Merge fix/kubevirt-vm-boot: real-KVM DataVolume VMs (R-PLAT-03/04 green; useEmulation:false, EFI, DataVolume roots)
This commit is contained in:
5 files changed
+208
-44
No files matched your search
@@ -10,9 +10,15 @@
|
||||
# exactly the container proof (data-survival), now for a KubeVirt VM
|
||||
# (R-STATE-01 covers PaaS + IaaS).
|
||||
#
|
||||
# METHOD (virtctl-free, filesystem-agnostic, deterministic): a containerDisk-root
|
||||
# VM (ephemeral) with a Longhorn BLOCK data disk. cloud-init writes a unique canary
|
||||
# to the raw block device and powers the guest off; runStrategy RerunOnFailure means
|
||||
# METHOD (virtctl-free, filesystem-agnostic, deterministic): a VM whose ROOT is a
|
||||
# CDI DataVolume on Longhorn (a mounted PVC — NOT an ephemeral containerDisk; the
|
||||
# containerDisk boot path is broken on this k3s cluster because KubeVirt v1.9 serves
|
||||
# the container-disk binary through a k8s `image` volume gated by the ALPHA
|
||||
# `ImageVolume` feature gate, which k3s v1.31 has disabled → the apiserver prunes the
|
||||
# volume and the guest dies at OCI init. DataVolume disks bypass that path and are the
|
||||
# spec-required disk model anyway — docs/06/R-STATE-01). The VM also has a SECOND
|
||||
# Longhorn BLOCK data disk; cloud-init writes a unique canary to that raw block device
|
||||
# and powers the guest off; runStrategy RerunOnFailure means
|
||||
# a clean shutdown STAYS down (VMI -> Succeeded), so the write is known-complete and
|
||||
# the disk is released. We then DELETE the VM (keeping the PVC) and bind a throwaway
|
||||
# busybox reader pod to the SAME Longhorn PVC as a raw block device — if the bytes
|
||||
@@ -38,9 +44,10 @@ metadata:
|
||||
Destroy a VM entirely, keep its Longhorn PVC, and a fresh workload re-bound to
|
||||
that PVC still reads the VM-written data. Skips cleanly until KubeVirt + longhorn exist.
|
||||
spec:
|
||||
# Boot a guest + run cloud-init + power off, then reattach a Longhorn RWO volume — far beyond 180s.
|
||||
# CDI import onto Longhorn + boot a guest + run cloud-init + power off, then reattach a
|
||||
# Longhorn RWO volume — far beyond 180s.
|
||||
timeouts:
|
||||
exec: 20m
|
||||
exec: 30m
|
||||
steps:
|
||||
- name: vm-data-survives-destroy-and-rebuild
|
||||
try:
|
||||
@@ -77,7 +84,35 @@ spec:
|
||||
storage: 1Gi
|
||||
EOF
|
||||
|
||||
# -- The VM: containerDisk root (ephemeral) + the Longhorn block disk (/dev/vdb) + a
|
||||
# -- The VM's ROOT disk: CDI imports Fedora onto a Longhorn PVC (bypasses the broken
|
||||
# containerDisk/image-volume path; standalone DataVolume). Wait for the import. --
|
||||
kubectl -n "$NS" apply -f - <<'EOF'
|
||||
apiVersion: cdi.kubevirt.io/v1beta1
|
||||
kind: DataVolume
|
||||
metadata:
|
||||
name: survivor-rootdisk
|
||||
spec:
|
||||
source:
|
||||
registry:
|
||||
url: "docker://quay.io/containerdisks/fedora:41"
|
||||
storage:
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
storageClassName: longhorn
|
||||
resources:
|
||||
requests:
|
||||
storage: 6Gi
|
||||
EOF
|
||||
dv_phase=""
|
||||
for i in $(seq 1 120); do
|
||||
dv_phase="$(kubectl -n "$NS" get dv survivor-rootdisk -o jsonpath='{.status.phase}' 2>/dev/null || true)"
|
||||
[ "$dv_phase" = "Succeeded" ] && break
|
||||
sleep 10
|
||||
done
|
||||
[ "$dv_phase" = "Succeeded" ] || { echo "FAIL: CDI import did not Succeed (last='$dv_phase')" >&2; exit 1; }
|
||||
echo "CDI import complete: survivor-rootdisk Succeeded (Longhorn PVC)"
|
||||
|
||||
# -- The VM: DataVolume root (Longhorn) + the Longhorn block disk (/dev/vdb) + a
|
||||
# cloud-init disk. cloud-init writes the canary to the raw device and powers off.
|
||||
# RerunOnFailure => a clean poweroff STAYS Succeeded (not restarted), so the write is
|
||||
# known-complete and the disk released. Only $CANARY expands (no other '$' in the body).
|
||||
@@ -95,6 +130,14 @@ spec:
|
||||
homelab.keithjackson.dev/egress-class: internet
|
||||
spec:
|
||||
domain:
|
||||
# The containerdisks/fedora:41 image is UEFI-native (ESP + /boot mounted via
|
||||
# systemd GPT auto-discovery). KubeVirt defaults to SeaBIOS, under which the guest
|
||||
# boots to emergency mode (ESP + /boot by-uuid mounts time out) and cloud-init's
|
||||
# runcmd/poweroff never runs. Boot with EFI (OVMF). secureBoot:false => no SMM needed.
|
||||
firmware:
|
||||
bootloader:
|
||||
efi:
|
||||
secureBoot: false
|
||||
cpu: { cores: 1 }
|
||||
memory: { guest: 1024Mi }
|
||||
devices:
|
||||
@@ -110,8 +153,8 @@ spec:
|
||||
memory: 1024Mi
|
||||
volumes:
|
||||
- name: rootdisk
|
||||
containerDisk:
|
||||
image: quay.io/containerdisks/fedora:41
|
||||
dataVolume:
|
||||
name: survivor-rootdisk
|
||||
- name: datadisk
|
||||
persistentVolumeClaim:
|
||||
claimName: vm-survivor
|
||||
@@ -168,5 +211,6 @@ spec:
|
||||
content: |
|
||||
kubectl -n "$NAMESPACE" delete vm survivor --ignore-not-found --wait=false || true
|
||||
kubectl -n "$NAMESPACE" delete pod reader --ignore-not-found --wait=false || true
|
||||
kubectl -n "$NAMESPACE" delete dv survivor-rootdisk --ignore-not-found --wait=false || true
|
||||
kubectl -n "$NAMESPACE" delete pvc vm-survivor --ignore-not-found --wait=false || true
|
||||
echo "cleanup best-effort; chainsaw namespace teardown finalizes"
|
||||
Reference in new issue
Block a user