chlam4 / kubeturbo

KubeTurbo

1. Overview
2. Getting Started
3. Kubeturbo Use Cases
4. Coming Soon

Overview

Kubeturbo leverages Turbonomic's patented analysis engine to provide visibility and control across the entire stack in order to assure the performance of running micro-services in Kubernetes Pods, as well as the efficiency of underlying infrastructure.

Getting Started

Kubeturbo Installation

• Review the prerequisites and Deploy Kubeturbo
• Once deployed, corresponding targets will show up in Turbonomic UI

Use Cases

• Full-Stack Visibility by leveraging 50+ existing Turbonomic controllers, from on-prem DataCenter to major public cloud providers. No more shadow IT
  • From Load Balancer all the way down to your physical Infrastructure
  • Real-Time resource monitoring across entire DataCenter
  • Real-Time Cost visibility for your public cloud deployment

• Provide Rescheduler capability by leveraging The Turbonomic analysis engine (Execution of moving pods requires Kubeturbo to be the scheduler of the pod)
  • Consolidating Pods in real-time to increase node efficiency
  • Reschedule Pod in advance to prevent suffering resource congestion from the underlying node
  • Reschedule Pod to new node added to the cluster
  • Reschedule Pods that peak together to different nodes, to avoid performance dropping

• Right-Sizing your Pod and your entire IT stack
  • Combining Turbonomic real-time performance monitoring and analysis engine, Turbonomic is able to provide right-sizing information for each individual pod as well as the entire IT stack.
  • Right-sizing up your Pod limit, if necessary, to avoid OOM
  • Right-sizing down your Pod requested resource, if necessary, to avoid resource overprovisioning or overspending in public cloud deployment.

Coming Soon

• Added dimensions in SLO based control
  • Manage horizontal scaling of services without thresholds
  • Manage the tradeoffs of performance, availability of resources, and compliance
  • Leverage your SLO data to add response time and througput - Istio, Prometheus, etc
• Support for Cluster Federation Control Plane
  • Complete visibility for your K8s deployments across different underlying infrastructures
  • Create affinity/anti-affinity policies directly from Turbonomic UI
  • Improve cost efficiency by consolidating workload across deployments and identifying the cheapest region and provider to deploy your workload
• What-If Planner
  • A complete What-If sandbox to help you plan your IT changes in advance
  • Plan for workload change: Add/Remove Containers
  • Plan for infrastructure change: Add/Remove/Replace hardware
  • Manage guaranteed resources: insight into requests across the nodes
  • Cluster Consolidation for federated clusters