Mohammad Alizadeh
Nick McKeown
Scott Shenker
ABSTRACT
We present, pFabric, a minimalistic datacenter fabric design that provides near-optimal performance in terms of completion time for high-priority flows and overall network utilization. pFabric's design eliminates nearly all buffering on switches (switches have only ~20KB of buffering per port), requires almost no congestion control and uses only simple mechanisms at each switch. Specifically, switches are only required to locally and greedily decide what packets to schedule and drop according to priorities in the packet header and do not maintain any flow state or rate estimates. Rate-control is almost unnecessary, all flows start at line-rate and only slow down in the extreme case of congestion collapse. We show via simulations using realistic workloads and topologies that this simple design achieves near optimal flow completion times and network utilization.
- M. Al-Fares, A. Loukissas, and A. Vahdat. A scalable, commodity data center network architecture. In Proc. of SIGCOMM, 2008. Google Scholar
Digital Library
- M. Alizadeh, A. Greenberg, D. A. Maltz, J. Padhye, P. Patel, B. Prabhakar, S. Sengupta, and M. Sridharan. Data center TCP (DCTCP). In Proc. of SIGCOMM, 2010. Google ScholarDigital Library
- M. Alizadeh, A. Kabbani, T. Edsall, B. Prabhakar, A. Vahdat, and M. Yasuda. Less is more: trading a little bandwidth for ultra-low latency in the data center. In Proc. of NSDI, 2012. Google ScholarDigital Library
- B. Atikoglu, Y. Xu, E. Frachtenberg, S. Jiang, and M. Paleczny. Workload analysis of a large-scale key-value store. In Proc. of SIGMETRICS, pages 53--64, New York, NY, USA, 2012. ACM. Google ScholarDigital Library
- A. Bar-Noy, M. M. Halldórsson, G. Kortsarz, R. Salman, and H. Shachnai. Sum multicoloring of graphs. J. Algorithms, 37(2): 422--450, Nov. 2000. Google ScholarDigital Library
- A. Greenberg, J. R. Hamilton, N. Jain, S. Kandula, C. Kim, P. Lahiri, D. A. Maltz, P. Patel, and S. Sengupta. VL2: a scalable and flexible data center network. In Proc. of SIGCOMM, 2009. Google ScholarDigital Library
- C.-Y. Hong, M. Caesar, and P. B. Godfrey. Finishing Flows Quickly with Preemptive Scheduling. In Proc. of SIGCOMM, 2012. Google ScholarDigital Library
- The Network Simulator NS-2. http://www.isi.edu/nsnam/ns/.Google Scholar
- B. Vamanan, J. Hasan, and T. N. Vijaykumar. Deadline-Aware Datacenter TCP (D2TCP). In Proc. of SIGCOMM, 2012. Google ScholarDigital Library
- V. Vasudevan, A. Phanishayee, H. Shah, E. Krevat, D. G. Andersen, G. R. Ganger, G. A. Gibson, and B. Mueller. Safe and effective fine-grained TCP retransmissions for datacenter communication. In Proc. of SIGCOMM, 2009. Google ScholarDigital Library
- C. Wilson, H. Ballani, T. Karagiannis, and A. Rowtron. Better never than late: meeting deadlines in datacenter networks. In Proc. of SIGCOMM, pages 50--61. ACM, 2011. Google ScholarDigital Library
- D. Zats, T. Das, P. Mohan, D. Borthakur, and R. H. Katz. DeTail: Reducing the Flow Completion Time Tail in Datacenter Networks. In Proc. of SIGCOMM, 2012. Google ScholarDigital Library
Index Terms
- Deconstructing datacenter packet transport
Recommendations
Nearly optimal FIFO buffer management for two packet classes
We consider a FIFO buffer with finite storage space. An arbitrary input stream of packets arrives at the buffer, but the output stream rate is bounded, so overflows may occur. We assume that each packet has value which is either 1 or α, for some α > 1. ...
Improving datacenter throughput and robustness with Lazy TCP over packet spraying
Packet spraying is being recognized as a promising multipath routing approach in datacenter for full utilization of multiple paths. However, existing TCP schemes face serious challenge of robustness when running over packet spraying. They suffer ...
Performance Evaluation of Quality of Service for Joint Packet Dropping and Scheduling
Quality of Service is particularly necessary to serve delay-sensitive applications in heavy-loaded wireless networks. In this paper we evaluate a strategy of combining packet dropping and scheduling policies at Medium Access Control layer in ...
Comments