[skip e2e]Add memory stress chaos test (#15907)

Signed-off-by: zhuwenxing <wenxing.zhu@zilliz.com>

.github/workflows/mem-stress-chaos-test.yaml

@@ -0,0 +1,197 @@
+name: Memory Stress Chaos Test
+
+on:
+  workflow_dispatch:
+jobs:
+  
+  test-memory-stress-chaos:
+   
+    runs-on: ubuntu-latest
+    timeout-minutes: 40
+    strategy:
+      fail-fast: false
+      matrix:
+        pod: [datanode, indexnode, proxy, pulsar, querynode, etcd, minio]
+    
+    steps:
+
+      - name: Set env param
+        run: |
+          echo "RELEASE=test-${{ matrix.pod }}-memory-stress" >> $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
+            pip install --upgrade protobuf
+      
+      - name: Deploy Chaos Mesh
+        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
+        shell: bash
+        working-directory: tests/python_client/chaos
+        run: |
+          echo "latest tag:"
+          bash ../../../scripts/docker_image_find_tag.sh -n milvusdb/milvus-dev -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 -f cluster-values.yaml  -n=chaos-testing; fi
+          if [[ ${{ matrix.pod }} == *"standalone"* ]]; then helm install --wait --timeout 720s ${{ env.RELEASE }} milvus/milvus -f standalone-values.yaml -n=chaos-testing; fi
+          kubectl get pods -n chaos-testing
+          sleep 20s
+          kubectl get pods -n chaos-testing
+          kubectl port-forward service/${{ 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
+          # check whether milvus server is healthy
+          python scripts/hello_milvus.py
+      
+      - 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\/mem_stress\/'/g" constants.py
+          sed -i "s/ALL_CHAOS_YAMLS =.*/ALL_CHAOS_YAMLS = \'chaos_${{ matrix.pod }}_mem_stress.yaml\'/g" constants.py
+          sed -i "s/RELEASE_NAME =.*/RELEASE_NAME = \'${{ 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: 15
+        shell: bash
+        working-directory: tests/python_client/chaos/reports
+        run: |
+          echo "result analysis"
+          cat ${{ env.RELEASE }}.log || echo "no log file"
+
+      - name: Milvus E2E Test
+        timeout-minutes: 10
+        if: ${{ always() }}
+        shell: bash
+        working-directory: tests/python_client
+        run: |
+          kubectl get networkchaos -n chaos-testing
+          kubectl get pod -n chaos-testing
+          # wait all pod to be ready
+          kubectl wait --for=condition=Ready pod -l app.kubernetes.io/instance=${{ 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
+
+          pytest -s -v testcases/test_e2e.py --host 127.0.0.1 --log-cli-level=INFO --capture=no
+          python chaos/scripts/hello_milvus.py --host 127.0.0.1
+
+      - 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: Deploy Milvus Again If Previous E2E Test Failed
+        timeout-minutes: 15
+        if: ${{ failure() }}
+        shell: bash
+        working-directory: tests/python_client/chaos
+        run: |
+          kubectl config set-context --current --namespace=chaos-testing
+          bash scripts/uninstall_milvus.sh ${{ env.RELEASE }}
+          if [ ${{ matrix.pod }} != "standalone" ]; then helm install --wait --timeout 720s ${{ env.RELEASE }} milvus/milvus -f cluster-values.yaml  -n=chaos-testing; fi
+          if [ ${{ matrix.pod }} == "standalone" ]; then helm install --wait --timeout 720s ${{ env.RELEASE }} milvus/milvus --set cluster.enabled=false --set etcd.replicaCount=1 --set minio.mode=standalone --set pulsar.enabled=false -n=chaos-testing; fi
+          kubectl get pods -n chaos-testing
+          sleep 20s
+          kubectl get pods -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
+          # check whether port-forward success
+          nc -vz 127.0.0.1 19530
+          # check whether milvus server is healthy
+          python scripts/hello_milvus.py              
+      
+      - name: Data Consist Test
+        timeout-minutes: 5
+        if: ${{ always() }}
+        shell: bash
+        working-directory: tests/python_client/chaos
+        run: |
+          pytest -s -v test_chaos_data_consist.py --host 127.0.0.1 --log-cli-level=INFO --capture=no || echo "data consist chaos test failed"
+
+      - name: Milvus E2E Test
+        timeout-minutes: 10
+        if: ${{ always() }}
+        shell: bash
+        working-directory: tests/python_client
+        run: |
+          kubectl get pod -n chaos-testing
+          kubectl wait --for=condition=Ready pod -l app.kubernetes.io/instance=${{ 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
+
+          pytest -s -v testcases/test_e2e.py --host 127.0.0.1 --log-cli-level=INFO --capture=no
+          python chaos/scripts/hello_milvus.py --host 127.0.0.1
+
+      - 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/data-consist-test
+          bash ../../scripts/export_log_k8s.sh chaos-testing chaos-daemon k8s_logs/chaos-mesh-daemon
+      
+      - name: Upload logs
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v2
+        with:
+          name: logs-${{ matrix.pod }}
+          path: |
+            tests/python_client/chaos/k8s_logs
+            tests/python_client/chaos/reports

