mirror of
https://github.com/krkn-chaos/krkn.git
synced 2026-02-14 09:59:59 +00:00
55 lines
4.6 KiB
YAML
55 lines
4.6 KiB
YAML
cerberus:
|
|
distribution: openshift # Distribution can be kubernetes or openshift
|
|
kubeconfig_path: ~/.kube/config # Path to kubeconfig
|
|
port: 8080 # http server port where cerberus status is published
|
|
watch_nodes: True # Set to True for the cerberus to monitor the cluster nodes
|
|
watch_cluster_operators: True # Set to True for cerberus to monitor cluster operators
|
|
watch_url_routes: # Route url's you want to monitor, this is a double array with the url and optional authorization parameter
|
|
watch_master_schedulable: # When enabled checks for the schedulable master nodes with given label.
|
|
enabled: True
|
|
label: node-role.kubernetes.io/master
|
|
watch_namespaces: # List of namespaces to be monitored
|
|
- openshift-etcd
|
|
- openshift-apiserver
|
|
- openshift-kube-apiserver
|
|
- openshift-monitoring
|
|
- openshift-kube-controller-manager
|
|
- openshift-machine-api
|
|
- openshift-kube-scheduler
|
|
- openshift-ingress
|
|
- openshift-sdn # When enabled, it will check for the cluster sdn and monitor that namespace
|
|
cerberus_publish_status: True # When enabled, cerberus starts a light weight http server and publishes the status
|
|
inspect_components: False # Enable it only when OpenShift client is supported to run
|
|
# When enabled, cerberus collects logs, events and metrics of failed components
|
|
|
|
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.
|
|
# This enables Cerberus to query prometheus and alert on observing high Kube API Server latencies.
|
|
|
|
slack_integration: False # When enabled, cerberus reports the failed iterations in the slack channel
|
|
# The following env vars needs to be set: SLACK_API_TOKEN ( Bot User OAuth Access Token ) and SLACK_CHANNEL ( channel to send notifications in case of failures )
|
|
# When slack_integration is enabled, a watcher can be assigned for each day. The watcher of the day is tagged while reporting failures in the slack channel. Values are slack member ID's.
|
|
watcher_slack_ID: # (NOTE: Defining the watcher id's is optional and when the watcher slack id's are not defined, the slack_team_alias tag is used if it is set else no tag is used while reporting failures in the slack channel.)
|
|
Monday:
|
|
Tuesday:
|
|
Wednesday:
|
|
Thursday:
|
|
Friday:
|
|
Saturday:
|
|
Sunday:
|
|
slack_team_alias: # The slack team alias to be tagged while reporting failures in the slack channel when no watcher is assigned
|
|
|
|
custom_checks: # Relative paths of files containing additional user defined checks
|
|
|
|
tunings:
|
|
timeout: 3 # Number of seconds before requests fail
|
|
iterations: 5 # Iterations to loop before stopping the watch, it will be replaced with infinity when the daemon mode is enabled
|
|
sleep_time: 5 # Sleep duration between each iteration
|
|
kube_api_request_chunk_size: 250 # Large requests will be broken into the specified chunk size to reduce the load on API server and improve responsiveness.
|
|
daemon_mode: True # Iterations are set to infinity which means that the cerberus will monitor the resources forever
|
|
cores_usage_percentage: 0.5 # Set the fraction of cores to be used for multiprocessing
|
|
|
|
database:
|
|
database_path: /tmp/cerberus.db # Path where cerberus database needs to be stored
|
|
reuse_database: False # When enabled, the database is reused to store the failures
|