用自然语言让集群调度更智能，降低运维门槛。
Cluster Workload Allocation: Semantic Soft Affinity Using Natural Language Processing
- 用大模型解析用户自然语言指令，实现软亲和性调度。
- 95%以上准确率，复杂场景下表现优于传统配置。
- 适合希望简化集群管理的开发者与运维人员。
集群工作负载分配通常需要复杂的配置，造成使用上的障碍。本文提出一种基于自然语言处理的语义意图驱动调度范式，利用大型语言模型（LLM）通过Kubernetes调度扩展器解析自然语言分配提示注解中的软亲和偏好。原型系统包含集群状态缓存和意图分析器（使用AWS Bedrock）。实证评估显示，顶级模型如Amazon Nova Pro/Premier和Mistral Pixtral Large在评估数据集上达到超过95%的子集准确率，显著优于基线引擎。在六种场景下的调度质量测试表明，该原型在标准Kubernetes配置基础上表现优异或相当，尤其在复杂和定量场景中表现突出，并能有效处理冲突的软偏好。结果验证了使用LLM实现可访问调度的可行性，但指出同步调用大模型带来的延迟问题，建议采用异步处理以提升生产就绪性。本工作证实了语义软亲和性在简化工作负载编排中的潜力，并提供了概念验证设计。
原文摘要 · Abstract (English)
Cluster workload allocation often requires complex configurations, creating a usability gap. This paper introduces a semantic, intent-driven scheduling paradigm for cluster systems using Natural Language Processing. The system employs a Large Language Model (LLM) integrated via a Kubernetes scheduler extender to interpret natural language allocation hint annotations for soft affinity preferences. A prototype featuring a cluster state cache and an intent analyzer (using AWS Bedrock) was developed. Empirical evaluation demonstrated high LLM parsing accuracy (>95% Subset Accuracy on an evaluation ground-truth dataset) for top-tier models like Amazon Nova Pro/Premier and Mistral Pixtral Large, significantly outperforming a baseline engine. Scheduling quality tests across six scenarios showed the prototype achieved superior or equivalent placement compared to standard Kubernetes configurations, particularly excelling in complex and quantitative scenarios and handling conflicting soft preferences. The results validate using LLMs for accessible scheduling but highlight limitations like synchronous LLM latency, suggesting asynchronous processing for production readiness. This work confirms the viability of semantic soft affinity for simplifying workload orchestration and presents a proof-of-concept design.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。