From: "Fabian Grünbichler" <f.gruenbichler@proxmox.com>
To: pve-devel@lists.proxmox.com
Subject: [pve-devel] [PATCH v3 qemu-server 09/10] migrate: add remote migration handling
Date: Wed, 22 Dec 2021 14:52:52 +0100 [thread overview]
Message-ID: <20211222135257.3242938-17-f.gruenbichler@proxmox.com> (raw)
In-Reply-To: <20211222135257.3242938-1-f.gruenbichler@proxmox.com>
remote migration uses a websocket connection to a task worker running on
the target node instead of commands via SSH to control the migration.
this websocket tunnel is started earlier than the SSH tunnel, and allows
adding UNIX-socket forwarding over additional websocket connections
on-demand.
the main differences to regular intra-cluster migration are:
- source VM config and disks are only removed upon request via --delete
- shared storages are treated like local storages, since we can't
assume they are shared across clusters (with potentical to extend this
by marking storages as shared)
- NBD migrated disks are explicitly pre-allocated on the target node via
tunnel command before starting the target VM instance
- in addition to storages, network bridges and the VMID itself is
transformed via a user defined mapping
- all commands and migration data streams are sent via a WS tunnel proxy
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
Notes:
requires bumped pve-guest-common
v3:
- move WS tunnel helpers to pve-guest-common-perl
- check bridge mapping early
v2:
- improve tunnel version info printing and error handling
- don't cleanup unix sockets twice
- url escape remote socket path
- cleanup nits and small issues
requires proxmox-websocket-tunnel
v3:
- fix misplaced parentheses
v2:
- improve tunnel version info printing and error handling
- don't cleanup unix sockets twice
- url escape remote socket path
- cleanup nits and small issues
PVE/API2/Qemu.pm | 2 +-
PVE/QemuMigrate.pm | 425 +++++++++++++++++++++++++++++++++++++--------
PVE/QemuServer.pm | 7 +-
3 files changed, 359 insertions(+), 75 deletions(-)
diff --git a/PVE/API2/Qemu.pm b/PVE/API2/Qemu.pm
index d188b77..cf90fe7 100644
--- a/PVE/API2/Qemu.pm
+++ b/PVE/API2/Qemu.pm
@@ -4803,7 +4803,7 @@ __PACKAGE__->register_method({
# bump/reset for breaking changes
# bump/bump for opt-in changes
return {
- api => 2,
+ api => $PVE::QemuMigrate::WS_TUNNEL_VERSION,
age => 0,
};
},
diff --git a/PVE/QemuMigrate.pm b/PVE/QemuMigrate.pm
index 897018b..3e9d29e 100644
--- a/PVE/QemuMigrate.pm
+++ b/PVE/QemuMigrate.pm
@@ -5,11 +5,10 @@ use warnings;
use IO::File;
use IPC::Open2;
-use POSIX qw( WNOHANG );
use Time::HiRes qw( usleep );
-use PVE::Format qw(render_bytes);
use PVE::Cluster;
+use PVE::Format qw(render_bytes);
use PVE::GuestHelpers qw(safe_boolean_ne safe_string_ne);
use PVE::INotify;
use PVE::RPCEnvironment;
@@ -17,6 +16,7 @@ use PVE::Replication;
use PVE::ReplicationConfig;
use PVE::ReplicationState;
use PVE::Storage;
+use PVE::StorageTunnel;
use PVE::Tools;
use PVE::Tunnel;
@@ -31,6 +31,9 @@ use PVE::QemuServer;
use PVE::AbstractMigrate;
use base qw(PVE::AbstractMigrate);
+# compared against remote end's minimum version
+our $WS_TUNNEL_VERSION = 2;
+
sub fork_tunnel {
my ($self, $ssh_forward_info) = @_;
@@ -43,6 +46,35 @@ sub fork_tunnel {
return PVE::Tunnel::fork_ssh_tunnel($self->{rem_ssh}, $cmd, $ssh_forward_info, $log);
}
+sub fork_websocket_tunnel {
