milvus/.github/workflows/pod-kill-chaos-test-kafka-version.yaml

name: Pod Kill Chaos Test For Kafka Version

on:
  workflow_dispatch:
    inputs:
      image_tag:
        description: The image tag to use for the chaos test
        required: true
        default: 'master-latest'
      image_repo:
        description: The image repo to use for the chaos test
        required: true
        default: 'milvusdb/milvus'
  schedule:
    - cron: "30 17 * * *"
jobs:

  test-pod-kill-chaos:

    runs-on: ubuntu-latest
    timeout-minutes: 40
    strategy:
      fail-fast: false
      matrix:
        pod: [allstandalone, allcluster, standalone, datacoord, datanode, indexcoord, indexnode, proxy, kafka, querycoord, querynode, rootcoord, etcd, minio]

    steps:

      - name: Set env param
        env:
          DEFAULT_IMAGE_TAG: master-latest
          DEFAULT_IMAGE_REPO: milvusdb/milvus
        run: |
          echo "RELEASE=test-${{ matrix.pod }}-pod-kill" >> $GITHUB_ENV
          echo "IMAGE_REPO=${{ github.event.inputs.image_repo || env.DEFAULT_IMAGE_REPO}}" >> $GITHUB_ENV
          echo "IMAGE_TAG=${{ github.event.inputs.image_tag || env.DEFAULT_IMAGE_TAG}}" >> $GITHUB_ENV          

      - name: Creating kind cluster
        uses: helm/kind-action@v1.2.0

      - name: Print cluster information
        run: |
          kubectl config view
          kubectl cluster-info
          kubectl get nodes
          kubectl get pods -n kube-system
          helm version
          kubectl version          

      - uses: actions/checkout@v2

      - name: Set up Python
        uses: actions/setup-python@v2
        with:
          python-version: 3.8

      - name: Install dependency
        uses: nick-invision/retry@v2
        with:
          timeout_minutes: 5
          max_attempts: 3
          retry_on: error
          shell: bash
          command: |
            pip install -r tests/python_client/requirements.txt --trusted-host https://test.pypi.org            

      - name: Deploy Chaos Mesh
        timeout-minutes: 2
        shell: bash
        run: |
          helm repo add chaos-mesh https://charts.chaos-mesh.org
          helm search repo chaos-mesh
          kubectl create ns chaos-testing
          helm install --wait --timeout 360s chaos-mesh chaos-mesh/chaos-mesh --namespace=chaos-testing --version v2.0.3 --set chaosDaemon.runtime=containerd --set chaosDaemon.socketPath=/run/containerd/containerd.sock
          kubectl get po -n chaos-testing          

      - name: Deploy Milvus
        timeout-minutes: 15
        shell: bash
        working-directory: tests/python_client/chaos
        run: |
          echo "latest tag:"
          bash ../../../scripts/docker_image_find_tag.sh -n milvusdb/milvus -t master-latest -f master- -F -L -q
          helm repo add milvus https://milvus-io.github.io/milvus-helm
          helm repo update
          if [[ ${{ matrix.pod }} != *"standalone"* ]]; then helm install --wait --timeout 720s ${{ env.RELEASE }} milvus/milvus --set pulsar.enabled=false --set kafka.enabled=true --set image.all.repository=${{ env.IMAGE_REPO }} --set image.all.tag=${{ env.IMAGE_TAG }} -f cluster-values.yaml  -n=chaos-testing; fi
          if [[ ${{ matrix.pod }} == *"standalone"* ]]; then helm install --wait --timeout 720s ${{ env.RELEASE }} milvus/milvus --set pulsar.enabled=false --set kafka.enabled=true --set image.all.repository=${{ env.IMAGE_REPO }} --set image.all.tag=${{ env.IMAGE_TAG }} -f standalone-values.yaml -n=chaos-testing; fi
          kubectl get pods -n chaos-testing
          sleep 20s
          kubectl get pods -n chaos-testing
          kubectl port-forward service/${{ env.RELEASE }}-milvus 19530 -n chaos-testing >/dev/null 2>&1 &
          sleep 20s
          # check whether port-forward success
          nc -vz 127.0.0.1 19530          

