Software Packet-Level Network Analytics at Cloud Scale
Software Packet-Level Network Analytics at Cloud Scale
复制标题
DOI：
10.1109/tnsm.2021.3058653
复制
发表时间：
2021-03
影响因子：
5.3
通讯作者：
Oliver Michel;John Sonchack;Greg Cusack;Maziyar Nazari;Eric Keller;Jonathan M. Smith
中科院分区：
文献类型：
--
作者：
Oliver Michel;John Sonchack;Greg Cusack;Maziyar Nazari;Eric Keller;Jonathan M. Smith
随着网络在速度、规模和复杂性方面的增长，可靠地运行网络需要持续的监控和日益复杂的分析。由于这些要求，支持云规模网络分析的平台面临着更高吞吐量（以跟上高数据包速率）和更高的通用性和可编程性（以覆盖更广泛的应用）的需求。最近的提案通过将分析应用逻辑卸载到线速可编程数据平面硬件来实现这些目标，因为扩展现有的软件分析平台是非常昂贵的。然而，数据平面设备的刚性设计和受限资源从根本上限制了分析的类型和可以并发运行的任务的数量。在这篇文章中，我们证明了不需要为了高性能而牺牲通用性。我们工作的核心思想不是将整个分析应用程序卸载到硬件上，而是只卸载在应用程序之间共享的关键预处理任务（例如，负载平衡）到线速硬件前端，同时优化核心分析软件以利用网络分析工作负载的属性。基于这种设计，我们提出了Jetstream，这是一个用于网络分析的混合平台，可以在16核商用服务器上以每秒高达2.5亿个数据包的吞吐量运行基于软件的自定义分析管道。Jetstream使复杂的网络范围的数据包分析成为可能，而不会影响通用性或性能。
As networks grow in speed, scale, and complexity, operating them reliably requires continuous monitoring and increasingly sophisticated analytics. Because of these requirements, the platforms that support analytics in cloud-scale networks face demands for both higher throughput (to keep up with high packet rates) and increased generality and programmability (to cover a wider range of applications). Recent proposals have worked toward these goals by offloading analytics application logic to line-rate programmable data plane hardware, as scaling existing software analytics platforms is prohibitively expensive. The rigid design and constrained resources of data plane devices, however, fundamentally limit the types of analysis and the number of tasks that can run concurrently. In this article, we demonstrate that generality need not be sacrificed for high performance. Rather than offloading entire analytics applications to hardware, the core idea of our work is to offload only critical preprocessing tasks that are shared among applications (e.g., load balancing) to a line-rate hardware frontend while optimizing the core analytics software to exploit properties of network analytics workloads. Based on this design, we present Jetstream, a hybrid platform for network analytics that can run custom software-based analytics pipelines at throughputs of up to 250 million packets per second on a 16-core commodity server. Jetstream makes sophisticated, network-wide packet analytics feasible without compromising on generality or performance.