Application of Proportional-Share with Punishment Principle for Resource-Sharing in Parallel Computing Applications

Year : 2026 | Volume : 13 | Issue : 01 | Page : 01 08
By

Manas Kumar Yogi,

  1. Assistant, Professor, Department of CSE, Pragati Engineering College (A), Surampalem, Andhra Pradesh, India

Abstract

Efficient resource-sharing is a cornerstone of high-performance parallel computing. While proportional-share scheduling has long been a foundational approach for distributing resources according to predefined weights, its effectiveness can be compromised by tasks that over-consume their allocated share, leading to system-wide performance degradation and unfairness. This review article investigates the application of the “proportional-share with punishment” (PSWP) principle, a hybrid scheduling paradigm designed to address this challenge. PSWP integrates the flexibility of proportional sharing with a robust penalty mechanism that dynamically corrects resource over-consumption, ensuring long-term fairness and stability. This article thoroughly synthesizes various recent scholarly works from 2020 to 2026 to provide a comprehensive overview of the PSWP principle, its theoretical underpinnings, and its practical implementations in parallel computing platforms, cloud platforms, and distributed systems. We explore the various forms of punishment mechanisms, their triggers, and their impact on system performance metrics like throughput, latency, and fairness. Furthermore, we examine the challenges associated with implementing PSWP, including the overhead of monitoring and the potential for unintended consequences.

Keywords: Big data, cluster, distributed, high performance computing, resource

[This article belongs to Recent Trends in Parallel Computing ]

How to cite this article: Manas Kumar Yogi. Application of Proportional-Share with Punishment Principle for Resource-Sharing in Parallel Computing Applications. Recent Trends in Parallel Computing. 2026; 13(01):01-08.
How to cite this URL: Manas Kumar Yogi. Application of Proportional-Share with Punishment Principle for Resource-Sharing in Parallel Computing Applications. Recent Trends in Parallel Computing. 2026; 13(01):01-08. Available from: https://journals.stmjournals.com/rtpc/article=2026/view=237661

References

  1. Waldspurger CA, Weihl WE. Lottery scheduling: flexible proportional-share resource management. First Symposium on Operating Systems Design and Implementation (OSDI ’94), Monterey, CA, USA. 1994. Monterey, CA. Berkeley (CA): USENIX Association; 1994. p. 1–11. Available from: https://www.usenix.org/conference/osdi-94/lottery-scheduling-flexible-proporti–onal-share-resource-management
  2. Saewong S, Rajkumar RR, Lehoczky JP, Klein MH. Analysis of hierarchical fixed-priority scheduling. Proceedings of the 14th Euromicro Conference on Real-Time Systems (ECRTS 2002), Vienna, Austria. 2002. p. 152–160. doi:10.1109/EMRTS.2002.1019197.
  3. Parekh AK, Gallager RG. A generalized processor sharing approach to flow control in integrated services networks: the single-node case. IEEE/ACM Trans Netw. 1993;1(3):344–357. doi:10.1109/90.234856.
  4. Fehr E, Gächter S. Altruistic punishment in humans. 2002;415(6868):137–140. doi:10.1038/415137a. PMID: 11805825.
  5. Brown Coverdale H. Putting proportional punishment into perspective. Crim Law Philos. 2025;19(2):181–201. doi:10.1007/s11572-024-09736-5.
  6. Sheng Y, Cao S, Li D, Zhu B, Li Z, Zhuo D, et al. Fairness in serving large language models. In: Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24); 2024. Santa Clara, CA. Berkeley (CA): USENIX Association; 2024. p. 965–988.
  7. Chandra A, Adler M, Shenoy P. Deadline fair scheduling: bridging the theory and practice of proportionate fair scheduling in multiprocessor systems. Proceedings Seventh IEEE Real-Time Technology and Applications Symposium, Taipei, Taiwan. 2001. p. 3–14. doi:10.1109/RTTAS.
    929861.
  8. Vuppalapati M, Fikioris G, Agarwal R, Cidon A, Khandelwal A, Tardos É. Karma: resource allocation for dynamic demands. Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23); 2023. Boston, MA. Berkeley (CA): USENIX Association; 2023. p. 645–662.
  9. Tang S, Chai Q, Yu C, Li Y, Sun C. Balancing fairness and efficiency for cache sharing in semi-external memory system. 49th International Conference on Parallel Processing (ICPP ’20), Edmonton, AB, Canada. 2020 Aug 17–20. Article 13. doi:10.1145/3404397.3404450.
  10. Windrich I, Kierspel S, Neumann T, Berger R, Vogt B. Enforcement of fairness norms by punishment: a comparison of gains and losses. Behav Sci (Basel). 2024;14(1):39. doi:10.3390/bs14010039. PMID: 38247691.
  11. Ohdaira T. The probabilistic pool punishment proportional to the difference of payoff outperforms previous pool and peer punishment. Sci Rep. 2022;12(1):6604. doi:10.1038/s41598-022-10582-5. PMID: 35459880.
  12. Shreedhar G, Tavoni A, Marchiori C. Monitoring and punishment networks in an experimental common pool resource dilemma. Environ Dev Econ. 2020;25(1):66–94. doi:10.1017/S1355770X1
  13. Blanco E, Struwe N, Walker JM. Experimental evidence on sharing rules and additionality in transfer payments. J Econ Behav Organ. 2021;188:1221–1247. doi:10.1016/j.jebo.2021.06.012.
  14. Patel Y, Yang L, Arulraj L, Arpaci-Dusseau AC, Arpaci-Dusseau RH, Swift MM. Avoiding scheduler subversion using scheduler-cooperative locks. Proceedings of the Fifteenth European Conference on Computer Systems (EuroSys); 2020 Apr 15–18; Heraklion, Greece. 2020. p. 1–17. doi:10.1145/3342195.3387521.
  15. Li J, Liu Y, Wang Z, Xia H. Egoistic punishment outcompetes altruistic punishment in the spatial public goods game. Sci Rep. 2021;11(1):6584. doi:10.1038/s41598-021-85814-1. PMID: 33753774.
  16. Obaidat MS, Boudriga NA. Fundamentals of performance evaluation of computer and telecom–unication systems. Hoboken (NJ): John Wiley & Sons; 2010. doi:10.1002/9780470567203.
  17. Zahedi SM, Fan S, Lee BC. Managing heterogeneous datacenters with tokens. ACM Trans Archit Code Optim. 2018;15(2):1–23. doi:10.1145/3191821.
  18. Cho H, Ravindran B, Jensen ED. An optimal real-time scheduling algorithm for multiprocessors. 27th IEEE International Real-Time Systems Symposium (RTSS 2006), Rio de Janeiro, Brazil. 2006. p. 101–110. doi:10.1109/RTSS.2006.10.
  19. Badia RM, Pierson JM, Morin C, Kortas S, Parlavantzas N. Market-based autonomous resource and application management in the cloud [dissertation]. Argonne (IL): Argonne National Laboratory; 2014.
  20. Ziv T, Whiteman JD, Sommerville JA. Toddlers’ interventions toward fair and unfair individuals. Cognition. 2021;214:104781. doi:10.1016/j.cognition.2021.104781. PMID: 34051419.
Regular Issue Subscription Review Article
Volume 13
Issue 01
Received 16/01/2026
Accepted 21/01/2026
Published 26/02/2026
Publication Time 41 Days

Login

My IP

PlumX Metrics