tests: k8s: coco: rely more on free runners

Run all CoCo non-TEE variants in a single job on the free runner with an
explicit environment matrix (vmm, snapshotter, pull_type, kbs,
containerd_version).

Here we're testing CoCo only with the "active" version of containerd.

Signed-off-by: Fabiano Fidêncio <ffidencio@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Fabiano Fidêncio
2026-02-15 15:26:35 +01:00
parent 50fab83173
commit aa3a795cd4
2 changed files with 60 additions and 57 deletions

View File

@@ -140,42 +140,35 @@ jobs:
strategy:
fail-fast: false
matrix:
vmm:
- qemu-coco-dev
- qemu-coco-dev-runtime-rs
snapshotter:
- nydus
pull-type:
- guest-pull
include:
- pull-type: experimental-force-guest-pull
vmm: qemu-coco-dev
snapshotter: ""
runs-on: ubuntu-22.04
environment: [
{ vmm: qemu-coco-dev, snapshotter: nydus, pull_type: guest-pull },
{ vmm: qemu-coco-dev-runtime-rs, snapshotter: nydus, pull_type: guest-pull },
{ vmm: qemu-coco-dev, snapshotter: "", pull_type: experimental-force-guest-pull },
]
runs-on: ubuntu-24.04
permissions:
id-token: write # Used for OIDC access to log into Azure
contents: read
environment: ci
env:
DOCKER_REGISTRY: ${{ inputs.registry }}
DOCKER_REPO: ${{ inputs.repo }}
DOCKER_TAG: ${{ inputs.tag }}
GH_PR_NUMBER: ${{ inputs.pr-number }}
KATA_HYPERVISOR: ${{ matrix.vmm }}
KATA_HYPERVISOR: ${{ matrix.environment.vmm }}
# Some tests rely on that variable to run (or not)
KBS: "true"
# Set the KBS ingress handler (empty string disables handling)
KBS_INGRESS: "aks"
KBS_INGRESS: "nodeport"
KUBERNETES: "vanilla"
PULL_TYPE: ${{ matrix.pull-type }}
PULL_TYPE: ${{ matrix.environment.pull_type }}
AUTHENTICATED_IMAGE_USER: ${{ vars.AUTHENTICATED_IMAGE_USER }}
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
SNAPSHOTTER: ${{ matrix.snapshotter }}
EXPERIMENTAL_FORCE_GUEST_PULL: ${{ matrix.pull-type == 'experimental-force-guest-pull' && matrix.vmm || '' }}
# Caution: current ingress controller used to expose the KBS service
# requires much vCPUs, lefting only a few for the tests. Depending on the
# host type chose it will result on the creation of a cluster with
# insufficient resources.
SNAPSHOTTER: ${{ matrix.environment.snapshotter }}
EXPERIMENTAL_FORCE_GUEST_PULL: ${{ matrix.environment.pull_type == 'experimental-force-guest-pull' && matrix.environment.vmm || '' }}
K8S_TEST_HOST_TYPE: "all"
CONTAINER_ENGINE: "containerd"
CONTAINER_ENGINE_VERSION: "active"
GH_TOKEN: ${{ github.token }}
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
@@ -198,39 +191,37 @@ jobs:
- name: Install kata-tools
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-tools-artifacts
- name: Log into the Azure account
uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2.3.0
with:
client-id: ${{ secrets.AZ_APPID }}
tenant-id: ${{ secrets.AZ_TENANT_ID }}
subscription-id: ${{ secrets.AZ_SUBSCRIPTION_ID }}
- name: Remove unnecessary directories to free up space
run: |
sudo rm -rf /usr/local/.ghcup
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf /usr/lib/jvm
sudo rm -rf /usr/share/swift
sudo rm -rf /usr/local/share/powershell
sudo rm -rf /usr/local/julia*
sudo rm -rf /opt/az
sudo rm -rf /usr/local/share/chromium
sudo rm -rf /opt/microsoft
sudo rm -rf /opt/google
sudo rm -rf /usr/lib/firefox
- name: Create AKS cluster
uses: nick-fields/retry@ce71cc2ab81d554ebbe88c79ab5975992d79ba08 # v3.0.2
with:
timeout_minutes: 15
max_attempts: 20
retry_on: error
retry_wait_seconds: 10
command: bash tests/integration/kubernetes/gha-run.sh create-cluster
- name: Deploy kubernetes
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh deploy-k8s
- name: Install `bats`
run: bash tests/integration/kubernetes/gha-run.sh install-bats
- name: Install `kubectl`
uses: azure/setup-kubectl@776406bce94f63e41d621b960d78ee25c8b76ede # v4.0.1
with:
version: 'latest'
- name: Download credentials for the Kubernetes CLI to use them
run: bash tests/integration/kubernetes/gha-run.sh get-cluster-credentials
- name: Deploy Kata
timeout-minutes: 20
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata-aks
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
env:
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: ${{ env.SNAPSHOTTER == 'nydus' }}
AUTO_GENERATE_POLICY: ${{ env.PULL_TYPE == 'experimental-force-guest-pull' && 'no' || 'yes' }}
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: ${{ matrix.environment.snapshotter == 'nydus' }}
AUTO_GENERATE_POLICY: ${{ matrix.environment.pull_type == 'experimental-force-guest-pull' && 'no' || 'yes' }}
- name: Deploy CoCo KBS
timeout-minutes: 10
@@ -252,18 +243,20 @@ jobs:
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Refresh OIDC token in case access token expired
if: always()
uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2.3.0
with:
client-id: ${{ secrets.AZ_APPID }}
tenant-id: ${{ secrets.AZ_TENANT_ID }}
subscription-id: ${{ secrets.AZ_SUBSCRIPTION_ID }}
- name: Delete AKS cluster
- name: Delete kata-deploy
if: always()
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh delete-cluster
run: bash tests/integration/kubernetes/gha-run.sh cleanup
- name: Delete CoCo KBS
if: always()
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs
- name: Delete CSI driver
if: always()
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh delete-csi-driver
# Generate jobs for testing CoCo on non-TEE environments with erofs-snapshotter
run-k8s-tests-coco-nontee-with-erofs-snapshotter:

View File

@@ -171,6 +171,15 @@ adapt_common_policy_settings_for_nvidia_gpu() {
jq '.kata_config.oci_version = "1.2.1"' "${settings_dir}/genpolicy-settings.json" > temp.json && mv temp.json "${settings_dir}/genpolicy-settings.json"
}
# Adapt OCI version in policy settings to match containerd version.
# containerd 2.2.x (active) vendors v1.3.0.
adapt_common_policy_settings_for_containerd_version() {
local settings_dir=${1}
info "Adapting common policy settings for containerd's latest release"
jq '.kata_config.oci_version = "1.3.0"' "${settings_dir}/genpolicy-settings.json" > temp.json && mv temp.json "${settings_dir}/genpolicy-settings.json"
}
# adapt common policy settings for various platforms
adapt_common_policy_settings() {
local settings_dir=$1
@@ -178,6 +187,7 @@ adapt_common_policy_settings() {
is_coco_platform || adapt_common_policy_settings_for_non_coco "${settings_dir}"
is_aks_cluster && adapt_common_policy_settings_for_aks "${settings_dir}"
is_nvidia_gpu_platform && adapt_common_policy_settings_for_nvidia_gpu "${settings_dir}"
[[ -n "${CONTAINER_ENGINE_VERSION:-}" ]] && adapt_common_policy_settings_for_containerd_version "${settings_dir}"
case "${KATA_HOST_OS}" in
"cbl-mariner")