Fix: Reslove ingress network chaos plugin issue

Added network_chaos to plugin step and job wait time to be based on the test duration and set the default wait_time to 30s

Signed-off-by: yogananth subramanian <ysubrama@redhat.com>

.gitignore

@@ -16,6 +16,7 @@ __pycache__/*
 *.out
 kube-burner*
 kube_burner*
+recommender_*.json
 
 # Project files
 .ropeproject

CI/config/common_test_config.yaml

@@ -29,7 +29,7 @@ tunings:
     daemon_mode: False                                     # Iterations are set to infinity which means that the kraken will cause chaos forever.
 telemetry:
     enabled: False                                           # enable/disables the telemetry collection feature
-    api_url: https://ulnmf9xv7j.execute-api.us-west-2.amazonaws.com/production #telemetry service endpoint
+    api_url: https://yvnn4rfoi7.execute-api.us-west-2.amazonaws.com/test #telemetry service endpoint
     username: $TELEMETRY_USERNAME                                      # telemetry service username
     password: $TELEMETRY_PASSWORD                                      # telemetry service password
     prometheus_namespace: 'prometheus-k8s'                                # prometheus namespace
@@ -49,3 +49,4 @@ telemetry:
         - "(\\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
+    telemetry_group: "funtests"

CI/tests/common.sh

@@ -8,8 +8,14 @@ function finish {
 }
 
 function error {
-    echo "Error caught."
-    ERRORED=true
+    exit_code=$?
+    if [ $exit_code == 1 ]
+    then
+      echo "Error caught."
+      ERRORED=true
+    else
+      echo "Exit code greater than zero detected: $exit_code"
+    fi
 }
 
 function get_node {

CI/tests/test_telemetry.sh

@@ -14,16 +14,20 @@ function functional_test_telemetry {
   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 '.performance_monitoring.check_critical_alerts=True' CI/config/common_test_config.yaml
+  yq -i '.performance_monitoring.prometheus_url="http://localhost:9090"' 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"`
+  RUN_FOLDER=`cat CI/out/test_telemetry.out | grep amazonaws.com | sed -rn "s#.*https:\/\/.*\/files/(.*)#\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 critical-alerts-00.json || ( echo "FAILED: critical-alerts-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!"

README.md

@@ -1,5 +1,4 @@
 # Krkn aka Kraken
-[![Docker Repository on Quay](https://quay.io/repository/krkn-chaos/krkn/status "Docker Repository on Quay")](https://quay.io/repository/krkn-chaos/krkn?tab=tags&tag=latest)
 ![Workflow-Status](https://github.com/krkn-chaos/krkn/actions/workflows/docker-image.yml/badge.svg)
 
 ![Krkn logo](media/logo.png)

config/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
     publish_kraken_status: True                            # Can be accessed at http://0.0.0.0:8081
@@ -15,7 +15,7 @@ kraken:
         - application_outages:
             - scenarios/openshift/app_outage.yaml
         - container_scenarios:                             # List of chaos pod scenarios to load
-            - -    scenarios/openshift/container_etcd.yml
+            - - scenarios/openshift/container_etcd.yml
         - plugin_scenarios:
             - scenarios/openshift/etcd.yml
             - scenarios/openshift/regex_openshift_pod_kill.yml
@@ -23,7 +23,7 @@ kraken:
             - scenarios/openshift/network_chaos_ingress.yml
             - scenarios/openshift/prom_kill.yml
         - node_scenarios:                                  # List of chaos node scenarios to load
-            -   scenarios/openshift/node_scenarios_example.yml
+            - scenarios/openshift/node_scenarios_example.yml
         - plugin_scenarios:
             - scenarios/openshift/openshift-apiserver.yml
             - scenarios/openshift/openshift-kube-apiserver.yml
@@ -51,7 +51,7 @@ cerberus:
 performance_monitoring:
     deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
     repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
+    prometheus_url:                                      # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set
     enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
@@ -65,14 +65,19 @@ 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
+    password: password                                    # telemetry service password
     prometheus_backup: True                                 # enables/disables prometheus data collection
+    prometheus_namespace: ""                                # namespace where prometheus is deployed (if distribution is kubernetes)
+    prometheus_container_name: ""                           # name of the prometheus container name (if distribution is kubernetes)
+    prometheus_pod_name: ""                                 # name of the prometheus pod (if distribution is kubernetes)
     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: 500000                                     # the size of the prometheus data archive size in KB. The lower the size of archive is
+    archive_size: 500000
+    telemetry_group: ''                                     # if set will archive the telemetry in the S3 bucket on a folder named after the value, otherwise will use "default"
+    # the size of the prometheus data archive size in KB. The lower the size of archive is
                                                             # the higher the number of archive files will be produced and uploaded (and processed by backup_threads
                                                             # simultaneously).
                                                             # For unstable/slow connection is better to keep this value low
@@ -85,6 +90,9 @@ telemetry:
      - "(\\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
+elastic: 
+    elastic_url: ""                                         # To track results in elasticsearch, give url to server here; will post telemetry details when url and index not blank
+    elastic_index: ""                                       # Elastic search index pattern to post results to
 
 
 

config/config_performance.yaml

@@ -77,3 +77,8 @@ telemetry:
      - "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
+elastic: 
+    elastic_url: ""                                         # To track results in elasticsearch, give url to server here; will post telemetry details when url and index not blank
+    elastic_index: ""                                       # Elastic search index pattern to post results to
+
+

config/recommender_config.yaml

@@ -7,6 +7,8 @@ auth_token: <Auth_Token>
 scrape_duration: 10m
 chaos_library: "kraken"
 log_level: INFO
+json_output_file: False
+json_output_folder_path:
 
