github/kata-containers
1
0
Fork 2
mirror of https://github.com/kata-containers/kata-containers.git synced 2026-05-12 18:17:05 +00:00
Code Issues Projects Releases Wiki Activity

ci: Add runtime-rs GPU shims to NVIDIA GPU CI workflow

Browse Source 
Add qemu-nvidia-gpu-runtime-rs and qemu-nvidia-gpu-snp-runtime-rs to
the NVIDIA GPU test matrix so CI covers the new runtime-rs shims.

Introduce a `coco` boolean field in each matrix entry and use it for
all CoCo-related conditionals (KBS, snapshotter, KBS deploy/cleanup
steps). This replaces fragile name-string comparisons that were already
broken for the runtime-rs variants: `nvidia-gpu (runtime-rs)` was
incorrectly getting KBS steps, and `nvidia-gpu-snp (runtime-rs)` was
not getting the right env vars.

Signed-off-by: Fabiano Fidêncio <ffidencio@nvidia.com>
This commit is contained in:
Fabiano Fidêncio
2026-04-05 23:46:48 +02:00
parent 09f5c85d53
commit 923162cecb
6 changed files with 25 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
.github/workflows/run-k8s-tests-on-nvidia-gpu.yaml vendored
View File

@@ -37,8 +37,10 @@ jobs:
fail-fast: false
matrix:
environment: [
{ name: nvidia-gpu, vmm: qemu-nvidia-gpu, runner: amd64-nvidia-a100 },
{ name: nvidia-gpu-snp, vmm: qemu-nvidia-gpu-snp, runner: amd64-nvidia-h100-snp },
{ name: nvidia-gpu, vmm: qemu-nvidia-gpu, runner: amd64-nvidia-a100, coco: false },
{ name: nvidia-gpu-runtime-rs, vmm: qemu-nvidia-gpu-runtime-rs, runner: amd64-nvidia-a100, coco: false },
{ name: nvidia-gpu-snp, vmm: qemu-nvidia-gpu-snp, runner: amd64-nvidia-h100-snp, coco: true },
{ name: nvidia-gpu-snp-runtime-rs, vmm: qemu-nvidia-gpu-snp-runtime-rs, runner: amd64-nvidia-h100-snp, coco: true },
]
runs-on: ${{ matrix.environment.runner }}
env:
@@ -48,9 +50,9 @@ jobs:
GH_PR_NUMBER: ${{ inputs.pr-number }}
KATA_HYPERVISOR: ${{ matrix.environment.vmm }}
KUBERNETES: kubeadm
KBS: ${{ matrix.environment.name == 'nvidia-gpu-snp' && 'true' || 'false' }}
SNAPSHOTTER: ${{ matrix.environment.name == 'nvidia-gpu-snp' && 'nydus' || '' }}
USE_EXPERIMENTAL_SNAPSHOTTER_SETUP: ${{ matrix.environment.name == 'nvidia-gpu-snp' && 'true' || 'false' }}
KBS: ${{ matrix.environment.coco && 'true' || 'false' }}
SNAPSHOTTER: ${{ matrix.environment.coco && 'nydus' || '' }}
USE_EXPERIMENTAL_SNAPSHOTTER_SETUP: ${{ matrix.environment.coco && 'true' || 'false' }}
K8S_TEST_HOST_TYPE: baremetal
steps:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
@@ -75,12 +77,12 @@ jobs:
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Uninstall previous `kbs-client`
if: matrix.environment.name != 'nvidia-gpu'
if: matrix.environment.coco
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh uninstall-kbs-client
- name: Deploy CoCo KBS
if: matrix.environment.name != 'nvidia-gpu'
if: matrix.environment.coco
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh deploy-coco-kbs
env:
@@ -88,7 +90,7 @@ jobs:
KBS_INGRESS: nodeport
- name: Install `kbs-client`
if: matrix.environment.name != 'nvidia-gpu'
if: matrix.environment.coco
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh install-kbs-client
@@ -127,7 +129,7 @@ jobs:
run: bash tests/integration/kubernetes/gha-run.sh cleanup
- name: Delete CoCo KBS
if: always() && matrix.environment.name != 'nvidia-gpu'
if: always() && matrix.environment.coco
timeout-minutes: 10
run: |
bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs

6
tests/gha-run-k8s-common.sh
View File

@@ -691,7 +691,7 @@ function helm_helper() {
# HELM_SHIMS is a space-separated list of shim names
# Enable each shim and set supported architectures
# TEE shims that need defaults unset (will be set based on env vars)
tee_shims="qemu-se qemu-se-runtime-rs qemu-cca qemu-snp qemu-snp-runtime-rs qemu-tdx qemu-tdx-runtime-rs qemu-coco-dev qemu-coco-dev-runtime-rs qemu-nvidia-gpu-snp qemu-nvidia-gpu-tdx"
tee_shims="qemu-se qemu-se-runtime-rs qemu-cca qemu-snp qemu-snp-runtime-rs qemu-tdx qemu-tdx-runtime-rs qemu-coco-dev qemu-coco-dev-runtime-rs qemu-nvidia-gpu-snp qemu-nvidia-gpu-tdx qemu-nvidia-gpu-snp-runtime-rs qemu-nvidia-gpu-tdx-runtime-rs"
for shim in ${HELM_SHIMS}; do
# Determine supported architectures based on shim name
@@ -705,7 +705,7 @@ function helm_helper() {
yq -i ".shims.${shim}.enabled = true" "${values_yaml}"
yq -i ".shims.${shim}.supportedArches = [\"arm64\"]" "${values_yaml}"
;;
qemu-snp|qemu-snp-runtime-rs|qemu-tdx|qemu-tdx-runtime-rs|qemu-nvidia-gpu-snp|qemu-nvidia-gpu-tdx)
qemu-snp|qemu-snp-runtime-rs|qemu-tdx|qemu-tdx-runtime-rs|qemu-nvidia-gpu-snp|qemu-nvidia-gpu-tdx|qemu-nvidia-gpu-snp-runtime-rs|qemu-nvidia-gpu-tdx-runtime-rs)
yq -i ".shims.${shim}.enabled = true" "${values_yaml}"
yq -i ".shims.${shim}.supportedArches = [\"amd64\"]" "${values_yaml}"
;;
@@ -717,7 +717,7 @@ function helm_helper() {
yq -i ".shims.${shim}.enabled = true" "${values_yaml}"
yq -i ".shims.${shim}.supportedArches = [\"amd64\", \"s390x\"]" "${values_yaml}"
;;
qemu-nvidia-gpu)
qemu-nvidia-gpu|qemu-nvidia-gpu-runtime-rs)
yq -i ".shims.${shim}.enabled = true" "${values_yaml}"
yq -i ".shims.${shim}.supportedArches = [\"amd64\", \"arm64\"]" "${values_yaml}"
;;

2
tests/integration/kubernetes/confidential_common.sh
View File

@@ -10,7 +10,7 @@ source "${BATS_TEST_DIRNAME}/../../common.bash"
load "${BATS_TEST_DIRNAME}/confidential_kbs.sh"
SUPPORTED_GPU_TEE_HYPERVISORS=("qemu-nvidia-gpu-snp" "qemu-nvidia-gpu-tdx")
SUPPORTED_GPU_TEE_HYPERVISORS=("qemu-nvidia-gpu-snp" "qemu-nvidia-gpu-tdx" "qemu-nvidia-gpu-snp-runtime-rs" "qemu-nvidia-gpu-tdx-runtime-rs")
SUPPORTED_TEE_HYPERVISORS=("qemu-snp" "qemu-snp-runtime-rs" "qemu-tdx" "qemu-se" "qemu-se-runtime-rs" "${SUPPORTED_GPU_TEE_HYPERVISORS[@]}")
SUPPORTED_NON_TEE_HYPERVISORS=("qemu-coco-dev" "qemu-coco-dev-runtime-rs")

2
tests/integration/kubernetes/gha-run.sh
View File

@@ -187,7 +187,7 @@ function deploy_kata() {
# Workaround to avoid modifying the workflow yaml files
case "${KATA_HYPERVISOR}" in
qemu-tdx|qemu-snp|qemu-snp-runtime-rs|qemu-nvidia-gpu-*)
qemu-tdx|qemu-snp|qemu-snp-runtime-rs|qemu-nvidia-gpu-tdx*|qemu-nvidia-gpu-snp*)
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER=true
SNAPSHOTTER="nydus"
EXPERIMENTAL_FORCE_GUEST_PULL=false

11
tests/integration/kubernetes/run_kubernetes_nv_tests.sh
View File

@@ -14,7 +14,12 @@ source "${kubernetes_dir}/../../common.bash"
# Enable NVRC trace logging for NVIDIA GPU runtime via drop-in config
enable_nvrc_trace() {
local config_dir="/opt/kata/share/defaults/kata-containers/runtimes/${KATA_HYPERVISOR}/config.d"
local kata_config_base="/opt/kata/share/defaults/kata-containers"
case "${KATA_HYPERVISOR}" in
*-runtime-rs) kata_config_base="${kata_config_base}/runtime-rs" ;;
esac
local config_dir="${kata_config_base}/runtimes/${KATA_HYPERVISOR}/config.d"
local drop_in_file="${config_dir}/90-nvrc-trace.toml"
local kernel_params_drop_in="${config_dir}/30-kernel-params.toml"
@@ -30,7 +35,7 @@ enable_nvrc_trace() {
if [[ -f "${kernel_params_drop_in}" ]]; then
base_params=$(grep -E '^kernel_params\s*=' "${kernel_params_drop_in}" | sed 's/^kernel_params\s*=\s*"\(.*\)"/\1/' || true)
else
local runtime_config="/opt/kata/share/defaults/kata-containers/runtimes/${KATA_HYPERVISOR}/configuration-${KATA_HYPERVISOR}.toml"
local runtime_config="${kata_config_base}/runtimes/${KATA_HYPERVISOR}/configuration-${KATA_HYPERVISOR}.toml"
if [[ -f "${runtime_config}" ]]; then
base_params=$(grep -E '^kernel_params\s*=' "${runtime_config}" | sed 's/^kernel_params\s*=\s*"\(.*\)"/\1/' || true)
fi
@@ -93,7 +98,7 @@ else
"k8s-nvidia-nim-service.bats")
fi
SUPPORTED_HYPERVISORS=("qemu-nvidia-gpu" "qemu-nvidia-gpu-snp" "qemu-nvidia-gpu-tdx")
SUPPORTED_HYPERVISORS=("qemu-nvidia-gpu" "qemu-nvidia-gpu-snp" "qemu-nvidia-gpu-tdx" "qemu-nvidia-gpu-runtime-rs" "qemu-nvidia-gpu-snp-runtime-rs" "qemu-nvidia-gpu-tdx-runtime-rs")
export KATA_HYPERVISOR="${KATA_HYPERVISOR:-qemu-nvidia-gpu}"
# shellcheck disable=SC2076 # intentionally use literal string matching
if [[ ! " ${SUPPORTED_HYPERVISORS[*]} " =~ " ${KATA_HYPERVISOR} " ]]; then

2
tests/integration/kubernetes/tests_common.sh
View File

@@ -82,7 +82,7 @@ auto_generate_policy_enabled() {
is_coco_platform() {
case "${KATA_HYPERVISOR}" in
"qemu-tdx"|"qemu-snp"|"qemu-snp-runtime-rs"|"qemu-coco-dev"|"qemu-coco-dev-runtime-rs"|"qemu-nvidia-gpu-tdx"|"qemu-nvidia-gpu-snp")
"qemu-tdx"|"qemu-snp"|"qemu-snp-runtime-rs"|"qemu-coco-dev"|"qemu-coco-dev-runtime-rs"|"qemu-nvidia-gpu-tdx"|"qemu-nvidia-gpu-snp"|"qemu-nvidia-gpu-tdx-runtime-rs"|"qemu-nvidia-gpu-snp-runtime-rs")
return 0
;;
*)