Added log telemetry piece to Krkn (#500)

* config

* log collection and upload

dictionary key fix

* escape regex in config.yaml

* bump krkn-lib version

* updated funtest github cli command

* update krkn-lib version to 1.3.2

* fixed requirements.txt

.github/workflows/functional_tests.yaml

@@ -34,7 +34,7 @@ jobs:
       - name: Check out Kraken
         uses: actions/checkout@v3
       - name: Checkout Pull Request
-        run: hub pr checkout ${{ github.event.issue.number }}
+        run: gh pr checkout ${{ github.event.issue.number }}
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       - name: Install OC CLI

config/config.yaml

@@ -89,3 +89,10 @@ telemetry:
                                                             # For unstable/slow connection is better to keep this value low
                                                             # increasing the number of backup_threads, in this way, on upload failure, the retry will happen only on the
                                                             # failed chunk without affecting the whole upload.
+    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
+

requirements.txt

@@ -1,40 +1,40 @@
-coverage
-datetime
-pyfiglet
 PyYAML>=5.1
-requests
-boto3
-google-api-python-client
-azure-mgmt-compute
-azure-keyvault
-azure-identity
-kubernetes
-oauth2client>=4.1.3
-python-openstackclient
-gitpython
-paramiko
-setuptools==65.5.1
-openshift-client
-python-ipmi
-podman-compose
-docker-compose
-docker
-jinja2==3.0.3
-itsdangerous==2.0.1
-werkzeug==2.2.3
-lxml >= 4.3.0
-pyVmomi >= 6.7
-zope.interface==5.4.0
 aliyun-python-sdk-core==2.13.36
 aliyun-python-sdk-ecs==4.24.25
-arcaflow-plugin-sdk>=0.9.0
-wheel
-service_identity
-git+https://github.com/vmware/vsphere-automation-sdk-python.git@v8.0.0.0
-git+https://github.com/redhat-chaos/arcaflow-plugin-kill-pod.git
 arcaflow >= 0.6.1
-prometheus_api_client
+arcaflow-plugin-sdk >= 0.10.0
+azure-identity
+azure-keyvault
+azure-mgmt-compute
+boto3==1.28.61
+coverage
+datetime
+docker
+docker-compose
+git+https://github.com/redhat-chaos/arcaflow-plugin-kill-pod.git
+git+https://github.com/vmware/vsphere-automation-sdk-python.git@v8.0.0.0
+gitpython
+google-api-python-client
 ibm_cloud_sdk_core
 ibm_vpc
+itsdangerous==2.0.1
+jinja2==3.0.3
+krkn-lib == 1.3.2
+kubernetes
+lxml >= 4.3.0
+oauth2client>=4.1.3
+openshift-client
+paramiko
+podman-compose
+prometheus_api_client
+pyVmomi >= 6.7
+pyfiglet
 pytest
-krkn-lib >= 1.2.1
+python-ipmi
+python-openstackclient
+requests
+service_identity
+setuptools==65.5.1
+werkzeug==2.2.3
+wheel
+zope.interface==5.4.0

run_kraken.py

@@ -386,7 +386,7 @@ def main(cfg):
         # in order to print decoded telemetry data even if telemetry collection
         # is disabled, it's necessary to serialize the ChaosRunTelemetry object
         # to json, and recreate a new object from it.
-
+        end_time = int(time.time())
         telemetry.collect_cluster_metadata(chaos_telemetry)
         decoded_chaos_run_telemetry = ChaosRunTelemetry(json.loads(chaos_telemetry.to_json()))
         logging.info(f"Telemetry data:\n{decoded_chaos_run_telemetry.to_json()}")
@@ -400,13 +400,15 @@ def main(cfg):
                     prometheus_archive_files = telemetry.get_ocp_prometheus_data(config["telemetry"], telemetry_request_id)
                     safe_logger.info("archives upload started:")
                     telemetry.put_ocp_prometheus_data(config["telemetry"], prometheus_archive_files, telemetry_request_id)
+                if config["telemetry"]["logs_backup"]:
+                    telemetry.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)}")
         else:
             logging.info("telemetry collection disabled, skipping.")
 
         # Capture the end time
-        end_time = int(time.time())
+
 
         # Capture metrics for the run
         if capture_metrics: