Design of a distributed storage architecture based on Ceph RADOS Block Device for virtualization and institutional private cloud
Article Sidebar
Main Article Content
Abstract
The increase in university technological services led to the proposal of a storage solution capable of supporting virtualization environments and private cloud services with greater stability, controlled growth, and unified administration. For this purpose, an architecture based on Ceph and oriented toward block storage was designed, considering the operational needs of an institutional data center.
The methodology consisted of reviewing technical requirements, calculating available capacity, defining the physical and logical organization of the cluster, and analyzing its connection with virtualization platforms. Servers, high-performance storage drives, separate networks for access traffic and internal operations, replication mechanisms, data distribution, permission control, and criteria for maintaining margin in the face of failures or expansion were considered.
As a result, a proposal consisting of seven storage nodes was obtained, with a distribution that made it possible to improve failure tolerance, organize resource usage, and separate responsibilities by platform. Aspects that needed to be addressed before full operation were also identified, such as continuous monitoring, credential protection, growth policies, and the review of recovery scenarios. It was concluded that the proposed architecture offered a viable technical foundation for strengthening institutional virtualization and private cloud services, as long as its adoption was accompanied by documentation, operational follow-up, and adjustments derived from the real behavior of the environment.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Este trabajo tiene la licencia CC BY-NC-ND 4.0
References
Bocchi, E., Lekshmanan, A., Valverde, R., & Goggin, Z. (2024). Enabling storage business continuity and disaster recovery with Ceph distributed storage. EPJ Web of Conferences, 295, 01021. https://doi.org/10.1051/epjconf/202429501021 DOI: https://doi.org/10.1051/epjconf/202429501021
Ceph Foundation. (s. f.). Ceph Block Device. Ceph Documentation. https://docs.ceph.com/en/squid/rbd/
Goggin, Z., Lekshmanan, A., Valverde, R., & Bocchi, E. (2025). Ceph at CERN in the multi-datacentre era. EPJ Web of Conferences, 337, 01331. https://doi.org/10.1051/epjconf/202533701331 DOI: https://doi.org/10.1051/epjconf/202533701331
Higuera-Balderrama, D., Morejón-López, D., Canosa-Reyes, R. M., Alonso-Labrada, R., & Marín-Hernández, F. (2023). Diseño e implementación de una red de almacenamiento distribuido basada en CEPH. Pädi Boletín Científico de Ciencias Básicas e Ingenierías del ICBI, 11(Especial 2), 55–60. https://doi.org/10.29057/icbi.v11iEspecial2.10839 DOI: https://doi.org/10.29057/icbi.v11iEspecial2.10839
Jelten, J., Wollek, A., Frank, D., & Lasser, T. (2023). Equilibrium: Optimization of Ceph cluster storage by size-aware shard balancing. arXiv. https://doi.org/10.48550/arXiv.2310.15805
Lee, D.-Y., Jeong, K., Han, S.-H., Kim, J.-S., Hwang, J.-Y., & Cho, S. (2017). Understanding write behaviors of storage backends in Ceph object store. MSST 2017. https://msstconference.org/MSST-history/2017/Papers/CephObjectStore.pdf
Miao, Y., Fan, Z., Zhang, M., & Yang, L. (2024). A data balanced distribution algorithm based on Ceph storage. Microelectronics & Computer, 41(3), 90–97. https://doi.org/10.19304/J.ISSN1000-7180.2023.0180
Zhao, L., Hu, G., & Xu, Y. (2024). Educational resource private cloud platform based on OpenStack. Computers, 13(9), 241. https://doi.org/10.3390/computers13090241 DOI: https://doi.org/10.3390/computers13090241