resiliency:
  resiliency_run_mode: standalone
  resiliency_file: config/alerts.yaml

kraken:
    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
    signal_state: RUN                                      # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
    signal_address: 0.0.0.0                                # Signal listening address
    port: 8081                                             # Signal port
    chaos_scenarios:
        # List of policies/chaos scenarios to load
        - hog_scenarios:
            - scenarios/kube/cpu-hog.yml
            - scenarios/kube/memory-hog.yml
            - scenarios/kube/io-hog.yml
        - application_outages_scenarios:
            - scenarios/openshift/app_outage.yaml
        - container_scenarios:                             # List of chaos pod scenarios to load
            - scenarios/openshift/container_etcd.yml
        - pod_network_scenarios:
              - scenarios/openshift/network_chaos_ingress.yml
              - scenarios/openshift/pod_network_outage.yml
        - pod_disruption_scenarios:
            - scenarios/openshift/etcd.yml
            - scenarios/openshift/regex_openshift_pod_kill.yml
            - scenarios/openshift/prom_kill.yml
            - scenarios/openshift/openshift-apiserver.yml
            - scenarios/openshift/openshift-kube-apiserver.yml
        - node_scenarios:                                  # List of chaos node scenarios to load
            - scenarios/openshift/aws_node_scenarios.yml
            - scenarios/openshift/vmware_node_scenarios.yml
            - scenarios/openshift/ibmcloud_node_scenarios.yml
        - time_scenarios:                                  # List of chaos time scenarios to load
            - scenarios/openshift/time_scenarios_example.yml
        - cluster_shut_down_scenarios:
            - scenarios/openshift/cluster_shut_down_scenario.yml
        - service_disruption_scenarios:
             - scenarios/openshift/regex_namespace.yaml
             - scenarios/openshift/ingress_namespace.yaml
        - zone_outages_scenarios:
            - scenarios/openshift/zone_outage.yaml
        - pvc_scenarios:
            - scenarios/openshift/pvc_scenario.yaml
        - network_chaos_scenarios:
            - scenarios/openshift/network_chaos.yaml
        - service_hijacking_scenarios:
              - scenarios/kube/service_hijacking.yaml
        - syn_flood_scenarios:
              - scenarios/kube/syn_flood.yaml

cerberus:
    cerberus_enabled: False                                # Enable it when cerberus is previously installed
    cerberus_url:                                          # When cerberus_enabled is set to True, provide the url where cerberus publishes go/no-go signal
    check_applicaton_routes: False                         # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run

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_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
    enable_metrics: False
    alert_profile: config/alerts.yaml                          # Path or URL to alert profile with the prometheus queries
    metrics_profile: config/metrics-report.yaml
    check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos
elastic:
    enable_elastic: False
    verify_certs: False
    elastic_url: ""                                         # To track results in elasticsearch, give url to server here; will post telemetry details when url and index not blank
    elastic_port: 32766
    username: "elastic"
    password: "test"
    metrics_index: "krkn-metrics"
    alerts_index: "krkn-alerts"
    telemetry_index: "krkn-telemetry"

tunings:
    wait_duration: 60                                      # Duration to wait between each chaos scenario
    iterations: 1                                          # Number of times to execute the scenarios
    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
    username: username                                      # telemetry service username
    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
    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
                                                            # 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
    events_backup: True                                     # enables/disables cluster events collection

health_checks:                                              # Utilizing health check endpoints to observe application behavior during chaos injection.
    interval:                                               # Interval in seconds to perform health checks, default value is 2 seconds
    config:                                                 # Provide list of health check configurations for applications
        - url:                                              # Provide application endpoint
          bearer_token:                                     # Bearer token for authentication if any
          auth:                                             # Provide authentication credentials (username , password) in tuple format if any, ex:("admin","secretpassword")
          exit_on_failure:                                  # If value is True exits when health check failed for application, values can be True/False
kubevirt_checks:                                            # Utilizing virt check endpoints to observe ssh ability to VMI's during chaos injection.
    interval: 2                                             # Interval in seconds to perform virt checks, default value is 2 seconds
    namespace:                                              # Namespace where to find VMI's
    name:                                                   # Regex Name style of VMI's to watch; optional, if left blank will find all names in namespace
    only_failures: False                                    # Boolean of whether to show all VMI's failures and successful ssh connection (False), or only failure status' (True) 
    ssh_node: ""                                      # If set, will be a backup way to ssh to a node. Will want to set to a node that isn't targeted in chaos
    node_names: ""                                    # List of node names to further filter down the VM's, will only watch VMs with matching name in the given namespace that are running on node. Can put multiple by separating by a comma

