Files
kata-containers/.github/workflows/run-kata-coco-tests.yaml
Fabiano Fidêncio e782d1ad50 ci: k8s: Test experimental_force_guest_pull
Now that we have added the ability to deploy kata-containers with
experimental_force_guest_pull configured, let's make sure we test it to
avoid any kind of regressions.

Signed-off-by: Fabiano Fidêncio <ffidencio@nvidia.com>
2025-10-10 20:08:10 +02:00

346 lines
11 KiB
YAML

name: CI | Run kata coco tests
on:
workflow_call:
inputs:
tarball-suffix:
required: false
type: string
registry:
required: true
type: string
repo:
required: true
type: string
tag:
required: true
type: string
pr-number:
required: true
type: string
commit-hash:
required: false
type: string
target-branch:
required: false
type: string
default: ""
secrets:
AUTHENTICATED_IMAGE_PASSWORD:
required: true
AZ_APPID:
required: true
AZ_TENANT_ID:
required: true
AZ_SUBSCRIPTION_ID:
required: true
ITA_KEY:
required: true
permissions: {}
jobs:
run-k8s-tests-on-tee:
name: run-k8s-tests-on-tee
strategy:
fail-fast: false
matrix:
include:
- runner: tdx
vmm: qemu-tdx
- runner: sev-snp
vmm: qemu-snp
runs-on: ${{ matrix.runner }}
env:
DOCKER_REGISTRY: ${{ inputs.registry }}
DOCKER_REPO: ${{ inputs.repo }}
DOCKER_TAG: ${{ inputs.tag }}
GH_PR_NUMBER: ${{ inputs.pr-number }}
KATA_HYPERVISOR: ${{ matrix.vmm }}
KUBERNETES: "vanilla"
USING_NFD: "false"
KBS: "true"
K8S_TEST_HOST_TYPE: "baremetal"
KBS_INGRESS: "nodeport"
SNAPSHOTTER: "nydus"
PULL_TYPE: "guest-pull"
AUTHENTICATED_IMAGE_USER: ${{ vars.AUTHENTICATED_IMAGE_USER }}
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
GH_ITA_KEY: ${{ secrets.ITA_KEY }}
AUTO_GENERATE_POLICY: "yes"
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Deploy Kata
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
- name: Uninstall previous `kbs-client`
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh uninstall-kbs-client
- name: Deploy CoCo KBS
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh deploy-coco-kbs
env:
ITA_KEY: ${{ env.KATA_HYPERVISOR == 'qemu-tdx' && env.GH_ITA_KEY || '' }}
- name: Install `kbs-client`
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh install-kbs-client
- name: Deploy CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh deploy-csi-driver
- name: Run tests
timeout-minutes: 100
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Delete kata-deploy
if: always()
run: bash tests/integration/kubernetes/gha-run.sh cleanup
- name: Delete CoCo KBS
if: always()
run: |
[[ "${KATA_HYPERVISOR}" == "qemu-tdx" ]] && echo "ITA_KEY=${GH_ITA_KEY}" >> "${GITHUB_ENV}"
bash tests/integration/kubernetes/gha-run.sh delete-coco-kbs
- name: Delete CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh delete-csi-driver
# Generate jobs for testing CoCo on non-TEE environments
run-k8s-tests-coco-nontee:
name: run-k8s-tests-coco-nontee
strategy:
fail-fast: false
matrix:
vmm:
- qemu-coco-dev
snapshotter:
- nydus
pull-type:
- guest-pull
include:
- pull-type: experimental-force-guest-pull
snapshotter: ""
runs-on: ubuntu-22.04
permissions:
id-token: write # Used for OIDC access to log into Azure
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 }}
# Some tests rely on that variable to run (or not)
KBS: "true"
# Set the KBS ingress handler (empty string disables handling)
KBS_INGRESS: "aks"
KUBERNETES: "vanilla"
PULL_TYPE: ${{ matrix.pull-type }}
AUTHENTICATED_IMAGE_USER: ${{ vars.AUTHENTICATED_IMAGE_USER }}
AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
SNAPSHOTTER: ${{ matrix.snapshotter }}
# 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.
K8S_TEST_HOST_TYPE: "all"
USING_NFD: "false"
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: get-kata-tarball
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: kata-static-tarball-amd64${{ inputs.tarball-suffix }}
path: kata-artifacts
- name: Install kata
run: bash tests/integration/kubernetes/gha-run.sh install-kata-tools kata-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: 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: 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: 10
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata-aks
env:
EXPERIMENTAL_FORCE_GUEST_PULL: ${{ env.PULL_TYPE == 'experimental-force-guest-pull' && env.KATA_HYPERVISOR || '' }}
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: ${{ env.SNAPSHOTTER == 'nydus' }}
AUTO_GENERATE_POLICY: ${{ env.PULL_TYPE == 'experimental-force-guest-pull' && 'no' || 'yes' }}
- name: Deploy CoCo KBS
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh deploy-coco-kbs
- name: Install `kbs-client`
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh install-kbs-client
- name: Deploy CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh deploy-csi-driver
- name: Run tests
timeout-minutes: 80
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests
- name: Refresh OIDC token in case access token expired
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
if: always()
run: bash tests/integration/kubernetes/gha-run.sh delete-cluster
# Generate jobs for testing CoCo on non-TEE environments with erofs-snapshotter
run-k8s-tests-coco-nontee-with-erofs-snapshotter:
name: run-k8s-tests-coco-nontee-with-erofs-snapshotter
strategy:
fail-fast: false
matrix:
vmm:
- qemu-coco-dev
snapshotter:
- erofs
pull-type:
- default
runs-on: ubuntu-24.04
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 }}
# Some tests rely on that variable to run (or not)
KBS: "false"
# Set the KBS ingress handler (empty string disables handling)
KBS_INGRESS: ""
KUBERNETES: "vanilla"
CONTAINER_ENGINE: "containerd"
CONTAINER_ENGINE_VERSION: "v2.2"
PULL_TYPE: ${{ matrix.pull-type }}
SNAPSHOTTER: ${{ matrix.snapshotter }}
USE_EXPERIMENTAL_SETUP_SNAPSHOTTER: "true"
K8S_TEST_HOST_TYPE: "all"
USING_NFD: "false"
# We are skipping the auto generated policy tests for now,
# but those should be enabled as soon as we work on that.
AUTO_GENERATE_POLICY: "no"
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.commit-hash }}
fetch-depth: 0
persist-credentials: false
- name: Rebase atop of the latest target branch
run: |
./tests/git-helper.sh "rebase-atop-of-the-latest-target-branch"
env:
TARGET_BRANCH: ${{ inputs.target-branch }}
- name: Remove unnecessary directories to free up space
run: |
sudo rm -rf /usr/local/.ghcup
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/lib/android
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf /usr/local/share/boost
sudo rm -rf "$AGENT_TOOLSDIRECTORY"
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: Deploy kubernetes
timeout-minutes: 15
run: bash tests/integration/kubernetes/gha-run.sh deploy-k8s
env:
GH_TOKEN: ${{ github.token }}
- name: Install `bats`
run: bash tests/integration/kubernetes/gha-run.sh install-bats
- name: Deploy Kata
timeout-minutes: 10
run: bash tests/integration/kubernetes/gha-run.sh deploy-kata
- name: Deploy CSI driver
timeout-minutes: 5
run: bash tests/integration/kubernetes/gha-run.sh deploy-csi-driver
- name: Run tests
timeout-minutes: 80
run: bash tests/integration/kubernetes/gha-run.sh run-tests
- name: Report tests
if: always()
run: bash tests/integration/kubernetes/gha-run.sh report-tests