Modern user-facing latency-sensitive web services include numerous distributed, intercommunicating microservices that promise to simplify software development and operation. However, multiplexing of compute resources across microservices is still challenging in production because contention for shared resources can cause latency spikes that violate the service-level objectives (SLOs) of user requests. This paper presents FIRM, an intelligent fine-grained resource management framework for predictable sharing of resources across microservices to drive up overall utilization. FIRM leverages online telemetry data and machine-learning methods to adaptively (a) detect/localize microservices that cause SLO violations, (b) identify low-level resources in contention, and (c) take actions to mitigate SLO violations via dynamic reprovisioning. Experiments across four microservice benchmarks demonstrate that FIRM reduces SLO violations by up to 16x while reducing the overall requested CPU limit by up to 62%. Moreover, FIRM improves performance predictability by reducing tail latencies by up to 11x.

中文翻译：

---

FIRM：面向 SLO 的微服务的智能细粒度资源管理框架

现代面向用户的延迟敏感型 Web 服务包括众多分布式、相互通信的微服务，这些微服务有望简化软件开发和操作。然而，跨微服务的计算资源多路复用在生产中仍然具有挑战性，因为对共享资源的争用会导致延迟峰值，从而违反用户请求的服务级别目标 (SLO)。本文介绍了 FIRM，这是一种智能细粒度资源管理框架，用于跨微服务进行可预测的资源共享以提高整体利用率。FIRM 利用在线遥测数据和机器学习方法自适应地 (a) 检测/定位导致 SLO 违规的微服务，(b) 识别竞争中的低级资源，以及 (c) 采取措施通过动态重新配置来缓解 SLO 违规。在四个微服务基准测试中的实验表明，FIRM 将 SLO 违规减少了多达 16 倍，同时将总体请求的 CPU 限制减少了多达 62%。此外，FIRM 通过将尾部延迟减少多达 11 倍来提高性能可预测性。