->{opts}->{migration_network}
+      if $self->{opts}->{migration_network};
+
+    if ($migration_type eq 'insecure') {
+	push @$cmd, '--stateuri', 'tcp';
+    } else {
+	push @$cmd, '--stateuri', 'unix';
+    }
 
     if ($self->{forcemachine}) {
 	push @$cmd, '--machine', $self->{forcemachine};
     }
 
+    if ($self->{opts}->{targetstorage}) {
+	push @$cmd, '--targetstorage', $self->{opts}->{targetstorage};
+    }
+
     my $spice_port;
 
     # Note: We try to keep $spice_ticket secret (do not pass via command line parameter)
@@ -339,14 +520,31 @@ sub phase2 {
 	if ($line =~ m/^migration listens on tcp:(localhost|[\d\.]+|\[[\d\.:a-fA-F]+\]):(\d+)$/) {
 	    $raddr = $1;
 	    $rport = int($2);
+	    $ruri = "tcp:$raddr:$rport";
+	}
+	elsif ($line =~ m!^migration listens on unix:(/run/qemu-server/(\d+)\.migrate)$!) {
+	    $raddr = $1;
+	    die "Destination UNIX sockets VMID does not match source VMID" if $vmid ne $2;
+	    $ruri = "unix:$raddr";
 	}
 	elsif ($line =~ m/^migration listens on port (\d+)$/) {
 	    $raddr = "localhost";
 	    $rport = int($1);
+	    $ruri = "tcp:$raddr:$rport";
 	}
         elsif ($line =~ m/^spice listens on port (\d+)$/) {
 	    $spice_port = int($1);
 	}
+        elsif ($line =~ m/^storage migration listens on nbd:(localhost|[\d\.]+|\[[\d\.:a-fA-F]+\]):(\d+):exportname=(\S+) volume:(\S+)$/) {
+	    my $volid = $4;
+	    my $nbd_uri = "nbd:$1:$2:exportname=$3";
+	    my $targetdrive = $3;
+	    $targetdrive =~ s/drive-//g;
+
+	    $self->{target_drive}->{$targetdrive}->{volid} = $volid;
+	    $self->{target_drive}->{$targetdrive}->{nbd_uri} = $nbd_uri;
+
+	}
     }, errfunc => sub {
 	my $line = shift;
 	$self->log('info', $line);
@@ -354,14 +552,59 @@ sub phase2 {
 
     die "unable to detect remote migration address\n" if !$raddr;
 
-    ## create tunnel to remote port
-    $self->log('info', "starting ssh migration tunnel");
-    my $pfamily = PVE::Tools::get_host_address_family($nodename);
-    my $lport = ($raddr eq "localhost") ? PVE::Tools::next_migrate_port($pfamily) : undef;
-    $self->{tunnel} = $self->fork_tunnel($self->{nodeip}, $lport, $rport);
+    if ($migration_type eq 'secure') {
+	$self->log('info', "start remote tunnel");
+
+	if ($ruri =~ /^unix:/) {
+	    unlink $raddr;
+	    $self->{tunnel} = $self->fork_tunnel("$raddr:$raddr");
+	    $self->{tunnel}->{sock_addr} = $raddr;
+
+	    my $unix_socket_try = 0; # wait for the socket to become ready
+	    while (! -S $raddr) {
+		$unix_socket_try++;
+		if ($unix_socket_try > 100) {
+		    $self->{errors} = 1;
+		    $self->finish_tunnel($self->{tunnel});
+		    die "Timeout, migration socket $ruri did not get ready";
+		}
+
+		usleep(50000);
+	    }
+
+	} elsif ($ruri =~ /^tcp:/) {
+	    my $tunnel_addr;
+	    if ($raddr eq "localhost") {
+		# for backwards compatibility with older qemu-server versions
+		my $pfamily = PVE::Tools::get_host_address_family($nodename);
+		my $lport = PVE::Tools::next_migrate_port($pfamily);
+		$tunnel_addr = "$lport:localhost:$rport";
+	    }
+
+	    $self->{tunnel} = $self->fork_tunnel($tunnel_addr);
+
+	} else {
+	    die "unsupported protocol in migration URI: $ruri\n";
+	}
+    }
 
     my $start = time();
-    $self->log('info', "starting online/live migration on $raddr:$rport");
+
+    if ($self->{opts}->{targetstorage} && defined($self->{online_local_volumes})) {
+	$self->{storage_migration} = 1;
+	$self->{storage_migration_jobs} = {};
+	$self->log('info', "starting storage migration");
+
+	die "The number of local disks does not match between the source and the destination.\n"
+	    if (scalar(keys %{$self->{target_drive}}) != scalar @{$self->{online_local_volumes}});
+	foreach my $drive (keys %{$self->{target_drive}}){
+	    my $nbd_uri = $self->{target_drive}->{$drive}->{nbd_uri};
+	    $self->log('info', "$drive: start migration to to $nbd_uri");
+	    PVE::QemuServer::qemu_drive_mirror($vmid, $drive, $nbd_uri, $vmid, undef, $self->{storage_migration_jobs}, 1);
+	}
+    }
+
+    $self->log('info', "starting online/live migration on $ruri");
     $self->{livemigration} = 1;
 
