ABSTRACT
Datacenters have traditionally been architected as a collection of servers wherein each server aggregates a fixed amount of computing, memory, storage, and communication resources. In this paper, we advocate an alternative construction in which the resources within a server are disaggregated and the datacenter is instead architected as a collection of standalone resources.
Disaggregation brings greater modularity to datacenter infrastructure, allowing operators to optimize their deployments for improved efficiency and performance. However, the key enabling or blocking factor for disaggregation will be the network since communication that was previously contained within a single server now traverses the datacenter fabric. This paper thus explores the question of whether we can build networks that enable disaggregation at datacenter scales.
- Apache Hadoop. http://hadoop.apache.org/.Google Scholar
- HP Moonshot System. http://goo.gl/fteii.Google Scholar
- Memcached - a distributed memory object caching system. http://memcached.org/.Google Scholar
- Open Compute Project. http://www.opencompute.org/.Google Scholar
- PigMix benchmark tool. http://cwiki.apache.org/confluence/display/PIG/PigMix.Google Scholar
- SeaMicro Technology Overview. http://seamicro.com/sites/default/files/SM_TO01_64_v2.5.pdf.Google Scholar
- M. Alizadeh, S. Yang, M. Sharif, S. Katti, N. McKeown, B. Prabhakar, and S. Shenker. pFabric: Minimal Near-Optimal Datacenter Transport. In Proc. SIGCOMM, 2013. Google ScholarDigital Library
- T. E. Anderson, D. E. Culler, and D. Patterson. A case for NOW (networks of workstations). Micro, IEEE, 15(1): 54--64, 1995. Google ScholarDigital Library
- P. Barham, B. Dragovic, K. Fraser, S. Hand, T. Harris, A. Ho, R. Neugebauer, I. Pratt, and A. Warfield. Xen and the Art of Virtualization. In Proc. SOSP, 2003. Google ScholarDigital Library
- L. A. Barroso, J. Dean, and U. Holzle. Web search for a planet: The Google cluster architecture. Micro, IEEE, 23(2): 22--28, 2003. Google ScholarDigital Library
- B. F. Cooper, A. Silberstein, E. Tam, R. Ramakrishnan, and R. Sears. Benchmarking cloud serving systems with YCSB. In Proc. SoCC, 2010. Google ScholarDigital Library
- A. Greenberg, G. Hjalmtysson, D. A. Maltz, A. Myers, J. Rexford, G. Xie, H. Yan, J. Zhan, and H. Zhang. A clean slate 4D approach to network control and management. ACM SIGCOMM Computer Communication Review, 35(5): 41--54, 2005. Google ScholarDigital Library
- N. Gude, T. Koponen, J. Pettit, B. Pfaff, M. Casado, N. McKeown, and S. Shenker. Nox: towards an operating system for networks. ACM SIGCOMM Computer Communication Review, 38(3): 105--110, 2008. Google ScholarDigital Library
- B. Hindman, A. Konwinski, M. Zaharia, A. Ghodsi, A. D. Joseph, R. Katz, S. Shenker, and I. Stoica. Mesos: A platform for fine-grained resource sharing in the data center. In Proc. NSDI, 2011. Google ScholarDigital Library
- Intel Newsroom. Intel, Facebook Collaborate on Future Data Center Rack Technologies. http://newsroom.intel.com/community/intel_newsroom/blog/2013/01/16/intel-facebook-collaborate-on-future-data-center-rack-technologies.Google Scholar
- K. Lim and J. Chang and T. Mudge and P. Ranganathan and S. K. Reinhardt and T. F. Wenisch. Disaggregated Memory for Expansion and Sharing in Blade Servers. In Proc. ISCA, 2009. Google ScholarDigital Library
- K. Lim and Y. Turner and J. R. Santos and A. AuYoung and J. Chang and P. Ranganathan and T. F. Wenisch. System-level implications of disaggregated memory. In Proc. HPCA, 2012. Google ScholarDigital Library
- Kshitij Sudan, Saisanthosh Balakrishnan, Sean Lie, Min Xu, Dhiraj Mallick, Gary Lauterbach, and Rajeev Balasubramonian. A Novel System Architecture for Web Scale Applications Using Lightweight CPUs and Virtualized I/O. In Proc. HPCA, 2013. Google ScholarDigital Library
- Y. Low, J. Gonzalez, A. Kyrola, D. Bickson, C. Guestrin, and J. M. Hellerstein. Graphlab: A new framework for parallel machine learning. 2010.Google Scholar
- C. Olston, B. Reed, U. Srivastava, R. Kumar, and A. Tomkins. Pig latin: a not-so-foreign language for data processing. In Proc. SIGMOD, 2008. Google ScholarDigital Library
- L. Popa, G. Kumar, M. Chowdhury, A. Krishnamurthy, S. Ratnasamy, and I. Stoica. FairCloud: sharing the network in cloud computing. In Proc. SIGCOMM, 2012. Google ScholarDigital Library
- L. Popa, P. Yalagandula, S. Banerjee, J. C. Mogul, and Y. T. J. R. Santos. ElasticSwitch: Practical Work-Conserving Bandwidth Guarantees for Cloud Computing. In Proc. SIGCOMM, 2013. Google ScholarDigital Library
- C. Reiss, J. Wilkes, and J. L. Hellerstein. Google cluster-usage traces: format + schema. Technical report, Google Inc., Mountain View, CA, USA, Nov. 2011. Revised 2012.03.20. Posted at URL http://code.google.com/p/googleclusterdata/wiki/TraceVersion2.Google Scholar
- S. Rumble, D. Ongaro, R. Stutsman, M. Rosenblum, and J. Ousterhout. It's time for low latency. In Proc. HotOS, 2011. Google ScholarDigital Library
- A. Shieh, S. Kandula, A. Greenberg, and C. Kim. Seawall: performance isolation for cloud datacenter networks. In Proc. HotCloud, 2010. Google ScholarDigital Library
- S. Soltesz, H. Pötzl, M. E. Fiuczynski, A. Bavier, and L. Peterson. Container-based operating system virtualization: a scalable, high-performance alternative to hypervisors. In Proc. EuroSys, 2007. Google ScholarDigital Library
- B. C. Vattikonda, G. Porter, A. Vahdat, and A. C. Snoeren. Practical TDMA for datacenter Ethernet. In Proc. EuroSys, 2012. Google ScholarDigital Library
Index Terms
- Network support for resource disaggregation in next-generation datacenters
Recommendations
Network requirements for resource disaggregation
OSDI'16: Proceedings of the 12th USENIX conference on Operating Systems Design and ImplementationTraditional datacenters are designed as a collection of servers, each of which tightly couples the resources required for computing tasks. Recent industry trends suggest a paradigm shift to a disaggregated datacenter (DDC) architecture containing a pool ...
An energy, performance efficient resource consolidation scheme for heterogeneous cloud datacenters
AbstractDatacenters are the principal electricity consumers for cloud computing that provide an IT backbone for today's business and economy. Numerous studies suggest that most of the servers, in the US datacenters, are idle or less-utilised, ...
Highlights- A consolidation method is suggested to manage datacenter resources – particularly, when container run inside VMs.
Distributed Autonomous Virtual Resource Management in Datacenters Using Finite-Markov Decision Process
To provide robust infrastructure as a service, clouds currently perform load balancing by migrating virtual machines VMs from heavily loaded physical machines PMs to lightly loaded PMs. Previous reactive load balancing algorithms migrate VMs upon the ...
Comments