How to Bid the Cloud

Amazon's Elastic Compute Cloud (EC2) uses auction-based spot pricing to sell spare capacity, allowing users to bid for cloud resources at a highly reduced rate. Amazon sets the spot price dynamically and accepts user bids above this price. Jobs with lower bids (including those already running) are interrupted and must wait for a lower spot price before resuming. Spot pricing thus raises two basic questions: how might the provider set the price, and what prices should users bid? Computing users' bidding strategies is particularly challenging: higher bid prices reduce the probability of, and thus extra time to recover from, interruptions, but may increase users' cost. We address these questions in three steps: (1) modeling the cloud provider's setting of the spot price and matching the model to historically offered prices, (2) deriving optimal bidding strategies for different job requirements and interruption overheads, and (3) adapting these strategies to MapReduce jobs with master and slave nodes having different interruption overheads. We run our strategies on EC2 for a variety of job sizes and instance types, showing that spot pricing reduces user cost by 90% with a modest increase in completion time compared to on-demand pricing.

[1]  S. David Wu,et al.  On combinatorial auction and Lagrangean relaxation for distributed resource scheduling , 1999 .

[2]  Jeffrey K. MacKie-Mason,et al.  Pricing the Internet , 1995 .

[3]  Marco Ajmone Marsan,et al.  Bounds on average delays and queue size averages and variances in input-queued cell-based switches , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).

[4]  Avrim Blum,et al.  Online algorithms for market clearing , 2002, SODA '02.

[5]  Margo I. Seltzer,et al.  Virtual worlds: fast and strategyproof auctions for dynamic resource allocation , 2003, EC '03.

[6]  Eric J. Friedman,et al.  Pricing WiFi at Starbucks: issues in online mechanism design , 2003, EC '03.

[7]  Michael P. Wellman,et al.  Exploring bidding strategies for market-based scheduling , 2003, EC '03.

[8]  Ryan Porter,et al.  Mechanism design for online real-time scheduling , 2004, EC '04.

[9]  Noam Nisan,et al.  Online ascending auctions for gradually expiring items , 2005, SODA '05.

[10]  Albert-László Barabási,et al.  The origin of bursts and heavy tails in human dynamics , 2005, Nature.

[11]  D. Parkes,et al.  A Decentralized Auction Framework to Promote Efficient Resource Allocation in Open Computational Grids , 2007 .

[12]  Mingyan Liu,et al.  Revenue generation for truthful spectrum auction in dynamic spectrum access , 2009, MobiHoc '09.

[13]  Roch Guérin,et al.  Modeling the Dynamics of Network Technology Adoption and the Role of Converters , 2010, IEEE/ACM Transactions on Networking.

[14]  Fei Teng,et al.  A New Game Theoretical Resource Allocation Algorithm for Cloud Computing , 2010, GPC.

[15]  Jan Broeckhove,et al.  Cost-Optimal Scheduling in Hybrid IaaS Clouds for Deadline Constrained Workloads , 2010, 2010 IEEE 3rd International Conference on Cloud Computing.

[16]  Randy H. Katz,et al.  A view of cloud computing , 2010, CACM.

[17]  Muli Ben-Yehuda,et al.  Deconstructing Amazon EC2 Spot Instance Pricing , 2011, 2011 IEEE Third International Conference on Cloud Computing Technology and Science.

[18]  Quanyan Zhu,et al.  Dynamic Resource Allocation for Spot Markets in Cloud Computing Environments , 2011, 2011 Fourth IEEE International Conference on Utility and Cloud Computing.

[19]  Navendu Jain,et al.  Managing cost, performance, and reliability tradeoffs for energy-aware server provisioning , 2011, 2011 Proceedings IEEE INFOCOM.

[20]  Asuman E. Ozdaglar,et al.  Socially optimal pricing of cloud computing resources , 2011, VALUETOOLS.

[21]  Rajkumar Buyya,et al.  Statistical Modeling of Spot Instance Prices in Public Cloud Environments , 2011, 2011 Fourth IEEE International Conference on Utility and Cloud Computing.

[22]  Benjamin Hindman,et al.  Dominant Resource Fairness: Fair Allocation of Multiple Resource Types , 2011, NSDI.

[23]  Barbara Panicucci,et al.  A game theoretic formulation of the service provisioning problem in cloud systems , 2011, WWW.

[24]  Randy H. Katz,et al.  Heterogeneity-Aware Resource Allocation and Scheduling in the Cloud , 2011, HotCloud.

[25]  Artur Andrzejak,et al.  Monetary Cost-Aware Checkpointing and Migration on Amazon Cloud Spot Instances , 2012, IEEE Transactions on Services Computing.

[26]  Kui Ren,et al.  When cloud meets eBay: Towards effective pricing for cloud computing , 2012, 2012 Proceedings IEEE INFOCOM.

[27]  Rajkumar Buyya,et al.  Revenue Maximization Using Adaptive Resource Provisioning in Cloud Computing Environments , 2012, 2012 ACM/IEEE 13th International Conference on Grid Computing.

[28]  Xi Fang,et al.  3. Full Four-channel 6.3-gb/s 60-ghz Cmos Transceiver with Low-power Analog and Digital Baseband Circuitry 7. Smart Grid — the New and Improved Power Grid: a Survey , 2022 .

[29]  Dan Suciu,et al.  How to Price Shared Optimizations in the Cloud , 2012, Proc. VLDB Endow..

[30]  Joseph Naor,et al.  Near-optimal scheduling mechanisms for deadline-sensitive jobs in large computing clusters , 2012, SPAA '12.

[31]  Sangtae Ha,et al.  TUBE: time-dependent pricing for mobile data , 2012, SIGCOMM '12.

[32]  Lakshmi Sobhana Kalli,et al.  Market-Oriented Cloud Computing : Vision , Hype , and Reality for Delivering IT Services as Computing , 2013 .

[33]  Xue Liu,et al.  Present or Future: Optimal Pricing for Spot Instances , 2013, 2013 IEEE 33rd International Conference on Distributed Computing Systems.

[34]  Shaolei Ren,et al.  Entry and Spectrum Sharing Scheme Selection in Femtocell Communications Markets , 2013, IEEE/ACM Transactions on Networking.

[35]  David Wentzlaff,et al.  The sharing architecture: sub-core configurability for IaaS clouds , 2014, ASPLOS.

[36]  Adam Wierman,et al.  On competitive provisioning of cloud services , 2014, PERV.

[37]  WentzlaffDavid,et al.  The sharing architecture , 2014 .

[38]  Ulrich Lampe,et al.  Pricing in Infrastructure Clouds - An Analytical and Empirical Examination , 2014, AMCIS.

[39]  Rajkumar Buyya,et al.  Fault-tolerant Workflow Scheduling using Spot Instances on Clouds , 2014, ICCS.

[40]  Christos Faloutsos,et al.  Beyond Poisson: Modeling Inter-Arrival Time of Requests in a Datacenter , 2014, PAKDD.

[41]  George Kesidis,et al.  Pricing of service in clouds: optimal response and strategic interactions , 2014, PERV.

[42]  Zongpeng Li,et al.  Dynamic resource provisioning in cloud computing: A randomized auction approach , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[43]  Antony I. T. Rowstron,et al.  Decentralized task-aware scheduling for data center networks , 2014, SIGCOMM.

[44]  Muli Ben-Yehuda,et al.  Ginseng: market-driven memory allocation , 2014, VEE '14.

[45]  Hai Jin,et al.  Towards Optimized Fine-Grained Pricing of IaaS Cloud Platform , 2015, IEEE Transactions on Cloud Computing.