     # load_defaults
@@ -388,6 +631,7 @@ sub phase2 {
 	$self->log('info', "migrate_set_downtime error: $@") if $@;
     }
 
+    $self->log('info', "set migration_caps");
     eval {
 	PVE::QemuServer::set_migration_caps($vmid);
     };
@@ -395,10 +639,12 @@ sub phase2 {
 
     #set cachesize 10% of the total memory
     my $cachesize = int($conf->{memory}*1048576/10);
+    $self->log('info', "set cachesize: $cachesize");
     eval {
-	PVE::QemuServer::vm_mon_cmd_nocheck($vmid, "migrate-set-cache-size", value => $cachesize);
+	PVE::QemuServer::vm_mon_cmd_nocheck($vmid, "migrate-set-cache-size", value => int($cachesize));
     };
-	
+    $self->log('info', "migrate-set-cache-size error: $@") if $@;
+
     if (PVE::QemuServer::vga_conf_has_spice($conf->{vga})) {
 	my $rpcenv = PVE::RPCEnvironment::get();
 	my $authuser = $rpcenv->get_user();
@@ -419,11 +665,12 @@ sub phase2 {
 
     }
 
+    $self->log('info', "start migrate command to $ruri");
     eval {
-        PVE::QemuServer::vm_mon_cmd_nocheck($vmid, "migrate", uri => "tcp:$raddr:$rport");
+        PVE::QemuServer::vm_mon_cmd_nocheck($vmid, "migrate", uri => $ruri);
     };
     my $merr = $@;
-    $self->log('info', "migrate uri => tcp:$raddr:$rport failed: $merr") if $merr;
+    $self->log('info', "migrate uri => $ruri failed: $merr") if $merr;
 
     my $lstat = 0;
     my $usleep = 2000000;
@@ -443,6 +690,7 @@ sub phase2 {
 	if (my $err = $@) {
 	    $err_count++;
 	    warn "query migrate failed: $err\n";
+	    $self->log('info', "query migrate failed: $err");
 	    if ($err_count <= 5) {
 		usleep(1000000);
 		next;
@@ -450,12 +698,12 @@ sub phase2 {
 	    die "too many query migrate failures - aborting\n";
 	}
 
-        if ($stat->{status} =~ m/^(setup)$/im) {
+        if (defined($stat->{status}) && $stat->{status} =~ m/^(setup)$/im) {
             sleep(1);
             next;
         }
 
-	if ($stat->{status} =~ m/^(active|completed|failed|cancelled)$/im) {
+	if (defined($stat->{status}) && $stat->{status} =~ m/^(active|completed|failed|cancelled)$/im) {
 	    $merr = undef;
 	    $err_count = 0;
 	    if ($stat->{status} eq 'completed') {
@@ -468,6 +716,7 @@ sub phase2 {
 	    }
 
 	    if ($stat->{status} eq 'failed' || $stat->{status} eq 'cancelled') {
+		$self->log('info', "migration status error: $stat->{status}");
 		die "aborting\n"
 	    }
 
@@ -520,8 +769,10 @@ sub phase2 {
 	    die "unable to parse migration status '$stat->{status}' - aborting\n";
 	}
     }
-    #to be sure tat the tunnel is closed 
-    if ($self->{tunnel}) {
+
+    # just to be sure that the tunnel gets closed on successful migration, on error
+    # phase2_cleanup closes it *after* stopping the remote waiting VM
+    if (!$self->{errors} && $self->{tunnel}) {
 	eval { finish_tunnel($self, $self->{tunnel});  };
 	if (my $err = $@) {
 	    $self->log('err', $err);
@@ -546,12 +797,25 @@ sub phase2_cleanup {
 
     my $conf = $self->{vmconf};
     delete $conf->{lock};
-    eval { PVE::QemuServer::update_config_nolock($vmid, $conf, 1) };
+    eval { PVE::QemuConfig->write_config($vmid, $conf) };
     if (my $err = $@) {
         $self->log('err', $err);
     }
 
