Flow Optimization in Data Centers With Clos Networks in Support of Cloud Applications
Flow Optimization in Data Centers With Clos Networks in Support of Cloud Applications
复制标题
DOI：
10.1109/tnsm.2017.2761321
复制
发表时间：
2017-10
影响因子：
5.3
通讯作者：
Wile Sehery;Charles Clancy
中科院分区：
文献类型：
--
作者：
Wile Sehery;Charles Clancy
云计算的激增迫使数据中心从数据中心内的任何物理位置支持大量的动态资源，如虚拟机和存储卷。这导致了高度不稳定和不可预测的流量模式。交换大量信息的云应用程序的出现创造了大量需要与其他类型的流量共存的持续流量。因此，提出了许多数据中心拓扑来支持云应用。CLOS网络是其中一种已获得突出地位的拓扑。一方面，Clos网络提供了许多良好的特性，如等距离跳数、带宽和延迟。另一方面，不同交通流量的路线选择仍然是一个问题。当前的诸如等成本多路径(ECMP)路由等依赖于等成本路径上的流散列的路由方法没有考虑业务量或网络状态。在本文中，我们研究了CLOS拓扑中的路由。我们将Clos网络中的最优流路由问题描述为一个二进制多商品流问题，并提出了一种改进的二进制多商品流问题--优化流重新路由，它使用启发式方法来最小化哈希冲突。我们还提出了一种实用的优化方法Flowfit，它利用网络状态来最优地将流重新分配到链路。我们的实验和模拟结果表明，与ECMP相比，我们在对分带宽和流完成时间方面有了显著的改善。
The proliferation of cloud computing has forced data centers to support a large number of dynamic resources such as virtual machines and storage volumes from any physical location within the data center. This has led to highly volatile and unpredictable traffic patterns. The emergence of cloud applications that exchange large volumes of information have created large persistent flows that need to coexist with other types of traffic. As a result, a number of data center topologies have been proposed to support cloud applications. One of the topologies that has gained prominence is the Clos network. On one hand, Clos networks provide many nice properties, such as equidistant hops, bandwidth, and latency. On the other hand the routing of diverse traffic flows still remains an issue. Current routing methods such as equal-cost multi-path (ECMP) routing that rely on flow hashing over equal cost paths do not take into consideration traffic volume nor network state. In this paper, we investigate routing in Clos topologies. We formulate optimal flow routing in Clos networks as a binary multicommodity flow problem and present optimized flow re-routing, a modified version of the binary multicommodity flow problem that uses a heuristics approach to minimize hash collisions. We also propose FlowFit, a practical optimization method that uses network state to optimally re-assign flows to links. Our experimental and simulation results show a significant improvement in bisection bandwidth and flow completion time over ECMP.