 # for output purpose only do not change if not needed
 chaos_tests:
@@ -26,4 +28,8 @@ chaos_tests:
     - pod_network_chaos
   MEM:
     - node_memory_hog
-    - pvc_disk_fill
+    - pvc_disk_fill
+
+threshold: .7
+cpu_threshold: .5
+mem_threshold: .5

containers/Dockerfile

@@ -12,7 +12,7 @@ COPY --from=azure-cli /usr/local/bin/az /usr/bin/az
 # Install dependencies
 RUN yum install -y git python39 python3-pip jq gettext wget && \
     python3.9 -m pip install -U pip && \
-    git clone https://github.com/krkn-chaos/krkn.git --branch v1.5.7 /root/kraken && \
+    git clone https://github.com/krkn-chaos/krkn.git --branch v1.5.10 /root/kraken && \
     mkdir -p /root/.kube && cd /root/kraken && \
     pip3.9 install -r requirements.txt && \
     pip3.9 install virtualenv && \
@@ -20,7 +20,7 @@ RUN yum install -y git python39 python3-pip jq gettext wget && \
 
 # Get Kubernetes and OpenShift clients from stable releases
 WORKDIR /tmp
-RUN wget https://mirror.openshift.com/pub/openshift-v4/clients/ocp/stable/openshift-client-linux.tar.gz && tar -xvf openshift-client-linux.tar.gz && cp oc /usr/local/bin/oc && cp kubectl /usr/local/bin/kubectl
+RUN wget https://mirror.openshift.com/pub/openshift-v4/clients/ocp/stable/openshift-client-linux.tar.gz && tar -xvf openshift-client-linux.tar.gz && cp oc /usr/local/bin/oc && cp oc /usr/bin/oc && cp kubectl /usr/local/bin/kubectl && cp kubectl /usr/bin/kubectl
 
 WORKDIR /root/kraken
 

containers/Dockerfile-ppc64le

@@ -14,7 +14,7 @@ COPY --from=azure-cli /usr/local/bin/az /usr/bin/az
 # Install dependencies
 RUN yum install -y git python39 python3-pip jq gettext wget && \
     python3.9 -m pip install -U pip && \
-    git clone https://github.com/redhat-chaos/krkn.git --branch v1.5.7 /root/kraken && \
+    git clone https://github.com/redhat-chaos/krkn.git --branch v1.5.10 /root/kraken && \
     mkdir -p /root/.kube && cd /root/kraken && \
     pip3.9 install -r requirements.txt && \
     pip3.9 install virtualenv && \
@@ -22,7 +22,7 @@ RUN yum install -y git python39 python3-pip jq gettext wget && \
 
 # Get Kubernetes and OpenShift clients from stable releases
 WORKDIR /tmp
-RUN wget https://mirror.openshift.com/pub/openshift-v4/clients/ocp/stable/openshift-client-linux.tar.gz && tar -xvf openshift-client-linux.tar.gz && cp oc /usr/local/bin/oc && cp kubectl /usr/local/bin/kubectl
+RUN wget https://mirror.openshift.com/pub/openshift-v4/clients/ocp/stable/openshift-client-linux.tar.gz && tar -xvf openshift-client-linux.tar.gz && cp oc /usr/local/bin/oc && cp oc /usr/bin/oc && cp kubectl /usr/local/bin/kubectl && cp kubectl /usr/bin/kubectl
 
 WORKDIR /root/kraken
 

docs/installation.md

@@ -22,7 +22,7 @@ the capabilities of the current supported scenarios.
 Pick the latest stable release to install [here](https://github.com/krkn-chaos/krkn/releases).
 ```
 $ git clone https://github.com/krkn-chaos/krkn.git --branch <release version>
-$ cd kraken
+$ cd krkn
 ```
 
 #### Install the dependencies

kraken/chaos_recommender/analysis.py

@@ -4,13 +4,10 @@ import pandas as pd
 import kraken.chaos_recommender.kraken_tests as kraken_tests
 import time
 
-threshold = .7  # Adjust the threshold as needed
-heatmap_cpu_threshold = .5
-heatmap_mem_threshold = .5
-
 KRAKEN_TESTS_PATH = "./kraken_chaos_tests.txt"
 
-#Placeholder, this should be done with topology
+
+# Placeholder, this should be done with topology
 def return_critical_services():
     return ["web", "cart"]
 
@@ -19,6 +16,7 @@ def load_telemetry_data(file_path):
     data = pd.read_csv(file_path, delimiter=r"\s+")
     return data
 
+
 def calculate_zscores(data):
     zscores = pd.DataFrame()
     zscores["Service"] = data["service"]
@@ -27,7 +25,8 @@ def calculate_zscores(data):
     zscores["Network"] = (data["NETWORK"] - data["NETWORK"].mean()) / data["NETWORK"].std()
     return zscores
 
-def identify_outliers(data):
+
+def identify_outliers(data, threshold):
     outliers_cpu = data[data["CPU"] > threshold]["Service"].tolist()
     outliers_memory = data[data["Memory"] > threshold]["Service"].tolist()
     outliers_network = data[data["Network"] > threshold]["Service"].tolist()
@@ -47,44 +46,64 @@ def get_services_above_heatmap_threshold(dataframe, cpu_threshold, mem_threshold
     return cpu_services, mem_services
 