+ my ($self, $storages, $bridges) = @_;
+
+ my $remote = $self->{opts}->{remote};
+ my $conn = $remote->{conn};
+
+ my $websocket_url = "https://$conn->{host}:$conn->{port}/api2/json/nodes/$self->{node}/qemu/$remote->{vmid}/mtunnelwebsocket";
+ my $url = "/nodes/$self->{node}/qemu/$remote->{vmid}/mtunnel";
+
+ my $tunnel_params = {
+ url => $websocket_url,
+ };
+
+ my $storage_list = join(',', keys %$storages);
+ my $bridge_list = join(',', keys %$bridges);
+
+ my $req_params = {
+ storages => $storage_list,
+ bridges => $bridge_list,
+ };
+
+ my $log = sub {
+ my $line = shift;
+ $self->log('info', $line);
+ };
+
+ return PVE::Tunnel::fork_websocket_tunnel($conn, $url, $req_params, $tunnel_params, $log);
+}
+
# tunnel_info:
# proto: unix (secure) or tcp (insecure/legacy compat)
# addr: IP or UNIX socket path
@@ -175,23 +207,34 @@ sub prepare {
}
my $vollist = PVE::QemuServer::get_vm_volumes($conf);
+
+ my $storages = {};
foreach my $volid (@$vollist) {
my ($sid, $volname) = PVE::Storage::parse_volume_id($volid, 1);
- # check if storage is available on both nodes
+ # check if storage is available on source node
my $scfg = PVE::Storage::storage_check_enabled($storecfg, $sid);
my $targetsid = $sid;
- # NOTE: we currently ignore shared source storages in mappings so skip here too for now
- if (!$scfg->{shared}) {
+ # NOTE: local ignores shared mappings, remote maps them
+ if (!$scfg->{shared} || $self->{opts}->{remote}) {
$targetsid = PVE::QemuServer::map_id($self->{opts}->{storagemap}, $sid);
}
- my $target_scfg = PVE::Storage::storage_check_enabled($storecfg, $targetsid, $self->{node});
- my ($vtype) = PVE::Storage::parse_volname($storecfg, $volid);
+ $storages->{$targetsid} = 1;
- die "$volid: content type '$vtype' is not available on storage '$targetsid'\n"
- if !$target_scfg->{content}->{$vtype};
+ if (!$self->{opts}->{remote}) {
+ # check if storage is available on target node
+ my $target_scfg = PVE::Storage::storage_check_enabled(
+ $storecfg,
+ $targetsid,
+ $self->{node},
+ );
+ my ($vtype) = PVE::Storage::parse_volname($storecfg, $volid);
+
+ die "$volid: content type '$vtype' is not available on storage '$targetsid'\n"
+ if !$target_scfg->{content}->{$vtype};
+ }
if ($scfg->{shared}) {
# PVE::Storage::activate_storage checks this for non-shared storages
@@ -201,10 +244,27 @@ sub prepare {
}
}
- # test ssh connection
- my $cmd = [ @{$self->{rem_ssh}}, '/bin/true' ];
- eval { $self->cmd_quiet($cmd); };
- die "Can't connect to destination address using public key\n" if $@;
+ if ($self->{opts}->{remote}) {
+ # test & establish websocket connection
+ my $bridges = map_bridges($conf, $self->{opts}->{bridgemap}, 1);
+ my $tunnel = $self->fork_websocket_tunnel($storages, $bridges);
+ my $min_version = $tunnel->{version} - $tunnel->{age};
+ $self->log('info', "local WS tunnel version: $WS_TUNNEL_VERSION");
+ $self->log('info', "remote WS tunnel version: $tunnel->{version}");
+ $self->log('info', "minimum required WS tunnel version: $min_version");
+ die "Remote tunnel endpoint not compatible, upgrade required\n"
+ if $WS_TUNNEL_VERSION < $min_version;
+ die "Remote tunnel endpoint too old, upgrade required\n"
+ if $WS_TUNNEL_VERSION > $tunnel->{version};
+
+ print "websocket tunnel started\n";
+ $self->{tunnel} = $tunnel;
+ } else {
+ # test ssh connection
+ my $cmd = [ @{$self->{rem_ssh}}, '/bin/true' ];