health_checks:
  interval: <time_in_seconds>                       # Defines the frequency of health checks, default value is 2 seconds
  config:                                           # List of application endpoints to check
    - url: "https://example.com/health"
      bearer_token: "hfjauljl..."                   # Bearer token for authentication if any
      auth:                                         
      exit_on_failure: True                         # If value is True exits when health check failed for application, values can be True/False
      verify_url: True                              # SSL Verification of URL, default to true
    - url: "https://another-service.com/status"
      bearer_token:
      auth: ("admin","secretpassword")              # Provide authentication credentials (username , password) in tuple format if any, ex:("admin","secretpassword")
      exit_on_failure: False
      verify_url: False  
    - url: http://general-service.com
      bearer_token:
      auth:
      exit_on_failure:  
      verify_url: False  

"health_checks": [
            {
                "url": "https://example.com/health",
                "status": False,
                "status_code": "503",
                "start_timestamp": "2025-02-25 11:51:33",
                "end_timestamp": "2025-02-25 11:51:40",
                "duration": "0:00:07"
            },
            {
                "url": "https://another-service.com/status",
                "status": True,
                "status_code": 200,
                "start_timestamp": "2025-02-25 22:18:19",
                "end_timestamp": "22025-02-25 22:22:46",
                "duration": "0:04:27"
            },
            {
                "url": "http://general-service.com",
                "status": True,
                "status_code": 200,
                "start_timestamp": "2025-02-25 22:18:19",
                "end_timestamp": "22025-02-25 22:22:46",
                "duration": "0:04:27"
            }
        ],

apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
  name: krkn-ns-privileged-role
  namespace: <target-namespace>
rules:
- apiGroups: [""]
  resources: ["pods", "services"]
  verbs: ["get", "list", "watch", "create", "delete"]
- apiGroups: ["apps"]
  resources: ["deployments", "statefulsets"]
  verbs: ["get", "list", "watch", "create", "delete"]
- apiGroups: ["batch"]
  resources: ["jobs"]
  verbs: ["get", "list", "watch", "create", "delete"]

apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  name: krkn-ns-privileged-rolebinding
  namespace: <target-namespace>
subjects:
- kind: ServiceAccount
  name: <krkn-sa>
  namespace: <target-namespace>
roleRef:
  kind: Role
  name: krkn-ns-privileged-role
  apiGroup: rbac.authorization.k8s.io

apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: krkn-privileged-clusterrole
rules:
- apiGroups: [""]
  resources: ["nodes"]
  verbs: ["get", "list", "watch", "create", "delete", "update", "patch"]
- apiGroups: [""]
  resources: ["pods", "services"]
  verbs: ["get", "list", "watch", "create", "delete", "update", "patch"]
- apiGroups: ["apps"]
  resources: ["deployments", "statefulsets"]
  verbs: ["get", "list", "watch", "create", "delete", "update", "patch"]
- apiGroups: ["batch"]
  resources: ["jobs"]
  verbs: ["get", "list", "watch", "create", "delete", "update", "patch"]

apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: krkn-privileged-clusterrolebinding
subjects:
- kind: ServiceAccount
  name: <krkn-sa>
  namespace: <krkn-namespace>
roleRef:
  kind: ClusterRole
  name: krkn-privileged-clusterrole
  apiGroup: rbac.authorization.k8s.io

kubectl create serviceaccount krkn-sa -n <namespace>

# For ns-privileged access
kubectl apply -f rbac/ns-privileged-role.yaml
kubectl apply -f rbac/ns-privileged-rolebinding.yaml

