Kubernetes prometheus telemetry + functional tests (krkn-chaos#566)

added comment on the node selector input.yaml

Signed-off-by: Tullio Sebastiani <[email protected]>

.github/workflows/tests.yml

@@ -1,8 +1,12 @@
 name: Functional & Unit Tests
 on:
   pull_request:
+  push:
+    branches:
+      - main
 jobs:
   tests:
+    # Common steps
     name: Functional & Unit Tests
     runs-on: ubuntu-latest
     steps:
@@ -47,8 +51,7 @@ jobs:
           sudo apt-get install build-essential python3-dev
           pip install --upgrade pip
           pip install -r requirements.txt
-#      - name: Run unit tests
-#        run: python -m coverage run -a -m unittest discover -s tests -v
+
       - name: Deploy test workloads
         run: |
           kubectl apply -f CI/templates/outage_pod.yaml
@@ -61,10 +64,14 @@ jobs:
       - name: Get Kind nodes
         run: |
           kubectl get nodes --show-labels=true
+      # Pull request only steps
+      - name: Run unit tests
+        if: github.event_name == 'pull_request'
+        run: python -m coverage run -a -m unittest discover -s tests -v
 
-      - name: Setup Functional Tests
+      - name: Setup Pull Request Functional Tests
+        if: github.event_name == 'pull_request'
         run: |
-            yq -i '.kraken.distribution="kubernetes"' CI/config/common_test_config.yaml
             yq -i '.kraken.port="8081"' CI/config/common_test_config.yaml
             yq -i '.kraken.signal_address="0.0.0.0"' CI/config/common_test_config.yaml
             yq -i '.kraken.performance_monitoring="localhost:9090"' CI/config/common_test_config.yaml
@@ -76,13 +83,33 @@ jobs:
             echo "test_arca_cpu_hog" >> ./CI/tests/functional_tests
             echo "test_arca_memory_hog" >> ./CI/tests/functional_tests
             echo "test_arca_io_hog" >> ./CI/tests/functional_tests
+
+      # Push on main only steps
+      - name: Configure AWS Credentials
+        if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region : ${{ secrets.AWS_REGION }}
+      - name: Setup Post Merge Request Functional Tests
+        if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+        run: |
+          yq -i '.kraken.port="8081"' CI/config/common_test_config.yaml
+          yq -i '.kraken.signal_address="0.0.0.0"' CI/config/common_test_config.yaml
+          yq -i '.kraken.performance_monitoring="localhost:9090"' CI/config/common_test_config.yaml
+          yq -i '.telemetry.username="${{secrets.TELEMETRY_USERNAME}}"' CI/config/common_test_config.yaml
+          yq -i '.telemetry.password="${{secrets.TELEMETRY_PASSWORD}}"' CI/config/common_test_config.yaml
+          echo "test_telemetry" > ./CI/tests/functional_tests
+
+      # Final common steps
       - name: Run Functional tests
+        env:
+          AWS_BUCKET: ${{ secrets.AWS_BUCKET }}
         run: |
           ./CI/run.sh
           cat ./CI/results.markdown >> $GITHUB_STEP_SUMMARY
           echo >> $GITHUB_STEP_SUMMARY
-      - name: Run Unit tests
-        run: python -m coverage run -a -m unittest discover -s tests -v
       - name: Upload CI logs
         uses: actions/upload-artifact@v3
         with:

