Files
krkn/config/config_performance.yaml
2026-02-09 09:48:51 -05:00

84 lines
6.6 KiB
YAML

kraken:
distribution: openshift # 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
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
- plugin_scenarios: # List of chaos pod scenarios to load
- scenarios/openshift/etcd.yml
- scenarios/openshift/regex_openshift_pod_kill.yml
- scenarios/openshift/prom_kill.yml
- node_scenarios: # List of chaos node scenarios to load
- scenarios/openshift/node_scenarios_example.yml
- plugin_scenarios:
- scenarios/openshift/openshift-apiserver.yml
- scenarios/openshift/openshift-kube-apiserver.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/openshift/zone_outage.yaml
- application_outages:
- scenarios/openshift/app_outage.yaml
- pvc_scenarios:
- scenarios/openshift/pvc_scenario.yaml
- network_chaos:
- scenarios/openshift/network_chaos.yaml
cerberus:
cerberus_enabled: True # Enable it when cerberus is previously installed
cerberus_url: http://0.0.0.0:8080 # When cerberus_enabled is set to True, provide the url where cerberus publishes go/no-go signal
check_application_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: True # 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"
capture_metrics: True
metrics_profile_path: config/metrics-aggregated.yaml
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: 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
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
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 temporarily 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
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