Datadog Integration®  Integration integration with Datadog to optimize application performance Datadog Integration
(A Datadog account is required for connecting and using Datadog. If you don’t have an account, visit the Datadog website and sign up for a free trial account. If you already have a Datadog account, please visit Datadog Marketplace to enjoy your free trial. )


ProphetStor  is an AI-based solution that helps enterprise manage, optimize, auto-scale resources for any applications on Kubernetes. Using advanced machine learning algorithms to predict application workload, scales the right amount of resources at the right time for optimized application performance.
  • AI-based workload prediction for Kafka or any applications
  • Resource recommendation based on workload prediction, application, Kubernetes and other related metrics
  • Automatic scaling of application containers through Datadog Watermark Pod Autoscaler (WPA)
With integration of ProphetStor, users can easily track the Kafka message production/consumption rate, as well as the prediction of message production rate from dashboard. Based on the prediction or message production rate, automatically scales Kafka consumer replicas to handle the workload. This can be visualized from dashboard where the recommended consumer replicas and the current number of consumer replicas are shown. Additionally, overall consumer lags as well as the average latency in the queue before a message is received by a consumer are also shown on the dashboard for better performance monitoring.® Dashboard Overview

Recommended Replicas vs Current/Desired Replicas

This timeseries graph shows the recommended replicas from the and the desired and current replicas in the system.

Production vs Consumption vs Production Prediction

This timeseries graph shows the Kafka message production rate and consumption rate and the production rate predicted by

Kafka Consumer Lag

This timeseries graph shows the sum  of consumer lags from all partitions.

Consumer Queue Latency  ( msec )

This timeseries graph shows the average latency of a message in the message queue before is it received by a consumer.

Deployment Memory Usage

This timeseries graph shows the memory usage of consumers.

Deployment CPU Usage

This timeseries graph shows the CPU usage of consumers.