[pve-devel] [RFC qemu-server 17/23] backup: implement backup for external providers

[Fiona Ebner <f.ebner@proxmox.com>]

The state of the VM's disk images at the time the backup is started
is preserved via a snapshot-access block node. Old data is moved to
the fleecing image when new guest writes come in. The snapshot-access
block node, as well as the associated bitmap in case of incremental
backup, will be exported via NBD to the external provider.

The provider can indicate that it wants to do an incremental backup by
returning the bitmap ID that was used for a previous backup and it
will then be told if the bitmap was newly created (either first backup
or old bitmap was invalid) or if the bitmap can be reused.

The provider then reads the parts of the NBD image it needs, either
the full disk for full backup, or the dirty parts according to the
bitmap for incremental backup. The bitmap has to be respected, reads
to other parts of the image will return an error. After backing up
each part of the disk, it should be discarded in the export to avoid
unnecessary space usage in the fleecing image (requires the storage
underlying the fleecing image to support discard too).

Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
---
 PVE/VZDump/QemuServer.pm | 176 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 176 insertions(+)

diff --git a/PVE/VZDump/QemuServer.pm b/PVE/VZDump/QemuServer.pm
index a138ebcf..7141d9e4 100644
--- a/PVE/VZDump/QemuServer.pm
+++ b/PVE/VZDump/QemuServer.pm
@@ -277,6 +277,8 @@ sub archive {
 
     if ($self->{vzdump}->{opts}->{pbs}) {
 	$self->archive_pbs($task, $vmid);
+    } elsif ($self->{vzdump}->{'backup-provider'}) {
+	$self->archive_external($task, $vmid);
     } else {
 	$self->archive_vma($task, $vmid, $filename, $comp);
     }
@@ -1122,6 +1124,23 @@ sub cleanup {
 
     # If VM was started only for backup, it is already stopped now.
     if (PVE::QemuServer::Helpers::vm_running_locally($vmid)) {
+	if ($task->{cleanup}->{'nbd-stop'}) {
+	    eval { PVE::QemuServer::QMPHelpers::nbd_stop($vmid); };
+	    $self->logerr($@) if $@;
+	}
+
+	if (my $info = $task->{cleanup}->{'backup-access-teardown'}) {
+	    my $params = {
+		'target-id' => $info->{'target-id'},
+		timeout => 60,
+		success => $info->{success} ? JSON::true : JSON::false,
+	    };
+
+	    $self->loginfo("tearing down backup-access");
+	    eval { mon_cmd($vmid, "backup-access-teardown", $params->%*) };
+	    $self->logerr($@) if $@;
+	}
+
 	$detach_tpmstate_drive->($task, $vmid);
 	detach_fleecing_images($task->{disks}, $vmid) if $task->{'use-fleecing'};
     }
@@ -1133,4 +1152,161 @@ sub cleanup {
     }
 }
 