+ eval { $self->cmd_quiet($cmd); };
+ die "Can't connect to destination address using public key\n" if $@;
+ }
return $running;
}
@@ -242,7 +302,7 @@ sub scan_local_volumes {
my @sids = PVE::Storage::storage_ids($storecfg);
foreach my $storeid (@sids) {
my $scfg = PVE::Storage::storage_config($storecfg, $storeid);
- next if $scfg->{shared};
+ next if $scfg->{shared} && !$self->{opts}->{remote};
next if !PVE::Storage::storage_check_enabled($storecfg, $storeid, undef, 1);
# get list from PVE::Storage (for unused volumes)
@@ -251,19 +311,24 @@ sub scan_local_volumes {
next if @{$dl->{$storeid}} == 0;
my $targetsid = PVE::QemuServer::map_id($self->{opts}->{storagemap}, $storeid);
- # check if storage is available on target node
- my $target_scfg = PVE::Storage::storage_check_enabled(
- $storecfg,
- $targetsid,
- $self->{node},
- );
-
- die "content type 'images' is not available on storage '$targetsid'\n"
- if !$target_scfg->{content}->{images};
+ my $bwlimit_sids = [$storeid];
+ if (!$self->{opts}->{remote}) {
+ # check if storage is available on target node
+ my $target_scfg = PVE::Storage::storage_check_enabled(
+ $storecfg,
+ $targetsid,
+ $self->{node},
+ );
+
+ die "content type 'images' is not available on storage '$targetsid'\n"
+ if !$target_scfg->{content}->{images};
+
+ push @$bwlimit_sids, $targetsid;
+ }
my $bwlimit = PVE::Storage::get_bandwidth_limit(
'migration',
- [$targetsid, $storeid],
+ $bwlimit_sids,
$self->{opts}->{bwlimit},
);
@@ -319,14 +384,17 @@ sub scan_local_volumes {
my $scfg = PVE::Storage::storage_check_enabled($storecfg, $sid);
my $targetsid = $sid;
- # NOTE: we currently ignore shared source storages in mappings so skip here too for now
- if (!$scfg->{shared}) {
+ # NOTE: local ignores shared mappings, remote maps them
+ if (!$scfg->{shared} || $self->{opts}->{remote}) {
$targetsid = PVE::QemuServer::map_id($self->{opts}->{storagemap}, $sid);
}
- PVE::Storage::storage_check_enabled($storecfg, $targetsid, $self->{node});
+ # check target storage on target node if intra-cluster migration
+ if (!$self->{opts}->{remote}) {
+ PVE::Storage::storage_check_enabled($storecfg, $targetsid, $self->{node});
- return if $scfg->{shared};
+ return if $scfg->{shared};
+ }
$local_volumes->{$volid}->{ref} = $attr->{referenced_in_config} ? 'config' : 'snapshot';
$local_volumes->{$volid}->{ref} = 'storage' if $attr->{is_unused};
@@ -415,6 +483,9 @@ sub scan_local_volumes {
my $migratable = $scfg->{type} =~ /^(?:dir|btrfs|zfspool|lvmthin|lvm)$/;
+ # TODO: what is this even here for?
+ $migratable = 1 if $self->{opts}->{remote};
+
die "can't migrate '$volid' - storage type '$scfg->{type}' not supported\n"
if !$migratable;
@@ -449,6 +520,10 @@ sub handle_replication {
my $local_volumes = $self->{local_volumes};
return if !$self->{replication_jobcfg};
+
+ die "can't migrate VM with replicated volumes to remote cluster/node\n"
+ if $self->{opts}->{remote};
+
if ($self->{running}) {
my $version = PVE::QemuServer::kvm_user_version();
@@ -548,24 +623,51 @@ sub sync_offline_local_volumes {
$self->log('info', "copying local disk images") if scalar(@volids);
foreach my $volid (@volids) {
- my $targetsid = $local_volumes->{$volid}->{targetsid};
- my $bwlimit = $local_volumes->{$volid}->{bwlimit};
- $bwlimit = $bwlimit * 1024 if defined($bwlimit); # storage_migrate uses bps
-
