Result Analysis of the Improved Contiguous Memory Allocation (ICMA) Approach in the Linux Kernel Research

doi:10.23940/ijpe.23.11.p6.753761

Int J Performability Eng ›› 2023, Vol. 19 ›› Issue (11): 753-761.doi: 10.23940/ijpe.23.11.p6.753761

Previous Articles Next Articles

Result Analysis of the Improved Contiguous Memory Allocation (ICMA) Approach in the Linux Kernel Research

Anmol Suryavanshi^* and Sanjeev Kumar Sharma

Department of Computer Science and Engineering, Oriental University, Indore, India

Contact: *E-mail address: eranmol89@gmail.com
About author:Anmol Suryavanshi is born in India on 1st July 1989. He had received his bachelor’s degree in Information Technology Engineering from KBC North Maharashtra University (NMUJ), Jalgaon, India in 2011. Later He had received his master’s degree from Rajiv Gandhi Technological University (RGPV), Bhopal, India in 2014. He is currently pursuing Ph.D. from Oriental University, Indore (OUI), India, since February 2020. He can be contacted at email: eranmol89@gmail.com.
Sanjeev Kumar Sharma is working as Professor (CSE) and Dean of Student Welfare in the Oriental Institute of Science and Technology, Bhopal and Adjunct faculty in the Oriental University, Indore. Apart from teaching, he is also associated with the activities of the Indian Army through the National Cadet Corps (NCC) to motivate and encourage the students to join the armed forces. He completed his Ph. D in computer science and engineering from Devi Ahilya University. He has more than 40 research papers in various national international journals and conferences. He is having 20 years of teaching experience and 12 years of experience in Research. He is also a member of various societies such as, AMIE, CSI, and ACM. He can be contacted at email: sanjeevsharma@oriental.ac.in.

Abstract

Abstract: The ICMA (Improved Contiguous Memory Allocation) approach represents a transformative rethinking of the traditional Contiguous Memory Allocation (CMA) method, aiming to optimize memory utilization, diminish allocation errors, reduce system overhead, and alleviate latency issues. It introduces a novel virtual memory remapping strategy that challenges conventional assumptions. ICMA adopts a deferred mapping approach, reserving mapping until explicitly required, necessitating a dedicated device driver for its operation. This research critically assesses ICMA's practical implications within the Linux Kernel, primarily focusing on memory allocation, overall system performance, and efficiency enhancements. The technical implementation details presented in this study underscore its effectiveness in addressing memory allocation failures and latency bottlenecks. Empirical testing on a Raspberry Pi 3 highlights the real-world applicability of ICMA. These findings contribute valuable insights into the potential benefits and challenges associated with ICMA, providing essential guidance for devising memory management strategies to significantly enhance system efficiency and performance.

Key words: improved contiguous memory allocation (ICMA), latency issues, 32-bit arm board, Raspberry Pi 3, allocation failures, remapping strategy, efficiency and performance

Anmol Suryavanshi and Sanjeev Kumar Sharma. Result Analysis of the Improved Contiguous Memory Allocation (ICMA) Approach in the Linux Kernel Research [J]. Int J Performability Eng, 2023, 19(11): 753-761.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