+sub archive_external {
+    my ($self, $task, $vmid) = @_;
+
+    my $config_file = "$task->{tmpdir}/qemu-server.conf";
+    my $firewall_file = "$task->{tmpdir}/qemu-server.fw";
+
+    my $opts = $self->{vzdump}->{opts};
+
+    my $backup_provider = $self->{vzdump}->{'backup-provider'};
+
+    $self->loginfo("starting external backup via " . $backup_provider->provider_name());
+
+    $backup_provider->backup_guest_config($vmid, $config_file);
+    $backup_provider->backup_firewall_config($vmid, $firewall_file) if -e $firewall_file;
+
+    my $starttime = time();
+
+    # get list early so we die on unkown drive types before doing anything
+    my $devlist = _get_task_devlist($task);
+
+    $self->enforce_vm_running_for_backup($vmid);
+    $self->{qmeventd_fh} = PVE::QemuServer::register_qmeventd_handle($vmid);
+
+    eval {
+	$SIG{INT} = $SIG{TERM} = $SIG{QUIT} = $SIG{HUP} = $SIG{PIPE} = sub {
+	    die "interrupted by signal\n";
+	};
+
+	my $qemu_support = mon_cmd($vmid, "query-proxmox-support");
+
+	$attach_tpmstate_drive->($self, $task, $vmid);
+
+	my $is_template = PVE::QemuConfig->is_template($self->{vmlist}->{$vmid});
+
+	my $fleecing = check_and_prepare_fleecing(
+	    $self, $vmid, $opts->{fleecing}, $task->{disks}, $is_template, $qemu_support, 1);
+	die "cannot setup backup access without fleecing\n" if !$fleecing;
+
+	$task->{'use-fleecing'} = 1;
+
+	my $fs_frozen = $self->qga_fs_freeze($task, $vmid);
+
+	my $target_id = $opts->{storage};
+
+	my $params = {
+	    'target-id' => $target_id,
+	    devlist => $devlist,
+	    timeout => 60,
+	};
+
+	my ($mechanism, $bitmap_name) = $backup_provider->backup_get_mechanism($vmid, 'qemu');
+	die "mechanism '$mechanism' requested by backup provider is not supported for VMs\n"
+	    if $mechanism ne 'nbd';
+
+	if ($bitmap_name) {
+	    # prepend storage ID so different providers can never cause clashes
+	    $bitmap_name = "$opts->{storage}-" . $bitmap_name;
+	    $params->{'bitmap-name'} = $bitmap_name;
+	}
+
+	$self->loginfo("setting up snapshot-access for backup");
+
+	my $backup_access_info = eval { mon_cmd($vmid, "backup-access-setup", $params->%*) };
+	my $qmperr = $@;
+
+	$task->{cleanup}->{'backup-access-teardown'} = { 'target-id' => $target_id, success => 0 };
+
+	if ($fs_frozen) {
+	    $self->qga_fs_thaw($vmid);
+	}
+
+	die $qmperr if $qmperr;
+
+	$self->resume_vm_after_job_start($task, $vmid);
+
+	my $bitmap_info = mon_cmd($vmid, 'query-pbs-bitmap-info');
+	for my $info (sort { $a->{drive} cmp $b->{drive} } $bitmap_info->@*) {
+	    my $text = $bitmap_action_to_human->($self, $info);
+	    my $drive = $info->{drive};
+	    $drive =~ s/^drive-//; # for consistency
+	    $self->loginfo("$drive: dirty-bitmap status: $text");
+	}
+
+	$self->loginfo("starting NBD server");
+
+	my $nbd_path = "/run/qemu-server/$vmid\_nbd.backup_access";
+	mon_cmd(
+	    $vmid, "nbd-server-start", addr => { type => 'unix', data => { path => $nbd_path } } );
+	$task->{cleanup}->{'nbd-stop'} = 1;
+
+	for my $info ($backup_access_info->@*) {
+	    $self->loginfo("adding NBD export for $info->{device}");
+
+	    my $export_params = {
+		id => $info->{device},
+		'node-name' => $info->{'node-name'},
+		writable => JSON::true, # for discard
+		type => "nbd",
+		name => $info->{device}, # NBD export name
+	    };
+
+	    if ($info->{'bitmap-name'}) {
+		$export_params->{bitmaps} = [{
+		    node => $info->{'bitmap-node-name'},
+		    name => $info->{'bitmap-name'},
+		}],
+	    }
+
+	    mon_cmd($vmid, "block-export-add", $export_params->%*);
+	}
+
+	for my $info ($backup_access_info->@*) {
+	    $self->loginfo("starting external backup for '$info->{device}'");
+
+	    my $bitmap_status = 'none';
+	    my $bitmap_name;
+	    if (my $bitmap_action = $info->{'bitmap-action'}) {
+		my $bitmap_action_to_status = {
+		    'not-used' => 'none',
+		    'not-used-removed' => 'none',
+		    'new' => 'new',
+		    'used' => 'reuse',
+		    'invalid' => 'new',
+		};
+
+		$bitmap_status = $bitmap_action_to_status->{$bitmap_action}
+		    or die "got unexpected bitmap action '$bitmap_action'\n";
+
+		$bitmap_name = $info->{'bitmap-name'} or die "bitmap-name is not present\n";
+	    }
+
+	    $backup_provider->backup_nbd(
+		$vmid,
+		$info->{device},
+		$nbd_path,
+		$bitmap_status,
+		$bitmap_name,
+		$opts->{bwlimit} * 1024,
+	    );
+
+	    $self->loginfo("backup for '$info->{device}' done");
+	}
+    };
+    my $err = $@;
+
+    if ($err) {
+	$self->logerr($err);
+	$self->resume_vm_after_job_start($task, $vmid);
+    } else {
+	$task->{size} = $backup_provider->backup_get_task_size($vmid);
+	$task->{cleanup}->{'backup-access-teardown'}->{success} = 1;
+    }
+    $self->restore_vm_power_state($vmid);
+
+    die $err if $err;
+}
+
 1;
-- 
2.39.2



_______________________________________________
pve-devel mailing list
pve-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pve-devel