Good afternoon, my network worker friend.
I have told you a lot about the computer room and the rack .
Today I will add another knowledge point for you, how to build a computer room.
Network workers who are familiar with computer room construction may know that a comprehensive data center computer room construction project generally includes:
Integrated wiring, anti-static floor laying, ceiling wall decoration, partition decoration, UPS, special constant temperature and humidity air conditioner, computer room environmental monitoring system, fresh air system, water leakage detection, ground wire system, lightning protection system, access control, monitoring, fire protection, alarm, shielding engineering, etc.
There are quite a lot of doorways here, right? What are the key issues in the design and construction of the data center computer room?
on this arrangement.
Today's article reading benefits: "Network System Integration Project Implementation Plan Template.doc"
No matter what the plan is, the networker must first complete the project plan. Private message me and send the password "implementation plan" to receive this classic project implementation plan template.
01 Where is the data center built?
It is important to analyze the climatic conditions of the location where the new data center will be built.
This will help determine the most appropriate cooling measures, including:
Water-cooled unit
Mechanical refrigeration and air conditioning
natural air cooling
indirect air cooling
adiabatic cooling
etc……
These are all for data center facilities to achieve their lower PUE goals.
02 What is the size of the rack required
The number of racks determines the space requirements of the data center.
The size of a traditional IT rack is 600x1000mm (width x depth), and a computer room with a space of 100 square meters can accommodate about 50 racks.
Of course racks come in other sizes, and knowing the size and number of racks, it's easy to estimate the space your data center will need.
If you want to know more about the rack, you can read the previous article: " It turns out that there are so many ways to network racks ".
03 What level of data center is needed
The Tier level of the data center determines the redundancy requirements and power distribution path of the data center.
For a Tier 2 data center, the redundancy of power and cooling equipment deployed in the "N+1" architecture is sufficient.
However, for a Tier 3 data center facility, it usually includes "N+1" cooling equipment redundancy, with dual power supply 2N power redundancy, and independent dual-circuit power distribution racks.
Therefore, knowing the class of the data center can determine the required redundancy design.
04 What is the average power density per rack
It is important to note that when designing data center power capacity, it should be based on average power density, not at maximum rated power.
The average power density of a rack multiplied by the number of racks is the maximum IT load for a data center.
Then, add the power of the data center's power system, cooling system and facilities such as switches and storage equipment.
To avoid expensive costs and to fully utilize the power system so that the data center has the right size of power and space, it is wise to adopt a modular strategy to reduce costs without sacrificing flexibility for future expansion.
05 Should O&M participate in planning and design?
The answer is of course yes.
Normally, the following should be done:
1. It can make up for the lack of knowledge of system operation and management by designers, improve design quality, and avoid or eliminate design deficiencies;
2. The needs of the operation and maintenance phase can be fully considered in the planning and design;
3. Able to fully understand and master the structure of the maintained system, weak links in reliability, legacy problems, and potential risks.
It is helpful to improve the quality of operation and maintenance, formulate operation and maintenance plans and practical transformation plans based on the basis.
06 Avoid being affected by internal and external factors
For problems that cannot correctly treat the differences between tendencies, preferences, restrictions, and constraints, and do not abide by the principles of scientific design, the following suggestions are made:
1. Avoid being influenced by individual decision makers in approval, decision-making and other links.
Some key functions were deleted and adjusted according to individual opinions, resulting in the final delivery of data center functions that could not meet the requirements of operation and maintenance.
2. Avoid being driven by inclinations, preferences or interests.
In the planning and design stage, some equipment manufacturers may influence the planning and design personnel's plan formulation and equipment selection by means of exaggerating equipment performance and confusing concepts.
07 What level of backup battery is required for an AC or DC rack
Server racks may need to be deployed with 100 percent DC power, or 100 percent AC power, or a combination of both.
For example, if a data center is being built for colocation purposes, there may be a need for an AC (UPS) power system, whereas if it is to be a telecom facility, this may require the deployment of a DC power system.
Knowing this, you will know the size and scale of the required DC power supply or UPS power system.
When deploying a backup battery, it is best to configure it based on a 15-minute backup discharge time.
Deploying backup batteries in this way would not significantly increase capital expenditures, which would be difficult to justify, but would be more cost-effective.
Enterprises need to increase the redundancy of backup generator sets, instead of wasting more money on increasing the number of batteries.
08 Avoid focusing on planning and design and focusing on construction
There is a status quo in the industry that focuses on planning and design and emphasizes construction, which is mainly manifested in:
1. Build the building structure first, then plan the data center, which brings insurmountable difficulties to the planning and design of the data center;
2. It is common to start reconstruction immediately after the construction of the computer room and equipment installation;
3. Determine the equipment first, and then determine the plan. Since the functions of the purchased equipment do not meet the requirements of the plan, or the site does not meet the requirements of the installation conditions, the equipment must be replaced before it is in operation;
4. The construction structure is difficult to meet the layout requirements of the data center site, which makes the partition planning of the computer room unreasonable; the outdoor unit of the air conditioner cannot be installed or the distance is too far; the distance between the power room and the main computer room is too far, which increases the difficulty of transmission and management, increases costs, and reduces reliability.