CI/config/common_test_config.yaml

@@ -1,5 +1,5 @@
 kraken:
-    distribution: openshift                                # Distribution can be kubernetes or openshift.
+    distribution: kubernetes                                # Distribution can be kubernetes or openshift.
     kubeconfig_path: ~/.kube/config                        # Path to kubeconfig.
     exit_on_failure: False                                 # Exit when a post action scenario fails.
     litmus_version: v1.13.6                                # Litmus version to install.
@@ -30,12 +30,22 @@ tunings:
 telemetry:
     enabled: False                                           # enable/disables the telemetry collection feature
     api_url: https://ulnmf9xv7j.execute-api.us-west-2.amazonaws.com/production #telemetry service endpoint
-    username: username                                      # telemetry service username
-    password: password                                      # telemetry service password
+    username: $TELEMETRY_USERNAME                                      # telemetry service username
+    password: $TELEMETRY_PASSWORD                                      # telemetry service password
+    prometheus_namespace: 'prometheus-k8s'                                # prometheus namespace
+    prometheus_pod_name: 'prometheus-kind-prometheus-kube-prome-prometheus-0'                                 # prometheus pod_name
+    prometheus_container_name: 'prometheus'
     prometheus_backup: True                                 # enables/disables prometheus data collection
     full_prometheus_backup: False                           # if is set to False only the /prometheus/wal folder will be downloaded.
     backup_threads: 5                                       # number of telemetry download/upload threads
     archive_path: /tmp                                      # local path where the archive files will be temporarly stored
     max_retries: 0                                          # maximum number of upload retries (if 0 will retry forever)
     run_tag: ''                                             # if set, this will be appended to the run folder in the bucket (useful to group the runs)
     archive_size: 10000                                     # the size of the prometheus data archive size in KB. The lower the size of archive is
+    logs_backup: True
+    logs_filter_patterns:
+        - "(\\w{3}\\s\\d{1,2}\\s\\d{2}:\\d{2}:\\d{2}\\.\\d+).+"         # Sep 9 11:20:36.123425532
+        - "kinit (\\d+/\\d+/\\d+\\s\\d{2}:\\d{2}:\\d{2})\\s+"          # kinit 2023/09/15 11:20:36 log
+        - "(\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}\\.\\d+Z).+"      # 2023-09-15T11:20:36.123425532Z log
+    oc_cli_path: /usr/bin/oc                                # optional, if not specified will be search in $PATH
+    events_backup: True                                     # enables/disables cluster events collection

CI/run.sh

@@ -39,7 +39,7 @@ echo '-----------------------|--------|---------' >> $results
 failed_tests=()
 for test_name in `cat CI/tests/functional_tests`
 do
-  wait_cluster_become_ready
+  #wait_cluster_become_ready
   return_value=`./CI/run_test.sh $test_name $results`
   if [[ $return_value == 1 ]]
   then
@@ -49,6 +49,7 @@ do
   wait_cluster_become_ready
 done
 
+
 if (( ${#failed_tests[@]}>0 ))
 then
   echo -e "\n\n======================================================================"

CI/tests/test_telemetry.sh

@@ -0,0 +1,33 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+
+function functional_test_telemetry {
+  AWS_CLI=`which aws`
+  [ -z "$AWS_CLI" ]&& echo "AWS cli not found in path" && exit 1
+  [ -z "$AWS_BUCKET" ] && echo "AWS bucket not set in environment" && exit 1
+
+  export RUN_TAG="funtest-telemetry"
+  yq -i '.telemetry.enabled=True' CI/config/common_test_config.yaml
+  yq -i '.telemetry.full_prometheus_backup=True' CI/config/common_test_config.yaml
+  yq -i '.telemetry.run_tag=env(RUN_TAG)' CI/config/common_test_config.yaml
+  export scenario_type="arcaflow_scenarios"
+  export scenario_file="scenarios/arcaflow/cpu-hog/input.yaml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/telemetry.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/telemetry.yaml
+  RUN_FOLDER=`cat CI/out/test_telemetry.out | grep amazonaws.com | sed -rn "s#.*https:\/\/.*\/download/(.*)#\1#p"`
+  $AWS_CLI s3 ls "s3://$AWS_BUCKET/$RUN_FOLDER/" | awk '{ print $4 }' > s3_remote_files
+  echo "checking if telemetry files are uploaded on s3"
+  cat s3_remote_files | grep events-00.json || ( echo "FAILED: events-00.json not uploaded" && exit 1 )
+  cat s3_remote_files | grep prometheus-00.tar || ( echo "FAILED: prometheus backup not uploaded" && exit 1 )
+  cat s3_remote_files | grep telemetry.json || ( echo "FAILED: telemetry.json not uploaded" && exit 1 )
+  echo "all files uploaded!"
+  echo "Telemetry Collection: Success"
+}
+
+functional_test_telemetry