 
-def analysis(file_path, chaos_tests_config):
+def analysis(file_path, chaos_tests_config, threshold, heatmap_cpu_threshold, heatmap_mem_threshold):
     # Load the telemetry data from file
+    logging.info("Fetching the Telemetry data")
     data = load_telemetry_data(file_path)
 
     # Calculate Z-scores for CPU, Memory, and Network columns
     zscores = calculate_zscores(data)
 
     # Identify outliers
-    outliers_cpu, outliers_memory, outliers_network = identify_outliers(zscores)
+    logging.info("Identifying outliers")
+    outliers_cpu, outliers_memory, outliers_network = identify_outliers(zscores, threshold)
     cpu_services, mem_services = get_services_above_heatmap_threshold(data, heatmap_cpu_threshold, heatmap_mem_threshold)
 
-    # Display the identified outliers
-    logging.info("======================== Profiling ==================================")
-    logging.info(f"CPU outliers: {outliers_cpu}")
-    logging.info(f"Memory outliers: {outliers_memory}")
-    logging.info(f"Network outliers: {outliers_network}")
-    logging.info("===================== HeatMap Analysis ==============================")
+    analysis_data = analysis_json(outliers_cpu, outliers_memory,
+                                  outliers_network, cpu_services,
+                                  mem_services, chaos_tests_config)
+
+    if not cpu_services:
+        logging.info("There are no services that are using significant CPU compared to their assigned limits (infinite in case no limits are set).")
+    if not mem_services:
+        logging.info("There are no services that are using significant MEMORY compared to their assigned limits (infinite in case no limits are set).")
+    time.sleep(2)
+
+    logging.info("Please check data in utilisation.txt for further analysis")
+
+    return analysis_data
+
+
+def analysis_json(outliers_cpu, outliers_memory, outliers_network,
+                  cpu_services, mem_services, chaos_tests_config):
+
+    profiling = {
+        "cpu_outliers": outliers_cpu,
+        "memory_outliers": outliers_memory,
+        "network_outliers": outliers_network
+    }
+
+    heatmap = {
+        "services_with_cpu_heatmap_above_threshold": cpu_services,
+        "services_with_mem_heatmap_above_threshold": mem_services
+    }
+
+    recommendations = {}
 
     if cpu_services:
-        logging.info("Services with CPU_HEATMAP above threshold:", cpu_services)
-    else:
-        logging.info("There are no services that are using siginificant CPU compared to their assigned limits (infinite in case no limits are set).")
+        cpu_recommend = {"services": cpu_services,
+                         "tests": chaos_tests_config['CPU']}
+        recommendations["cpu_services_recommendations"] = cpu_recommend
+
     if mem_services:
-        logging.info("Services with MEM_HEATMAP above threshold:", mem_services)
-    else:
-        logging.info("There are no services that are using siginificant MEMORY compared to their assigned limits (infinite in case no limits are set).")
-    time.sleep(2)
-    logging.info("======================= Recommendations =============================")
-    if cpu_services:
-        logging.info(f"Recommended tests for {str(cpu_services)}  :\n {chaos_tests_config['CPU']}")
-        logging.info("\n")
-    if mem_services:
-        logging.info(f"Recommended tests for {str(mem_services)}  :\n {chaos_tests_config['MEM']}")
-        logging.info("\n")
+        mem_recommend = {"services": mem_services,
+                         "tests": chaos_tests_config['MEM']}
+        recommendations["mem_services_recommendations"] = mem_recommend
 
     if outliers_network:
-        logging.info(f"Recommended tests for  str(outliers_network)  :\n {chaos_tests_config['NETWORK']}")
-        logging.info("\n")
+        outliers_network_recommend = {"outliers_networks": outliers_network,
+                                      "tests": chaos_tests_config['NETWORK']}
+        recommendations["outliers_network_recommendations"] = (
+            outliers_network_recommend)
 
-    logging.info("\n")
-    logging.info("Please check data in utilisation.txt for further analysis")
+    return [profiling, heatmap, recommendations]

kraken/chaos_recommender/prometheus.py

@@ -1,6 +1,5 @@
 import logging
 
-import pandas
 from prometheus_api_client import PrometheusConnect
 import pandas as pd
 import urllib3
@@ -8,6 +7,7 @@ import urllib3
 
 saved_metrics_path = "./utilisation.txt"
 
+
 def convert_data_to_dataframe(data, label):
     df = pd.DataFrame()
     df['service'] = [item['metric']['pod'] for item in data]
@@ -25,6 +25,7 @@ def convert_data(data, service):
         result[pod_name] = value
     return result.get(service, '100000000000') # for those pods whose limits are not defined they can take as much resources, there assigning a very high value
 
+
 def save_utilization_to_file(cpu_data, cpu_limits_result, mem_data, mem_limits_result, network_data, filename):
     df_cpu = convert_data_to_dataframe(cpu_data, "CPU")
     merged_df = pd.DataFrame(columns=['service','CPU','CPU_LIMITS','MEM','MEM_LIMITS','NETWORK'])
@@ -39,8 +40,6 @@ def save_utilization_to_file(cpu_data, cpu_limits_result, mem_data, mem_limits_r
                     "NETWORK" : convert_data(network_data, s)}, index=[0])
         merged_df = pd.concat([merged_df, new_row_df], ignore_index=True)
 
-
-
     # Convert columns to string
     merged_df['CPU'] = merged_df['CPU'].astype(str)
     merged_df['MEM'] = merged_df['MEM'].astype(str)
@@ -57,40 +56,39 @@ def save_utilization_to_file(cpu_data, cpu_limits_result, mem_data, mem_limits_r
 
     merged_df.to_csv(filename, sep='\t', index=False)
 
