Federator.ai® & Datadog Integration

Datadog provides monitoring for servers, applications, and services. With Datadog, enterprise customers are able to monitor their application workloads and get visibility into Kubernetes clusters of any scale. By integrating with ProphetStor Federator.ai, you can track and predict the resource usages of Kubernetes containers, namespaces, and cluster nodes to make the right recommendations and prevent costly over-provisioning or performance-impacting under-provisioning. With easy integration to CI/CD pipeline, Federator.ai enables continuous optimization of containers whenever they are deployed in a Kubernetes cluster. Utilizing application workload predictions, Federator.ai auto-scales application containers at the right time and optimizes performance with the right number of container replicas through Kubernetes HPA or Datadog Watermark Pod Autoscaling (WPA).

DiagramThe Federator.ai/Datadog integration workflow


Datadog Agent posts workload metrics to Datadog Services.


Data Adapter queries workload metrics from Datadog Services.


Data Adapter posts the prediction/ recommendation created by Federator.ai to Datadog Services.


Datadog Cluster Agent gets recommendation from Datadog Services.


HPA autoscales applications based on recommendations.


Datadog Dashboards display workload metrics and prediction/recommendation by Federator.ai.

A Single-pane-of-glass Management Console

Other than using the GUI of Federator.ai, users who are already familiar with Datadog can also use the Datadog web portal to take advantage of AI-based predictions and recommendations from Federator.ai. There are four custom dashboards as shown below:

ProphetStor Federator.ai Cluster Overview

It shows future CPU and memory usage predictions and recommendations for the entire cluster and for each individual cluster node in the next 24 hours, 7 days, or 30 days. It also displays cluster node CPU/memory resource utilization history in daily, weekly, or monthly view.

ProphetStor Federator.ai Application Overview

It shows the application workload predictions and resource recommendations for the next 24 hours/ 7 days/ 30 days, and also displays current and previous predicted CPU and memory usages. If autoscaling is enabled for an application, it displays the current/desired/recommended replicas, and the requested/ limited/ current usage of CPU and memory and their recommended limits.

ProphetStor Federator.ai Kafka Overview

It shows the current/ recommended replicas of Kafka consumers, the current/ predicted Kafka message production rate and consumption rate, the consumer lags, the Consumer Queue Latency (msec), and the CPU/memory usage of Kafka consumers.

ProphetStor Federator.ai Cost Analysis Overview

It provides visibility on the current cluster cost and the most cost-effective configuration recommendations for public cloud service providers, including AWS, Azure, and GCP. It also shows highest current daily cost and the highest predicted monthly cost of the namespace in the current cluster.