Abstract
This study is to provide a design of low-cost and high-availability data center infrastructure for small/medium-scale businesses. The basic concept is to establish an infrastructure consisting of primary and backup sides through the clustering technology. By default, the primary side is active and responsible for data switching while the backup side is standby for the failure of the primary side. The design achieves the features of 1) providing full-level high availability (HA) at network, server, application, and management levels, 2) controlling the routing among network-level clusters to solve the “PPPOE connection racing” and “winding path” problems, 3) monitoring and recovering the objects in each level with an economic and effective way, and 4) handling events resulting from changing of object states in an event center. Finally, the experiment results are exhibited with five testing scenarios for verification and elaboration of the effectiveness of the HA design. The system can recover the failed objects and solve the routing problems of PPPOE connection racing and winding path among HA clusters automatically.
Highlights
With the development of Information Technology (IT) in recent years, the concepts of Cloud [1, 2, 19]have been utilized in the data centers of enterprises
The proposed design for the data center infrastructure has the features of 1) providing full-level High Availability (HA) at network, server, application, and management levels, 2) controlling the routing among network-level clusters, 3) monitoring and recovering the objects in each level with an economic and effective way, and 4) handling events resulting from changing of object states in an event center
When using high availability heartbeat suite, the failover technology is achieved using “IP address takeover”; the active node of a cluster will have a virtual IP address to provide client-side services
Summary
With the development of Information Technology (IT) in recent years, the concepts of Cloud [1, 2, 19]. The proposed design for the data center infrastructure has the features of 1) providing full-level HA at network, server, application, and management levels, 2) controlling the routing among network-level clusters, 3) monitoring and recovering the objects in each level with an economic and effective way, and 4) handling events resulting from changing of object states in an event center. It can achieve a highavailability and low-cost infrastructure since the HA functions and monitor mechanisms are designed in these four levels as mentioned previously and implemented by free, open source software, such as Linux Virtual Server (LVS) [8], Vyatta Router and Firewall [9], and NMap Scanner [10]. The final section concludes the paper and describes the future work
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
