A Scalable, Commodity Data Center Network Architecture¶

ABSTRACT¶

Today’s data centers may contain tens of thousands of computers with signiﬁcant aggregate bandwidth requirements. The network architecture typically consists of a tree of routing and switching elements with progressively more specialized and expensive equipment moving up the network hierarchy. Unfortunately, even when deploying the highest-end IP switches/routers, resulting topologies may only support 50% of the aggregate bandwidth available at the edge of the network, while still incurring tremendous cost. Nonuniform bandwidth among data center nodes complicates application design and limits overall system performance.

当今的数据中心可能包含数万台计算机，其总带宽需求相当可观。网络架构通常由一棵由路由和交换设备组成的树状结构构成，随着网络层级的上升，这些设备变得越来越专业化且昂贵。然而，即使部署了最高端的IP交换机/路由器，最终的拓扑结构可能也只能支持网络边缘可用总带宽的50%，同时还会带来巨大的成本。数据中心节点之间带宽的不均匀性增加了应用设计的复杂性，并限制了整个系统的性能。

In this paper, we show how to leverage largely commodity Ethernet switches to support the full aggregate bandwidth of clusters consisting of tens of thousands of elements. Similar to how clusters of commodity computers have largely replaced more specialized SMPs and MPPs, we argue that appropriately architected and interconnected commodity switches may deliver more performance at less cost than available from today’s higher-end solutions. Our approach requires no modiﬁcations to the end host network interface, operating system, or applications; critically, it is fully backward compatible with Ethernet, IP, and TCP.

在本文中，我们展示了如何利用大规模的商用以太网交换机来支持由数万个节点组成的集群的全部总带宽。类似于商用计算机集群在很大程度上已经取代了更为专业化的SMP（对称多处理器）和MPP（大规模并行处理器），我们认为，经过适当架构和互联的商用交换机，可能比当前的高端解决方案提供更高的性能且成本更低。我们的方法无需对终端主机的网络接口、操作系统或应用程序进行任何修改；最重要的是，它完全向后兼容以太网、IP和TCP。

Note

Categories and Subject Descriptors

C.2.1 [Network Architecture and Design]: Network topology;
C.2.2 [Network Protocols]: Routing protocols

General Terms

Design, Performance, Management, Reliability

Keywords

Data center topology, equal-cost routing