+
 def fetch_utilization_from_prometheus(prometheus_endpoint, auth_token, namespace, scrape_duration):
     urllib3.disable_warnings()
     prometheus = PrometheusConnect(url=prometheus_endpoint, headers={'Authorization':'Bearer {}'.format(auth_token)}, disable_ssl=True)
 
     # Fetch CPU utilization
+    logging.info("Fetching utilization")
     cpu_query = 'sum (rate (container_cpu_usage_seconds_total{image!="", namespace="%s"}[%s])) by (pod) *1000' % (namespace,scrape_duration)
-    logging.info(cpu_query)
     cpu_result = prometheus.custom_query(cpu_query)
-    cpu_data = cpu_result
-
 
     cpu_limits_query = '(sum by (pod) (kube_pod_container_resource_limits{resource="cpu", namespace="%s"}))*1000' %(namespace)
-    logging.info(cpu_limits_query)
     cpu_limits_result = prometheus.custom_query(cpu_limits_query)
 
-
     mem_query = 'sum by (pod) (avg_over_time(container_memory_usage_bytes{image!="", namespace="%s"}[%s]))' % (namespace, scrape_duration)
-    logging.info(mem_query)
     mem_result = prometheus.custom_query(mem_query)
-    mem_data = mem_result
 
     mem_limits_query = 'sum by (pod) (kube_pod_container_resource_limits{resource="memory", namespace="%s"})  ' %(namespace)
-    logging.info(mem_limits_query)
     mem_limits_result = prometheus.custom_query(mem_limits_query)
 
-
     network_query = 'sum by (pod) ((avg_over_time(container_network_transmit_bytes_total{namespace="%s"}[%s])) + \
     (avg_over_time(container_network_receive_bytes_total{namespace="%s"}[%s])))' % (namespace, scrape_duration, namespace, scrape_duration)
     network_result = prometheus.custom_query(network_query)
-    logging.info(network_query)
-    network_data = network_result
-
-
-    save_utilization_to_file(cpu_data, cpu_limits_result, mem_data, mem_limits_result, network_data, saved_metrics_path)
-    return saved_metrics_path
+
+    save_utilization_to_file(cpu_result, cpu_limits_result, mem_result, mem_limits_result, network_result, saved_metrics_path)
+    queries = json_queries(cpu_query, cpu_limits_query, mem_query, mem_limits_query)
+    return saved_metrics_path, queries
 
 
+def json_queries(cpu_query, cpu_limits_query, mem_query, mem_limits_query):
+    queries = {
+        "cpu_query": cpu_query,
+        "cpu_limit_query": cpu_limits_query,
+        "memory_query": mem_query,
+        "memory_limit_query": mem_limits_query
+    }
+    return queries

kraken/plugins/__init__.py

@@ -213,6 +213,12 @@ PLUGINS = Plugins(
                 "error"
             ]
         ),
+        PluginStep(
+            network_chaos,
+            [
+                "error"
+            ]
+        ),        
         PluginStep(
             pod_outage,
             [

kraken/plugins/network/ingress_shaping.py

@@ -62,7 +62,7 @@ class NetworkScenarioConfig:
         typing.Optional[int],
         validation.min(1)
     ] = field(
-        default=300,
+        default=30,
         metadata={
             "name": "Wait Duration",
             "description":
@@ -864,7 +864,7 @@ def network_chaos(cfg: NetworkScenarioConfig) -> typing.Tuple[
                 )
             logging.info("Waiting for parallel job to finish")
             start_time = int(time.time())
-            wait_for_job(batch_cli, job_list[:], cfg.wait_duration)
+            wait_for_job(batch_cli, job_list[:], cfg.test_duration+100)
             end_time = int(time.time())
             if publish:
                 cerberus.publish_kraken_status(
@@ -893,7 +893,7 @@ def network_chaos(cfg: NetworkScenarioConfig) -> typing.Tuple[
                     )
                 logging.info("Waiting for serial job to finish")
                 start_time = int(time.time())
-                wait_for_job(batch_cli, job_list[:], cfg.wait_duration)
+                wait_for_job(batch_cli, job_list[:], cfg.test_duration+100)
                 logging.info("Deleting jobs")
                 delete_jobs(cli, batch_cli, job_list[:])
                 job_list = []

kraken/prometheus/client.py

@@ -1,10 +1,13 @@
 import datetime
 import os.path
+from typing import Optional
+
 import urllib3
 import logging
 import sys
 
 import yaml
+from krkn_lib.models.krkn import ChaosRunAlertSummary, ChaosRunAlert
 from krkn_lib.prometheus.krkn_prometheus import KrknPrometheus
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 def alerts(prom_cli: KrknPrometheus, start_time, end_time, alert_profile):
@@ -27,4 +30,59 @@ def alerts(prom_cli: KrknPrometheus, start_time, end_time, alert_profile):
 
