Merge pull request #10177 from GabyCT/topic/cocoghas

gha: Add k8s stability Kata CoCo GHA workflow

.github/workflows/ci-coco-stability.yaml

@@ -0,0 +1,19 @@
+name: Kata Containers CoCo Stability Tests Weekly
+on:
+  schedule:
+    - cron: '0 0 * * 0'
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  kata-containers-ci-on-push:
+    uses: ./.github/workflows/run-kata-coco-stability-tests.yaml
+    with:
+      commit-hash: ${{ github.sha }}
+      pr-number: "weekly"
+      tag: ${{ github.sha }}-weekly
+      target-branch: ${{ github.ref_name }}
+    secrets: inherit

.github/workflows/run-kata-coco-stability-tests.yaml

@@ -0,0 +1,113 @@
+name: CI | Run Kata CoCo k8s Stability Tests
+on:
+  workflow_call:
+    inputs:
+      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: ""
+
+jobs:
+  # Generate jobs for testing CoCo on non-TEE environments
+  run-stability-k8s-tests-coco-nontee:
+    strategy:
+      fail-fast: false
+      matrix:
+        vmm:
+          - qemu-coco-dev
+        snapshotter:
+          - nydus
+        pull-type:
+          - guest-pull
+    runs-on: ubuntu-latest
+    env:
+      DOCKER_REGISTRY: ${{ inputs.registry }}
+      DOCKER_REPO: ${{ inputs.repo }}
+      DOCKER_TAG: ${{ inputs.tag }}
+      GH_PR_NUMBER: ${{ inputs.pr-number }}
+      KATA_HOST_OS: ${{ matrix.host_os }}
+      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: ${{ secrets.AUTHENTICATED_IMAGE_USER }}
+      AUTHENTICATED_IMAGE_PASSWORD: ${{ secrets.AUTHENTICATED_IMAGE_PASSWORD }}
+      SNAPSHOTTER: ${{ matrix.snapshotter }}
+      USING_NFD: "false"
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.commit-hash }}
+          fetch-depth: 0
+
+      - 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: Download Azure CLI
+        run: bash tests/integration/kubernetes/gha-run.sh install-azure-cli
+
+      - name: Log into the Azure account
+        run: bash tests/integration/kubernetes/gha-run.sh login-azure
+        env:
+          AZ_APPID: ${{ secrets.AZ_APPID }}
+          AZ_PASSWORD: ${{ secrets.AZ_PASSWORD }}
+          AZ_TENANT_ID: ${{ secrets.AZ_TENANT_ID }}
+          AZ_SUBSCRIPTION_ID: ${{ secrets.AZ_SUBSCRIPTION_ID }}
+
+      - name: Create AKS cluster
+        timeout-minutes: 10
+        run: 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`
+        run: bash tests/integration/kubernetes/gha-run.sh install-kubectl
+
+      - name: Download credentials for the Kubernetes CLI to use them
+        run: bash tests/integration/kubernetes/gha-run.sh get-cluster-credentials
+
+      - name: Deploy Snapshotter
+        timeout-minutes: 5
+        run: bash tests/integration/kubernetes/gha-run.sh deploy-snapshotter
+
+      - name: Deploy Kata
+        timeout-minutes: 10
+        run: bash tests/integration/kubernetes/gha-run.sh deploy-kata-aks
+
+      - 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: Run stability tests
+        timeout-minutes: 100
+        run: bash tests/stability/gha-stability-run.sh run-tests
+
+      - name: Delete AKS cluster
+        if: always()
+        run: bash tests/integration/kubernetes/gha-run.sh delete-cluster

tests/stability/gha-stability-run.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+#
+# Copyright (c) 2024 Intel Corporation
+#
+# SPDX-License-Identifier: Apache-2.0
+#
+
+set -o errexit
+set -o nounset
+set -o pipefail
+
+stability_dir="$(dirname "$(readlink -f "$0")")"
+source "${stability_dir}/../common.bash"
+source "${stability_dir}/../metrics/lib/common.bash"
+
+function run_tests() {
+	info "Running scability test using ${KATA_HYPERVISOR} hypervisor"
+	bash "${stability_dir}/kubernetes_stability.sh"
+}
+
+function main() {
+	action="${1:-}"
+	case "${action}" in
+		run-tests) run_tests ;;
+		*) >&2 die "Invalid argument" ;;
+	esac
+}
+
+main "$@"
+