/ Contributor Guide Se�ng up the development environment Development process End-To-End Tes�ng Framework How to contribute Pull request review process Building Container Images Documenta�on CI / Jenkins implemented using BPF using efficient hashtables allowing for almost unlimited scale and supports direct server return (DSR) if the loadbalancing opera�on is not performed on the source host. Note: load balancing Policy decision tracing: Why is a packet being dropped or a request rejected. The policy tracing framework allows to trace the policy decision process for both, running workloads and based on arbitrary label

Contributor Guide Setting up the development environment Development process End-To-End Testing Framework How to contribute Pull request review process Building Container Images Documentation Developer’s implemented using BPF using efficient hashtables allowing for almost unlimited scale and supports direct server return (DSR) if the loadbalancing operation is not performed on the source host. Note: load balancing Policy decision tracing: Why is a packet being dropped or a request rejected. The policy tracing framework allows to trace the policy decision process for both, running workloads and based on arbitrary label

for testing CI Failure Triage Infrastructure details Documentation Building End-To-End Testing Framework Introduction Running End-To-End Tests Test Reports Best Practices for Writing Tests Ginkgo Extensions implemented using BPF using efficient hashtables allowing for almost unlimited scale and supports direct server return (DSR) if the loadbalancing operation is not performed on the source host. Note: load balancing Policy decision tracing: Why is a packet being dropped or a request rejected. The policy tracing framework allows to trace the policy decision process for both, running workloads and based on arbitrary label

Jenkins for testing CI Failure Triage Infrastructure details Documentation End-To-End Testing Framework Introduction Running End-To-End Tests Test Reports Best Practices for Writing Tests Ginkgo Extensions Golang Package Compatibility Guarantees API Reference Hubble internals Hubble Architecture Hubble server Hubble Relay Reference Command Cheatsheet Command utilities: Command examples: Kubernetes examples: implemented using BPF using efficient hashtables allowing for almost unlimited scale and supports direct server return (DSR) if the loadbalancing operation is not performed on the source host. Note: load balancing

Jenkins for testing CI Failure Triage Infrastructure details Documentation End-To-End Testing Framework Introduction Running End-To-End Tests Test Reports Best Practices for Writing Tests Ginkgo Extensions Golang Package Compatibility Guarantees API Reference Hubble internals Hubble Architecture Hubble server Hubble Relay Reference Command Cheatsheet Command utilities: Command examples: Kubernetes examples: optimized for maximum performance, can be attached to XDP (eXpress Data Path), and supports direct server return (DSR) as well as Maglev consistent hashing if the load balancing operation is not performed

Jenkins for testing CI Failure Triage Infrastructure details Documentation End-To-End Testing Framework Introduction Running End-To-End Tests Test Reports Best Practices for Writing Tests Ginkgo Extensions optimized for maximum performance, can be attached to XDP (eXpress Data Path), and supports direct server return (DSR) as well as Maglev consistent hashing if the load balancing operation is not performed Policy decision tracing: Why is a packet being dropped or a request rejected. The policy tracing framework allows to trace the policy decision process for both, running workloads and based on arbitrary label

Jenkins for testing CI Failure Triage Infrastructure details Documentation End-To-End Testing Framework Introduction Running End-To-End Tests Test Reports Best Practices for Writing Tests Ginkgo Extensions optimized for maximum performance, can be attached to XDP (eXpress Data Path), and supports direct server return (DSR) as well as Maglev consistent hashing if the load balancing operation is not performed kube-system/l7-default-backend-7fd66b8b88- qqhh5 ♻ Restarted unmanaged pod kube-system/metrics-server-v0.3.6- 7b5cdbcbb8-kjl65 ♻ Restarted unmanaged pod kube-system/stackdriver-metadata-agent- clu

nodePort 访问 传统的 nodePort 转发，伴随着 SNAT的发生。而 Cilium 为 nodePort 提供了 native 和 IPIP 等方式的 DSR （direct server return）实现，有效减 少了网络转发的跳数，极大提升了 nodePort的转发性能，降低访问延时。 相关测试表明： • kube proxy iptables模式下，请求完 成时间 1.6ms