Karpenter is an open-source node provisioning project for Kubernetes, sponsored by AWS. It improves efficiency and cost by provisioning nodes that meet the requirements of unschedulable pods, removing the need to specify node types or groups. Users can provide criteria for instance selection, such as using spot instances for certain workloads. Karpenter is a common alternative to the default Kubernetes autoscaler for AWS users.
Sedai enhances Karpenter by using AI to continuously configure Karpenter with optimal settings based on a deep understanding of your application's needs. Sedai monitors and learns your application, considering factors like statefulness, CPU/memory intensity, and scaling responses. This allows Sedai to inform Karpenter's node selection, enable predictive scaling, and optimize spot vs. on-demand purchasing decisions, resulting in improved cost, performance, and availability.
The main use cases for combining Karpenter with Sedai are:
While Karpenter reacts to unschedulable pods by provisioning new nodes, Sedai performs predictive scaling at the workload or application level. Sedai can forecast the need for additional pods before traffic spikes occur, reducing the risk of performance degradation and ensuring smoother scaling during high-demand periods.
Sedai analyzes workload attributes to recommend when to use spot instances, providing a 'spot friendly' rating based on factors like execution time, restartability, and scheduled run windows. Users can manually accept these recommendations, which Sedai implements through Karpenter. After sufficient production experience, spot selection can be switched to autonomous mode for further optimization.
To integrate Sedai with Karpenter, you can install Karpenter through Sedai's agent when connecting to an AWS account, with an additional installation step. Alternatively, Karpenter can be added later. Sedai sends configuration changes to Karpenter's Provisioner resource for ongoing joint operation, enabling continuous optimization of compute provisioning for Kubernetes clusters.
Sedai and Karpenter are designed to work together in Kubernetes environments, particularly those running on AWS. Karpenter is sponsored by AWS and is a popular choice for AWS-based Kubernetes clusters, but Sedai's optimization capabilities can benefit any supported Kubernetes environment where Karpenter is deployed.
Using Sedai with Karpenter provides superior performance, availability, and cost optimization for Kubernetes clusters. Sedai's AI-driven insights inform Karpenter's real-time node selection, enable predictive scaling, and optimize spot instance usage, resulting in reduced costs, improved application performance, and higher reliability.
Karpenter typically uses an approximation between lowest-price and capacity-optimized strategies for node selection. Sedai's AI-driven approach leverages granular application insights, such as performance vs. cost sensitivity and ideal CPU/memory ratios, to inform more precise and effective node selection and scaling strategies.
Yes, after sufficient production experience and validation, Sedai can switch spot instance selection to autonomous mode, allowing for fully automated, AI-driven spot purchasing decisions through Karpenter for optimal cost efficiency.
The Provisioner resource in Karpenter is a custom resource used to configure compute provisioning for Kubernetes clusters. When integrated with Sedai, Sedai sends configuration changes to the Provisioner, enabling continuous, AI-driven optimization of node provisioning and scaling strategies.
Sedai continuously monitors your application, learning about its stateful or stateless nature, CPU and memory intensity, scaling responses, and the behavior of its dependencies. This deep understanding enables Sedai to make informed, AI-driven decisions for optimizing Kubernetes scaling and resource allocation.
Yes, Sedai allows users to manually review and accept recommendations for node selection, scaling, and spot instance usage. This ensures you maintain control over optimization decisions before enabling full autonomy.
By leveraging Sedai's AI-driven optimization with Karpenter, users can expect improved application performance, reduced latency, and more efficient resource utilization. For example, Sedai has helped customers like Belcorp achieve a 77% reduction in AWS Lambda latency and up to 50% cost savings in production environments (see KnowBe4 case study).
Yes, Sedai integrates with a variety of Kubernetes autoscalers, including HPA (Horizontal Pod Autoscaler), VPA (Vertical Pod Autoscaler), and Karpenter. This allows Sedai to optimize scaling strategies across different Kubernetes environments and use cases.
You can access detailed technical documentation for Sedai, including integration guides and best practices, at docs.sedai.io/get-started. Additional resources, case studies, and solution briefs are available at sedai.io/resources.
Sedai's setup process is designed to be fast and efficient. For general use cases, setup takes about 5 minutes, and for specific scenarios like AWS Lambda, it may take up to 15 minutes. Integration with Karpenter can be completed during this process or added later as needed.
Sedai provides comprehensive onboarding support, including one-on-one sessions with the engineering team, detailed documentation, a community Slack channel, and email/phone support. Enterprise customers also receive a dedicated Customer Success Manager for tailored assistance.
Sedai offers autonomous optimization, predictive scaling, application-aware intelligence, proactive issue resolution, release intelligence, and full-stack cloud coverage. These features enable Sedai to optimize compute, storage, and data resources across AWS, Azure, GCP, and Kubernetes environments, delivering up to 50% cost savings and 75% latency reduction.
Yes, Sedai supports optimization across AWS, Azure, GCP, and Kubernetes environments, providing a unified solution for multi-cloud and hybrid cloud operations.
Sedai integrates with monitoring and APM tools like Cloudwatch, Prometheus, Datadog, and Azure Monitor; Kubernetes autoscalers such as HPA, VPA, and Karpenter; IaC and CI/CD tools like GitLab, GitHub, Bitbucket, and Terraform; ITSM tools like ServiceNow and Jira; notification tools like Slack and Microsoft Teams; and various runbook automation platforms.