             prom_cli.process_alert(alert,
                                    datetime.datetime.fromtimestamp(start_time),
-                                   datetime.datetime.fromtimestamp(end_time))
+                                   datetime.datetime.fromtimestamp(end_time))
+
+
+def critical_alerts(prom_cli: KrknPrometheus,
+                    summary: ChaosRunAlertSummary,
+                    run_id,
+                    scenario,
+                    start_time,
+                    end_time):
+    summary.scenario = scenario
+    summary.run_id = run_id
+    query = r"""ALERTS{severity="critical"}"""
+    logging.info("Checking for critical alerts firing post chaos")
+
+    during_critical_alerts = prom_cli.process_prom_query_in_range(
+        query,
+        start_time=datetime.datetime.fromtimestamp(start_time),
+        end_time=end_time
+
+    )
+
+    for alert in during_critical_alerts:
+        if "metric" in alert:
+            alertname = alert["metric"]["alertname"] if "alertname" in alert["metric"] else "none"
+            alertstate = alert["metric"]["alertstate"] if "alertstate" in alert["metric"] else "none"
+            namespace = alert["metric"]["namespace"] if "namespace" in alert["metric"] else "none"
+            severity = alert["metric"]["severity"] if "severity" in alert["metric"] else "none"
+            alert = ChaosRunAlert(alertname, alertstate, namespace, severity)
+            summary.chaos_alerts.append(alert)
+
+
+    post_critical_alerts = prom_cli.process_query(
+        query
+    )
+
+    for alert in post_critical_alerts:
+        if "metric" in alert:
+            alertname = alert["metric"]["alertname"] if "alertname" in alert["metric"] else "none"
+            alertstate = alert["metric"]["alertstate"] if "alertstate" in alert["metric"] else "none"
+            namespace = alert["metric"]["namespace"] if "namespace" in alert["metric"] else "none"
+            severity = alert["metric"]["severity"] if "severity" in alert["metric"] else "none"
+            alert = ChaosRunAlert(alertname, alertstate, namespace, severity)
+            summary.post_chaos_alerts.append(alert)
+
+    during_critical_alerts_count = len(during_critical_alerts)
+    post_critical_alerts_count = len(post_critical_alerts)
+    firing_alerts = False
+
+    if during_critical_alerts_count > 0:
+        firing_alerts = True
+
+    if post_critical_alerts_count > 0:
+        firing_alerts = True
+
+    if not firing_alerts:
+        logging.info("No critical alerts are firing!!")

requirements.txt

@@ -10,13 +10,12 @@ itsdangerous==2.0.1
 coverage==7.4.1
 datetime==5.4
 docker==7.0.0
-docker-compose==1.29.2
 gitpython==3.1.41
 google-api-python-client==2.116.0
 ibm_cloud_sdk_core==3.18.0
 ibm_vpc==0.20.0
 jinja2==3.1.3
-krkn-lib==1.4.9
+krkn-lib==2.1.0
 lxml==5.1.0
 kubernetes==26.1.0
 oauth2client==4.1.3
@@ -31,11 +30,12 @@ python-ipmi==0.5.4
 python-openstackclient==6.5.0
 requests==2.31.0
 service_identity==24.1.0
-PyYAML==5.4.1
+PyYAML==6.0
 setuptools==65.5.1
 werkzeug==3.0.1
 wheel==0.42.0
 zope.interface==5.4.0
 
 git+https://github.com/krkn-chaos/arcaflow-plugin-kill-pod.git
-git+https://github.com/vmware/vsphere-automation-sdk-python.git@v8.0.0.0
+git+https://github.com/vmware/vsphere-automation-sdk-python.git@v8.0.0.0
+cryptography>=42.0.4 # not directly required, pinned by Snyk to avoid a vulnerability

run_kraken.py

@@ -9,6 +9,8 @@ import optparse
 import pyfiglet
 import uuid
 import time
+
+from krkn_lib.models.krkn import ChaosRunOutput, ChaosRunAlertSummary
 from krkn_lib.prometheus.krkn_prometheus import KrknPrometheus
 import kraken.time_actions.common_time_functions as time_actions
 import kraken.performance_dashboards.setup as performance_dashboards
@@ -27,6 +29,7 @@ import server as server
 from kraken import plugins
 from krkn_lib.k8s import KrknKubernetes
 from krkn_lib.ocp import KrknOpenshift
+from krkn_lib.telemetry.elastic import KrknElastic
 from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
 from krkn_lib.models.telemetry import ChaosRunTelemetry
@@ -94,6 +97,9 @@ def main(cfg):
             config["performance_monitoring"], "check_critical_alerts", False
         )
         telemetry_api_url = config["telemetry"].get("api_url")
+        elastic_config = get_yaml_item_value(config,"elastic",{})
+        elastic_url = get_yaml_item_value(elastic_config,"elastic_url","")
+        elastic_index = get_yaml_item_value(elastic_config,"elastic_index","")
         
         # Initialize clients
         if (not os.path.isfile(kubeconfig_path) and
@@ -129,8 +135,6 @@ def main(cfg):
         except:
             kubecli.initialize_clients(None)
 
-
-
         # find node kraken might be running on
         kubecli.find_kraken_node()
 
@@ -161,8 +165,13 @@ def main(cfg):
             if prometheus_url is None:
                 try:
                     connection_data = ocpcli.get_prometheus_api_connection_data()
-                    prometheus_url = connection_data.endpoint
-                    prometheus_bearer_token = connection_data.token
+                    if connection_data:
+                        prometheus_url = connection_data.endpoint
+                        prometheus_bearer_token = connection_data.token
+                    else: 
+                        # If can't make a connection, set alerts to false
+                        enable_alerts = False
+                        critical_alerts = False
                 except Exception:
                     logging.error("invalid distribution selected, running openshift scenarios against kubernetes cluster."
                                   "Please set 'kubernetes' in config.yaml krkn.platform and try again")
@@ -175,9 +184,9 @@ def main(cfg):
         # KrknTelemetry init
         telemetry_k8s = KrknTelemetryKubernetes(safe_logger, kubecli)
         telemetry_ocp = KrknTelemetryOpenshift(safe_logger, ocpcli)
-
-
-        if enable_alerts:
+        telemetry_elastic = KrknElastic(safe_logger,elastic_url)
+        summary = ChaosRunAlertSummary()
+        if enable_alerts or check_critical_alerts:
             prometheus = KrknPrometheus(prometheus_url, prometheus_bearer_token)
 
         logging.info("Server URL: %s" % kubecli.get_host())
@@ -208,7 +217,8 @@ def main(cfg):
 
