(1) position (the location of the physical position and the position of the IT personnel)
Data center migration, like in the real estate market, the location of the site is always the most important. For IDC providers, location means the resources and location that the area can provide, which has great influence on the security and good availability of data center assets. We should take into account the availability of local climate (flood, extreme temperature fluctuations, storm frequency and intensity), earthquake history and critical infrastructure (such as lines, roads and airports). For industries that must strictly abide by regulations (such as financial industry), it may prohibit the provision of data storage services to customers in international or even national boundaries.
The same principle applies to supporting employees. Whether or not to retain your own employees or to allow IDC providers to provide staff maintenance, you need to understand the IDC staff arrangements. Although some IDC tenants can still retain the site of the IT staff, other tenants are completely as part of the outsourcing contract, before taking the next step, to develop a detection procedure according to their scorecard, aims to reduce as much as possible the potential suppliers, this is a fair proposal for lease IDC the customer of space.
(2) the operation of the cooling system
The cooling system in the IDC space is essential after a fixed source of power is obtained. The efficiency of power supply (PUE) is crucial in optimizing the cost and efficiency of cooling. PUE can show how much the cost is related to the rack delivery. Ideally, the tenant only multiplies the power (measurement) by the PUE coefficient to indicate the extra power required for cooling. Look for the use of mixed cooling technology (for example, using natural cooling) IDC to ensure the redundancy of the refrigeration system.
(3) having DCIM software
Although DCIM software has become a standard for managing data centers, not all IDC providers can provide complete technical support. Because data centers have always had a lot of dedicated devices, and these devices have a lot of complex technology, and the management of these technologies can be a problem. Normally, devices have management software, but individual software systems may not be compatible or integrated. This will lead to chaos in the data center. So make sure that the IDC provider has DCIM software. Do you know if all the systems in the data center are interconnected? Are all the sensors connected to the software and monitored by these software? Can they dynamically generate dashboards and reports and move quickly to the site, cabinet, and rack level? Do they have end - to - end asset management capabilities? Have they been integrated into other ITSM systems (IT service management systems) so that you can take advantage of the most needed functionality?
(4) physical safety
Without a tight security guarantee for financial assets, any bank would not want to operate properly. The same is true of the data center assets, which may contain only the most valuable assets outside of human capital. For a really safe facility, please insist on the internal security team. When analyzing security mode, we must evaluate internal security personnel, layered security area, camera and security system. These systems can be covered by 360 degrees, and have advanced security authentication, such as PCI DSS 2, SSAE 16 and ISO 27002..
(5) power supply
Electricity is not only a broad problem, but also a narrow problem. At the macro level, the stability and redundancy of the infrastructure of the regional power grid should be considered. Look for the distance and location of power stations, substations, cables to data centers, and the consideration of the redundancy of the entire distribution system. Ensure that there is no power limit for the operation of the IDC area. It sounds a bit far away, but if you have gone through a sluice limit or an electric rush or seasonal supply, you don't think so. Don't forget to understand the recent local power interruption and maintenance records so as to make a corresponding emergency plan.
At the micro level, it is necessary to consider the power monitoring in the IDC space. Can they accurately quantify the measurement power, whether they increase or decrease the flexibility of power consumption over time, so as to understand the current situation of power utilization? Do they have the means to detect, monitor, and mitigate the surge of electricity and other anomalies? What are their backup and disaster recovery plans when power interruptions occur in a hosting facility that is not related to external power? All of this needs to be carefully considered.
Similarly, balance the work load, continuity and disaster recovery for sustainability is crucial, the data must be the amount of bandwidth and hosting providers to provide mobile distance can mean the difference between managed deployment of great user experience and failure, their workflow management system or whether they are good, some data can help to determine the delivery priority and infrastructure components. In addition, it will help to determine which needs higher runtime requirements and lower priority applications. In bottleneck or emergency situations, you will be able to access the most important information first.
留言列表