feat: introduce talos.exp.wipe kernel param to wipe system disk

Fixes: #4399 Signed-off-by: Artem Chernyshev <[email protected]>
siderolabs · Dec 29, 2021 · da0b36e · da0b36e
1 parent c079eb3
commit da0b36e
Show file tree

Hide file tree

Showing 5 changed files with 38 additions and 0 deletions.
diff --git a/hack/release.toml b/hack/release.toml
@@ -19,6 +19,14 @@ preface = """\
         title = "Component Updates"
         description="""\
 * Linux: 5.15.11
+"""
+
+    [notes.wipe]
+        title = "Wipe System Kernel Parameter"
+        description="""\
+Added new kernel parameter `talos.experimental.wipe=system` which can help resetting system disk for the machine
+and start over with a fresh installation.
+See [Resetting a Machine](https://www.talos.dev/docs/v0.15/guides/resetting-a-machine/#kernel-parameter) on how to use it.
 """
 
 [make_deps]
@@ -34,3 +42,4 @@ preface = """\
     [make_deps.extras]
         variable = "EXTRAS"
         repository = "github.com/talos-systems/extras"
+
diff --git a/internal/app/machined/pkg/runtime/v1alpha1/v1alpha1_sequencer.go b/internal/app/machined/pkg/runtime/v1alpha1/v1alpha1_sequencer.go
@@ -5,9 +5,12 @@
 package v1alpha1
 
 import (
+	"github.com/talos-systems/go-procfs/procfs"
+
 	"github.com/talos-systems/talos/internal/app/machined/pkg/runtime"
 	machineapi "github.com/talos-systems/talos/pkg/machinery/api/machine"
 	"github.com/talos-systems/talos/pkg/machinery/config/types/v1alpha1/machine"
+	"github.com/talos-systems/talos/pkg/machinery/constants"
 )
 
 // Sequencer implements the sequencer interface.
@@ -164,6 +167,11 @@ func (*Sequencer) Install(r runtime.Runtime) []runtime.Phase {
 func (*Sequencer) Boot(r runtime.Runtime) []runtime.Phase {
 	phases := PhaseList{}
 
+	wipe := procfs.ProcCmdline().Get(constants.KernelParamWipe).First()
+	if wipe != nil && *wipe == "system" {
+		return phases.Append("wipeSystemDisk", ResetSystemDisk).Append("reboot", Reboot)
+	}
+
 	phases = phases.AppendWhen(
 		r.State().Platform().Mode() != runtime.ModeContainer,
 		"saveStateEncryptionConfig",

diff --git a/pkg/machinery/constants/constants.go b/pkg/machinery/constants/constants.go
@@ -38,6 +38,10 @@ const (
 	// kernel log delivery destination.
 	KernelParamLoggingKernel = "talos.logging.kernel"
 
+	// KernelParamWipe is the kernel parameter name for specifying the
+	// disk to wipe on the next boot and reboot.
+	KernelParamWipe = "talos.experimental.wipe"
+
 	// BoardNone indicates that the install is not for a specific board.
 	BoardNone = "none"
 

diff --git a/website/content/docs/v0.15/Guides/resetting-a-machine.md b/website/content/docs/v0.15/Guides/resetting-a-machine.md
@@ -7,6 +7,8 @@ From time to time, it may be beneficial to reset a Talos machine to its "origina
 Bear in mind that this is a destructive action for the given machine.
 Doing this means removing the machine from Kubernetes, Etcd (if applicable), and clears any data on the machine that would normally persist a reboot.
 
+## CLI
+
 > WARNING: Running a `talosctl reset` on cloud VM's might result in the VM being unable to boot as this wipes the entire disk.
 It might be more useful to just wipe the `STATE` and `EPHEMERAL` partitions on a cloud VM if not booting via `iPXE`.
 `talosctl reset --system-labels-to-wipe STATE --system-labels-to-wipe EPHEMERAL`
@@ -25,3 +27,11 @@ The `graceful` flag is especially important when considering HA vs. non-HA Talos
 If the machine is part of an HA cluster, a normal, graceful reset should work just fine right out of the box as long as the cluster is in a good state.
 However, if this is a single node cluster being used for testing purposes, a graceful reset is not an option since Etcd cannot be "left" if there is only a single member.
 In this case, reset should be used with `--graceful=false` to skip performing checks that would normally block the reset.
+
+## Kernel Parameter
+
+Another way to reset a machine is to specify `talos.experimental.wipe=system` kernel parameter.
+If the machine got stuck in the boot loop and you access to the console you can use GRUB to specify this kernel argument.
+Then when Talos boots for the next time it will reset system disk and reboot.
+
+Next steps can be to install Talos either using PXE boot or by mounting an ISO.
diff --git a/website/content/docs/v0.15/Reference/kernel.md b/website/content/docs/v0.15/Reference/kernel.md
@@ -115,3 +115,10 @@ Several of these are enforced by the Kernel Self Protection Project [KSPP](https
   DHCP server, this can add significant boot delays.
 
   This option may be specified multiple times for multiple network interfaces.
+
+#### `talos.experimental.wipe`
+
+  Resets the disk before starting up the system.
+
+  Valid options are:
+    - `system` resets system disk.