KEDA event-driven autoscaling¶

Overview¶

KEDA (Kubernetes Event-Driven Autoscaling) and the KEDA HTTP Add-on are generic cluster amenities that multiple DataRobot components rely on for HTTP- and event-based horizontal scaling, including the ability to scale to zero for cost optimization. Because KEDA is installed cluster-wide and shared across components, its prerequisites, installation, configuration values, network requirements, and version requirements are documented here rather than in any single component's page.

Components that use KEDA include:

• Custom model deployments (LRS) — path-based (pathPrefixes/hosts) HTTPScaledObject routing. See LRS auto-scaling with KEDA.
• Workload API protons — header-based (spec.headers) HTTPScaledObject routing, which requires the KEDA HTTP Add-on 0.12.0 or later. See KEDA HTTP Add-on version requirements.

Prerequisites¶

Before enabling any KEDA-based autoscaling, the following components must be installed and configured in your Kubernetes cluster:

Required components¶

1. KEDA (Kubernetes Event-Driven Autoscaling)
2. Version 2.17 or later recommended
3. Must be installed cluster-wide

4. https://github.com/kedacore/keda?tab=readme-ov-file#deploying-keda

5. KEDA HTTP Add-on

6. Compatible with your KEDA version
7. Provides HTTP-specific scaling capabilities
8. See the version requirements for the minimum version your workloads need
9. https://github.com/kedacore/http-add-on/?tab=readme-ov-file#installation

Installation requirements¶

KEDA and the KEDA HTTP Add-on must be installed by your platform administrator before enabling autoscaling features. Contact your DataRobot administrator or refer to the KEDA documentation for installation instructions.

Configuration values for KEDA HTTP Add-on¶

When installing the KEDA HTTP Add-on, ensure the following default values are configured:

keda-add-ons-http:
    interceptor:
      responseHeaderTimeout: 600s
      replicas:
        waitTimeout: 300s

This configuration ensures proper handling of long-running requests and prevents premature timeouts.

See additional configuration options here https://github.com/kedacore/charts/blob/main/http-add-on/Chart.yaml

Network¶

The HTTP Add-on brings a proxy component that records metrics and routes traffic from the ingress to the scaled workload. It's therefore crucial that the HTTP Add-on has network access to send traffic to the target workload's pods.

KEDA HTTP Add-on version requirements¶

DataRobot uses the KEDA HTTP Add-on for two scaling paths with different minimum versions:

Workload API protons route requests with header-based HTTPScaledObject rules (spec.headers), introduced in the KEDA HTTP Add-on v0.12.0. For scale-to-zero to work properly, clusters that run Workload API protons must install the KEDA HTTP Add-on 0.12.0 or later. Custom model (LRS) deployments use path-based routing and continue to work on earlier versions.