Sedai integrates with Infrastructure as Code (IaC), IT Service Management (ITSM), and compliance workflows to ensure all changes are safe, validated, and auditable. Every optimization is constrained, reversible, and subject to enterprise-grade governance.
Sedai offers three modes of operation: Datapilot (observability), Copilot (one-click optimizations), and Autopilot (fully autonomous execution). This provides flexibility to match different operational needs and risk tolerances.
Platform engineers, DevOps teams, IT/cloud operations, technology leaders, SREs, and FinOps professionals managing Kubernetes clusters—especially in AWS environments—can benefit from Sedai's autonomous optimization, predictive scaling, and cost management capabilities.
Customers can expect up to 50% cloud cost savings, 75% latency reduction, 6X productivity gains, and improved reliability. For example, Palo Alto Networks saved $3.5 million and KnowBe4 achieved 50% cost savings in production using Sedai's autonomous optimization.
Sedai addresses pain points such as manual scaling, cost overruns, performance bottlenecks, operational toil, and lack of proactive issue resolution. It automates routine tasks, aligns engineering and cost efficiency goals, and provides actionable insights for continuous improvement.
Yes, Sedai has helped companies like Belcorp reduce AWS Lambda latency by 77%, Palo Alto Networks save $3.5 million, and KnowBe4 achieve 50% cost savings. These case studies demonstrate Sedai's effectiveness in optimizing Kubernetes and cloud environments. See more at sedai.io/resources.
Sedai differentiates itself with 100% autonomous optimization, proactive issue resolution, application-aware intelligence, predictive scaling, and release intelligence. Unlike competitors that rely on static rules or manual adjustments, Sedai continuously learns and optimizes based on real application behavior, delivering measurable cost and performance benefits.
Sedai's unique features include autonomous optimization, predictive scaling, application-aware intelligence, release intelligence, and plug-and-play implementation. These capabilities enable Sedai to deliver up to 50% cost savings, 75% latency reduction, and 6X productivity gains, setting it apart from traditional tools.
Yes, Sedai is SOC 2 certified, demonstrating its commitment to stringent security and compliance standards. This certification ensures that Sedai meets industry requirements for data protection and operational integrity. Learn more at Sedai Security.
Sedai provides detailed technical documentation, case studies, datasheets, and strategic guides. These resources are available at docs.sedai.io/get-started and sedai.io/resources to help users understand features, setup, and best practices.
Sedai's case studies cover industries such as cybersecurity (Palo Alto Networks), IT (HP), financial services (Experian, CapitalOne Bank), security awareness training (KnowBe4), travel (Expedia), healthcare (GSK), car rental (Avis), retail/e-commerce (Belcorp), SaaS (Freshworks), and digital commerce (Campspot). See more at sedai.io/resources.
Notable Sedai customers include Palo Alto Networks, HP, Experian, KnowBe4, Expedia, CapitalOne Bank, GSK, and Avis. These organizations trust Sedai to optimize their cloud and Kubernetes environments for cost, performance, and reliability.
Hari Chandrasekhar
Content Writer
August 14, 2024
Featured
In this article we'll explore how to fully realize the potential of Karpenter’s unique real-time node selection by using AI to continuously configure Karpenter with the optimal configuration.
Karpenter is an open-source node provisioning project built for Kubernetes, sponsored by AWS. Karpenter improves the efficiency and cost of running workloads on Kubernetes clusters by provisioning nodes that meet the requirements of the pods (e.g., 10 CPUs, 20GB memory) that the Kubernetes schedulerhas marked as unschedulable. Karpenter removes the requirement to specify node type (e.g., m5.large) & node groups, although users can provide criteria to choose specific instances (e.g., use spot for certain workloads). It is the most common alternative to the default Kubernetes autoscaler for AWS users. See below for an overview of how Karpenter works:
Sedai runs your applications at its best performance, cost and availability. Sedai continuously monitors and learns your application to make informed decisions based on application infrastructure affinity. Sedai builds a clear understanding of your application, its stateful or stateless nature, CPU & memory intensity and response to horizontal or vertical scaling and the ideal and anomalous behavior of each of its dependencies. While Karpenter supports your Kubernetes Cluster Scheduler, Sedai focuses on cost, performance and availability from a holistic application & infrastructure perspective.
The combination of Karpenter and Sedai can provide superior overall performance, availability and cost. Karpenter’s real-time scaling of nodes (adding and picking node types) is a unique function not performed by the Sedai platform. Karpenter’s real-time scaling can be made more powerful by leveraging Sedai’s granular understanding of application needs and traffic prediction capability. Three use cases for Karpenter with Sedai are:
Initial setup of Sedai with Karpenter could be achieved by installing Karpenter through Sedai’s agent when the agent is connected to an AWS account with an additional installation step. Alternatively Karpenter can be added later. Karpenter’s compute provisioning for Kubernetes clusters is configured by a custom resource called Provisioner. Ongoing joint operation of Karpenter with Sedai would be achieved by Sedai sending configuration changes to Provisioner.
The diagram below shows Karpenter integrated into an example architecture.
Please reach out to me or the Sedai team for more details. They look forward to working with you to achieve the best possible cost, performance and availability for your Kubernetes applications.
