Efficient I/O intensive multi tenant SaaS system using L4 level cache
The Internet through Web services is providing innovative ways of business and flexible computing paradigm. SaaS (Software as a Service) is an emerging new model for software as a service. The number of SaaS services are available in the market such as Twitter, Gmail, Saleforce.com and Google Maps to configure SaaS based Web service system. But, there are several issues to achieve these requirements, Scalable, Configurable, Multi-Tenant- Efficient SaaS model. To meet these requirements, SaaS infrastructure is required to have scale out architecture with data interoperable function without any data contamination. It also needs short latency of time service because Web service is online and follows the remote client-server model. If service response time does not meet them timeliness requirements, users would not be use SaaS application services again. This paper proposes autonomous system architecture for the scalable SaaS infrastructure to meet timeliness and multi- tenant access for SaaS applications. The paper proposes concept and architecture of of L4 cache block level cache for specific data and content and copes with the above issues efficiently. The paper carried out the evaluation of the proposed system architecture and also evaluated VMM environment as well.
L4 cache Timeliness Write back cache Block IO device Locality of reference IOPS Bonnie Bench mark program VMM
Hironao Takahashi Kinji Mori Hafiz Farooq Ahmad
Department of Computer Science,Tokyo Institute of TechnologyTokyo, Japan School of Electrical Engineering and Computer Science National University of Sciences and Technology
国际会议
南京
英文
222-228
2010-06-04（万方平台首次上网日期，不代表论文的发表时间）