[1] Park S., Kim M., andYeom H.Y.GCMA: Guaranteed Contiguous Memory Allocator. IEEE Transactions on Computers, vol. 68, no. 3, pp. 390-401, 2018.
[2] Suryavanshi, A.S. and Sharma, S.An Approach Towards Improvement of Contiguous Memory Allocation Linux Kernel: A Review. Indonesian Journal of Electrical Engineering and Computer Science, vol. 25, pp. 1607, 2022.
[3] Stojkovic J., Mantri N., Skarlatos D., Xu T., andTorrellas J.Memory-Efficient Hashed Page Tables. In2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA), IEEE, pp. 1221-1235, 2023.
[4] Corbet J.,Five-Level Page Tables, https://lwn.net/Articles/717293/, accessed on December 1, 2023.
[5] Magenheimer D.,In-Kernel Memory Compression, http://lwn.net/Articles/545244/, accessed on December 1, 2023.
[6] Pazzaglia P., Casini D., Biondi A., andDi Natale, M. Optimal Memory Allocation and Scheduling for Dma Data Transfers under the Let Paradigm. In2021 58th ACM/IEEE Design Automation Conference (DAC), IEEE, pp. 1171-1176, 2021.
[7] Chatterjee A.Formulating Support for Superpages to Reduce the Number of TLB Faults in Contiguous Virtual Memory Space. In2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), IEEE, pp. 708-715, 2019.
[8] Zeng T. M.,The Android ION Memory Allocator, https://lwn.net/Articles/480055/, accessed on December 1, 2023.
[9] Raghuvanshi D.Memory Management in Operating System. International Journal of Trend in Scientific Research and Development, vol. 2, no. 5, pp. 2346-2347, 2018.
[10] Nazarewicz M.,Contiguous Memory Allocator, https://events.static.linuxfound.org/images/stories/pdf/lceu2012_nazarwicz.pdf, accessed on December 1, 2023.
[11] Park S.,Introduce Gcma, http://lwn.net/Articles/619865, accessed on December 1, 2023.
[12] Waltz, C.R. and Carr, M.A.Watershed Load Balancing Technique for Distributed Memory Parallelization of Fast Multipole Methods with Near-Field Preconditioning. In IEEE Antennas and Propagation Society Symposium, IEEE, vol. 2, pp. 1215-1218, 2004.
[13] Horsch J., Huber M., andWessel S.Transcrypt: Transparent Main Memory Encryption using a Minimal Arm Hypervisor. In2017 IEEE Trustcom/BigDataSE/ICESS, IEEE, pp. 152-161, 2017.
[14] Lameter C.,User Space Contiguous Memory Allocation for DMA, https://www.linuxplumbersconf.org/2017/ocw/proposals/4669, accessed on December 1, 2023.
[15] Ma Z., Tan Y., Jiang H., Yan Z., Liu D., Chen X., Zhuge Q., Sha E.H.M., and Wang, C. Unified-Tp: A Unified Tlb and Page Table Cache Structure for Efficient Address Translation. In2020 IEEE 38th International Conference on Computer Design (ICCD), IEEE, pp. 255-262, 2020.
[16] Katal A., Sethi V., Gupta A., andRastogi A.Dynamic Memory Manager: A Memory Usage Statistical Tool. In2022 2nd International Conference on Intelligent Technologies (CONIT), IEEE, pp. 1-5, 2022.
[17] Sha E.H.M., Jia, Y., Chen, X., Zhuge, Q., Jiang, W., and Qin, J. The Design and Implementation of an Efficient User-Space in-Memory File System. In2016 5th Non-Volatile Memory Systems and Applications Symposium (NVMSA), IEEE, pp. 1-6, 2016.
[18] Lin, M. and Chen, S.Flash-Aware Linux Swap System for Portable Consumer Electronics. IEEE Transactions on Consumer Electronics, vol. 58, no. 2, pp. 419-427, 2012.
[19] Shi, H. and Chen, L. from Spectrum Bonding to Contiguous-Resource Batching Task Scheduling. IEEE/ACM Transactions on Networking, vol. 30, no. 3, pp. 1245-1254, 2022.
[20] Gilmiyarov R., Galimzyanova L., andPorshnev S.The Concept of Allocating Access Rights to Virtual Memory Area in Linux-Based Operating Systems. In2021 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT), IEEE, pp. 0423-0426, 2021.
[21] Kayande, D. and Shrawankar, U.Performance Analysis for Improved RAM Utilization for Android Applications. In2012 CSI Sixth International Conference on Software Engineering (CONSEG), IEEE, pp. 1-6, 2012.
[22] Baruah T., Sun Y., Dinçer A.T., Mojumder S.A., Abellán J.L., Ukidave Y., Joshi A., Rubin N., Kim J., andKaeli D.Griffin: Hardware-Software Support for Efficient Page Migration in Multi-Gpu Systems. In2020 IEEE International Symposium on High Performance Computer Architecture (HPCA), IEEE, pp. 596-609, 2020.
[23] Chu, W.W. and Opderbeck, H.Performance of Replacement Algorithms with Different Page Sizes. Computer, vol. 7, no. 11
pp. 14-23, 1974.
[24] Jeong J., Kim H., andLee J.Transparently Exploiting Device-Reserved Memory for Application Performance in Mobile Systems. IEEE Transactions on Mobile Computing, vol. 15, no. 11, pp. 2878-2891, 2015.
[25] Liu, J.K. and Wang, S.D.CFFS: A Persistent Memory File System for Contiguous File Allocation with Fine-Grained Metadata. IEEE Access, vol. 10, pp. 91678-91698, 2022.
[26] Liu Y., Ma J., Zhang Z., Li L., Qi Z., andGuan H.Megatron: Software-Managed Device Tlb for Shared-Memory Fpga Virtualization. In2021 58th ACM/IEEE Design Automation Conference (DAC), IEEE, pp. 1213-1218, 2021.
[27] Karakostas V., Gandhi J., Ayar F., Cristal A., Hill M.D., McKinley, K.S., Nemirovsky, M., Swift, M.M., and Ünsal, O. Redundant Memory Mappings for Fast Access to Large Memories. ACM SIGARCH Computer Architecture News, vol. 43, no. 3S, pp. 66-78, 2015.
[28] Jingwei D., Zhuo W., Rui W., andXianwei S.Optimizing Software of Memory Management on ARM. In2012 Second International Conference on Instrumentation, Measurement, Computer, Communication and Control, IEEE, pp. 1390-1392, 2012.
[29] Böhnert, M. and Scholl, C.A Dynamic Virtual Memory Management under Real-Time Constraints. In2014 IEEE 20th International Conference on Embedded and Real-Time Computing Systems and Applications, IEEE, pp. 1-10, 2014.
[30] Page and Hagin. Improving the Performance of Buddy Systems. IEEE Transactions on Computers, vol. 100, no. 5, pp. 441-447, 1986.
[31] Min, R. and Hu, Y.Improving Performance of Large Physically Indexed Caches by Decoupling Memory Addresses from Cache Addresses. IEEE Transactions on Computers, vol. 50, no. 11, pp. 1191-1201, 2001.
[32] Suryavanshi, A.S. and Rastogi, N.Performance Evaluation of CMMBCR Method to Improve Battery Power Awareness in Ad Hoc Network. Performance Evaluation, vol. 3, no. 8, 2014.
[33] Fu H.C., Wang P.H., andYang C.L.Active Forwarding: Eliminate IOMMU Address Translation for Accelerator-Rich Architectures. InProceedings of the 55th Annual Design Automation Conference, pp. 1-6, 2018.
[34] Park C.H., Cha S., Kim B., Kwon Y., Black-Schaffer, D., and Huh, J. Perforated Page: Supporting Fragmented Memory Allocation for Large Pages. In2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA), IEEE, pp. 913-925, 2020.
[35] Pupykina, A. and Agosta, G.Survey of Memory Management Techniques for Hpc and Cloud Computing. IEEE Access, vol. 7
pp. 167351-167373, 2019.

Result Analysis of the Improved Contiguous Memory Allocation (ICMA) Approach in the Linux Kernel Research

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 0

Recommended 0