New

The executive guide to generative AI

Read more
About usPartnersSupport|Login
IMPORTANT: No additional bug fixes or documentation updates will be released for this version. For the latest information, see the current release documentation.
« Metricbeat anomaly detection configurations Nginx anomaly detection configurations »
Elastic Docs ›Machine Learning in the Elastic Stack [7.15] ›Anomaly detection ›Supplied anomaly detection configurations

Metrics anomaly detection configurations

edit

Metrics anomaly detection configurations

edit

These anomaly detection jobs can be created in the Metrics app in Kibana.

The jobs below detect anomalous memory and network behavior on hosts and Kubernetes pods. For more details, see the datafeed and job definitions in the metrics_ui_* folders in GitHub.

hosts_memory_usage
  • For memory usage data about hosts in the Metrics app.
  • Models system memory usage.
  • Detects unusual increases in memory usage across hosts.
hosts_network_in
  • For network traffic across hosts in the Metrics app.
  • Models inbound network traffic.
  • Detects unusually high inbound traffic across hosts.
hosts_network_out
  • For network traffic across hosts in the Metrics app.
  • Models outbound network traffic.
  • Detects unusually high outbound traffic across hosts.
k8s_memory_usage
  • For memory usage data about Kubernetes pods in the Metrics app.
  • Models system memory usage.
  • Detects unusual increases in memory usage across Kubernetes pods.
k8s_network_in
  • For network traffic across Kubernetes pods in the Metrics app.
  • Models inbound network traffic.
  • Detects unusually high inbound traffic across Kubernetes pods.
k8s_network_out
  • For network traffic across Kubernetes pods in the Metrics app.
  • Models outbound network traffic.
  • Detects unusually high outbound traffic across Kubernetes pods.
« Metricbeat anomaly detection configurations Nginx anomaly detection configurations »
Was this helpful?
Feedback