For this Spring Festival when the new crown virus epidemic occurred, the passing can be described as "sad reminders". But we can also see that the government’s timely policy management and guidance, the operation of a strong emergency guarantee mechanism, and the united efforts of the people from all walks of life have effectively controlled the epidemic, and the situation is slowly improving. I believe it will soon be warmer. bloom.
In these days of staying at home, I pay attention to the emergency support work of the People’s Liberation Army military medical support, the establishment of emergency hospitals, and the transportation of materials on the news every day. Although these tasks are urgent, they are tightly organized and not panic. The government's daily scientific management and emergency protection mechanism. As an ordinary practitioner in the IT industry, I wonder whether our IT infrastructure, such as data centers, can also use scientific daily management to encourage us to perform operations and maintenance more efficiently?
With the acceleration of the informatization process, people's work and life are almost completely dependent on data. The data center is responsible for the calculation and operation of various data (such as the calculation and analysis of data related to the new coronavirus), and the important role played by it does not need to be repeated. . Let's take a look at the current status of daily operation and maintenance management of data centers: To maintain normal and stable operation of data centers, a large number of professional and technical personnel are required to perform 24-hour uninterrupted maintenance on duty. Let's take a look at the daily operation and maintenance management. Three aspects of work: daily inspection work , not only to check the environment of the computer room (fire protection, electricity, temperature and humidity, monitoring, etc.), but also to check the operating efficiency of equipment and network; daily application changes , the business carried by the data center will not be Invariably, with the diversification and adjustment of business, it is necessary to make some corresponding changes to the server and network; software and hardware upgrades , data center equipment has a responsive operating cycle (mostly five years), hardware equipment Elimination and upgrading require synchronous software upgrades, hardware and software equipment failures and defects, etc., but also timely replacement and upgrades; for sudden failures , no data center dares to say that it will not fail, but There are various problems such as big and small, which requires our high-level operation and maintenance personnel to use scientific daily management and guarantee mechanisms to quickly find faults and solve problems.
The daily operation and maintenance work of the data center mentioned above may be very tedious and boring. Basic system and method protection are indispensable. The benevolent sees the benevolent and the wise sees the wisdom. Each has its own processes and methods, but we Looking at some of the equipment itself (electricity and fire warning) and software provided by equipment manufacturers (such as network management software, security protection software), the equipment will not directly talk and communicate with us, and it is difficult to tell us the problem in the first time. , This also requires us to arrange a large number of personnel at various points for on-duty operation and maintenance, and puts forward higher requirements on the level and sense of responsibility of our operation and maintenance personnel.
Have we considered whether there is a way to make these devices that are usually invisible, intangible, and unable to communicate without being in front of you, become visualized, so that daily inspections, changes, upgrades, and troubleshooting are all under control How about? Some people say that this is a beautiful idea and vision, but the progress of science and technology often tells us that we can only imagine that we can’t do it. Let me talk about the domestic advanced Nvidia visual integrated wiring management software I know: for the current IT infrastructure For many pain points of operation and maintenance, the Navedi visualization platform is based on the physical layer, and realizes the visual management of lines, equipment, documents, association relationships and status through the easiest to identify and understand 2D virtual reality representation, which can effectively improve the work of maintenance personnel Performance, improving resource utilization, and reducing downtime are an important part of intelligent operation and maintenance solutions. For specific product information, we can learn more about the company's official website http://www.nwvdi.com/ .
Although I have also talked about the daily operation and maintenance management, the benevolent sees the benevolent and the wise sees wisdom, each has its own ideas and methods, but technology is constantly improving, and our operation and maintenance processes and management methods should also keep pace with the times, especially human resources. Today, with increasing costs, we should focus on the use of scientific operation and maintenance processes and management methods to win smartly while cultivating and using high-quality operation and maintenance personnel, and to ensure the operation and maintenance of our IT infrastructure more stably and efficiently.