R2D2: Bufferless, switchless data center networks using commodity Ethernet hardware

R2D2: Bufferless, switchless data center networks using commodity Ethernet hardware. Grosvenor, M. P., Schwarzkopf, M., & Moore, A. W. Computer Communication Review, 43(4):507–508, ACM Press, Dec, 2013.
doi abstract bibtex

Modern data centers commonly run distributed applications that require low-latency communication, and whose performance is critical to service revenue. If as little as one machine in 10,000 is a latency outlier, around 18% of requests will experience high latency. The sacrifice of latency determinism for bandwidth, however, is not an inevitable one. In our R2D2 architecture, we conceptually split the data centre network into an unbuffered, unswitched low-latency network (LLNet) and a deeply buffered bandwidth centric network (BBNet). Through explicitly scheduling network multiplexing in software, our prototype implementation achieves 99.995% and 99.999% messaging latencies of 35us and 75us respectively for 1514-byte packets on a fully loaded network. Furthermore, we show that it is possible to merge the conceptually separate LLNet and BBNet networks onto the same physical infrastructure using commodity switched Ethernet hardware. © 2013 Authors.

@Article{Grosvenor2013R2D2,
  author            = {Grosvenor, Matthew P. and Schwarzkopf, Malte and Moore, Andrew W.},
  journal           = {Computer Communication Review},
  title             = {{R2D2: Bufferless, switchless data center networks using commodity Ethernet hardware}},
  year              = {2013},
  issn              = {0146-4833},
  month             = {Dec},
  number            = {4},
  pages             = {507--508},
  volume            = {43},
  abstract          = {Modern data centers commonly run distributed applications that require low-latency communication, and whose performance is critical to service revenue. If as little as one machine in 10,000 is a latency outlier, around 18\% of requests will experience high latency. The sacrifice of latency determinism for bandwidth, however, is not an inevitable one. In our R2D2 architecture, we conceptually split the data centre network into an unbuffered, unswitched low-latency network (LLNet) and a deeply buffered bandwidth centric network (BBNet). Through explicitly scheduling network multiplexing in software, our prototype implementation achieves 99.995\% and 99.999\% messaging latencies of 35us and 75us respectively for 1514-byte packets on a fully loaded network. Furthermore, we show that it is possible to merge the conceptually separate LLNet and BBNet networks onto the same physical infrastructure using commodity switched Ethernet hardware. © 2013 Authors.},
  booktitle         = {Proceedings of the ACM SIGCOMM 2013 conference on SIGCOMM - SIGCOMM '13},
  conference        = {the ACM SIGCOMM 2013 conference},
  day               = {1},
  doi               = {10.1145/2534169.2491722},
  eissn             = {1943-5819},
  finishday         = {16},
  finishmonth       = {Aug},
  finishyear        = {2013},
  isbn              = {9781450320566},
  publicationstatus = {published},
  publisher         = {ACM Press},
  startday          = {12},
  startmonth        = {Aug},
  startyear         = {2013},
}

Downloads: 0