Abstract
We study the problem of allocating multiple types of resources to agents with Leontief preferences. The classic Dominant Resource Fairness (DRF) mechanism satisfies several desired fairness and incentive properties, but is known to have poor performance in terms of social welfare approximation ratio. In this work, we propose a new approximation ratio measure, called fair-ratio, which is defined as the worst-case ratio between the optimal social welfare (resp. utilization) among all fair allocations and that by the mechanism, allowing us to break the lower bound barrier under the classic approximation ratio. We then generalize DRF and present several new mechanisms with two and multiple types of resources that satisfy the same set of properties as DRF but with better social welfare and utilization guarantees under the new benchmark. We also demonstrate the effectiveness of these mechanisms through experiments on both synthetic and real-world datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bei, X., Li, Z., Luo, J.: Fair and efficient multi-resource allocation for cloud computing. CoRR abs/2210.05237 (2022). https://arxiv.org/abs/2210.05237
Bonald, T., Roberts, J.: Enhanced cluster computing performance through proportional fairness. Perform. Eval. 79, 134–145 (2014)
Bonald, T., Roberts, J.: Multi-resource fairness: objectives, algorithms and performance. In: Proceedings of the 2015 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, pp. 31–42 (2015)
Dolev, D., Feitelson, D.G., Halpern, J.Y., Kupferman, R., Linial, N.: No justified complaints: on fair sharing of multiple resources. In: Innovations in Theoretical Computer Science 2012, pp. 68–75 (2012)
Friedman, E., Ghodsi, A., Psomas, C.A.: Strategyproof allocation of discrete jobs on multiple machines. In: Proceedings of the 15th ACM Conference on Economics and Computation (EC), pp. 529–546 (2014)
Friedman, E.J., Ghodsi, A., Shenker, S., Stoica, I.: Strategyproofness, leontief economies and the Kalai-Smorodinsky solution (2011)
Ghodsi, A., Zaharia, M., Hindman, B., Konwinski, A., Shenker, S., Stoica, I.: Dominant resource fairness: fair allocation of multiple resource types. In: Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation (NSDI), pp. 323–336 (2011)
Grandl, R., Ananthanarayanan, G., Kandula, S., Rao, S., Akella, A.: Multi-resource packing for cluster schedulers. ACM SIGCOMM Comput. Commun. Rev. 44(4), 455–466 (2014)
Gutman, A., Nisarr, N.: Fair allocation without trade. In: Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 816–823 (2012)
Jiang, S., Wu, J.: Multi-resource allocation in cloud data centers: a trade-off on fairness and efficiency. Concurr. Comput. Pract. Exp. 33(6), e6061 (2021)
Jin, Y., Hayashi, M.: Efficiency comparison between proportional fairness and dominant resource fairness with two different type resources. In: 2016 Annual Conference on Information Science and Systems (CISS), pp. 643–648 (2016)
Jin, Y., Hayashi, M.: Trade-off between fairness and efficiency in dominant alpha-fairness family. In: INFOCOM 2018 - IEEE Conference on Computer Communications Workshops, pp. 391–396 (2018)
Joe-Wong, C., Sen, S., Lan, T., Chiang, M.: Multiresource allocation: fairness-efficiency tradeoffs in a unifying framework. IEEE/ACM Trans. Network. 21(6), 1785–1798 (2013)
Kash, I., Procaccia, A.D., Shah, N.: No agent left behind: dynamic fair division of multiple resources. J. Artif. Intell. Res. 51, 579–603 (2014)
Li, J., Xue, J.: Egalitarian division under leontief preferences. Econ. Theor. 54(3), 597–622 (2013)
Li, W., Liu, X., Zhang, X., Zhang, X.: Multi-resource fair allocation with bounded number of tasks in cloud computing systems. In: National Conference of Theoretical Computer Science (NCTCS), pp. 3–17 (2017)
Narayana, S., Kash, I.A.: Fair and efficient allocations with limited demands. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI), vol. 35, pp. 5620–5627 (2021)
Nicoló, A.: Efficiency and truthfulness with leontief preferences. A note on two-agent, two-good economies. Rev. Econ. Des. 8(4), 373–382 (2004)
Parkes, D.C., Procaccia, A.D., Shah, N.: Beyond dominant resource fairness: extensions, limitations, and indivisibilities. ACM Trans. Econ. Comput. (TEAC) 3(1), 1–22 (2015)
Reiss, C., Wilkes, J., Hellerstein, J.L.: Google cluster-usage traces: format + schema. In: White Paper, pp. 1–14. Google Inc. (2011)
Tahir, Y., Yang, S., Koliousis, A., McCann, J.: UDRF: multi-resource fairness for complex jobs with placement constraints. In: 2015 IEEE Global Communications Conference (GLOBECOM), pp. 1–7 (2015)
Tang, S., He, B., Zhang, S., Niu, Z.: Elastic multi-resource fairness: balancing fairness and efficiency in coupled CPU-GPU architectures. In: SC 2016: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 875–886 (2016)
Tang, S., Yu, C., Li, Y.: Fairness-efficiency scheduling for cloud computing with soft fairness guarantees. IEEE Trans. Cloud Comput. 1–1 (2020)
Wang, W., Li, B., Liang, B.: Dominant resource fairness in cloud computing systems with heterogeneous servers. In: IEEE INFOCOM 2014-IEEE Conference on Computer Communications, pp. 583–591 (2014)
Wang, W., Li, B., Liang, B., Li, J.: Multi-resource fair sharing for datacenter jobs with placement constraints. In: SC 2016: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1003–1014 (2016)
Acknowledgements
This work was supported by the Ministry of Education, Singapore, under its Academic Research Fund Tier 1 (RG23/20).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bei, X., Li, Z., Luo, J. (2022). Fair and Efficient Multi-resource Allocation for Cloud Computing. In: Hansen, K.A., Liu, T.X., Malekian, A. (eds) Web and Internet Economics. WINE 2022. Lecture Notes in Computer Science, vol 13778. Springer, Cham. https://doi.org/10.1007/978-3-031-22832-2_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-22832-2_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22831-5
Online ISBN: 978-3-031-22832-2
eBook Packages: Computer ScienceComputer Science (R0)