arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01044cs.SE
收藏

Morphis: 面向时间变化调用图的微服务资源调度

Morphis: SLO-Aware Resource Scheduling for Microservices with Time-Varying Call Graphs

Zhejiang University(浙江大学);ByteDance Ltd.(字节跳动有限公司)

Yu Tang, Hailiang Zhao, Chuansheng Lu, Yifei Zhang, Kingsum Chow, Shuiguang Deng, Rui Shi

AI总结:

Morphis通过依赖感知的资源配置框架,利用模式感知的轨迹分析与全局优化,有效降低CPU消耗并保持SLO合规性。

摘要:

现代微服务系统由于工作负载波动、故障响应和部署活动,在运行时调用图中表现出持续的结构演变。尽管这种复杂性,我们对字节跳动超过50万条生产轨迹的分析揭示出一个隐含的规律:执行路径集中在一小组反复出现的调用模式周围。然而,现有的资源管理方法未能利用这种结构。工业自动扩展器如Kubernetes HPA忽略服务间依赖关系,而近期的学术方法通常假设静态拓扑,使其在动态执行上下文中无效。在本工作中,我们提出了Morphis,一个依赖感知的资源配置框架,它将模式感知的轨迹分析与全局优化统一起来。它引入了结构指纹技术,将轨迹分解为稳定的执行骨干和可解释的偏差子图。然后,资源分配被公式化为一个在预测模式分布上的约束优化问题,共同最小化总体CPU使用量,同时满足端到端尾部延迟SLOs。我们在TrainTicket基准测试中的广泛评估表明,Morphis相比最先进的基线减少了35-38%的CPU消耗,同时保持98.8%的SLO合规性。

英文摘要:

Modern microservice systems exhibit continuous structural evolution in their runtime call graphs due to workload fluctuations, fault responses, and deployment activities. Despite this complexity, our analysis of over 500,000 production traces from ByteDance reveals a latent regularity: execution paths concentrate around a small set of recurring invocation patterns. However, existing resource management approaches fail to exploit this structure. Industrial autoscalers like Kubernetes HPA ignore inter-service dependencies, while recent academic methods often assume static topologies, rendering them ineffective under dynamic execution contexts. In this work, we propose Morphis, a dependency-aware provisioning framework that unifies pattern-aware trace analysis with global optimization. It introduces structural fingerprinting that decomposes traces into a stable execution backbone and interpretable deviation subgraphs. Then, resource allocation is formulated as a constrained optimization problem over predicted pattern distributions, jointly minimizing aggregate CPU usage while satisfying end-to-end tail-latency SLOs. Our extensive evaluations on the TrainTicket benchmark demonstrate that Morphis reduces CPU consumption by 35-38% compared to state-of-the-art baselines while maintaining 98.8% SLO compliance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