This article explains how Youzan transformed its Kubernetes clusters from static over‑commit scheduling to load‑balanced mixed workloads using Koordinator and the Longxi kernel, achieving higher CPU utilization, lower costs, and better resource management for both online and offline services.
Koordinator v1.4.0 introduces mixed K8s/YARN workloads, NUMA‑aware scheduling, CPU‑normalization, enhanced ElasticQuota with tree structures and non‑preemptible pods, cold‑memory reporting, QoS for non‑containerized applications, and a suite of bug‑fixes and performance improvements for enterprise Kubernetes clusters.
Xiaohongshu’s cloud‑native platform adopted a four‑stage mixed‑workload scheduling strategy—reusing idle nodes, whole‑machine time‑sharing, normal mixed pools, and a unified scheduler (Tusker) that coordinates CPU, GPU and memory across Kubernetes and YARN—boosting average cluster CPU utilization from under 20 % to over 45 % and delivering millions of low‑cost core‑hours while preserving QoS for latency‑sensitive, mid, and batch jobs.
Koordinator, an open‑source cloud‑native mixed‑workload scheduler born from Alibaba’s internal container orchestration experience, enables Xiaohongshu to reclaim idle resources, improve CPU utilization beyond 45%, reduce resource costs by millions of core‑hours, and seamlessly integrate Kubernetes with YARN for batch and AI workloads.
This article explains ByteDance’s cloud‑native mixed‑workload strategy, describing how the open‑source Katalyst system leverages Kubernetes and Yarn to dynamically share idle resources between online and offline services, improve utilization from 23% to 60%, and reduce operational costs.
Bilibili’s Kubernetes cloud platform boosts server utilization by co‑locating latency‑sensitive online services with batch‑oriented offline jobs on the same nodes, using custom schedulers, extended resources, dynamic CPU/memory isolation, and a management console, achieving average CPU usage around 35 % and significant cost savings.
This article explains how Alibaba Cloud's open‑source Koordinator system tackles mixed‑workload challenges by introducing priority and QoS models, resource overcommit, load‑aware scheduling, fine‑grained CPU orchestration, and upcoming features such as GPU scheduling and resource recommendation, all illustrated with architecture diagrams and code examples.
This article analyzes Baidu's offline mixed‑tenant technology that combines online and offline workloads on the same physical servers, detailing the resource‑usage problems, dynamic resource views, priority schemes, isolation mechanisms, high‑performance scheduling, and future directions for cloud‑native clusters.
This article presents ByteDance's private cloud platform TCE architecture and explains how automated elastic scaling, dynamic over‑commit, and mixed‑workload deployment are used to improve resource utilization for millions of services, balancing online peak demand with offline batch tasks.
