CNCF [Cloud Native Computing Foundation] Courses

CNCF TAG Network and Service Mesh Working Group - Introduction and Project Overview

探讨云原生网络和服务网格技术的最新发展,深入介绍CNCF工作组管理的相关项目,包括负载均衡、可观察性、安全等关键网络原语。

• YouTube
• 29 minutes
• On-Demand
• Free Video

Accelerating Robot Application Development with Kubernetes

Explore how cloud-native technologies and Kubernetes accelerate robot application development, from containerization to simulation, deployment, and fleet operations.

• YouTube
• 24 minutes
• On-Demand
• Conference Talk

C++ Workflow - Task-based Parallel Computing and Asynchronous Networking Engine

基于任务的并行计算和异步网络引擎,支持高并发请求处理。整合通信、计算、IO等异步资源,提供任务流概念实现复杂业务逻辑。跨平台、多协议,具备服务管理和负载均衡能力。

• YouTube
• 35 minutes
• On-Demand
• Conference Talk

Bagua - Lightweight Distributed Learning on Kubernetes

Explore Bagua, a high-performance distributed deep learning project for Kubernetes, offering innovative communication algorithms and seamless integration for efficient training across various scenarios.

• YouTube
• 36 minutes
• On-Demand
• Conference Talk

A Full-Scenario Colocation of Workloads Based on Kubernetes

Maximizing resource utilization through workload colocation on Kubernetes, featuring techniques like prediction, isolation, and interference detection for cost-effective, high-performance deployments.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

Accelerate Federated Learning Model Deployment with KServe - KFServing

探索利用KServe加速联邦学习模型部署的实践。介绍Kubeflow、KFServing和推理服务工作流程,联邦学习基础知识,以及如何从水平训练的联邦学习模型创建服务。

• YouTube
• 30 minutes
• On-Demand
• Conference Talk

Graceful Node Shutdown – A Beginner’s Journey of Kubernetes Development

探索Kubernetes优雅节点关闭功能的开发历程，从初学者视角介绍社区协作、功能实现和Pod优先级机制，展示Kubernetes生态系统的持续改进。

• YouTube
• 19 minutes
• On-Demand
• Conference Talk

Intelligent Analysis on Cloud Infrastructure With AIOps

探索AIOps在云基础设施智能分析中的应用,包括异常检测、资源预测、故障检测和根因分析,以提高云服务管理和运营效率。

• YouTube
• 30 minutes
• On-Demand
• Conference Talk

DGL Operator - Distributed Graph Neural Network Training with DGL and K8s

Explore distributed GNN training using DGL and Kubernetes, improving resource utilization and scalability while reducing complexity. Learn about DGL Operator's implementation and future design.

• YouTube
• 31 minutes
• On-Demand
• Conference Talk

CPU Burst - Getting Rid of Unnecessary Throttling, Achieving High CPU Utilization and Application Performance at the Same Time

Explore CPU Burst feature to solve throttling issues, improve utilization, and enhance performance in Kubernetes environments without compromising resource limits.

• YouTube
• 24 minutes
• On-Demand
• Conference Talk

Keep Persistent Volumes Healthy for Stateful Workloads

Explore volume health monitoring in Kubernetes for stateful workloads. Learn about current capabilities, ongoing improvements, and potential automatic correction methods for storage issues.

• YouTube
• 22 minutes
• On-Demand
• Conference Talk

Kubernetes Data Protection WG Intro & Deep Dive

Kubernetes数据保护工作组介绍:探讨当前状况、未来发展及如何参与。深入分析数据保护定义、用例、现有构建模块、缺失功能,以及应用程序备份和恢复的工作流程。

• YouTube
• 31 minutes
• On-Demand
• Conference Talk

How to Build Your Cybersecurity Toolkits with Open Source Tools

使用开源工具构建云原生环境的网络安全工具包,保护初创企业的云原生环境。探讨如何利用生态系统中现有的开源工具创建安全工具集,为全生命周期提供保护。

• YouTube
• 40 minutes
• On-Demand
• Conference Talk

Creating a Unified Network Plane across Kubernetes with Kube-OVN

Kube-OVN 集成多个 Kubernetes 网络创建统一网络平面，提高节点利用率，降低复杂性，支持数据中心级灾难恢复。演讲介绍构建跨 Kubernetes 网络平面并部署 TiDB 的方法。

• YouTube
• 31 minutes
• On-Demand
• Conference Talk

Deep Dive Into Profilers - How CPU Profilers Measure Your Application's Performance

深入探讨CPU分析工具如何测量应用性能,介绍Linux perf、Golang pprof等工具的使用,并提出任务级CPU分析方法,有助于多租户服务的资源消耗评估。

• YouTube
• 28 minutes
• On-Demand
• Conference Talk