# For privileged access
kubectl apply -f rbac/privileged-clusterrole.yaml
kubectl apply -f rbac/privileged-clusterrolebinding.yaml

oc adm policy add-scc-to-user privileged -z krkn-sa -n <namespace>

oc adm policy add-scc-to-user privileged user1

VERSION=$(curl https://storage.googleapis.com/kubevirt-prow/release/kubevirt/kubevirt/stable.txt)
ARCH=$(uname -s | tr A-Z a-z)-$(uname -m | sed 's/x86_64/amd64/') || windows-amd64.exe
echo ${ARCH}
curl -L -o virtctl https://github.com/kubevirt/kubevirt/releases/download/${VERSION}/virtctl-${VERSION}-${ARCH}
chmod +x virtctl
sudo install virtctl /usr/local/bin

kubevirt_checks:                                      # Utilizing virt check endpoints to observe ssh ability to VMI's during chaos injection.
    interval: 2                                       # Interval in seconds to perform virt checks, default value is 2 seconds, required
    namespace: runner                                 # Regex Namespace where to find VMI's, required for checks to be enabled
    name: "^windows-vm-.$"                            # Regex Name style of VMI's to watch, optional, if left blank will find all names in namespace
    only_failures: False                              # Boolean of whether to show all VMI's failures and successful ssh connection (False), or only failure status' (True) 
    disconnected: False                               # Boolean of how to try to connect to the VMIs; if True will use the ip_address to try ssh from within a node, if false will use the name and uses virtctl to try to connect  
    ssh_node: ""                                      # If set, will be a backup way to ssh to a node. Will want to set to a node that isn't targeted in chaos
    node_names: ""                                    # List of node names to further filter down the VM's, will only watch VMs with matching name in the given namespace that are running on node. Can put multiple by separating by a comma
    exit_on_failure:                                        # If value is True and VMI's are failing post chaos returns failure, values can be True/False

disconnected: True                               # Boolean of how to try to connect to the VMIs; if True will use the ip_address to try ssh from within a node, if false will use the name and uses virtctl to try to connect

# Example with krknctl
krknctl run --config config.yaml -e id_rsa=/path/to/your/id_rsa

# Example with krkn-hub
podman run --name=<container_name> --net=host \
  -v /path/to/your/id_rsa:/home/krkn/.ssh/id_rsa:Z \. # do not change path on right of colon
  -v /path/to/your/id_rsa.pub:/home/krkn/.ssh/id_rsa.pub:Z \. # do not change path on right of colon
  -v /path/to/config.yaml:/root/kraken/config/config.yaml:Z \
  -d quay.io/krkn-chaos/krkn-hub:<scenario_type>

"virt_checks": [
      {
          "node_name": "000-000",
          "namespace": "runner",
          "vm_name": "windows-vm-1",
          "ip_address": "0.0.0.0",
          "status": false,
          "start_timestamp": "2025-07-22T13:41:53.461951",
          "end_timestamp": "2025-07-22T13:42:30.696498",
          "duration": 37.234547,
          "new_ip_address": "0.0.0.2",
      },
      {
          "node_name": "000-000",
          "namespace": "runner",
          "vm_name": "windows-vm-0",
          "ip_address": "0.0.0.1",
          "status": true,
          "start_timestamp": "2025-07-22T13:41:49.346861",
          "end_timestamp": "2025-07-22T13:43:17.949613",
          "duration": 88.602752,
          "new_ip_address": ""
      },
      {
          "node_name": "000-000",
          "namespace": "runner",
          "vm_name": "windows-vm-1",
          "ip_address": "0.0.0.2",
          "status": true,
          "start_timestamp": "2025-07-22T13:42:36.260780",
          "end_timestamp": "2025-07-22T13:43:17.949613",
          "duration": 41.688833,
          "new_ip_address": ""
      }
  ],
"post_virt_checks": [
      {
          "node_name": "000-000",
          "namespace": "runner",
          "vm_name": "windows-vm-4",
          "ip_address": "0.0.0.3",
          "status": false,
          "start_timestamp": "2025-07-22T13:43:30.461951",
          "end_timestamp": "2025-07-22T13:43:30.461951",
          "duration": 0.0,
          "new_ip_address": "",
      }
]

- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[10m:]) > 0.01
  description: 10 minutes avg. 99th etcd fsync latency higher than 10ms
  severity: warning

- expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
  description: etcd cluster has no leader
  severity: critical

- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[10m:]) > 0.01
  description: 10 minutes avg. 99th etcd fsync latency higher than 10ms
  severity: warning
  weight: 5

- expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
  description: etcd cluster has no leader
  severity: critical
  weight: 10

# Business-critical SLO with custom high weight
- expr: up{job="payment-service"} == 0
  description: Payment service is down
  severity: critical
  weight: 15

