Shulou(Shulou.com)06/02 Report--

The construction of university data center can be said to be the top priority of intelligent campus construction. Today, with the vigorous development of digital business, with the increasing expansion of network scale and the increase of application services, university data centers are facing many problems. For example, a series of challenges, such as the rapid growth of data, low server utilization, complex system management, insufficient construction site of computer room, high cost of operation and maintenance, high energy consumption, low level of business security and so on. In the construction of traditional data center, various applications present a "shaft" architecture.

In the face of traditional application island data centers, the main manifestations are as follows:

Data center construction plan:

For colleges and universities, the basic platform of information system is virtualized and integrated from two aspects, namely storage virtualization and server virtualization, which lays a solid foundation for intelligent campus construction and cloud computing.

Design content:

1) integrate server resources and carry out unified management through server virtualization

2) make full use of the existing resources of the school and reduce the hardware investment

3) integrate decentralized applications in schools by using server virtualization

4) rapidly expand applications through virtual machine resource allocation

5) make use of virtualization technology to ensure business security

6) considering the needs of later business development, software and hardware can support smooth expansion.

Design principles:

Fully considering the actual situation of your school, and according to your school's business needs, functional requirements and investment needs, the design adheres to the construction principles of ensuring the use requirements, moderately controlling the scale, giving consideration to the long-term development and paying attention to the investment benefits. proceed from the needs of ensuring the business of the system, make full use of the existing resources of the system, and design the scheme with as little investment as possible to meet the needs related to business development.

The main design principles are as follows:

1) the principle of practicality and advancement

2) the principle of sustainable development

3) principle of openness

4) the principle of flexibility

5) principle of safety and reliability

6) the principle of high performance-price ratio

7) easy to manage and maintain

1. Server consolidation

1) multiple virtual machines can be run on one server, and each virtual machine is supported to install a different operating system.

2) the virtual server supports Windows, Linux and Unix series operating systems.

3) the server utilization can be increased to more than 80%.

two。 Centralized and unified management

1) use the unified console to centrally manage multi-server resources, and use the Bax S architecture.

2) build a resource pool for physical servers of local area network and heterogeneous CPU

3) dynamically create, delete, backup and manage virtual machines according to business needs

4) Rapid deployment of virtual business environment

5) shared storage management and rational allocation of resources

6) event log

7) alarm tracking

3. Virtual machine dynamic migration

1) physical server failure, the virtual machine can be migrated online to another server without service interruption to ensure business continuity

2) migrate virtual machines to servers with limited computing power during peak hours to ensure the quality of application service and dynamically balance the load of the data center.

3) maintenance and maintenance to migrate the virtual machine to another physical server to run.

4. Performance real-time monitoring and early warning

1) Real-time running status of real-time servers and virtual machines, and reasonable allocation of virtual machine resources

2) provide statistical analysis for the last 5 minutes, 1 hour, 1 week, 1 month, and 1 year.

3) by monitoring the data, when the CPU, memory and disk of the host and virtual machine reach the critical value, the administrator can be alerted in advance by means of e-mail and SMS, so as to provide a basis for realizing server load balancing in the resource pool.

5. Backup and recovery

1) remote virtual machines perform snapshots online

2) when the error report of the virtual server affects the normal operation of the business, it can recover quickly and avoid the business interruption caused by the system failure.

Reference case:

The data center of a university was faced with the problems of too many servers, low utilization and insufficient computer room space. After adopting the server virtualization solution:

1) realize server consolidation and reduce the number of services from 8 to 2

2) increase the resource utilization of the server from 8% to 40%

3) using the surplus server, HA is deployed, which provides fast backup and recovery, and improves the availability and reliability of the system.

4) better server monitoring and simplified server management

5) eliminate the old servers, reduce the space occupation of the computer room, reduce the energy consumption, and reduce the total cost of TCO.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.