关于Ceph优化企业云后端存储方案的研究

解辰辉; 刘承亮; 曲左阳

关于Ceph优化企业云后端存储方案的研究

中国铁道科学研究院集团有限公司电子计算技术研究所, 北京 100081

基金项目:

中国铁道科学研究院集团公司科研开发基金项目（1751DZ0305）

详细信息

作者简介:
解辰辉,工程师;刘承亮,高级工程师。

中图分类号: U29;TP39
出版历程
- 收稿日期: 2018-05-30
- 刊出日期: 2020-08-04

Optimizing enterprise cloud backend storage scheme based on Ceph

Institute of Computing Technologies, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China

摘要

摘要: 以Ceph为基础为企业构建数据私密程度较高的企业云分布式存储系统，同时支持对象存储，块存储和文件存储。研究一种在实际环境中可以使用的混合存储方案。通过尝试社区版本的Ceph与基于OpenStack的企业云进行融合，发现其在应用过程中存在诸多问题。因此，根据企业云自身的业务特点，优化Ceph对于企业云后端存储的支持，在Ceph原有的框架基础上，增加部分扩展，使得原生Ceph更加适合企业的生产环境。
- 企业云 /
- 后端存储 /
- OpenStack /
- Ceph
Abstract: Based on Ceph, a distributed enterprise cloud storage system with high degree of data privacy was built forenterprises. The system also supported object storage, block storage and file storage. This article studied a hybrid storagescheme that could be used in real environment. There were many problems in the application process by trying to integrate thecommunity version of Ceph with the enterprise cloud based on OpenStack. Therefore, according to the business characteristicsof enterprise cloud, the article optimized the Ceph support for enterprise cloud backend storage, and added some expansionbased on the original framework of Ceph, made native Ceph more suitable for enterprise production environment.
- enterprise cloud /
- backend storage /
- OpenStack /
- Ceph

HTML全文

参考文献(12)

[1]	熊振华.基于OPENSTACK云存储技术的研究[D].长春:吉林大学, 2014.
[2]	唐国纯,罗自强.云计算体系结构中的多层次研究[J].铁路计算机应用, 2012, 21(11):4-7.
[3]	Weil SA, Brandt SA, Miller EL, et al. CRUSH:Controlled,Scalable, Decentralized Placement of Replicated Data[C]//SC'06:Proceedings of the 2006 ACM/IEEE Conference onSupercomputing, Tampa, FL, USA, 2006:31.
[4]	Weil SA, Leung AW, Brandt SA, et al. RADOS:a scalable,reliable storage service for petabyte-scale storage clusters[C]//International Petascale Data Storage Workshop. DBLP, 2007:35-44.
[5]	Weil S A, Brandt S A, Miller E L, et al. Ceph:a scalable, highperformance distributed file system[C]//Symposium onOperating Systems Design and Implementation. USENIXAssociation, Seattle, WA, USA, 2006:307-320.
[6]	Johanes J, Johari MF, Khalid M, et al. Comparison of VariousVirtual Machine Disk Images Performance on GlusterFS andCeph Rados Block Devices[C]//International Conference onInformatics Applications, 2014.
[7]	Azagury A, Dreizin V, Factor M, et al. Towards an ObjectStore[C]//MASS Storage Systems and Technologies. IEEE,2003:165-176.
[8]	Wei Kong, et al. Multi-level image software assembly technology based on OpenStack and Ceph[A]. IEEE BeijingSection、Global Union Academy of Science and Technology,Chongqing Global Union Academy of Science and Technology.Proceedings of 2016 IEEE Information Technology,Networking,Electronic and Automation Control Conference (ITNEC 2016)[C]//IEEE Beijing Section, Global Union Academy of Scienceand Technology, Chongqing Global Union Academy of Scienceand Technology, 2016:4.
[9]	Gudu D, Hardt M, Streit A, et al. Evaluating the performanceand scalability of the Ceph distributed storage system[C]//Big Data (Big Data), 2014 IEEE International Conference,Washington, DC, USA,2014:177-182.
[10]	赵铁柱.分布式文件系统性能建模及应用研究[D].广州:华南理工大学, 2011.
[11]	李翔. Ceph分布式文件系统的研究及性能测试[D].西安:西安电子科技大学, 2014.
[12]	王斌. Ceph存储在铁路站车Wi-Fi运营服务系统中的应用[C]//中国智能交通协会.第十一届中国智能交通年会优秀论文集.北京:电子工业出版社, 2016.