qemu-server: add support for unsecure migration (setting in datacenter.cfg)

This patch adds support for unsecure migration using a direct tcp connection
KVM <=> KVM instead of an extra SSH tunnel. Without ssh the limit is just the
bandwith and no longer the CPU / one single core.

You can enable this by adding:
migration_unsecure: 1
to datacenter.cfg

Examples using qemu 1.4 as migration with qemu 1.3 still does not work for me:

current default with SSH Tunnel VM uses 2GB mem:
Dec 27 21:10:32 starting migration of VM 105 to node 'cloud1-1202' (10.255.0.20)
Dec 27 21:10:32 copying disk images
Dec 27 21:10:32 starting VM 105 on remote node 'cloud1-1202'
Dec 27 21:10:35 starting ssh migration tunnel
Dec 27 21:10:36 starting online/live migration on localhost:60000
Dec 27 21:10:36 migrate_set_speed: 8589934592
Dec 27 21:10:36 migrate_set_downtime: 1
Dec 27 21:10:38 migration status: active (transferred 152481002, remaining 1938546688), total 2156396544) , expected downtime 0
Dec 27 21:10:40 migration status: active (transferred 279836995, remaining 1811140608), total 2156396544) , expected downtime 0
Dec 27 21:10:42 migration status: active (transferred 421265271, remaining 1669840896), total 2156396544) , expected downtime 0
Dec 27 21:10:44 migration status: active (transferred 570987974, remaining 1520152576), total 2156396544) , expected downtime 0
Dec 27 21:10:46 migration status: active (transferred 721469404, remaining 1369939968), total 2156396544) , expected downtime 0
Dec 27 21:10:48 migration status: active (transferred 875595258, remaining 1216057344), total 2156396544) , expected downtime 0
Dec 27 21:10:50 migration status: active (transferred 1034654822, remaining 1056931840), total 2156396544) , expected downtime 0
Dec 27 21:10:54 migration status: active (transferred 1176288424, remaining 915369984), total 2156396544) , expected downtime 0
Dec 27 21:10:56 migration status: active (transferred 1339734759, remaining 752050176), total 2156396544) , expected downtime 0
Dec 27 21:10:58 migration status: active (transferred 1503743261, remaining 588206080), total 2156396544) , expected downtime 0
Dec 27 21:11:02 migration status: active (transferred 1645097827, remaining 446906368), total 2156396544) , expected downtime 0
Dec 27 21:11:04 migration status: active (transferred 1810562934, remaining 281751552), total 2156396544) , expected downtime 0
Dec 27 21:11:06 migration status: active (transferred 1964377505, remaining 126033920), total 2156396544) , expected downtime 0
Dec 27 21:11:08 migration status: active (transferred 2077930417, remaining 0), total 2156396544) , expected downtime 0
Dec 27 21:11:09 migration speed: 62.06 MB/s - downtime 37 ms
Dec 27 21:11:09 migration status: completed
Dec 27 21:11:13 migration finished successfuly (duration 00:00:41)
TASK OK

with unsecure migration without SSH Tunnel:
Dec 27 22:43:14 starting migration of VM 105 to node 'cloud1-1203' (10.255.0.22)
Dec 27 22:43:14 copying disk images
Dec 27 22:43:14 starting VM 105 on remote node 'cloud1-1203'
Dec 27 22:43:17 starting online/live migration on 10.255.0.22:60000
Dec 27 22:43:17 migrate_set_speed: 8589934592
Dec 27 22:43:17 migrate_set_downtime: 1
Dec 27 22:43:19 migration speed: 1024.00 MB/s - downtime 1100 ms
Dec 27 22:43:19 migration status: completed
Dec 27 22:43:22 migration finished successfuly (duration 00:00:09)
TASK OK

diff --git a/PVE/QemuMigrate.pm b/PVE/QemuMigrate.pm
index 01d4185532e325a6d28e1fbd7fe8e98e94297591..0c0f3c83e4dc31200a57ce25648061d0fd04eedf 100644 (file)
--- a/PVE/QemuMigrate.pm
+++ b/PVE/QemuMigrate.pm
@@ -76,7 +76,9 @@ sub finish_command_pipe {
 sub fork_tunnel {
     my ($self, $nodeip, $lport, $rport) = @_;
 
-    my $cmd = [@{$self->{rem_ssh}}, '-L', "$lport:localhost:$rport",
+    my @localtunnelinfo = (defined $lport) ? qw(-L $lport:localhost:$rport) : ();
+
+    my $cmd = [@{$self->{rem_ssh}}, @localtunnelinfo,
               'qm', 'mtunnel' ];
 
     my $tunnel = $self->fork_command_pipe($cmd);
@@ -307,8 +309,8 @@ sub phase2 {
 
     $self->log('info', "starting VM $vmid on remote node '$self->{node}'");
 
