feat: preserve maintenance machine configs

When a machine has a partial machine config (e.g., `SideroLinkConfig` or `KmsgLogConfig`) while being in maintenance mode, detect and store it on Omni side.

When this machine has a config applied to it (i.e., when it joins to a cluster) or when its config is updated, always preserve these detected configs in addition to the main (`v1alpha1`) config.

This allows machines to join Omni by using partial configs (for example, by using cloud user data) instead of having kernel args for the SideroLink and kernel log sync configuration.

We do not fail in the cases where we are not authorized to access the COSI resource API, as the full access to the resources over SideroLink is only available in Talos v1.6.5 and above.

Modify the Talos upgrade integration tests to apply a partial config during maintenance mode, and later assert that it was preserved through the upgrade/revert flow.

Additionally, bump the default Talos version and the version used in the integration tests to 1.6.6.

Closes #13.

Signed-off-by: Utku Ozdemir <[email protected]>

client/api/omni/specs/omni.proto

@@ -135,6 +135,11 @@ message MachineStatusSpec {
     bool invalid = 2;
   }
 
+  message MaintenanceConfig {
+    // Config is the machine config.
+    string config = 1;
+  }
+
   // Talos version.
   string talos_version = 1;
 
@@ -178,6 +183,8 @@ message MachineStatusSpec {
   map<string, string> image_labels = 13;
 
   Schematic schematic = 14;
+
+  MaintenanceConfig maintenance_config = 15;
 }
 
 // TalosConfigSpec describes a Talos cluster config.

client/pkg/constants/constants.go

@@ -14,7 +14,7 @@ const SecureBoot = "secureboot"
 // DefaultTalosVersion is pre-selected in the UI, default image and used in the integration tests.
 //
 // tsgen:DefaultTalosVersion
-const DefaultTalosVersion = "1.6.4"
+const DefaultTalosVersion = "1.6.6"
 
 const (
 	// TalosRegistry is the default Talos repository URL.

cmd/integration-test/pkg/tests/cluster.go

@@ -33,6 +33,9 @@ import (
 	"github.com/siderolabs/omni/client/pkg/omni/resources/virtual"
 )
 
+// BeforeClusterCreateFunc is a function that is called before a cluster is created.
+type BeforeClusterCreateFunc func(ctx context.Context, t *testing.T, cli *client.Client, machineIDs []resource.ID)
+
 // ClusterOptions are the options for cluster creation.
 //
 //nolint:govet
@@ -48,6 +51,8 @@ type ClusterOptions struct {
 	EtcdBackup             *specs.EtcdBackupConf
 
 	MachineOptions MachineOptions
+
+	BeforeClusterCreateFunc BeforeClusterCreateFunc
 }
 
 // MachineOptions are the options for machine creation.
@@ -68,6 +73,10 @@ func CreateCluster(testCtx context.Context, cli *client.Client, options ClusterO
 		pickUnallocatedMachines(ctx, t, st, options.ControlPlanes+options.Workers, func(machineIDs []resource.ID) {
 			checkExtensionWithRetries(ctx, t, cli, HelloWorldServiceExtensionName, machineIDs...)
 
+			if options.BeforeClusterCreateFunc != nil {
+				options.BeforeClusterCreateFunc(ctx, t, cli, machineIDs)
+			}
+
 			cluster := omni.NewCluster(resources.DefaultNamespace, options.Name)
 			cluster.TypedSpec().Value.TalosVersion = options.MachineOptions.TalosVersion
 			cluster.TypedSpec().Value.KubernetesVersion = options.MachineOptions.KubernetesVersion