arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.07477cs.NIcs.DCcs.PF
收藏

T-RACK:一种数据中心网络中TCP的快速恢复机制

T-RACKs: A Faster Recovery Mechanism for TCP in Data Center Networks

Ahmed M. Abdelmoniem, Brahim Bensaou

摘要:

云交互式数据驱动应用程序生成大量小型TCP流,这些流争夺数据中心交换机中的小缓冲区空间。这些应用需要短的流程完成时间(FCT)来有效地执行其工作。然而,TCP忽略了应用程序数据的复合性质,并人为地将这些流的FCT膨胀了几个数量级。这是由于TCP的以互联网为中心的设计将重传超时(RTO)固定为至少数百毫秒。为了更好地理解这个问题,在本文中,我们使用经验测量在一个小的测试床研究,在微观层面上,各种类型的数据包丢失对TCP的性能的影响。特别是,我们挑出的数据包丢失,影响小流量的尾端,以及突发性的损失,跨越数据中心的TCP流的小拥塞窗口的一个显着的部分,显示FCT的不可忽略的影响。基于此,我们提出了所谓的,及时重传的ACK(或T-RACK),一个简单的丢失恢复机制,即使在存在严重的数据包丢失隐藏长RTO的缺点。有趣的是,T-RACKS对TCP本身透明地实现了这一点,因为它不需要在租户的虚拟机(VM)中对TCP进行任何更改。T-RACK可以作为虚拟机和服务器NIC之间的虚拟机管理程序中的软件shim层实现,也可以作为SmartNIC中的网络功能在硬件中实现。仿真和实际测试结果表明,T-RACK取得了显着的性能改善。

英文摘要:

Cloud interactive data-driven applications generate swarms of small TCP flows that compete for the small buffer space in data-center switches. Such applications require a short flow completion time (FCT) to perform their jobs effectively. However, TCP is oblivious to the composite nature of application data and artificially inflates the FCT of such flows by several orders of magnitude. This is due to TCP's Internet-centric design that fixes the retransmission timeout (RTO) to be at least hundreds of milliseconds. To better understand this problem, in this paper, we use empirical measurements in a small testbed to study, at a microscopic level, the effects of various types of packet losses on TCP's performance. In particular, we single out packet losses that impact the tail end of small flows, as well as bursty losses, that span a significant fraction of the small congestion window of TCP flows in data-centers, to show a non-negligible effect on the FCT. Based on this, we propose the so-called, timely-retransmitted ACKs (or T-RACKs), a simple loss recovery mechanism to conceal the drawbacks of the long RTO even in the presence of heavy packet losses. Interestingly enough, T-RACKS achieves this transparently to TCP itself as it does not require any change to TCP in the tenant's virtual machine (VM). T-RACKs can be implemented as a software shim layer in the hypervisor between the VMs and server's NIC or in hardware as a networking function in a SmartNIC. Simulation and real testbed results show that T-RACKs achieves remarkable performance improvements.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