Jupiter rising: a decade of clos topologies and centralized control in Google's datacenter network

@article{Singh2016JupiterRA,
  title={Jupiter rising: a decade of clos topologies and centralized control in Google's datacenter network},
  author={Arjun Singh and J. Ong and Amit Agarwal and Glen Anderson and Ashby Armistead and Roy Bannon and Seb Boving and Gaurav Desai and Bob Felderman and Paulie Germano and Anand Kanagala and Hong Liu and Jeff Provost and Jason Simmons and Eiichi Tanda and Jim Wanderer and Urs H{\"o}lzle and Stephen Stuart and Amin Vahdat},
  journal={Commun. ACM},
  year={2016},
  volume={59},
  pages={88-97}
}
We present our approach for overcoming the cost, operational complexity, and limited scale endemic to datacenter networks a decade ago. Three themes unify the five generations of datacenter networks detailed in this paper. First, multi-stage Clos topologies built from commodity switch silicon can support cost-effective deployment of building-scale networks. Second, much of the general, but complex, decentralized network routing and management protocols supporting arbitrary deployment scenarios… Expand

Paper Mentions

The stellar transformation: From interconnection networks to datacenter networks
TLDR
It is found that GQ outperforms both FiConn and DPillar (sometimes significantly so) and that there is substantial scope for the stellar transformation to yield new dual-port server-centric datacenter networks that are a considerable improvement on existing ones. Expand
Orion: Google's Software-Defined Networking Control Plane
TLDR
Orion was designed around a modular, micro-service architecture with a central publish-subscribe database to enable a distributed, yet tightlycoupled, software-defined network control system, and today enables Google’s Software-Defined Networks. Expand
A Tale of Two Topologies: Exploring Convertible Data Center Network Architectures with Flat-tree
TLDR
The flat-tree prototype architecture is proposed, which can be implemented as a Clos network and later be converted to approximate random graphs of different sizes, thus achieving both Clos-like implementation simplicity and random-graph-like transmission performance. Expand
Expander Datacenters: From Theory to Practice
TLDR
This paper examines if expanders can be effective for the technology and environments practical in today's data centers, including the use of traditional protocols, at both small and large scale while complying with common practices such as over-subscription. Expand
Sirius: A Flat Datacenter Network with Nanosecond Optical Switching
TLDR
Sirius, an optically-switched network for datacenters providing the abstraction of a single, high-radix switch that can connect thousands of nodes---racks or servers---in a datacenter while achieving nanosecond-granularity reconfiguration, is proposed. Expand
Random Folded Clos Topologies for Datacenter Networks
TLDR
It is shown that RFCs constitute an interesting alternative to currently deployed networks since they appropriately balance all the important design requirements and do that at much lower cost than the fat-tree, their natural competitor. Expand
RotorNet: A Scalable, Low-complexity, Optical Datacenter Network
TLDR
While RotorNet dynamically reconfigures its constituent circuit switches, it decouples switch configuration from traffic patterns, obviating the need for demand collection and admitting a fully decentralized control plane. Expand
Routing in Fat Trees: a protocol analyzer for debugging and experimentation
TLDR
This work presents an implementation of a RIFT packet dissector for Wireshark, which permits to analyze control-plane traffic under different scenarios, and can be easily extended to parse any RIFT generated Thrift code. Expand
P-FatTree: A multi-channel datacenter network topology
TLDR
P-FatTree is proposed, which is a FatTree topology designed specifically for the future multi-channel reality that requires fewer switch chips and as a result has lower cost, power consumption, and latency than existing approaches. Expand
Congestion Control for Cross-Datacenter Networks
TLDR
The design and implementation of GEMINI is presented, that strategically integrates both ECN and delay signals for cross-DC congestion control and achieves low latency and high throughput. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 39 REFERENCES
A scalable, commodity data center network architecture
TLDR
This paper shows how to leverage largely commodity Ethernet switches to support the full aggregate bandwidth of clusters consisting of tens of thousands of elements and argues that appropriately architected and interconnected commodity switches may deliver more performance at less cost than available from today's higher-end solutions. Expand
VL2: a scalable and flexible data center network
TLDR
VL2 is a practical network architecture that scales to support huge data centers with uniform high capacity between servers, performance isolation between services, and Ethernet layer-2 semantics, and is built on a working prototype. Expand
B4: experience with a globally-deployed software defined wan
TLDR
This work presents the design, implementation, and evaluation of B4, a private WAN connecting Google's data centers across the planet, using OpenFlow to control relatively simple switches built from merchant silicon. Expand
Jellyfish: Networking Data Centers Randomly
TLDR
Jellyfish is a high-capacity network interconnect which, by adopting a random graph topology, yields itself naturally to incremental expansion, and is more cost-efficient than a fat-tree. Expand
Dcell: a scalable and fault-tolerant network structure for data centers
TLDR
Results from theoretical analysis, simulations, and experiments show that DCell is a viable interconnection structure for data centers and can be incrementally expanded and a partial DCell provides the same appealing features. Expand
Data Center Switch Architecture in the Age of Merchant Silicon
TLDR
This paper describes how to save cost and power by repackaging an entire data center network as a distributed multi-stage switch using a fat-tree topology and merchant silicon instead of proprietary ASICs. Expand
BCube: a high performance, server-centric network architecture for modular data centers
TLDR
Experiments in the testbed demonstrate that BCube is fault tolerant and load balancing and it significantly accelerates representative bandwidth-intensive applications. Expand
Scale-Out Networking in the Data Center
TLDR
Through the UCSD Triton network architecture, the authors explore issues in managing the network as a single plug-and-play virtualizable fabric scalable to hundreds of thousands of ports and petabits per second of aggregate bandwidth. Expand
KLAT2's Flat Neighborhood Network
  • H. Dietz, T. Mattox
  • Engineering, Computer Science
  • Annual Linux Showcase & Conference
  • 2000
TLDR
This paper describes a novel "Flat Neighborhood" network topology that was designed by a genetic algorithm (GA) and how this new network architecture was derived, how it is used, and how it performs. Expand
...
1
2
3
4
...