     # cleanup ressources on target host
+    if ($self->{storage_migration}) {
+
+	eval { PVE::QemuServer::qemu_blockjobs_cancel($vmid, $self->{storage_migration_jobs}) };
+	if (my $err = $@) {
+	    $self->log('err', $err);
+	}
+
+	eval { PVE::QemuMigrate::cleanup_remotedisks($self) };
+	if (my $err = $@) {
+	    $self->log('err', $err);
+	}
+    }
+
     my $nodename = PVE::INotify::nodename();
  
     my $cmd = [@{$self->{rem_ssh}}, 'qm', 'stop', $vmid, '--skiplock', '--migratedfrom', $nodename];
@@ -593,15 +857,52 @@ sub phase3_cleanup {
     my $conf = $self->{vmconf};
     return if $self->{phase2errors};
 
+    if ($self->{storage_migration}) {
+	# finish block-job
+	eval { PVE::QemuServer::qemu_drive_mirror_monitor($vmid, undef, $self->{storage_migration_jobs}); };
+
+	if (my $err = $@) {
+	    eval { PVE::QemuServer::qemu_blockjobs_cancel($vmid, $self->{storage_migration_jobs}) };
+	    eval { PVE::QemuMigrate::cleanup_remotedisks($self) };
+	    die "Failed to completed storage migration\n";
+	} else {
+	    foreach my $target_drive (keys %{$self->{target_drive}}) {
+		my $drive = PVE::QemuServer::parse_drive($target_drive, $self->{target_drive}->{$target_drive}->{volid});
+		$conf->{$target_drive} = PVE::QemuServer::print_drive($vmid, $drive);
+		PVE::QemuConfig->write_config($vmid, $conf);
+	    }
+	}
+    }
+
+    # transfer replication state before move config
+    $self->transfer_replication_state();
+
     # move config to remote node
-    my $conffile = PVE::QemuServer::config_file($vmid);
-    my $newconffile = PVE::QemuServer::config_file($vmid, $self->{node});
+    my $conffile = PVE::QemuConfig->config_file($vmid);
+    my $newconffile = PVE::QemuConfig->config_file($vmid, $self->{node});
 
     die "Failed to move config to node '$self->{node}' - rename failed: $!\n"
         if !rename($conffile, $newconffile);
 
+    $self->switch_replication_job_target();
+
     if ($self->{livemigration}) {
-	# now that config file is move, we can resume vm on target if livemigrate
+	if ($self->{storage_migration}) {
+	    # remove drives referencing the nbd server from source
+	    # otherwise vm_stop might hang later on
+	    foreach my $drive (keys %{$self->{target_drive}}){
+		PVE::QemuServer::vm_mon_cmd_nocheck($vmid, "device_del", id => $drive);
+	    }
+	    # stop nbd server on remote vm - requirement for resume since 2.9
+	    my $cmd = [@{$self->{rem_ssh}}, 'qm', 'nbdstop', $vmid];
+
+	    eval{ PVE::Tools::run_command($cmd, outfunc => sub {}, errfunc => sub {}) };
+	    if (my $err = $@) {
+		$self->log('err', $err);
+		$self->{errors} = 1;
+	    }
+	}
+	# config moved and nbd server stopped - now we can resume vm on target
 	my $cmd = [@{$self->{rem_ssh}}, 'qm', 'resume', $vmid, '--skiplock', '--nocheck'];
 	eval{ PVE::Tools::run_command($cmd, outfunc => sub {}, 
 		errfunc => sub {
@@ -616,7 +917,6 @@ sub phase3_cleanup {
     }
 
     eval {
-
 	my $timer = 0;
 	if (PVE::QemuServer::vga_conf_has_spice($conf->{vga}) && $self->{running}) {
 	    $self->log('info', "Waiting for spice server migration");
@@ -647,6 +947,21 @@ sub phase3_cleanup {
 	$self->{errors} = 1;
     }
 
+    if($self->{storage_migration}) {
+	# destroy local copies
+	my $volids = $self->{online_local_volumes};
+
+	foreach my $volid (@$volids) {
+	    eval { PVE::Storage::vdisk_free($self->{storecfg}, $volid); };
+	    if (my $err = $@) {
+		$self->log('err', "removing local copy of '$volid' failed - $err");
+		$self->{errors} = 1;
+		last if $err =~ /^interrupted by signal$/;
+	    }
+	}
+
+    }
+
     # clear migrate lock
     my $cmd = [ @{$self->{rem_ssh}}, 'qm', 'unlock', $vmid ];
     $self->cmd_logerr($cmd, errmsg => "failed to clear migrate lock");