- my $storage_migrate_opts = {
- 'ratelimit_bps' => $bwlimit,
- 'insecure' => $opts->{migration_type} eq 'insecure',
- 'with_snapshots' => $local_volumes->{$volid}->{snapshots},
- 'allow_rename' => !$local_volumes->{$volid}->{is_vmstate},
- };
+ my $new_volid;
- my $logfunc = sub { $self->log('info', $_[0]); };
- my $new_volid = eval {
- PVE::Storage::storage_migrate($storecfg, $volid, $self->{ssh_info},
- $targetsid, $storage_migrate_opts, $logfunc);
- };
- if (my $err = $@) {
- die "storage migration for '$volid' to storage '$targetsid' failed - $err\n";
+ my $opts = $self->{opts};
+ if ($opts->{remote}) {
+ my $log = sub {
+ my $line = shift;
+ $self->log('info', $line);
+ };
+
+ $new_volid = PVE::StorageTunnel::storage_migrate(
+ $self->{tunnel},
+ $storecfg,
+ $volid,
+ $self->{vmid},
+ $opts->{remote}->{vmid},
+ $local_volumes->{$volid},
+ $log,
+ );
+ } else {
+ my $targetsid = $local_volumes->{$volid}->{targetsid};
+
+ my $bwlimit = $local_volumes->{$volid}->{bwlimit};
+ $bwlimit = $bwlimit * 1024 if defined($bwlimit); # storage_migrate uses bps
+
+ my $storage_migrate_opts = {
+ 'ratelimit_bps' => $bwlimit,
+ 'insecure' => $opts->{migration_type} eq 'insecure',
+ 'with_snapshots' => $local_volumes->{$volid}->{snapshots},
+ 'allow_rename' => !$local_volumes->{$volid}->{is_vmstate},
+ };
+
+ my $logfunc = sub { $self->log('info', $_[0]); };
+ $new_volid = eval {
+ PVE::Storage::storage_migrate(
+ $storecfg,
+ $volid,
+ $self->{ssh_info},
+ $targetsid,
+ $storage_migrate_opts,
+ $logfunc,
+ );
+ };
+ if (my $err = $@) {
+ die "storage migration for '$volid' to storage '$targetsid' failed - $err\n";
+ }
}
$self->{volume_map}->{$volid} = $new_volid;
@@ -581,6 +683,12 @@ sub sync_offline_local_volumes {
sub cleanup_remotedisks {
my ($self) = @_;
+ if ($self->{opts}->{remote}) {
+ PVE::Tunnel::finish_tunnel($self->{tunnel}, 1);
+ delete $self->{tunnel};
+ return;
+ }
+
my $local_volumes = $self->{local_volumes};
foreach my $volid (values %{$self->{volume_map}}) {
@@ -630,8 +738,100 @@ sub phase1 {
$self->handle_replication($vmid);
$self->sync_offline_local_volumes();
+ $self->phase1_remote($vmid) if $self->{opts}->{remote};
};
+sub map_bridges {
+ my ($conf, $map, $scan_only) = @_;
+
+ my $bridges = {};
+
+ foreach my $opt (keys %$conf) {
+ next if $opt !~ m/^net\d+$/;
+
+ next if !$conf->{$opt};
+ my $d = PVE::QemuServer::parse_net($conf->{$opt});
+ next if !$d || !$d->{bridge};
+
+ my $target_bridge = PVE::QemuServer::map_id($map, $d->{bridge});
+ $bridges->{$target_bridge}->{$opt} = $d->{bridge};
+
+ next if $scan_only;
+
+ $d->{bridge} = $target_bridge;
+ $conf->{$opt} = PVE::QemuServer::print_net($d);
+ }
+
+ return $bridges;
+}
+
+sub phase1_remote {
+ my ($self, $vmid) = @_;
+
+ my $remote_conf = PVE::QemuConfig->load_config($vmid);
+ PVE::QemuConfig->update_volume_ids($remote_conf, $self->{volume_map});
+
+ my $bridges = map_bridges($remote_conf, $self->{opts}->{bridgemap});
+ for my $target (keys $bridges->%*) {
+ for my $nic (keys $bridges->{$target}->%*) {
+ $self->log('info', "mapped: $nic from $bridges->{$target}->{$nic} to $target");
+ }
+ }
+
+ my @online_local_volumes = $self->filter_local_volumes('online');
+
+ my $storage_map = $self->{opts}->{storagemap};
+ $self->{nbd} = {};
+ PVE::QemuConfig->foreach_volume($remote_conf, sub {
+ my ($ds, $drive) = @_;
+
+ # TODO eject CDROM?