run_kraken.py

@@ -156,12 +156,17 @@ def main(cfg):
         # Cluster info
         logging.info("Fetching cluster info")
         cv = ""
-        if config["kraken"]["distribution"] == "openshift":
+        if distribution == "openshift":
             cv = ocpcli.get_clusterversion_string()
             if prometheus_url is None:
-                connection_data = ocpcli.get_prometheus_api_connection_data()
-                prometheus_url = connection_data.endpoint
-                prometheus_bearer_token = connection_data.token
+                try:
+                    connection_data = ocpcli.get_prometheus_api_connection_data()
+                    prometheus_url = connection_data.endpoint
+                    prometheus_bearer_token = connection_data.token
+                except Exception:
+                    logging.error("invalid distribution selected, running openshift scenarios against kubernetes cluster."
+                                  "Please set 'kubernetes' in config.yaml krkn.platform and try again")
+                    sys.exit(1)
         if cv != "":
             logging.info(cv)
         else:
@@ -366,7 +371,7 @@ def main(cfg):
         # if platform is openshift will be collected
         # Cloud platform and network plugins metadata
         # through OCP specific APIs
-        if config["kraken"]["distribution"] == "openshift":
+        if distribution == "openshift":
             telemetry_ocp.collect_cluster_metadata(chaos_telemetry)
         else:
             telemetry_k8s.collect_cluster_metadata(chaos_telemetry)
@@ -381,12 +386,33 @@ def main(cfg):
                 telemetry_k8s.send_telemetry(config["telemetry"], telemetry_request_id, chaos_telemetry)
                 telemetry_k8s.put_cluster_events(telemetry_request_id, config["telemetry"], start_time, end_time)
                 # prometheus data collection is available only on Openshift
-                if config["telemetry"]["prometheus_backup"] and config["kraken"]["distribution"] == "openshift":
-                    safe_logger.info("archives download started:")
-                    prometheus_archive_files = telemetry_ocp.get_ocp_prometheus_data(config["telemetry"], telemetry_request_id)
-                    safe_logger.info("archives upload started:")
-                    telemetry_k8s.put_prometheus_data(config["telemetry"], prometheus_archive_files, telemetry_request_id)
-                if config["telemetry"]["logs_backup"]:
+                if config["telemetry"]["prometheus_backup"]:
+                    prometheus_archive_files = ''
+                    if distribution == "openshift" :
+                        prometheus_archive_files = telemetry_ocp.get_ocp_prometheus_data(config["telemetry"], telemetry_request_id)
+                    else:
+                        if (config["telemetry"]["prometheus_namespace"] and
+                                config["telemetry"]["prometheus_pod_name"] and
+                                config["telemetry"]["prometheus_container_name"]):
+                            try:
+                                prometheus_archive_files = telemetry_k8s.get_prometheus_pod_data(
+                                    config["telemetry"],
+                                    telemetry_request_id,
+                                    config["telemetry"]["prometheus_pod_name"],
+                                    config["telemetry"]["prometheus_container_name"],
+                                    config["telemetry"]["prometheus_namespace"]
+                                )
+                            except Exception as e:
+                                logging.error(f"failed to get prometheus backup with exception {str(e)}")
+                        else:
+                            logging.warning("impossible to backup prometheus,"
+                                            "check if config contains telemetry.prometheus_namespace, "
+                                            "telemetry.prometheus_pod_name and "
+                                            "telemetry.prometheus_container_name")
+                    if prometheus_archive_files:
+                        safe_logger.info("starting prometheus archive upload:")
+                        telemetry_k8s.put_prometheus_data(config["telemetry"], prometheus_archive_files, telemetry_request_id)
+                if config["telemetry"]["logs_backup"] and distribution == "openshift":
                     telemetry_ocp.put_ocp_logs(telemetry_request_id, config["telemetry"], start_time, end_time)
             except Exception as e:
                 logging.error(f"failed to send telemetry data: {str(e)}")

scenarios/arcaflow/cpu-hog/input.yaml

@@ -5,5 +5,9 @@ input_list:
     duration: 1s
     kubeconfig: ''
     namespace: default
-    node_selector:
-      kubernetes.io/hostname: kind-worker2
+    # set the node selector as a key-value pair eg.
+    # node_selector:
+    #  kubernetes.io/hostname: kind-worker2
+    node_selector: {}
+
+

scenarios/arcaflow/io-hog/input.yaml

@@ -5,6 +5,9 @@ input_list:
   io_write_bytes: 10m
   kubeconfig: ''
   namespace: default
+  # set the node selector as a key-value pair eg.
+  # node_selector:
+  #  kubernetes.io/hostname: kind-worker2
   node_selector: {}
   target_pod_folder: /hog-data
   target_pod_volume:

scenarios/arcaflow/memory-hog/input.yaml

@@ -2,10 +2,10 @@ input_list:
 - duration: 30s
   vm_bytes: 10%
   vm_workers: 2
-  node_selector: { }
-  # node selector example
+  # set the node selector as a key-value pair eg.
   # node_selector:
-  #   kubernetes.io/hostname: master
+  #  kubernetes.io/hostname: kind-worker2
+  node_selector: { }
   kubeconfig: ""
   namespace: default