Reliable Multicast in Data Center Networks
Reliable Multicast in Data Center Networks
复制标题
数据中心网络中的可靠组播
DOI：
10.1109/tc.2013.91
复制
发表时间：
2014-08
影响因子：
3.7
通讯作者：
Guihai Chen
中科院分区：
文献类型：
--
作者：
Mingwei Xu;Jingyi Wang;Yong Cui;Guihai Chen
组播有利于数据中心群通信，既节省了网络流量，又提高了应用吞吐量。数据中心组播需要可靠的分组传输，以满足数据密集型计算的需要。然而，现有的可靠的Internet组播解决方案并不适合数据中心环境，特别是在保证组播吞吐量不因丢包而降低方面，这在数据中心是常态而不是例外。提出了一种新的数据中心网络可靠组播协议RDCM。RDCM的核心思想是利用数据中心丰富的链路资源，最大限度地减少丢包对组播吞吐量的影响。组播树感知备份覆盖明确地建立在组成员上，用于点对点数据包修复。备份覆盖层以这样一种方式组织，它导致很少的个人修复负担、控制开销以及整体修复流量。RDCM还实现了基于窗口的拥塞控制，使其发送速率适应网络中的流量状态。在典型数据中心网络中的仿真结果表明，RDCM比其他具有代表性的可靠组播协议具有更高的应用吞吐量和更小的流量占用。我们已经在Windows平台上将RDCM实现为用户级库。在我们的测试平台上的实验表明，RDCM在高速数据传输过程中处理丢包没有明显的吞吐量下降，对链路故障和接收器故障的响应优雅，对数据中心服务器的CPU开销小于10%。
Multicast benefits data center group communication in both saving network traffic and improving application throughput. Reliable packet delivery is required in data center multicast for data-intensive computations. However, existing reliable multicast solutions for the Internet are not suitable for the data center environment, especially with regard to keeping multicast throughput from degrading upon packet loss, which is norm instead of exception in data centers. We present RDCM, a novel reliable multicast protocol for data center network. The key idea of RDCM is to minimize the impact of packet loss on the multicast throughput, by leveraging the rich link resource in data centers. A multicast-tree-aware backup overlay is explicitly built on group members for peer-to-peer packet repair. The backup overlay is organized in such a way that it causes little individual repair burden, control overhead, as well as overall repair traffic. RDCM also realizes a window-based congestion control to adapt its sending rate to the traffic status in the network. Simulation results in typical data center networks show that RDCM can achieve higher application throughput and less traffic footprint than other representative reliable multicast protocols. We have implemented RDCM as a user-level library on Windows platform. The experiments on our test bed show that RDCM handles packet loss without obvious throughput degradation during high-speed data transmission, gracefully respond to link failure and receiver failure, and causes less than 10% CPU overhead to data center servers.
登录
查看更多内容
DOI：
10.1109/tnet.2010.2053718
发表时间：
2011-02
期刊：
IEEE/ACM Transactions on Networking
影响因子：
--
作者：
Dan Li;Chuanxiong Guo;Haitao Wu;Kun Tan;Yongguang Zhang;Songwu Lu;Jianping Wu
通讯作者：
Dan Li;Chuanxiong Guo;Haitao Wu;Kun Tan;Yongguang Zhang;Songwu Lu;Jianping Wu
DOI：
10.1109/infcom.2004.1354672
发表时间：
2004-03
期刊：
IEEE INFOCOM 2004
影响因子：
--
作者：
Lisong Xu;Khaled Harfoush;I. Rhee
通讯作者：
Lisong Xu;Khaled Harfoush;I. Rhee
DOI：
10.1145/989.357400
发表时间：
1984-08
期刊：
ACM Trans. Comput. Syst.
影响因子：
--
作者：
Jo-Mei Chang;N. Maxemchuk
通讯作者：
Jo-Mei Chang;N. Maxemchuk
DOI：
10.1145/1644893.1644918
发表时间：
2009-11
期刊：
--
影响因子：
--
作者：
Srikanth Kandula;S. Sengupta;A. Greenberg;Parveen Patel;R. Chaiken
通讯作者：
Srikanth Kandula;S. Sengupta;A. Greenberg;Parveen Patel;R. Chaiken
DOI：
10.1145/217382.217470
发表时间：
1995-10
期刊：
--
影响因子：
--
作者：
S. Floyd;V. Jacobson;S. McCanne;Ching-Gung Liu;Lixia Zhang
通讯作者：
S. Floyd;V. Jacobson;S. McCanne;Ching-Gung Liu;Lixia Zhang