+ return if PVE::QemuServer::drive_is_cdrom($drive);
+
+ my $volid = $drive->{file};
+ return if !$volid;
+
+ return if !grep { $_ eq $volid} @online_local_volumes;
+
+ my ($storeid, $volname) = PVE::Storage::parse_volume_id($volid);
+ my $scfg = PVE::Storage::storage_config($self->{storecfg}, $storeid);
+ my $source_format = PVE::QemuServer::qemu_img_format($scfg, $volname);
+
+ # set by target cluster
+ my $oldvolid = delete $drive->{file};
+ delete $drive->{format};
+
+ my $targetsid = PVE::QemuServer::map_id($storage_map, $storeid);
+
+ my $params = {
+ format => $source_format,
+ storage => $targetsid,
+ drive => $drive,
+ };
+
+ $self->log('info', "Allocating volume for drive '$ds' on remote storage '$targetsid'..");
+ my $res = PVE::Tunnel::write_tunnel($self->{tunnel}, 600, 'disk', $params);
+
+ $self->log('info', "volume '$oldvolid' os '$res->{volid}' on the target\n");
+ $remote_conf->{$ds} = $res->{drivestr};
+ $self->{nbd}->{$ds} = $res;
+ });
+
+ my $conf_str = PVE::QemuServer::write_vm_config("remote", $remote_conf);
+
+ # TODO expose in PVE::Firewall?
+ my $vm_fw_conf_path = "/etc/pve/firewall/$vmid.fw";
+ my $fw_conf_str;
+ $fw_conf_str = PVE::Tools::file_get_contents($vm_fw_conf_path)
+ if -e $vm_fw_conf_path;
+ my $params = {
+ conf => $conf_str,
+ 'firewall-config' => $fw_conf_str,
+ };
+
+ PVE::Tunnel::write_tunnel($self->{tunnel}, 10, 'config', $params);
+}
+
sub phase1_cleanup {
my ($self, $vmid, $err) = @_;
@@ -662,7 +862,6 @@ sub phase2_start_local_cluster {
my $local_volumes = $self->{local_volumes};
my @online_local_volumes = $self->filter_local_volumes('online');
- $self->{storage_migration} = 1 if scalar(@online_local_volumes);
my $start = $params->{start_params};
my $migrate = $params->{migrate_opts};
@@ -793,10 +992,34 @@ sub phase2_start_local_cluster {
return ($tunnel_info, $spice_port);
}
+sub phase2_start_remote_cluster {
+ my ($self, $vmid, $params) = @_;
+
+ die "insecure migration to remote cluster not implemented\n"
+ if $params->{migrate_opts}->{type} ne 'websocket';
+
+ my $remote_vmid = $self->{opts}->{remote}->{vmid};
+
+ my $res = PVE::Tunnel::write_tunnel($self->{tunnel}, 10, "start", $params);
+
+ foreach my $drive (keys %{$res->{drives}}) {
+ $self->{stopnbd} = 1;
+ $self->{target_drive}->{$drive}->{drivestr} = $res->{drives}->{$drive}->{drivestr};
+ my $nbd_uri = $res->{drives}->{$drive}->{nbd_uri};
+ die "unexpected NBD uri for '$drive': $nbd_uri\n"
+ if $nbd_uri !~ s!/run/qemu-server/$remote_vmid\_!/run/qemu-server/$vmid\_!;
+
+ $self->{target_drive}->{$drive}->{nbd_uri} = $nbd_uri;
+ }
+
+ return ($res->{migrate}, $res->{spice_port});
+}
+
sub phase2 {
my ($self, $vmid) = @_;
my $conf = $self->{vmconf};
+ my $local_volumes = $self->{local_volumes};
# version > 0 for unix socket support
my $nbd_protocol_version = 1;
@@ -828,10 +1051,39 @@ sub phase2 {
},
};
- my ($tunnel_info, $spice_port) = $self->phase2_start_local_cluster($vmid, $params);
+ my ($tunnel_info, $spice_port);
+
+ my @online_local_volumes = $self->filter_local_volumes('online');
+ $self->{storage_migration} = 1 if scalar(@online_local_volumes);
+
+ if (my $remote = $self->{opts}->{remote}) {
+ my $remote_vmid = $remote->{vmid};
+ $params->{migrate_opts}->{remote_node} = $self->{node};
+ ($tunnel_info, $spice_port) = $self->phase2_start_remote_cluster($vmid, $params);
+ die "only UNIX sockets are supported for remote migration\n"
+ if $tunnel_info->{proto} ne 'unix';
+
+ my $remote_socket = $tunnel_info->{addr};
+ my $local_socket = $remote_socket;
+ $local_socket =~ s/$remote_vmid/$vmid/g;
+ $tunnel_info->{addr} = $local_socket;
+
+ $self->log('info', "Setting up tunnel for '$local_socket'");
+ PVE::Tunnel::forward_unix_socket($self->{tunnel}, $local_socket, $remote_socket);
+
+ foreach my $remote_socket (@{$tunnel_info->{unix_sockets}}) {
+ my $local_socket = $remote_socket;
+ $local_socket =~ s/$remote_vmid/$vmid/g;
+ next if $self->{tunnel}->{forwarded}->{$local_socket};
+ $self->log('info', "Setting up tunnel for '$local_socket'");
+ PVE::Tunnel::forward_unix_socket($self->{tunnel}, $local_socket, $remote_socket);
+ }
+ } else {
+ ($tunnel_info, $spice_port) = $self->phase2_start_local_cluster($vmid, $params);
- $self->log('info', "start remote tunnel");
- $self->start_remote_tunnel($tunnel_info);
+ $self->log('info', "start remote tunnel");
+ $self->start_remote_tunnel($tunnel_info);
+ }
my $migrate_uri = "$tunnel_info->{proto}:$tunnel_info->{addr}";
$migrate_uri .= ":$tunnel_info->{port}"
@@ -841,8 +1093,6 @@ sub phase2 {
$self->{storage_migration_jobs} = {};
$self->log('info', "starting storage migration");
- my @online_local_volumes = $self->filter_local_volumes('online');
-
die "The number of local disks does not match between the source and the destination.\n"
if (scalar(keys %{$self->{target_drive}}) != scalar(@online_local_volumes));
foreach my $drive (keys %{$self->{target_drive}}){
@@ -915,7 +1165,7 @@ sub phase2 {
};
$self->log('info', "migrate-set-parameters error: $@") if $@;
- if (PVE::QemuServer::vga_conf_has_spice($conf->{vga})) {
+ if (PVE::QemuServer::vga_conf_has_spice($conf->{vga}) && !$self->{opts}->{remote}) {
my $rpcenv = PVE::RPCEnvironment::get();
my $authuser = $rpcenv->get_user();
@@ -1112,11 +1362,15 @@ sub phase2_cleanup {
my $nodename = PVE::INotify::nodename();
- my $cmd = [@{$self->{rem_ssh}}, 'qm', 'stop', $vmid, '--skiplock', '--migratedfrom', $nodename];
- eval{ PVE::Tools::run_command($cmd, outfunc => sub {}, errfunc => sub {}) };
- if (my $err = $@) {
- $self->log('err', $err);
- $self->{errors} = 1;
+ if ($self->{tunnel} && $self->{tunnel}->{version} >= 2) {
+ PVE::Tunnel::write_tunnel($self->{tunnel}, 10, 'stop');
+ } else {
+ my $cmd = [@{$self->{rem_ssh}}, 'qm', 'stop', $vmid, '--skiplock', '--migratedfrom', $nodename];
+ eval{ PVE::Tools::run_command($cmd, outfunc => sub {}, errfunc => sub {}) };
+ if (my $err = $@) {
+ $self->log('err', $err);
+ $self->{errors} = 1;
+ }
}
# cleanup after stopping, otherwise disks might be in-use by target VM!
@@ -1149,7 +1403,7 @@ sub phase3_cleanup {
my $tunnel = $self->{tunnel};
- if ($self->{volume_map}) {
+ if ($self->{volume_map} && !$self->{opts}->{remote}) {
my $target_drives = $self->{target_drive};
# FIXME: for NBD storage migration we now only update the volid, and
@@ -1165,27 +1419,34 @@ sub phase3_cleanup {
}
# transfer replication state before move config
- $self->transfer_replication_state() if $self->{is_replicated};
- PVE::QemuConfig->move_config_to_node($vmid, $self->{node});
- $self->switch_replication_job_target() if $self->{is_replicated};
+ if (!$self->{opts}->{remote}) {
+ $self->transfer_replication_state() if $self->{is_replicated};
+ PVE::QemuConfig->move_config_to_node($vmid, $self->{node});
