Proteus: A Topology Malleable Data Center Network Ankit Singla (University of Illinois Urbana-Champaign) Atul Singh, Kishore Ramachandran, Lei Xu, Yueping.

Slides:



Advertisements
Similar presentations
Kai Chen, Ankit Singla, Atul Singh, Kishore Ramachandran,
Advertisements

Next-Generation ROADMs
Dynamic Topology Optimization for Supercomputer Interconnection Networks Layer-1 (L1) switch –Dumb switch, Electronic “patch panel” –Establishes hard links.
Improving Datacenter Performance and Robustness with Multipath TCP Costin Raiciu, Sebastien Barre, Christopher Pluntke, Adam Greenhalgh, Damon Wischik,
ElasticTree: Saving Energy in Data Center Networks Brandon Heller, Srini Seetharaman, Priya Mahadevan, Yiannis Yiakoumis, Puneed Sharma, Sujata Banerjee,
Optical Networks BM-UC Davis122 Part III Wide-Area (Wavelength-Routed) Optical Networks – 1.Virtual Topology Design 2.Wavelength Conversion 3.Control and.
1 EL736 Communications Networks II: Design and Algorithms Class3: Network Design Modeling Yong Liu 09/19/2007.
A Review of Traffic Grooming in WDM Optical Networks: Architectures and Challenges* Keyao Zhu and Biswanath Mukherjee.
Filippos BALASIS TANAKA LAB Catching Up With The Global Bandwidth Demand: 2023 And Beyond.
Chapter 4 Circuit-Switching Networks
Reconfigurable Network Topologies at Rack Scale
Datacenter Network Topologies
A Scalable Switch for Service Guarantees Bill Lin (University of California, San Diego) Isaac Keslassy (Technion, Israel)
RIT Campus Data Network. General Network Statistics Over 23,000 wired outlets Over 14,500 active switched ethernet ports > 250 network closets > 1,000.
Hardness of Approximation and Greedy Algorithms for the Adaptation Problem in Virtual Environments Ananth I. Sundararaj, Manan Sanghi, John R. Lange and.
VROOM: Virtual ROuters On the Move Yi Wang (Princeton) With: Kobus van der Merwe (AT&T Labs - Research) Jennifer Rexford (Princeton)
Chuanxiong Guo, Haitao Wu, Kun Tan,
Alternative Switching Technologies: Optical Circuit Switches Hakim Weatherspoon Assistant Professor, Dept of Computer Science CS 5413: High Performance.
FireFly: A Reconfigurable Wireless Datacenter Fabric using Free-Space Optics Navid Hamedazimi, Zafar Qazi, Himanshu Gupta, Vyas Sekar, Samir Das, Jon.
Outline Introduction Switching Techniques Optical Burst Switching
Ji-Yong Shin * Bernard Wong +, and Emin Gün Sirer * * Cornell University + University of Waterloo 2 nd ACM Symposium on Cloud ComputingOct 27, 2011 Small-World.
Helios: A Hybrid Electrical/Optical Switch Architecture for Modular Data Centers Nathan Farrington George Porter, Sivasankar Radhakrishnan,
Energy Aware Network Operations Authors: Priya Mahadevan, Puneet Sharma, Sujata Banerjee, Parthasarathy Ranganathan HP Labs IEEE Global Internet Symposium.
Not All Microseconds are Equal: Fine-Grained Per-Flow Measurements with Reference Latency Interpolation Myungjin Lee †, Nick Duffield‡, Ramana Rao Kompella†
Optical Switching Switch Fabrics, Techniques and Architectures 원종호 (INC lab) Oct 30, 2006.
LIGHTNESS Introduction 10th Oct, 2012 Low latency and hIGH Throughput dynamic NEtwork infrastructureS for high performance datacentre interconnectS.
Integrated Dynamic IP and Wavelength Routing in IP over WDM Networks Murali Kodialam and T. V. Lakshman Bell Laboratories Lucent Technologies IEEE INFOCOM.
Capacity Scaling with Multiple Radios and Multiple Channels in Wireless Mesh Networks Oguz GOKER.
Routing & Architecture
Copyright © 2011, Programming Your Network at Run-time for Big Data Applications 張晏誌 指導老師:王國禎 教授.
David G. Andersen CMU Guohui Wang, T. S. Eugene Ng Rice Michael Kaminsky, Dina Papagiannaki, Michael A. Kozuch, Michael Ryan Intel Labs Pittsburgh 1 c-Through:
