Data center TCP (DCTCP)

Computer Communication Review - Tập 40 Số 4 - Trang 63-74 - 2010
Mohammad Alizadeh1, Albert Greenberg2, David A. Maltz2, Jitendra Padhye2, Parveen Patel2, Balaji Prabhakar1, Sudipta Sengupta2, Murari Sridharan2
1Stanford University, Palo Alto, CA, USA
2Microsoft Research, Redmond, WA, USA

Tóm tắt

Cloud data centers host diverse applications, mixing workloads that require small predictable latency with others requiring large sustained throughput. In this environment, today's state-of-the-art TCP protocol falls short. We present measurements of a 6000 server production cluster and reveal impairments that lead to high application latencies, rooted in TCP's demands on the limited buffer space available in data center switches. For example, bandwidth hungry "background" flows build up queues at the switches, and thus impact the performance of latency sensitive "foreground" traffic. To address these problems, we propose DCTCP, a TCP-like protocol for data center networks. DCTCP leverages Explicit Congestion Notification (ECN) in the network to provide multi-bit feedback to the end hosts. We evaluate DCTCP at 1 and 10Gbps speeds using commodity, shallow buffered switches. We find DCTCP delivers the same or better throughput than TCP, while using 90% less buffer space. Unlike TCP, DCTCP also provides high burst tolerance and low latency for short flows. In handling workloads derived from operational measurements, we found DCTCP enables the applications to handle 10X the current background traffic, without impacting foreground traffic. Further, a 10X increase in foreground traffic does not cause any timeouts, thus largely eliminating incast problems.

Từ khóa


Tài liệu tham khảo

P. Agarwal , B. Kwan , and L. Ashvin . Flexible buffer allocation entities for traffic aggregate containment. US Patent 2009 0207848, August 2009. P. Agarwal, B. Kwan, and L. Ashvin. Flexible buffer allocation entities for traffic aggregate containment. US Patent 20090207848, August 2009.

10.1145/1402958.1402967

M. Alizadeh etal Data Center TCP (DCTCP). Technical report. M. Alizadeh et al. Data Center TCP (DCTCP). Technical report.

10.1145/1015467.1015499

10.1145/190314.190317

10.1007/11499169_22

S. Floyd. RED: Discussions of setting parameters. http://www.icir.org/floyd/REDparameters.txt. S. Floyd. RED: Discussions of setting parameters. http://www.icir.org/floyd/REDparameters.txt.

S. Floyd. RFC 3649: HighSpeed TCP for large congestion windows. S. Floyd. RFC 3649: HighSpeed TCP for large congestion windows.

S. Floyd , R. Gummadi , and S. Shenker . Adaptive RED: An algorithm for increasing the robustness of RED's active queue management. Technical report , ACIRI , 2001 . S. Floyd, R. Gummadi, and S. Shenker. Adaptive RED: An algorithm for increasing the robustness of RED's active queue management. Technical report, ACIRI, 2001.

10.1109/90.251892

10.1109/90.298431

10.1145/1592568.1592576

10.1145/1592681.1592693

Y. Gu , D. Towsley , C. Hollot , and H. Zhang . Congestion control for small buffer high bandwidth networks . In INFOCOM , 2007 . Y. Gu, D. Towsley, C. Hollot, and H. Zhang. Congestion control for small buffer high bandwidth networks. In INFOCOM, 2007.

10.1145/1592568.1592577

J. Hamilton . On designing and deploying Internet-scale services . In USENIX LISA , 2007 . J. Hamilton. On designing and deploying Internet-scale services. In USENIX LISA, 2007.

10.5555/897477

A. Kabbani and B. Prabhakar . In defense of TCP . In The Future of TCP: Train-wreck or Evolution , 2008 . A. Kabbani and B. Prabhakar. In defense of TCP. In The Future of TCP: Train-wreck or Evolution, 2008.

10.1145/1644893.1644918

10.1145/1384609.1384615

10.1145/1281192.1281295

D. Leith , R. Shorten , and G. McCullagh . Experimental evaluation of cubic-TCP . In Proc. Protocols for Fast Long Distance Networks 2007 , 2007 . D. Leith, R. Shorten, and G. McCullagh. Experimental evaluation of cubic-TCP. In Proc. Protocols for Fast Long Distance Networks 2007, 2007.

10.1109/TNET.2007.896240

R. Pan B. Prabhakar and A. Laxmikantha. QCN: Quantized congestion notification an overview. http://www.ieee802.org/1/files/public/docs2007/au_ prabhakar_qcn_overview_geneva.pdf. R. Pan B. Prabhakar and A. Laxmikantha. QCN: Quantized congestion notification an overview. http://www.ieee802.org/1/files/public/docs2007/au_ prabhakar_qcn_overview_geneva.pdf.

10.1109/INFCOM.2009.5061901

10.1145/1070873.1070885

K. Ramakrishnan S. Floyd and D. Black. RFC 3168: the addition of explicit congestion notification (ECN) to IP. K. Ramakrishnan S. Floyd and D. Black. RFC 3168: the addition of explicit congestion notification (ECN) to IP.

10.1145/78952.78955

J. Rothschild. High performance at massive scale: Lessons learned at facebook. mms://video-jsoe.ucsd.edu/calit2/JeffRothschildFacebook.wmv. J. Rothschild. High performance at massive scale: Lessons learned at facebook. mms://video-jsoe.ucsd.edu/calit2/JeffRothschildFacebook.wmv.

10.1145/1400097.1400105

10.1109/INFOCOM.2006.188

10.1145/1592568.1592604

10.1109/TNET.2006.886335

10.1145/1080091.1080098

Thông tin
Thông tin xuất bản

Computer Communication Review

Tập 40 Số 4

63-74

Thông tin tác giả