         # Capture the start time
         start_time = int(time.time())
-
+        post_critical_alerts = 0
+        chaos_output = ChaosRunOutput()
         chaos_telemetry = ChaosRunTelemetry()
         chaos_telemetry.run_uuid = run_uuid
         # Loop to run the chaos starts here
@@ -339,25 +349,21 @@ def main(cfg):
                             failed_post_scenarios, scenario_telemetries = network_chaos.run(scenarios_list, config, wait_duration, kubecli, telemetry_k8s)
 
                         # Check for critical alerts when enabled
-                        if enable_alerts and check_critical_alerts :
-                            logging.info("Checking for critical alerts firing post choas")
+                        post_critical_alerts = 0
+                        if check_critical_alerts:
+                            prometheus_plugin.critical_alerts(prometheus,
+                                                              summary,
+                                                              run_uuid,
+                                                              scenario_type,
+                                                              start_time,
+                                                              datetime.datetime.now())
 
-                            ##PROM
-                            query = r"""ALERTS{severity="critical"}"""
-                            end_time = datetime.datetime.now()
-                            critical_alerts = prometheus.process_prom_query_in_range(
-                                query,
-                                start_time = datetime.datetime.fromtimestamp(start_time),
-                                end_time = end_time
+                            chaos_output.critical_alerts = summary
+                            post_critical_alerts = len(summary.post_chaos_alerts)
+                            if post_critical_alerts > 0:
+                                logging.error("Post chaos critical alerts firing please check, exiting")
+                                break
 
-                            )
-                            critical_alerts_count = len(critical_alerts)
-                            if critical_alerts_count > 0:
-                                logging.error("Critical alerts are firing: %s", critical_alerts)
-                                logging.error("Please check, exiting")
-                                sys.exit(1)
-                            else:
-                                logging.info("No critical alerts are firing!!")
 
             iteration += 1
             logging.info("")
@@ -377,14 +383,18 @@ def main(cfg):
             telemetry_k8s.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()}")
-
+        chaos_output.telemetry = decoded_chaos_run_telemetry
+        logging.info(f"Chaos data:\n{chaos_output.to_json()}")
+        telemetry_elastic.upload_data_to_elasticsearch(decoded_chaos_run_telemetry.to_json(), elastic_index)
         if config["telemetry"]["enabled"]:
-            logging.info(f"telemetry data will be stored on s3 bucket folder: {telemetry_api_url}/download/{telemetry_request_id}")
+            logging.info(f'telemetry data will be stored on s3 bucket folder: {telemetry_api_url}/files/'
+                         f'{(config["telemetry"]["telemetry_group"] if config["telemetry"]["telemetry_group"] else "default")}/'
+                         f'{telemetry_request_id}')
             logging.info(f"telemetry upload log: {safe_logger.log_file_name}")
             try:
                 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)
+                telemetry_k8s.put_critical_alerts(telemetry_request_id, config["telemetry"], summary)
                 # prometheus data collection is available only on Openshift
                 if config["telemetry"]["prometheus_backup"]:
                     prometheus_archive_files = ''
@@ -434,11 +444,15 @@ def main(cfg):
                 logging.error("Alert profile is not defined")
                 sys.exit(1)
 
+        if post_critical_alerts > 0:
+            logging.error("Critical alerts are firing, please check; exiting")
+            sys.exit(2)
+
         if failed_post_scenarios:
             logging.error(
                 "Post scenarios are still failing at the end of all iterations"
             )
-            sys.exit(1)
+            sys.exit(2)
 
         logging.info(
             "Successfully finished running Kraken. UUID for the run: "

scenarios/arcaflow/cpu-hog/config.yaml

@@ -4,7 +4,7 @@ deployers:
     connection: {}
     deployer_name: kubernetes
 log:
-  level: debug
+  level: error
 logged_outputs:
   error:
     level: error

scenarios/arcaflow/io-hog/config.yaml

@@ -3,7 +3,7 @@ deployers:
     connection: {}
     deployer_name: kubernetes
 log:
-  level: debug
+  level: error
 logged_outputs:
   error:
     level: error

scenarios/arcaflow/memory-hog/config.yaml

@@ -4,7 +4,7 @@ deployers:
     connection: {}
     deployer_name: kubernetes
 log:
-  level: debug
+  level: error
 logged_outputs:
   error:
     level: error

utils/chaos_recommender/README.md

@@ -20,6 +20,8 @@ This tool profiles an application and gathers telemetry data such as CPU, Memory
     $ git clone https://github.com/krkn-chaos/krkn.git 
     $ cd krkn
     $ pip3 install -r requirements.txt
+    Edit configuration file:
+    $ vi config/recommender_config.yaml 
     $ python3.9 utils/chaos_recommender/chaos_recommender.py
     ```
 
@@ -37,11 +39,16 @@ You can customize the default values by editing the `krkn/config/recommender_con
   - `auth_token`: Auth token to connect to prometheus endpoint (must).
   - `scrape_duration`: For how long data should be fetched, e.g., '1m' (must).
   - `chaos_library`: "kraken" (currently it only supports kraken).
+  - `json_output_file`: True or False (by default False).
+  - `json_output_folder_path`: Specify folder path where output should be saved. If empty the default path is used.
   - `chaos_tests`: (for output purpose only do not change if not needed)
     - `GENERAL`: list of general purpose tests available in Krkn
     - `MEM`: list of memory related tests available in Krkn
     - `NETWORK`: list of network related tests available in Krkn
     - `CPU`: list of memory related tests available in Krkn
+  - `threshold`: Specify the threshold to use for comparison and identifying outliers
+  - `cpu_threshold`: Specify the cpu threshold to compare with the cpu limits set on the pods and identify outliers
+  - `mem_threshold`: Specify the memory threshold to compare with the memory limits set on the pods and identify outliers
 
 *TIP:* to collect prometheus endpoint and token from your OpenShift cluster you can run the following commands:
         ```
@@ -74,6 +81,8 @@ You can also provide the input values through command-line arguments launching t
                         Chaos library
   -L LOG_LEVEL, --log-level LOG_LEVEL
                         log level (DEBUG, INFO, WARNING, ERROR, CRITICAL
+  -J [FOLDER_PATH], --json-output-file [FOLDER_PATH]
+                        Create output file, the path to the folder can be specified, if not specified the default folder is used.
   -M MEM [MEM ...], --MEM MEM [MEM ...]
                         Memory related chaos tests (space separated list)
   -C CPU [CPU ...], --CPU CPU [CPU ...]
@@ -82,7 +91,12 @@ You can also provide the input values through command-line arguments launching t
                         Network related chaos tests (space separated list)
   -G GENERIC [GENERIC ...], --GENERIC GENERIC [GENERIC ...]
                         Memory related chaos tests (space separated list)
-
+  --threshold THRESHOLD
+                        Threshold
+  --cpu_threshold CPU_THRESHOLD
+                        CPU threshold to compare with the cpu limits
+  --mem_threshold MEM_THRESHOLD
+                        Memory threshold to compare with the memory limits
 ```
 
 If you provide the input values through command-line arguments, the corresponding config file inputs would be ignored.
@@ -97,7 +111,7 @@ After obtaining telemetry data, sourced either locally or from Prometheus, the t
 
 ## Customizing Thresholds and Options
 
-You can customize the thresholds and options used for data analysis by modifying the `krkn/kraken/chaos_recommender/analysis.py` file. For example, you can adjust the threshold for identifying outliers by changing the value of the `threshold` variable in the `identify_outliers` function.
+You can customize the thresholds and options used for data analysis and identifying the outliers by setting the threshold, cpu_threshold and mem_threshold parameters in the config.
 
 ## Additional Files
 

utils/chaos_recommender/chaos_recommender.py

@@ -1,7 +1,9 @@
 import argparse
+import json
 import logging
 import os.path
 import sys
+import time
 import yaml
 # kraken module import for running the recommender
 # both from the root directory and the recommender
@@ -9,12 +11,13 @@ import yaml
 sys.path.insert(0, './')
 sys.path.insert(0, '../../')
 
+from krkn_lib.utils import get_yaml_item_value
+
 import kraken.chaos_recommender.analysis as analysis
 import kraken.chaos_recommender.prometheus as prometheus
 from kubernetes import config as kube_config
 
 
-
 def parse_arguments(parser):
 
     # command line options
@@ -27,6 +30,9 @@ def parse_arguments(parser):
     parser.add_argument("-s", "--scrape-duration", action="store", default="10m", help="Prometheus scrape duration")
     parser.add_argument("-L", "--log-level", action="store", default="INFO", help="log level (DEBUG, INFO, WARNING, ERROR, CRITICAL")
 
+    parser.add_argument("-J", "--json-output-file", default=False, nargs="?", action="store",
+                        help="Create output file, the path to the folder can be specified, if not specified the default folder is used")
+
     parser.add_argument("-M", "--MEM", nargs='+', action="store", default=[],
                         help="Memory related chaos tests (space separated list)")
     parser.add_argument("-C", "--CPU", nargs='+', action="store", default=[],
@@ -35,10 +41,13 @@ def parse_arguments(parser):
                         help="Network related chaos tests (space separated list)")
     parser.add_argument("-G", "--GENERIC", nargs='+', action="store", default=[],
                         help="Memory related chaos tests (space separated list)")
-
+    parser.add_argument("--threshold", action="store", default="", help="Threshold")
+    parser.add_argument("--cpu-threshold", action="store", default="", help="CPU threshold")
+    parser.add_argument("--mem-threshold", action="store", default="", help="Memory threshold")
 
     return parser.parse_args()
 
+
 def read_configuration(config_file_path):
     if not os.path.exists(config_file_path):
         logging.error(f"Config file not found: {config_file_path}")
@@ -48,15 +57,25 @@ def read_configuration(config_file_path):
         config = yaml.safe_load(config_file)
 
     log_level = config.get("log level", "INFO")
-    namespace = config.get("namespace", "")
-    kubeconfig = config.get("kubeconfig", kube_config.KUBE_CONFIG_DEFAULT_LOCATION)
+    namespace = config.get("namespace")
+    kubeconfig = get_yaml_item_value(config, "kubeconfig", kube_config.KUBE_CONFIG_DEFAULT_LOCATION)
 
-    prometheus_endpoint = config.get("prometheus_endpoint", "")
-    auth_token = config.get("auth_token", "")
-    scrape_duration = config.get("scrape_duration", "10m")
-    chaos_tests = config.get("chaos_tests" , {})
+    prometheus_endpoint = config.get("prometheus_endpoint")
+    auth_token = config.get("auth_token")
+    scrape_duration = get_yaml_item_value(config, "scrape_duration", "10m")
+    threshold = get_yaml_item_value(config, "threshold", ".7")
+    heatmap_cpu_threshold = get_yaml_item_value(config, "cpu_threshold", ".5")
+    heatmap_mem_threshold = get_yaml_item_value(config, "mem_threshold", ".3")
+    output_file = config.get("json_output_file", False)
+    if output_file is True:
+        output_path = config.get("json_output_folder_path")
+    else:
+        output_path = False
+    chaos_tests = config.get("chaos_tests", {})
     return (namespace, kubeconfig, prometheus_endpoint, auth_token, scrape_duration,
-            chaos_tests, log_level)
+            chaos_tests, log_level, threshold, heatmap_cpu_threshold,
+            heatmap_mem_threshold, output_path)
+
 
 def prompt_input(prompt, default_value):
     user_input = input(f"{prompt} [{default_value}]: ")
@@ -64,6 +83,44 @@ def prompt_input(prompt, default_value):
         return user_input
     return default_value
 
+
+def make_json_output(inputs, queries, analysis_data, output_path):
+    time_str = time.strftime("%Y-%m-%d_%H-%M-%S", time.localtime())
+
+    data = {
+        "inputs": inputs,
+        "queries": queries,
+        "profiling": analysis_data[0],
+        "heatmap_analysis": analysis_data[1],
+        "recommendations": analysis_data[2]
+    }
+
+    logging.info(f"Summary\n{json.dumps(data, indent=4)}")
+
+    if output_path is not False:
+        file = f"recommender_{inputs['namespace']}_{time_str}.json"
+        path = f"{os.path.expanduser(output_path)}/{file}"
+
+        with open(path, "w") as json_output:
+            logging.info(f"Saving output file in {output_path} folder...")
+            json_output.write(json.dumps(data, indent=4))
+            logging.info(f"Recommendation output saved in {file}.")
+
+
+def json_inputs(namespace, kubeconfig, prometheus_endpoint, scrape_duration, chaos_tests, threshold, heatmap_cpu_threshold, heatmap_mem_threshold):
+    inputs = {
+        "namespace": namespace,
+        "kubeconfig": kubeconfig,
+        "prometheus_endpoint": prometheus_endpoint,
+        "scrape_duration": scrape_duration,
+        "chaos_tests": chaos_tests,
+        "threshold": threshold,
+        "heatmap_cpu_threshold": heatmap_cpu_threshold,
+        "heatmap_mem_threshold": heatmap_mem_threshold
+    }
+    return inputs
+
+
 def main():
     parser = argparse.ArgumentParser(description="Krkn Chaos Recommender Command-Line tool")
     args = parse_arguments(parser)
@@ -81,7 +138,11 @@ def main():
          auth_token,
          scrape_duration,
          chaos_tests,
-         log_level
+         log_level,
+         threshold,
+         heatmap_cpu_threshold,
+         heatmap_mem_threshold,
+         output_path
          ) = read_configuration(args.config_file)
 
     if args.options:
@@ -91,27 +152,35 @@ def main():
         scrape_duration = args.scrape_duration
         log_level = args.log_level
         prometheus_endpoint = args.prometheus_endpoint
+        output_path = args.json_output_file
         chaos_tests = {"MEM": args.MEM, "GENERIC": args.GENERIC, "CPU": args.CPU, "NETWORK": args.NETWORK}
+        threshold = args.threshold
+        heatmap_mem_threshold = args.mem_threshold
+        heatmap_cpu_threshold = args.cpu_threshold
 
-    if log_level not in ["DEBUG","INFO", "WARNING", "ERROR","CRITICAL"]:
+    if log_level not in ["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"]:
         logging.error(f"{log_level} not a valid log level")
         sys.exit(1)
 
     logging.basicConfig(level=log_level)
 
-    logging.info("============================INPUTS===================================")
-    logging.info(f"Namespace: {namespace}")
-    logging.info(f"Kubeconfig: {kubeconfig}")
-    logging.info(f"Prometheus endpoint: {prometheus_endpoint}")
-    logging.info(f"Scrape duration: {scrape_duration}")
-    for test in chaos_tests.keys():
-        logging.info(f"Chaos tests {test}: {chaos_tests[test]}")
-    logging.info("=====================================================================")
+    if output_path is not False:
+        if output_path is None:
+            output_path = "./recommender_output"
+            logging.info(f"Path for output file not specified. "
+                         f"Using default folder {output_path}")
+        if not os.path.exists(os.path.expanduser(output_path)):
+            logging.error(f"Folder {output_path} for output not found.")
+            sys.exit(1)
+    logging.info("Loading inputs...")
+    inputs = json_inputs(namespace, kubeconfig, prometheus_endpoint, scrape_duration, chaos_tests, threshold, heatmap_cpu_threshold, heatmap_mem_threshold)
     logging.info("Starting Analysis ...")
-    logging.info("Fetching the Telemetry data")
 
-    file_path = prometheus.fetch_utilization_from_prometheus(prometheus_endpoint, auth_token, namespace, scrape_duration)
-    analysis(file_path, chaos_tests)
+    file_path, queries = prometheus.fetch_utilization_from_prometheus(prometheus_endpoint, auth_token, namespace, scrape_duration)
+    analysis_data = analysis(file_path, chaos_tests, threshold, heatmap_cpu_threshold, heatmap_mem_threshold)
+
+    make_json_output(inputs, queries, analysis_data, output_path)
+
 
 if __name__ == "__main__":
     main()