+ $self->switch_replication_job_target() if $self->{is_replicated};
+ }
if ($self->{livemigration}) {
if ($self->{stopnbd}) {
$self->log('info', "stopping NBD storage migration server on target.");
# stop nbd server on remote vm - requirement for resume since 2.9
- my $cmd = [@{$self->{rem_ssh}}, 'qm', 'nbdstop', $vmid];
+ if ($tunnel && $tunnel->{version} && $tunnel->{version} >= 2) {
+ PVE::Tunnel::write_tunnel($tunnel, 30, 'nbdstop');
+ } else {
+ 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);
- $self->{errors} = 1;
+ eval{ PVE::Tools::run_command($cmd, outfunc => sub {}, errfunc => sub {}) };
+ if (my $err = $@) {
+ $self->log('err', $err);
+ $self->{errors} = 1;
+ }
}
}
# config moved and nbd server stopped - now we can resume vm on target
if ($tunnel && $tunnel->{version} && $tunnel->{version} >= 1) {
+ my $cmd = $tunnel->{version} == 1 ? "resume $vmid" : "resume";
eval {
- PVE::Tunnel::write_tunnel($tunnel, 30, "resume $vmid");
+ PVE::Tunnel::write_tunnel($tunnel, 30, $cmd);
};
if (my $err = $@) {
$self->log('err', $err);
@@ -1205,18 +1466,24 @@ sub phase3_cleanup {
}
if ($self->{storage_migration} && PVE::QemuServer::parse_guest_agent($conf)->{fstrim_cloned_disks} && $self->{running}) {
- my $cmd = [@{$self->{rem_ssh}}, 'qm', 'guest', 'cmd', $vmid, 'fstrim'];
- eval{ PVE::Tools::run_command($cmd, outfunc => sub {}, errfunc => sub {}) };
+ if ($self->{opts}->{remote}) {
+ PVE::Tunnel::write_tunnel($self->{tunnel}, 600, 'fstrim');
+ } else {
+ my $cmd = [@{$self->{rem_ssh}}, 'qm', 'guest', 'cmd', $vmid, 'fstrim'];
+ eval{ PVE::Tools::run_command($cmd, outfunc => sub {}, errfunc => sub {}) };
+ }
}
}
# close tunnel on successful migration, on error phase2_cleanup closed it
- if ($tunnel) {
+ if ($tunnel && $tunnel->{version} == 1) {
eval { PVE::Tunnel::finish_tunnel($tunnel); };
if (my $err = $@) {
$self->log('err', $err);
$self->{errors} = 1;
}
+ $tunnel = undef;
+ delete $self->{tunnel};
}
eval {
@@ -1254,6 +1521,9 @@ sub phase3_cleanup {
# destroy local copies
foreach my $volid (@not_replicated_volumes) {
+ # remote is cleaned up below
+ next if $self->{opts}->{remote};
+
eval { PVE::Storage::vdisk_free($self->{storecfg}, $volid); };
if (my $err = $@) {
$self->log('err', "removing local copy of '$volid' failed - $err");
@@ -1263,8 +1533,19 @@ sub phase3_cleanup {
}
# clear migrate lock
- my $cmd = [ @{$self->{rem_ssh}}, 'qm', 'unlock', $vmid ];
- $self->cmd_logerr($cmd, errmsg => "failed to clear migrate lock");
+ if ($tunnel && $tunnel->{version} >= 2) {
+ PVE::Tunnel::write_tunnel($tunnel, 10, "unlock");
+
+ PVE::Tunnel::finish_tunnel($tunnel);
+ } else {
+ my $cmd = [ @{$self->{rem_ssh}}, 'qm', 'unlock', $vmid ];
+ $self->cmd_logerr($cmd, errmsg => "failed to clear migrate lock");
+ }
+
+ if ($self->{opts}->{remote} && $self->{opts}->{delete}) {
+ eval { PVE::QemuServer::destroy_vm($self->{storecfg}, $vmid, 1, undef, 0) };
+ warn "Failed to remove source VM - $@\n" if $@;
+ }
}
sub final_cleanup {
diff --git a/PVE/QemuServer.pm b/PVE/QemuServer.pm
index 9971f2c..9490615 100644
--- a/PVE/QemuServer.pm
+++ b/PVE/QemuServer.pm
@@ -5425,7 +5425,10 @@ sub vm_start_nolock {
my $defaults = load_defaults();
# set environment variable useful inside network script
- $ENV{PVE_MIGRATED_FROM} = $migratedfrom if $migratedfrom;
+ # for remote migration the config is available on the target node!