09 Avoid neglecting design for system maintainability and repairability
The system is divided into three parts for construction and seven parts for maintenance . Any equipment may fail, and quick repair has become a key indicator for improving availability.
The phenomenon of ignoring maintainability and repairability is manifested in:
1. The planning and design stage did not consider the later maintenance access and maintenance space.
For example, the device is too close to the wall, the battery is placed against the wall, the cable layout is unreasonable, the cable pipeline or the cable rack blocks the weak wire slot above, making it impossible to repair later, and the maintenance tools are difficult to use.
2. When a failure occurs, emergency supplies and spare parts cannot be moved quickly, and there is no maintenance and operation space for the replacement of failed equipment and components, which delays the time limit for troubleshooting and even causes major accidents.
3. Failure to consider the redundancy support capability of the system when a failure occurs in the later period for equipment maintenance.
4. Use automated means as much as possible to minimize manual operations by maintenance personnel and reduce uncertainty and uncontrollability due to manual operations.
10 Avoid usability design without scientific basis
System availability is the most important indicator of data center planning and design, but there is a lack of scientific basis for planning and design, the main manifestations are:
1. The reliability of each system will be calculated during the planning and design of the data center.
However, at present, the calculation basis and data sources for the reliability of various design institutes and different designers have not been unified, resulting in different definitions and different results for the design level and reliability of the same data center.
2. For usability, there are cases where planning, design and construction are carried out first, and then the design level is deduced after the construction is completed, and the reversed level standard is used to recommend to data center users.
This is a design with the cart before the horse, often because of some key defects in the design, although most of the designs meet the grade requirements, the grade is lowered due to the existence of key defects.
3. Only pay attention to the availability of equipment or links (subsystems), while ignoring the influence of the correlation between subsystems in the entire system on availability.
11 Avoid setting high targets out of actual need and feasibility
In the early stage of planning and design, the functional indicators of the data center are subjectively determined, and the blind pursuit of large scale, high availability level, high rack power density, and low energy consumption index PUE is unrealistic.
However, in the specific planning and design, detailed demonstrations were not strictly followed in accordance with the planning principles and procedures, and the specific schemes and practical measures did not match the overall plan. The result was:
1. Due to the unclear actual demand and the lack of necessary conditions for feasibility, repeated design and modification not only result in waste of cost, but also greatly prolong the construction period;
2. The computer rooms that have been built and put into use are not fully utilized. The reason may be that there is no expected business demand, or because the conditions of the computer rooms do not meet the needs of users, they must be re-optimized before they can be used;
3. The functions envisioned by the plan cannot be realized, such as the system availability not reaching the planned level, the cooling scheme not supporting the planned high power density of the rack, the generator not supporting the continuous operation of the system, and excessive planning making the system energy consumption index PUE remain high, etc.
12 Avoid the misunderstanding of focusing on equipment and ignoring systems
The industry, especially the planning and design personnel, generally has the phenomenon of focusing on equipment and ignoring the system and ignoring the overall situation, which is mainly manifested in:
1. First determine the equipment specification model and even the manufacturer, and then select or modify the design scheme according to the equipment;
2. The power supply system is designed according to the highest available level of 2N redundancy, but the result of the design is that only the UPS system has 2N functions, but the entire power supply system has a single path failure point;
3. The whole system is designed according to the highest level of redundant fault-tolerant system, but the air-conditioning and refrigeration equipment is powered by a single path;
4. The system is equipped with an AC backup energy diesel generator, but the generator does not have an automatic start function, because the planner lacks the understanding that continuous refrigeration is also an important condition for the continuous operation of the system.
13 Pay attention to overall design
It is very important to improve the system overall design ability to complete the planning and design tasks with high quality.
1. In the process of data center construction, there are a lot of problems in the planning and design of phased and professional implementation of phased projects, and the lack of consideration of the connection between different professional constructions. As a result, the delivered data center does not meet the business and maintenance requirements, and some problems even require large investment to complete the transformation;
2. Different designers only pay attention to the content they are responsible for, and lack of overall consideration for whether there is a perfect connection with other majors, and whether there are contradictions and conflicts with other professional designs;
3. Planning and design personnel lack accurate grasp of future business development, and insufficient consideration of later capacity management and expansion;
4. Planning and design personnel are not familiar with the surrounding resource environment and physical environment, and the designed scheme may have poor implementation feasibility or bring insurmountable difficulties to subsequent operation and maintenance work.
Say it at the end.
There are many other issues to consider when building a new data center.
However, industry experience tells you that mastering the above 13 key points in the process of data center construction and design will help ensure that the final construction results are as close as possible to the real needs of users, which is worth learning.
Finishing: Lao Yang 丨 10-year senior network engineer, more network workers to improve dry goods, please pay attention to the official account: Network Engineer Club