TTM1 – 2013: Core networks and Optical Circuit Switching (OCS)
1 A Presentation on Design and Implementation of Wavelength-Flexible Network Nodes Carl Nuzman, Juerg Leuthold, Roland Ryf, S.Chandrasekar, c. Randy Giles.
1 Heterogeneity in Multi-Hop Wireless Networks Nitin H. Vaidya University of Illinois at Urbana-Champaign © 2003 Vaidya.
Scalable Reconfigurable Interconnects Ali Pinar Lawrence Berkeley National Laboratory joint work with Shoaib Kamil, Lenny Oliker, and John Shalf CSCAPES.
Patch Panels in the Sky: A Case for Free-Space Optics in Data Centers Navid Hamed Azimi, Himanshu Gupta Vyas Sekar, Samir Das.
Wavelength Assignment in Waveband Switching Networks with Wavelength Conversion Xiaojun Cao; Chunming Qiao; Anand, V. Jikai LI GLOBECOM '04. IEEE Volume.
LAN Switching and Wireless – Chapter 1
A Survey on Optical Interconnects for Data Centers Speaker: Shih-Chieh Chien Adviser: Prof Dr. Ho-Ting Wu.
VL2: A Scalable and Flexible Data Center Network Albert Greenberg, James R. Hamilton, Navendu Jain, Srikanth Kandula, Changhoon Kim, Parantap Lahiri, David.
Applied research laboratory 1 Scaling Internet Routers Using Optics Isaac Keslassy, et al. Proceedings of SIGCOMM Slides:
Software Defined Networks for Dynamic Datacenter and Cloud Environments.
Clustering In A SAN For High Availability Steve Dalton, President and CEO Gadzoox Networks September 2002.
NETWORK HARDWARE CABLES NETWORK INTERFACE CARD (NIC)
Five Essential Elements for Future Regional Optical Networks Harold Snow Sr. Systems Architect, CTO Group.
Intradomain Traffic Engineering By Behzad Akbari These slides are based in part upon slides of J. Rexford (Princeton university)
Dual Centric Data Center Network Architectures DAWEI LI, JIE WU (TEMPLE UNIVERSITY) ZHIYONG LIU, AND FA ZHANG (CHINESE ACADEMY OF SCIENCES) ICPP 2015.
Reconfigurable Optical Mesh and Network Intelligence Nazar Neayem Alcatel-Lucent Internet 2 - Summer 2007 Joint Techs Workshop Fermilab - Batavia, IL July.
Optical Networking University of Southern Queensland.
Advanced Computer Networks Lecturer: E EE Eng. Ahmed Hemaid Office: I 114.
Traffic grooming in WDM Networks Dynamic Traffic Grooming in WDM Mesh Networks Using a Novel Graph Model by Hongyue Zhu, Hui Zang, Keyao Zhu, and Biswanath.
Interconnect Networks Basics. Generic parallel/distributed system architecture On-chip interconnects (manycore processor) Off-chip interconnects (clusters.
Theophilus Benson*, Ashok Anand*, Aditya Akella*, Ming Zhang + *University of Wisconsin, Madison + Microsoft Research.
C-Through: Part-time Optics in Data centers Aditi Bose, Sarah Alsulaiman.
MMPTCP: A Multipath Transport Protocol for Data Centres 1 Morteza Kheirkhah University of Edinburgh, UK Ian Wakeman and George Parisis University of Sussex,
Virtual-Topology Adaptation for WDM Mesh Networks Under Dynamic Traffic.
XFabric: a Reconfigurable In-Rack Network for Rack-Scale Computers Sergey Legtchenko, Nicholas Chen, Daniel Cletheroe, Antony Rowstron, Hugh Williams,
Yiting Xia, T. S. Eugene Ng Rice University
Data Center Network Topologies II
Data Center Network Architectures
Chuanxiong Guo, et al, Microsoft Research Asia, SIGCOMM 2008
Improving Datacenter Performance and Robustness with Multipath TCP
Reconfigurable Optical Mesh and Network Intelligence
Improving Datacenter Performance and Robustness with Multipath TCP
Chuanxiong Guo, Haitao Wu, Kun Tan,
Dingming Wu+, Yiting Xia+*, Xiaoye Steven Sun+,
Jellyfish: Networking Data Centers Randomly
Alcatel Confidential and Proprietary
Data Center Architectures
SURVIVABILITY IN IP-OVER-WDM NETWORKS (2)
Presentation transcript:

Proteus: A Topology Malleable Data Center Network Ankit Singla (University of Illinois Urbana-Champaign) Atul Singh, Kishore Ramachandran, Lei Xu, Yueping Zhang (NEC Labs, Princeton)

 Data centers: Foundation of Internet services, enterprise operation –Need good bandwidth connectivity between servers Data Centers 2

“Good” Bandwidth Connectivity  Connect all servers at full bandwidth?  Fat-trees [SIGCOMM 2008], VL2 [SIGCOMM 2009] 3 C ABLING C OMPLEXITY U PGRADE TO 40/100-G IG E? P OWER C ONSUMPTION ?

Oversubscribed Networks  Is all-to-all full bandwidth connectivity always necessary? –Small number of ‘hot’ ToR-ToR connections Flyways [HotNets 2009] –>90% bytes flow in ‘elephant flows’ VL2 [SIGCOMM 2009] – ~60% ToRs see <20% change in traffic for between sec The Case for Fine-grained TE in Data Centers [WREN 2010]  Flyways [HotNets 2009], c-Through and Helios [SIGCOMM 2010]  Supplement electrical network with wireless/optics –Wireless/Optical connections are set up between hot ToRs –Some flexibility to adjust to changes in traffic matrix 4

Proteus  Proteus is a novel interconnect above the ToR layer –Topology adjusts to traffic demands –Low cabling complexity –Easier migration to 40/100-GigE –Low power consumption 5 A N EW D ESIGN P OINT : A LL - OPTICS Optical Interconnect ToR... ToR... Servers Proteus is an oversubscribed network with topology malleability topology malleability

Malleability AB C D E F GH G C F A D E B H C HANGE TOPOLOGY G C F A D E B H C HANGE CAPACITY T RAFFIC C HANGE P ICK R OUTES AG10 BH CE DF BD AG BH CE GF20 BD10 6

1 Gigabit X 64, Terabits* X 1 * Achieved by NEC Labs and AT&T Low complexity, reconfigurability, low power consumption MEMS D C B A A C B D A B C D A B C D A C D WSS MEMS C IRCUIT SETUP TIME L IMITED W AVELENGTHS TOPOLOGY MANAGEMENT 7 MEMS = Micro-Electro Mechanical Switch WSS = Wavelength Selective Switch Optics: Perfect Fit

Problem Setting: Container-sized DCN  Proteus-2560: Connect 80 ToRs, each with 32 servers  Typical container-size in containerized data center architectures Image adapted from: 8

ToR Perspective 9 … N ON - BLOCKING T O R … O PTICAL I NTERCONNECT S ERVERS 32 PORTS TOWARDS INTERCONNECT 32 PORTS FOR S ERVERS

ToR Perspective 10 … N ON - BLOCKING T O R … O E O I NTRA -R ACK T RAFFIC T RANSIT T RAFFIC (H OP - BY - HOP ) C ROSS -R ACK T RAFFIC T RANSCEIVERS W ITH U NIQUE W AVELENGTHS (O-E-O conversions add sub-nanosecond latency at each hop) L IMITED BY T O R PORT CAPACITY

11 … TOR1TOR1 … O PTICAL C OMPONENTS ToR 13 ToR 21 ToR 45 ToR 73 I NCOMING H IGH C APACITY L INK L OW C APACITY L INK ToR 67 ToR 11 ToR 29 ToR 55 C HANGE T OPOLOGY C HANGE C APACITY O PTICAL C OMPONENTS

T OPOLOGY (MEMS) B I - DIRECTIONALITY (C IRCULATORS ) C APACITY (WSS) 12 MEMS (320 ports) C C C C WSS MUX … … ToR 26 … … … … C C C C … … ToR 59 … COUPLER DEMUX To ToR 2 To ToR S S R R

Proteus-2560 Properties  Build any 4-regular ToR topology  Each link’s capacity varies in each direction –Capacity Є {10, 20, 30, …, 320 } Gbps –Provided sum of capacities of 4 links <= 320 Gbps –(Also avoid wavelength contention)  Use hop-by-hop connections to other ToRs –Transit traffic doesn’t interfere with intra-ToR traffic 13

Topology Management  We formulate the problem as a mixed-integer linear program  Describe a heuristic approach backed by graph-theoretic insights –Likely to take under a couple of hundred milliseconds C OMPLEX PROBLEM : A LL CONFIGURATIONS ARE INTERDEPENDENT D CB A ? A C D ? A B C D ? MEMS WSSHop-by-hop routing 14

Heuristic Approach – Key Ideas  Topology: Weighted 4-matching over hot ToR-ToR connections –Check and correct for connectivity  Routing: Can use shortest paths –Ideally, need low-congestion routing schemes  Capacities: Graph edge-coloring over wavelengths –Ensure each link carries at least one wavelength 15

Preliminary Analysis  Cabling: #Fibers ≈ 1/5 th #cables in a fat-tree  Ease of upgrade: When ToRs move to 40/100-GigE, nothing else changes!  Cost: similar to a fat-tree –Optics is yet to benefit from commoditization –To some extent, dispels the optics is expensive myth  Power: 50% of fat-tree power consumption  Fat-tree is also fault tolerant though 16

Conclusion, Ongoing Work  A novel data center architecture –Unprecedented topology flexibility –Reduced cabling complexity –Easier migration to 40/100-GigE –Reduced power consumption –Explores a new design point – all-optics  Experimental evaluation  Incremental update heuristics  Mega-data-center scale  Fault tolerance 17 T RANSIENT B EHAVIOR ? R OUTING ? S YNCHRONIZATION ?

Thank You! Questions?

Extras / Backup 19

Hop-by-hop Through ToRs  MEMS – limited end-to-end circuits  Need hop-by-hop routes over these circuits  Feasibility assessment: works fine! 20

Helios [SIGCOMM ’10]  Pods are still fat-trees  Requires design-time decision on stable vs. unstable traffic  Does not exploit multi-hop optical routes  Does not leverage WSS technology for variable capacity Image from “Helios: A Hybrid Electrical/Optical Switch Architecture for Modular Data Centers” – Farrington et al 21