tests/python_client/chaos/chaos_objects/mem_stress/chaos_datanode_mem_stress.yaml

@@ -0,0 +1,21 @@
+kind: StressChaos
+apiVersion: chaos-mesh.org/v1alpha1
+metadata:
+  name: test-datanode-memory-stress
+  namespace: chaos-testing
+spec:
+  selector:
+    namespaces:
+      - chaos-testing
+    labelSelectors:
+      app.kubernetes.io/instance: milvus-chaos
+      component: datanode
+  mode: all
+  stressors:
+    cpu:
+      workers: 4
+      load: 80
+    memory:
+      workers: 4
+      size: 2048Mi
+  duration: 5m

tests/python_client/chaos/chaos_objects/mem_stress/chaos_etcd_mem_stress.yaml

@@ -0,0 +1,21 @@
+kind: StressChaos
+apiVersion: chaos-mesh.org/v1alpha1
+metadata:
+  name: test-etcd-memory-stress
+  namespace: chaos-testing
+spec:
+  selector:
+    namespaces:
+      - chaos-testing
+    labelSelectors:
+      app.kubernetes.io/instance: milvus-chaos
+      app.kubernetes.io/name: etcd
+  mode: all
+  stressors:
+    cpu:
+      workers: 4
+      load: 80
+    memory:
+      workers: 4
+      size: 2048Mi
+  duration: 5m

tests/python_client/chaos/chaos_objects/mem_stress/chaos_indexnode_mem_stress.yaml

@@ -0,0 +1,21 @@
+kind: StressChaos
+apiVersion: chaos-mesh.org/v1alpha1
+metadata:
+  name: test-indexnode-memory-stress
+  namespace: chaos-testing
+spec:
+  selector:
+    namespaces:
+      - chaos-testing
+    labelSelectors:
+      app.kubernetes.io/instance: pulsar-mem-stress-14-04-25
+      component: indexnode
+  mode: one
+  stressors:
+    cpu:
+      workers: 4
+      load: 80
+    memory:
+      workers: 4
+      size: 2048Mi
+  duration: 5m

tests/python_client/chaos/chaos_objects/mem_stress/chaos_minio_mem_stress.yaml

@@ -0,0 +1,21 @@
+kind: StressChaos
+apiVersion: chaos-mesh.org/v1alpha1
+metadata:
+  name: test-datanode-memory-stress
+  namespace: chaos-testing
+spec:
+  selector:
+    namespaces:
+      - chaos-testing
+    labelSelectors:
+      release: milvus-chaos
+      app: minio
+  mode: one
+  stressors:
+    cpu:
+      workers: 4
+      load: 80
+    memory:
+      workers: 4
+      size: 2048Mi
+  duration: 5m

tests/python_client/chaos/chaos_objects/mem_stress/chaos_proxy_mem_stress.yaml

@@ -0,0 +1,21 @@
+kind: StressChaos
+apiVersion: chaos-mesh.org/v1alpha1
+metadata:
+  name: test-datanode-memory-stress
+  namespace: chaos-testing
+spec:
+  selector:
+    namespaces:
+      - chaos-testing
+    labelSelectors:
+      app.kubernetes.io/instance: milvus-chaos
+      component: proxy
+  mode: one
+  stressors:
+    cpu:
+      workers: 4
+      load: 80
+    memory:
+      workers: 4
+      size: 2048Mi
+  duration: 5m