+ if (!$migrate_opts->{remote_node}) {
+ $ENV{PVE_MIGRATED_FROM} = $migratedfrom;
+ }
PVE::GuestHelpers::exec_hookscript($conf, $vmid, 'pre-start', 1);
@@ -5667,7 +5670,7 @@ sub vm_start_nolock {
my $migrate_storage_uri;
# nbd_protocol_version > 0 for unix socket support
- if ($nbd_protocol_version > 0 && $migration_type eq 'secure') {
+ if ($nbd_protocol_version > 0 && ($migration_type eq 'secure' || $migration_type eq 'websocket')) {
my $socket_path = "/run/qemu-server/$vmid\_nbd.migrate";
mon_cmd($vmid, "nbd-server-start", addr => { type => 'unix', data => { path => $socket_path } } );
$migrate_storage_uri = "nbd:unix:$socket_path";
--
2.30.2
next prev parent reply other threads:[~2021-12-22 13:54 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-22 13:52 [pve-devel] [PATCH v3 qemu-server++ 0/21] remote migration Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 guest-common 1/3] migrate: handle migration_network with " Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 guest-common 2/3] add tunnel helper module Fabian Grünbichler
2022-01-03 12:30 ` Fabian Ebner
[not found] ` <<47e7d41f-e328-d9fa-25b7-f7585de8ce5b@proxmox.com>
2022-01-19 14:30 ` Fabian Grünbichler
2022-01-20 9:57 ` Fabian Ebner
2021-12-22 13:52 ` [pve-devel] [PATCH v3 guest-common 3/3] add storage tunnel module Fabian Grünbichler
2022-01-03 14:30 ` Fabian Ebner
[not found] ` <<af15fed1-2d06-540e-cde8-ed1ce772aeb4@proxmox.com>
2022-01-19 14:31 ` Fabian Grünbichler
2022-01-05 10:50 ` Fabian Ebner
2021-12-22 13:52 ` [pve-devel] [PATCH v3 proxmox-websocket-tunnel 1/4] initial commit Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 proxmox-websocket-tunnel 2/4] add tunnel implementation Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 proxmox-websocket-tunnel 3/4] add fingerprint validation Fabian Grünbichler
2022-01-04 11:37 ` Fabian Ebner
2022-01-19 10:34 ` Fabian Grünbichler
2022-01-19 12:16 ` Fabian Ebner
2022-01-19 12:53 ` Josef Johansson
2021-12-22 13:52 ` [pve-devel] [PATCH v3 proxmox-websocket-tunnel 4/4] add packaging Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 qemu-server 01/10] refactor map_storage to map_id Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 qemu-server 02/10] schema: use pve-bridge-id Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 qemu-server 03/10] parse_config: optional strict mode Fabian Grünbichler
2022-01-04 11:57 ` Fabian Ebner
2021-12-22 13:52 ` [pve-devel] [PATCH v3 qemu-server 04/10] update_vm: allow simultaneous setting of boot-order and dev Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 qemu-server 05/10] nbd alloc helper: allow passing in explicit format Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 qemu-server 06/10] migrate: move tunnel-helpers to pve-guest-common Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 qemu-server 07/10] mtunnel: add API endpoints Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 qemu-server 08/10] migrate: refactor remote VM/tunnel start Fabian Grünbichler
2021-12-22 13:52 ` Fabian Grünbichler [this message]
2022-01-04 13:58 ` [pve-devel] [PATCH v3 qemu-server 09/10] migrate: add remote migration handling Fabian Ebner
2022-01-04 16:44 ` Roland
2022-01-11 8:19 ` Thomas Lamprecht
[not found] ` <<554040de-09d6-974b-143a-80c2d66b9573@proxmox.com>
2022-01-19 14:32 ` Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 qemu-server 10/10] api: add remote migrate endpoint Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 storage 1/4] volname_for_storage: parse volname before calling Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 storage 2/4] storage_migrate: pull out snapshot decision Fabian Grünbichler
2022-01-05 9:00 ` Fabian Ebner
2022-01-19 14:38 ` Fabian Grünbichler
2021-12-22 13:52 ` [pve-devel] [PATCH v3 storage 3/4] storage_migrate: pull out import/export_prepare Fabian Grünbichler
2022-01-05 9:59 ` Fabian Ebner
2021-12-22 13:52 ` [pve-devel] [PATCH v3 storage 4/4] add volume_import/export_start helpers Fabian Grünbichler
2021-12-23 13:56 ` [pve-devel] [PATCH v3 qemu-server++ 0/21] remote migration Fabian Grünbichler
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20211222135257.3242938-17-f.gruenbichler@proxmox.com \
--to=f.gruenbichler@proxmox.com \
--cc=pve-devel@lists.proxmox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox