[pve-devel] [PATCH v4 qemu-server 11/11] qcow2: add external snapshot support

[Alexandre Derumier via pve-devel <pve-devel@lists.proxmox.com>]

[-- Attachment #1: Type: message/rfc822, Size: 15743 bytes --]

From: Alexandre Derumier <alexandre.derumier@groupe-cyllene.com>
To: pve-devel@lists.proxmox.com
Subject: [PATCH v4 qemu-server 11/11] qcow2: add external snapshot support
Date: Tue, 11 Mar 2025 11:29:05 +0100
Message-ID: <20250311102905.2680524-18-alexandre.derumier@groupe-cyllene.com>

Signed-off-by: Alexandre Derumier <alexandre.derumier@groupe-cyllene.com>
---
 PVE/QemuConfig.pm       |   4 +-
 PVE/QemuServer.pm       | 226 +++++++++++++++++++++++++++++++++++++---
 PVE/QemuServer/Drive.pm |   4 +
 3 files changed, 220 insertions(+), 14 deletions(-)

diff --git a/PVE/QemuConfig.pm b/PVE/QemuConfig.pm
index b60cc398..2b3acb15 100644
--- a/PVE/QemuConfig.pm
+++ b/PVE/QemuConfig.pm
@@ -377,7 +377,7 @@ sub __snapshot_create_vol_snapshot {
 
     print "snapshotting '$device' ($drive->{file})\n";
 
-    PVE::QemuServer::qemu_volume_snapshot($vmid, $device, $storecfg, $volid, $snapname);
+    PVE::QemuServer::qemu_volume_snapshot($vmid, $device, $storecfg, $drive, $snapname);
 }
 
 sub __snapshot_delete_remove_drive {
@@ -414,7 +414,7 @@ sub __snapshot_delete_vol_snapshot {
     my $storecfg = PVE::Storage::config();
     my $volid = $drive->{file};
 
-    PVE::QemuServer::qemu_volume_snapshot_delete($vmid, $storecfg, $volid, $snapname);
+    PVE::QemuServer::qemu_volume_snapshot_delete($vmid, $storecfg, $drive, $snapname);
 
     push @$unused, $volid;
 }
diff --git a/PVE/QemuServer.pm b/PVE/QemuServer.pm
index 60481acc..6ce3e9c6 100644
--- a/PVE/QemuServer.pm
+++ b/PVE/QemuServer.pm
@@ -4449,20 +4449,200 @@ sub qemu_block_resize {
 }
 
 sub qemu_volume_snapshot {
-    my ($vmid, $deviceid, $storecfg, $volid, $snap) = @_;
+    my ($vmid, $deviceid, $storecfg, $drive, $snap) = @_;
 
+    my $volid = $drive->{file};
     my $running = check_running($vmid);
-
-    if ($running && do_snapshots_with_qemu($storecfg, $volid, $deviceid)) {
-	mon_cmd($vmid, 'blockdev-snapshot-internal-sync', device => $deviceid, name => $snap);
+    my $do_snapshots_with_qemu = do_snapshots_with_qemu($storecfg, $volid, $deviceid) if $running;
+    if ($do_snapshots_with_qemu) {
+	if($do_snapshots_with_qemu == 2) {
+	    my $snapshots = PVE::Storage::volume_snapshot_info($storecfg, $volid);
+	    my $parent_snap = $snapshots->{'current'}->{parent};
+	    my $size = PVE::Storage::volume_size_info($storecfg, $volid, 5);
+	    blockdev_rename($storecfg, $vmid, $deviceid, $drive, 'current', $snap, $parent_snap);
+	    blockdev_external_snapshot($storecfg, $vmid, $deviceid, $drive, $snap, $size);
+	} else {
+	    mon_cmd($vmid, 'blockdev-snapshot-internal-sync', device => $deviceid, name => $snap);
+	}
     } else {
 	PVE::Storage::volume_snapshot($storecfg, $volid, $snap);
     }
 }
 
+sub blockdev_external_snapshot {
+    my ($storecfg, $vmid, $deviceid, $drive, $snap, $size) = @_;
+
+    my $volid = $drive->{file};
+
+    #be sure to add drive in write mode
+    delete($drive->{ro});
+
+    my $new_file_blockdev = generate_file_blockdev($storecfg, $drive);
+    my $new_fmt_blockdev = generate_format_blockdev($storecfg, $drive, $new_file_blockdev);
+
+    my $snap_file_blockdev = generate_file_blockdev($storecfg, $drive, $snap);
+    my $snap_fmt_blockdev = generate_format_blockdev($storecfg, $drive, $snap_file_blockdev, $snap);
+
+    #preallocate add a new current file with reference to backing-file
+    my ($storeid, $volname) = PVE::Storage::parse_volume_id($volid);
+    my $name = (PVE::Storage::parse_volname($storecfg, $volid))[1];
+    PVE::Storage::vdisk_alloc($storecfg, $storeid, $vmid, 'qcow2', $name, $size/1024, $snap_file_blockdev->{filename});
+
+    #backing need to be forced to undef in blockdev, to avoid reopen of backing-file on blockdev-add
+    $new_fmt_blockdev->{backing} = undef;
+
+    PVE::QemuServer::Monitor::mon_cmd($vmid, 'blockdev-add', %$new_fmt_blockdev);
+
+    mon_cmd($vmid, 'blockdev-snapshot', node => $snap_fmt_blockdev->{'node-name'}, overlay => $new_fmt_blockdev->{'node-name'});
+}
+
+sub blockdev_delete {
+    my ($storecfg, $vmid, $drive, $file_blockdev, $fmt_blockdev) = @_;
+
+    #add eval as reopen is auto removing the old nodename automatically only if it was created at vm start in command line argument
+    eval { mon_cmd($vmid, 'blockdev-del', 'node-name' => $file_blockdev->{'node-name'}) };
+    eval { mon_cmd($vmid, 'blockdev-del', 'node-name' => $fmt_blockdev->{'node-name'}) };
+
+    #delete the file (don't use vdisk_free as we don't want to delete all snapshot chain)
+    print"delete old $file_blockdev->{filename}\n";
+
+    my $storage_name = PVE::Storage::parse_volume_id($drive->{file});
+    my $scfg = $storecfg->{ids}->{$storage_name};
+    if ($scfg->{type} eq 'lvm') {
+	PVE::Storage::LVMPlugin::lvremove($file_blockdev->{filename});
+    } else {
+	unlink($file_blockdev->{filename});
+    }
+}
+
+sub blockdev_rename {
+    my ($storecfg, $vmid, $deviceid, $drive, $src_snap, $target_snap, $parent_snap) = @_;
+
+    print "rename $src_snap to $target_snap\n";
+
+    my $volid = $drive->{file};
+
+    my $src_file_blockdev = generate_file_blockdev($storecfg, $drive, $src_snap);
+    my $src_fmt_blockdev = generate_format_blockdev($storecfg, $drive, $src_file_blockdev, $src_snap);
+    my $target_file_blockdev = generate_file_blockdev($storecfg, $drive, $target_snap);
+    my $target_fmt_blockdev = generate_format_blockdev($storecfg, $drive, $target_file_blockdev, $target_snap);
+
+    #create a hardlink
+    link($src_file_blockdev->{filename}, $target_file_blockdev->{filename});
+
+    if($target_snap eq 'current' || $src_snap eq 'current') {
+	#rename from|to current
+
+	#add backing to target
+	if ($parent_snap) {
+	    my $parent_fmt_nodename = encode_nodename('fmt', $volid, $parent_snap);
+	    $target_fmt_blockdev->{backing} = $parent_fmt_nodename;
+	}
+	PVE::QemuServer::Monitor::mon_cmd($vmid, 'blockdev-add', %$target_fmt_blockdev);
+
+	#reopen the current throttlefilter nodename with the target fmt nodename
+	my $drive_blockdev = generate_drive_blockdev($storecfg, $vmid, $drive);
+	delete $drive_blockdev->{file};
+	$drive_blockdev->{file} = $target_fmt_blockdev->{'node-name'};
+	PVE::QemuServer::Monitor::mon_cmd($vmid, 'blockdev-reopen', options => [$drive_blockdev]);
+    } else {
+	#intermediate snapshot
+	PVE::QemuServer::Monitor::mon_cmd($vmid, 'blockdev-add', %$target_fmt_blockdev);
+
+	#reopen the parent node with the new target fmt backing node
+	my $parent_file_blockdev = generate_file_blockdev($storecfg, $drive, $parent_snap);
+	my $parent_fmt_blockdev = generate_format_blockdev($storecfg, $drive, $parent_file_blockdev, $parent_snap);
+	$parent_fmt_blockdev->{backing} = $target_fmt_blockdev->{'node-name'};
+	PVE::QemuServer::Monitor::mon_cmd($vmid, 'blockdev-reopen', options => [$parent_fmt_blockdev]);
+
+	#change backing-file in qcow2 metadatas
+	PVE::QemuServer::Monitor::mon_cmd($vmid, 'change-backing-file', device => $deviceid, 'image-node-name' => $parent_fmt_blockdev->{'node-name'}, 'backing-file' => $target_file_blockdev->{filename});
+    }
+
+    # delete old file|fmt nodes
+    # add eval as reopen is auto removing the old nodename automatically only if it was created at vm start in command line argument
+    eval { PVE::QemuServer::Monitor::mon_cmd($vmid, 'blockdev-del', 'node-name' => $src_file_blockdev->{'node-name'})};
+    eval { PVE::QemuServer::Monitor::mon_cmd($vmid, 'blockdev-del', 'node-name' => $src_fmt_blockdev->{'node-name'})};
+
+    unlink($src_file_blockdev->{filename});
+
+    #rename underlay
+    my $storage_name = PVE::Storage::parse_volume_id($volid);
+    my $scfg = $storecfg->{ids}->{$storage_name};
+    return if $scfg->{type} ne 'lvm';
+
+    print "rename underlay lvm volume $src_file_blockdev->{filename} to $target_file_blockdev->{filename}\n";
+    PVE::Storage::LVMPlugin::lvrename(undef, $src_file_blockdev->{filename}, $target_file_blockdev->{filename});
+}
+
+sub blockdev_commit {
+    my ($storecfg, $vmid, $deviceid, $drive, $src_snap, $target_snap) = @_;
+
+    my $volid = $drive->{file};
+
+    print "block-commit $src_snap to base:$target_snap\n";
+    $src_snap = undef if $src_snap && $src_snap eq 'current';
+
+    my $target_file_blockdev = generate_file_blockdev($storecfg, $drive, $target_snap);
+    my $target_fmt_blockdev = generate_format_blockdev($storecfg, $drive, $target_file_blockdev, $target_snap);
+
+    my $src_file_blockdev = generate_file_blockdev($storecfg, $drive, $src_snap);
+    my $src_fmt_blockdev = generate_format_blockdev($storecfg, $drive, $src_file_blockdev, $src_snap);
+
+    my $job_id = "commit-$deviceid";
+    my $jobs = {};
+    my $opts = { 'job-id' => $job_id, device => $deviceid };
+
+    my $complete = undef;
+    if ($src_snap) {
+	$complete = 'auto';
+	$opts->{'top-node'} = $src_fmt_blockdev->{'node-name'};
+	$opts->{'base-node'} = $target_fmt_blockdev->{'node-name'};
+    } else {
+	$complete = 'complete';
+	$opts->{'base-node'} = $target_fmt_blockdev->{'node-name'};
+	$opts->{replaces} = $src_fmt_blockdev->{'node-name'};
+    }
+
+    mon_cmd($vmid, "block-commit", %$opts);
+    $jobs->{$job_id} = {};
+    qemu_drive_mirror_monitor ($vmid, undef, $jobs, $complete, 0, 'commit');
+
+    blockdev_delete($storecfg, $vmid, $drive, $src_file_blockdev, $src_fmt_blockdev);
+}
+
+sub blockdev_stream {
+    my ($storecfg, $vmid, $deviceid, $drive, $snap, $parent_snap, $target_snap) = @_;
+
+    my $volid = $drive->{file};
+    $target_snap = undef if $target_snap eq 'current';
+
+    my $parent_file_blockdev = generate_file_blockdev($storecfg, $drive, $parent_snap);
+    my $parent_fmt_blockdev = generate_format_blockdev($storecfg, $drive, $parent_file_blockdev, $parent_snap);
+
+    my $target_file_blockdev = generate_file_blockdev($storecfg, $drive, $target_snap);
+    my $target_fmt_blockdev = generate_format_blockdev($storecfg, $drive, $target_file_blockdev, $target_snap);
+
+    my $snap_file_blockdev = generate_file_blockdev($storecfg, $drive, $snap);
+    my $snap_fmt_blockdev = generate_format_blockdev($storecfg, $drive, $snap_file_blockdev, $snap);
+
+    my $job_id = "stream-$deviceid";
+    my $jobs = {};
+    my $options = { 'job-id' => $job_id, device => $target_fmt_blockdev->{'node-name'} };
+    $options->{'base-node'} = $parent_fmt_blockdev->{'node-name'};
+    $options->{'backing-file'} = $parent_file_blockdev->{filename};
+
+    mon_cmd($vmid, 'block-stream', %$options);
+    $jobs->{$job_id} = {};
+    qemu_drive_mirror_monitor($vmid, undef, $jobs, 'auto', 0, 'stream');
+
+    blockdev_delete($storecfg, $vmid, $drive, $snap_file_blockdev, $snap_fmt_blockdev);
+}
+
 sub qemu_volume_snapshot_delete {
-    my ($vmid, $storecfg, $volid, $snap) = @_;
+    my ($vmid, $storecfg, $drive, $snap) = @_;
 
+    my $volid = $drive->{file};
     my $running = check_running($vmid);
     my $attached_deviceid;
 
@@ -4474,13 +4654,35 @@ sub qemu_volume_snapshot_delete {
 	});
     }
 
-    if ($attached_deviceid && do_snapshots_with_qemu($storecfg, $volid, $attached_deviceid)) {
-	mon_cmd(
-	    $vmid,
-	    'blockdev-snapshot-delete-internal-sync',
-	    device => $attached_deviceid,
-	    name => $snap,
-	);
+    my $do_snapshots_with_qemu = do_snapshots_with_qemu($storecfg, $volid, $attached_deviceid) if $running;
+    if ($attached_deviceid && $do_snapshots_with_qemu) {
+
+	if ($do_snapshots_with_qemu == 2) {
+
+	    my $path = PVE::Storage::path($storecfg, $volid);
+	    my $snapshots = PVE::Storage::volume_snapshot_info($storecfg, $volid);
+	    my $parentsnap = $snapshots->{$snap}->{parent};
+	    my $childsnap = $snapshots->{$snap}->{child};
+
+	    # if we delete the first snasphot, we commit because the first snapshot original base image, it should be big.
+            # improve-me: if firstsnap > child : commit, if firstsnap < child do a stream.
+	    if(!$parentsnap) {
+		print"delete first snapshot $snap\n";
+		blockdev_commit($storecfg, $vmid, $attached_deviceid, $drive, $childsnap, $snap);
+		blockdev_rename($storecfg, $vmid, $attached_deviceid, $drive, $snap, $childsnap, $snapshots->{$childsnap}->{child});
+	    } else {
+		#intermediate snapshot, we always stream the snapshot to child snapshot
+		print"stream intermediate snapshot $snap to $childsnap\n";
+		blockdev_stream($storecfg, $vmid, $attached_deviceid, $drive, $snap, $parentsnap, $childsnap);
+	    }
+	} else {
+	    mon_cmd(
+	        $vmid,
+		'blockdev-snapshot-delete-internal-sync',
+		device => $attached_deviceid,
+		name => $snap,
+	    );
+	}
     } else {
 	PVE::Storage::volume_snapshot_delete(
 	    $storecfg, $volid, $snap, $attached_deviceid ? 1 : undef);
diff --git a/PVE/QemuServer/Drive.pm b/PVE/QemuServer/Drive.pm
index 51513546..7ba401bd 100644
--- a/PVE/QemuServer/Drive.pm
+++ b/PVE/QemuServer/Drive.pm
@@ -1117,6 +1117,8 @@ sub print_drive_throttle_group {
 sub generate_file_blockdev {
     my ($storecfg, $drive, $snap, $nodename) = @_;
 
+    $snap = undef if $snap && $snap eq 'current';
+
     my $volid = $drive->{file};
     my $blockdev = {};
 
@@ -1260,6 +1262,8 @@ sub do_snapshots_with_qemu {
 sub generate_format_blockdev {
     my ($storecfg, $drive, $file, $snap, $nodename) = @_;
 
+    $snap = undef if $snap && $snap eq 'current';
+
     my $volid = $drive->{file};
     die "format_blockdev can't be used for nbd" if $volid =~ /^nbd:/;
 
-- 
2.39.5



[-- Attachment #2: Type: text/plain, Size: 160 bytes --]

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