in popular Linux distributions • Cons • O(N^2) in control plane / O(N) in data plane • Poor in scheduling algorithm • Iptables rules are difficult to debug IPVS mode • Services are organized in hash Pros • O(1) time complexity in control/data plane • Stably runs for two decades • Support rich scheduling algorithm • Cons • Performance cost caused by conntrack • Some bugs How to optimize • Guidelines del refer • V.S service in pure eBPF • Reuse the IPVS’s functionality and maturity • Many scheduling algorithms • Reuse IPVS timer to reclaim eBPF map • More efficient and secure • V.S Taobao IPVS

Level Request Load Level Real Load Level Real Load Level Assigned to Node2 The native K8S scheduling is based on the resource request of Pod. However, in many cases, some nodes have low resource

斐波那契数列第 n 项 斐波那契数列第 n 项：并行 tbb::task_group 的封装： tbb::parallel_invoke 任务划分得够细时，转为串行，缓解调度负担（ scheduling overhead ） 标准库提供的排序 快速排序 std::hash 用于从输入生成随机数，输入不变则结果不 变。 随机枢轴的位置防止数据已经有序造成最坏的 O(n²) 。 并行快速排序