tests/python_client/chaos/chaos_objects/mem_stress/chaos_pulsar_mem_stress.yaml

@@ -0,0 +1,21 @@
+kind: StressChaos
+apiVersion: chaos-mesh.org/v1alpha1
+metadata:
+  name: test-datanode-memory-stress
+  namespace: chaos-testing
+spec:
+  selector:
+    namespaces:
+      - chaos-testing
+    labelSelectors:
+      release: milvus-chaos
+      app: pulsar
+  mode: one
+  stressors:
+    cpu:
+      workers: 4
+      load: 80
+    memory:
+      workers: 4
+      size: 2048Mi
+  duration: 5m

tests/python_client/chaos/chaos_objects/mem_stress/chaos_querynode_mem_stress.yaml

@@ -0,0 +1,21 @@
+kind: StressChaos
+apiVersion: chaos-mesh.org/v1alpha1
+metadata:
+  name: test-querynode-memory-stress
+  namespace: chaos-testing
+spec:
+  selector:
+    namespaces:
+      - chaos-testing
+    labelSelectors:
+      app.kubernetes.io/instance: milvus-chaos
+      component: querynode
+  mode: one
+  stressors:
+    cpu:
+      workers: 4
+      load: 80
+    memory:
+      workers: 4
+      size: 2048Mi
+  duration: 5m

tests/python_client/chaos/chaos_objects/mem_stress/chaos_standalone_mem_stress.yaml

@@ -0,0 +1,21 @@
+kind: StressChaos
+apiVersion: chaos-mesh.org/v1alpha1
+metadata:
+  name: test-datanode-memory-stress
+  namespace: chaos-testing
+spec:
+  selector:
+    namespaces:
+      - chaos-testing
+    labelSelectors:
+      app.kubernetes.io/instance: milvus-chaos
+      component: standalone
+  mode: one
+  stressors:
+    cpu:
+      workers: 4
+      load: 80
+    memory:
+      workers: 4
+      size: 2048Mi
+  duration: 5m

tests/python_client/chaos/chaos_objects/mem_stress/testcases.yaml

@@ -0,0 +1,85 @@
+# Memory Stress Testcases All-in-one
+#   memory stress
+#     standalone
+#       todo
+#     cluster-1-node
+#       11 pods(querynode, datanode, indexnode, pulsar, etcd, minio)
+#     cluster-n-nodes
+#       todo
+
+Collections:
+  -
+    testcase:
+      name: test_querynode_mem_stress
+      chaos: chaos_querynode_mem_stress.yaml
+      expectation:
+          cluster_1_node:
+            search: fail
+            query: fail
+          cluster_n_nodes:
+            search: degrade
+            query: degrade
+  -
+    testcase:
+      name: test_datanode_mem_stress
+      chaos: chaos_datanode_mem_stress.yaml
+      expectation:
+          cluster_1_node:
+            flush: fail
+          cluster_n_nodes:
+            flush: degrade
+  -
+    testcase:
+      name: test_proxy_mem_stress
+      chaos: chaos_proxy_mem_stress.yaml
+      expectation:
+          cluster_1_node:
+            flush: fail
+          cluster_n_nodes:
+            flush: degrade
+  -
+    testcase:
+      name: test_indexnode_mem_stress
+      chaos: chaos_indexnode_mem_stress.yaml
+      expectation:
+          cluster_1_node:
+            flush: fail
+          cluster_n_nodes:
+            flush: degrade
+
+  -
+    testcase:
+      name: test_pulsar_mem_stress
+      chaos: chaos_pulsar_mem_stress.yaml
+      expectation:
+          cluster_1_node:
+            flush: fail
+          cluster_n_nodes:
+            flush: degrade
+  -
+    testcase:
+      name: test_minio_mem_stress
+      chaos: chaos_minio_mem_stress.yaml
+      expectation:
+          cluster_1_node:
+            flush: fail
+          cluster_n_nodes:
+            flush: degrade
+  -
+    testcase:
+      name: test_etcd_mem_stress
+      chaos: chaos_etcd_mem_stress.yaml
+      expectation:
+          cluster_1_node:
+            flush: fail
+          cluster_n_nodes:
+            flush: degrade
+  -
+    testcase:
+      name: test_standalone_mem_stress
+      chaos: chaos_standalone_mem_stress.yaml
+      expectation:
+          cluster_1_node:
+            flush: fail
+          cluster_n_nodes:
+            flush: degrade