+    my $raddr;
     my $rport;
-
     my $nodename = PVE::INotify::nodename();
 
     ## start on remote node
@@ -333,9 +335,15 @@ sub phase2 {
     PVE::Tools::run_command($cmd, input => $spice_ticket, outfunc => sub {
        my $line = shift;
 
-       if ($line =~ m/^migration listens on port (\d+)$/) {
+       if ($line =~ m/^migration listens on tcp:([\d\.]+|localhost):(\d+)$/) {
+           $raddr = $1;
+           $rport = int($2);
+       }
+       elsif ($line =~ m/^migration listens on port (\d+)$/) {
+           $raddr = "localhost";
            $rport = int($1);
-       }elsif ($line =~ m/^spice listens on port (\d+)$/) {
+       }
+        elsif ($line =~ m/^spice listens on port (\d+)$/) {
            $spice_port = int($1);
        }
     }, errfunc => sub {
@@ -343,18 +351,16 @@ sub phase2 {
        $self->log('info', $line);
     });
 
-    die "unable to detect remote migration port\n" if !$rport;
-
-    $self->log('info', "starting migration tunnel");
+    die "unable to detect remote migration address\n" if !$raddr;
 
     ## create tunnel to remote port
-    my $lport = PVE::Tools::next_migrate_port();
+    $self->log('info', "starting ssh migration tunnel");
+    my $lport = ($raddr eq "localhost") ? PVE::Tools::next_migrate_port() : undef;
     $self->{tunnel} = $self->fork_tunnel($self->{nodeip}, $lport, $rport);
 
-    $self->log('info', "starting online/live migration on port $lport");
-    # start migration
-
     my $start = time();
+    $self->log('info', "starting online/live migration on $raddr:$rport");
+    $self->{livemigration} = 1;
 
     # load_defaults
     my $defaults = PVE::QemuServer::load_defaults();
@@ -415,9 +421,10 @@ sub phase2 {
     }
 
     eval {
-        PVE::QemuServer::vm_mon_cmd_nocheck($vmid, "migrate", uri => "tcp:localhost:$lport");
+        PVE::QemuServer::vm_mon_cmd_nocheck($vmid, "migrate", uri => "tcp:$raddr:$rport");
     };
     my $merr = $@;
+    $self->log('info', "migrate uri => tcp:$raddr:$rport failed: $merr") if $merr;
 
     my $lstat = 0;
     my $usleep = 2000000;
@@ -569,8 +576,8 @@ sub phase3_cleanup {
     die "Failed to move config to node '$self->{node}' - rename failed: $!\n"
         if !rename($conffile, $newconffile);
 
-    # now that config file is move, we can resume vm on target if livemigrate
-    if ($self->{tunnel}) {
+    if ($self->{livemigration}) {
+       # now that config file is move, we can resume vm on target if livemigrate
        my $cmd = [@{$self->{rem_ssh}}, 'qm', 'resume', $vmid, '--skiplock'];
        eval{ PVE::Tools::run_command($cmd, outfunc => sub {}, 
                errfunc => sub {

diff --git a/PVE/QemuServer.pm b/PVE/QemuServer.pm
index c5bd44433df0438ce3df893375d175b286523352..e3fee94b986abec204e22b5b9297fe8de34e2fcf 100644 (file)
--- a/PVE/QemuServer.pm
+++ b/PVE/QemuServer.pm
@@ -3053,11 +3053,17 @@ sub vm_start {
        my ($cmd, $vollist, $spice_port) = config_to_command($storecfg, $vmid, $conf, $defaults, $forcemachine);
 
        my $migrate_port = 0;
-
+       my $migrate_uri;
        if ($statefile) {
            if ($statefile eq 'tcp') {
+               my $localip = "localhost";
+               my $datacenterconf = PVE::Cluster::cfs_read_file('datacenter.cfg');
+               if ($datacenterconf->{migration_unsecure}) {
+                       my $nodename = PVE::INotify::nodename();
+                       $localip = PVE::Cluster::remote_node_ip($nodename, 1);
+               }
                $migrate_port = PVE::Tools::next_migrate_port();
-               my $migrate_uri = "tcp:localhost:${migrate_port}";
+               $migrate_uri = "tcp:${localip}:${migrate_port}";
                push @$cmd, '-incoming', $migrate_uri;
                push @$cmd, '-S';
            } else {
@@ -3085,7 +3091,7 @@ sub vm_start {
        my $err = $@;
        die "start failed: $err" if $err;
 
-       print "migration listens on port $migrate_port\n" if $migrate_port;
+       print "migration listens on $migrate_uri\n" if $migrate_uri;
 
        if ($statefile && $statefile ne 'tcp')  {
            eval { vm_mon_cmd_nocheck($vmid, "cont"); };