      - name: Run e2e test before chaos
        timeout-minutes: 5
        shell: bash
        working-directory: tests/python_client
        run: |
          pytest -s -v testcases/test_e2e.py --host 127.0.0.1 --log-cli-level=INFO --capture=no          

      - name: Run data presistence test before chaos
        timeout-minutes: 5
        shell: bash
        working-directory: tests/python_client/chaos
        run: |
          pytest -s -v testcases/test_data_persistence.py --host 127.0.0.1 --log-cli-level=INFO --capture=no                

      - name: Chaos Test
        timeout-minutes: 15
        shell: bash
        working-directory: tests/python_client/chaos
        run: |
          # replace chaos object
          sed -i "s/TESTS_CONFIG_LOCATION =.*/TESTS_CONFIG_LOCATION = \'chaos_objects\/pod_kill\/'/g" constants.py
          sed -i "s/ALL_CHAOS_YAMLS =.*/ALL_CHAOS_YAMLS = \'chaos_${{ matrix.pod }}_pod_kill.yaml\'/g" constants.py
          sed -i "s/RELEASE_NAME =.*/RELEASE_NAME = \'${{ env.RELEASE }}\'/g" constants.py
          cat constants.py
          timeout 14m pytest -s -v test_chaos.py --host 127.0.0.1 --log-cli-level=INFO --capture=no || echo "chaos test failed"          

      - name: Result Analysis
        timeout-minutes: 1
        shell: bash
        working-directory: tests/python_client/chaos/reports
        run: |
          echo "result analysis"
          cat ${{ env.RELEASE }}.log || echo "no log file"          

      - name: Wait all pods ready
        timeout-minutes: 5
        shell: bash
        working-directory: tests/python_client
        run: |
          kubectl get pod -n chaos-testing
          # wait all pod to be ready
          kubectl wait --for=condition=Ready pod -l app.kubernetes.io/instance=${{ env.RELEASE }} -n chaos-testing --timeout=360s
          kubectl wait --for=condition=Ready pod -l release=${{ env.RELEASE }} -n chaos-testing --timeout=360s
          kubectl get pod -n chaos-testing
          ps aux|grep forward|grep -v grep|awk '{print $2}'|xargs kill -9
          kubectl port-forward service/${{ env.RELEASE }}-milvus 19530 -n chaos-testing >/dev/null 2>&1 &

          sleep 20s
          nc -vz 127.0.0.1 19530          

      - name: Run e2e test after chaos
        timeout-minutes: 5
        shell: bash
        working-directory: tests/python_client
        run: |

          pytest -s -v testcases/test_e2e.py --host 127.0.0.1 --log-cli-level=INFO --capture=no

      - name: Run data presistence test after chaos
        timeout-minutes: 5
        shell: bash
        working-directory: tests/python_client/chaos
        run: |
          pytest -s -v testcases/test_data_persistence.py --host 127.0.0.1 --log-cli-level=INFO --capture=no              

      - name: Verify all collections after chaos
        timeout-minutes: 15
        shell: bash
        working-directory: tests/python_client/chaos
        run: |
          
          pytest -s -v testcases/test_get_collections.py --host 127.0.0.1 --log-cli-level=INFO --capture=no
          sleep 2s
          pytest -s -v testcases/test_all_collections_after_chaos.py --host 127.0.0.1 -n 4 --log-cli-level=INFO --capture=no          

      - name: Export logs
        if: ${{ always() }}
        shell: bash
        working-directory: tests/python_client/chaos
        run: |
          #in this step, verify whether pod has been killed by pod's age
          kubectl get po -n chaos-testing
          # export k8s log for chaos mesh and milvus
          bash ../../scripts/export_log_k8s.sh chaos-testing ${{ env.RELEASE }} k8s_logs/chaos-test          
      
      - name: Upload logs
        if: ${{ ! success() }}
        uses: actions/upload-artifact@v2
        with:
          name: logs-${{ matrix.pod }}
          path: |
            tests/python_client/chaos/k8s_logs
            tests/python_client/chaos/reports