# Standard critical SLO (uses default weight of 3)
- expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
  description: etcd cluster has no leader
  severity: critical

# Low-priority warning with reduced weight
- expr: node_filesystem_free_bytes{mountpoint="/"} / node_filesystem_size_bytes < 0.1
  description: Root filesystem less than 10% free
  severity: warning
  weight: 0.5

# Standard warning (uses default weight of 1)
- expr: rate(http_requests_total{code="500"}[5m]) > 0.01
  description: High rate of 500 errors
  severity: warning

resiliency:
  resiliency_run_mode: standalone  # Options: standalone, controller, disabled
  resiliency_file: config/alerts.yaml  # Path to SLO definitions

{
  "telemetry": {
    "run_uuid": "717c8135-2aa0-47c9-afdf-3a6fe855c535",
    "job_status": false,
    "overall_resiliency_report": {
            "scenarios": {
                "<scenario_1>": 97,
                "<scenario_2>": 97
            },
            "resiliency_score": 97,
            "passed_slos": 26,
            "total_slos": 27
        },
  }
}

{
  "scenarios": [
    {
      "name": "<scenario_1>",
      "window": {
        "start": "2026-03-18T15:36:14",
        "end": "2026-03-18T15:36:25"
      },
      "score": 97,
      "weight": 1,
      "breakdown": {
        "total_points": 45,
        "points_lost": 1,
        "passed": 26,
        "failed": 1
      },
      "slo_results": {
        "10 minutes avg. 99th etcd fsync latency on {{$labels.pod}} higher than 10ms. {{$value}}s": true,
        ...
      },
      "health_check_results": {}
    },
    {
      "name": "<scenario_2>",
      "window": {
        "start": "2026-03-18T15:36:27",
        "end": "2026-03-18T15:37:19"
      },
      "score": 97,
      "weight": 1,
      "breakdown": {
        "total_points": 45,
        "points_lost": 1,
        "passed": 26,
        "failed": 1
      },
      "slo_results": {
        "10 minutes avg. 99th etcd fsync latency on {{$labels.pod}} higher than 10ms. {{$value}}s": true,
        ...
      },
      "health_check_results": {}
    }
  ]
}

2025-11-10 10:30:05 [INFO] Resiliency check complete. Score: 76.6%
KRKN_RESILIENCY_REPORT_JSON:{"scenarios":[{"name":"node-cpu-hog","score":76,"weight":1.0,"breakdown":{"total_points":30,"points_lost":7,"passed":18,"failed":2}}]}

# Business-critical: Payment processing must stay available
- expr: up{job="payment-api"} == 0
  description: Payment API is completely down
  severity: critical
  weight: 20

# Business-critical: Core authentication service
- expr: up{job="auth-service"} == 0
  description: Authentication service is down
  severity: critical
  weight: 15

# Standard critical: etcd cluster health (uses default weight of 3)
- expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
  description: etcd cluster has no leader
  severity: critical

# High-priority warning: API latency
- expr: histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket[5m])) by (le)) > 1
  description: 99th percentile API latency exceeds 1s
  severity: warning
  weight: 5

# Standard warning: Disk space (uses default weight of 1)
- expr: node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes < 0.2
  description: Root filesystem less than 20% free
  severity: warning

# Low-priority informational warning
- expr: rate(http_requests_total{code=~"4.."}[5m]) > 10
  description: High rate of client errors
  severity: warning
  weight: 0.5

    port: 8081
    publish_kraken_status: True
    signal_state: RUN

import http.client as cli

conn = cli.HTTPConnection("0.0.0.0", "<port>")

conn.request("POST", "/STOP", {})

# conn.request('POST', '/PAUSE', {})

# conn.request('POST', '/RUN', {})

response = conn.getresponse()
print(response.read().decode())

curl -X POST http:/0.0.0.0:8081/STOP

curl -X POST http:/0.0.0.0:8081/PAUSE

curl -X POST http:/0.0.0.0:8081/RUN

performance_monitoring:
    check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos

performance_monitoring:
    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.
    enable_alerts: True                                   # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error.
    alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries.

- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[5m:]) > 0.01
  description: 5 minutes avg. etcd fsync latency on {{$labels.pod}} higher than 10ms {{$value}}
  severity: error

- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[5m]))[5m:]) > 0.1
  description: 5 minutes avg. etcd network peer round trip on {{$labels.pod}} higher than 100ms {{$value}}
  severity: info

- expr: increase(etcd_server_leader_changes_seen_total[2m]) > 0
  description: etcd leader changes observed
  severity: critical

info: Prints an info message with the alarm description to stdout. By default all expressions have this severity.
warning: Prints a warning message with the alarm description to stdout.
error: Prints a error message with the alarm description to stdout and sets Krkn rc = 1
critical: Prints a fatal message with the alarm description to stdout and exits execution inmediatly with rc != 0

metrics:
# API server
  - query: histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb!~"WATCH", subresource!="log"}[2m])) by (verb,resource,subresource,instance,le)) > 0
    metricName: API99thLatency

  - query: sum(irate(apiserver_request_total{apiserver="kube-apiserver",verb!="WATCH",subresource!="log"}[2m])) by (verb,instance,resource,code) > 0
    metricName: APIRequestRate

  - query: sum(apiserver_current_inflight_requests{}) by (request_kind) > 0
    metricName: APIInflightRequests

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
    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: 500000                                     # 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
                                                            # 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

{
    "telemetry": {
        "scenarios": [
            {
                "start_timestamp": 1745343338,
                "end_timestamp": 1745343683,
                "scenario": "scenarios/network_chaos.yaml",
                "scenario_type": "pod_disruption_scenarios",
                "exit_status": 0,
                "parameters_base64": "",
                "parameters": [
                    {
                        "config": {
                            "execution_type": "parallel",
                            "instance_count": 1,
                            "kubeconfig_path": "/root/.kube/config",
                            "label_selector": "node-role.kubernetes.io/master",
                            "network_params": {
                                "bandwidth": "10mbit",
                                "latency": "500ms",
                                "loss": "50%"
                            },
                            "node_interface_name": null,
                            "test_duration": 300,
                            "wait_duration": 60
                        },
                        "id": "network_chaos"
                    }
                ],
                "affected_pods": {
                    "recovered": [],
                    "unrecovered": [],
                    "error": null
                },
                "affected_nodes": [],
                "cluster_events": []
            }
        ],
        "node_summary_infos": [
            {
                "count": 3,
                "architecture": "amd64",
                "instance_type": "n2-standard-4",
                "nodes_type": "master",
                "kernel_version": "5.14.0-427.60.1.el9_4.x86_64",
                "kubelet_version": "v1.31.6",
                "os_version": "Red Hat Enterprise Linux CoreOS 418.94.202503121207-0"
            },
            {
                "count": 3,
                "architecture": "amd64",
                "instance_type": "n2-standard-4",
                "nodes_type": "worker",
                "kernel_version": "5.14.0-427.60.1.el9_4.x86_64",
                "kubelet_version": "v1.31.6",
                "os_version": "Red Hat Enterprise Linux CoreOS 418.94.202503121207-0"
            }
        ],
        "node_taints": [
            {
                "node_name": "prubenda-g-qdcvv-master-0.c.chaos-438115.internal",
                "effect": "NoSchedule",
                "key": "node-role.kubernetes.io/master",
                "value": null
            },
            {
                "node_name": "prubenda-g-qdcvv-master-1.c.chaos-438115.internal",
                "effect": "NoSchedule",
                "key": "node-role.kubernetes.io/master",
                "value": null
            },
            {
                "node_name": "prubenda-g-qdcvv-master-2.c.chaos-438115.internal",
                "effect": "NoSchedule",
                "key": "node-role.kubernetes.io/master",
                "value": null
            }
        ],
        "kubernetes_objects_count": {
            "ConfigMap": 530,
            "Pod": 294,
            "Deployment": 69,
            "Route": 8,
            "Build": 1
        },
        "network_plugins": [
            "OVNKubernetes"
        ],
        "timestamp": "2025-04-22T17:35:37Z",
        "health_checks": null,
        "total_node_count": 6,
        "cloud_infrastructure": "GCP",
        "cloud_type": "self-managed",
        "cluster_version": "4.18.0-0.nightly-2025-03-13-035622",
        "major_version": "4.18",
        "run_uuid": "96348571-0b06-459e-b654-a1bb6fd66239",
        "job_status": true
    },
    "critical_alerts": null
}