Data processing center- this is a building or part of it, the primary function of which is the placement of equipment for processing and storing information, as well as auxiliary (engineering) facilities that ensure its operation (definition given in the American standard EIA / TIA-942).

In the data center on a relatively small area are concentrated powerful servers, carrying out storage and processing of information; network equipment responsible for data exchange with the outside world; engineering systems that ensure the vital activity of this “cyber brain”, and security systems that protect the data center from unwanted intrusions.

Rice. Data Center: Schematic Diagram


Life support systems: ventilation, air conditioning, fire extinguishing, access control and video surveillance systems, structured cabling.

Servers and network equipment: resource servers, application servers, information presentation servers.

Information security system: anti-virus protection, spam filter, intrusion protection.

Which companies need a data center

For a growing business, sooner or later become characteristic:

  • a significant increase in the volume of information
  • growth in the number of used business applications
  • data processing in remote friend from other divisions.

It's time to consolidate data processing and centrally manage IT infrastructure and information systems - for this you need to build a data processing center (DPC).

Data centers are necessary for all companies for which the maximum degree of availability, fault tolerance, and reliability of information systems are critical. These are large companies that operate complex business applications (ERP-, CRM-systems and others), telecom service operators, banks servicing client accounts and making settlements on plastic cards, insurance companies and others.

Rice. Which companies need a data center


Now in Russia, the number of data center creation projects is growing, data centers are becoming more complex and increasing in size. The benefits of using data centers are beginning to be realized medium business. Large companies that have long acquired them are increasingly resorting to the creation of reserve capacities. In general, the system integration market is now evolving towards the creation of data center networks.

DATA CENTER NEEDS BY INDUSTRY

Traditional consumers of IT services have been and remain enterprises where information technology is critical for business, and the very performance of business functions directly depends on the level, quality and degree of availability of IT services. Such traditional consumers included government agencies, banks and telecommunications companies. Today, these are mature, in terms of the level of IT development, users with an established culture, approaches and understanding of the place information technologies in the hierarchy of a company or organization. From a technical point of view, these are formed data centers equipped with modern hardware and software. They are characterized by a different range of problems: where to get electricity, how to build an efficient operation service capable of servicing the largest possible fleet of equipment with a minimum number of employees in the face of a widespread shortage of qualified IT personnel, how to retain specialists, etc. For such companies and organizations, it is also important other questions directly related to their business: for example, how to ensure the integrity of the IT structure when buying one enterprise by another? Or how to separate an integral IT infrastructure when dividing an organization?

Today in Russia there is a new round of development of information technologies, when industrial enterprises, retail trade networks, insurance companies become the most “greedy” for them. It is here that there is the greatest interest in IT, in particular in data centers. Companies are in the stage of a permanent search: where is it better to place their data center, what software tools will be able to solve problems most fully, what is the optimal hardware platform for the necessary applications.

Thus, players of an increasing number of market segments are realizing the criticality of information technologies for business, IT is penetrating deeper into the economy of enterprises, and their role as a business tool is increasing. In other words, the market is on the rise today, and system integrator companies have enough work to do.


Source: IT manager

Benefits of implementing a data center

Unlike a decentralized approach to organizing a company's IT infrastructure, having a data center saves money and increases:

  • reliability of the entire information system (reliability of data storage, fault tolerance of equipment and software)
  • level of services provided by the company to its customers
  • employee productivity by increasing the speed of operations, improving control, etc.

In addition, the data center provides the following opportunities:

  • modernize and build up computing systems in the context of the introduction of new business applications
  • centrally manage IT infrastructure and information systems
  • reduce the cost of ownership of information systems.

Corporate and hosting data centers

A corporate data center is initially created to solve the problems of automating business processes of the customer and the owner of the data center.


A hosted data center is rented out: the owner of the data center allocates rack spaces or clusters to organizations, which are filled with the equipment of the tenant.


A mixed data center is partly focused on supporting the business processes of the owner, and partly on solving the problems of tenants.

Primary and backup data center

The main data center is the core of the information and telecommunications system. It takes over the entire load in normal mode.


The backup data center provides the normal mode of providing services in case of failure, preventive maintenance or hot replacement of equipment installed in the main data center.

The place of the data center in the IT infrastructure of the company

The Data Processing Center is a strategically important node of an organization's information system.

The data center provides:

  • consolidated data processing and storage
  • maintenance of the specified mode of automation of business tasks of the enterprise
  • the safety of corporate information, which, as a rule, is of high commercial value.

The success and competitiveness of the Customer directly depends on the stability, reliability, timeliness, efficiency and completeness of its services.

According to Meta Group, the financial costs in case of failure of systems and equipment are:

  • $ 6.5 million per hour in the event of a failure of systems that provide brokerage operations
  • $2.6 million per hour if credit card authorization systems fail
  • $14,500 per hour in case of ATM failure
  • $330,000 average cost per hour of data center downtime.

ANNOUNCEMENTS

We approached writing this material about data processing centers outside the box. On the one hand, the article is informative and educational in nature, and on the other hand, we will cite the real Moscow TEL Hosting as an example.

Data Processing Center (DPC) - a high-tech facility for the placement of computing equipment. Initially, data centers were used mainly for the own needs of enterprises and organizations. Recently this term has become widespread in the commercial sphere, due to the growing interest in and demand for private data center services among customers.

Data center services

Data processing centers offer their customers a whole range of telecommunications services related to the storage and processing of information. In addition to standard solutions, some DCs offer additional services.

Standard Data Center Services:

Additional data center services:

Technologies used in data centers

A highly developed technical infrastructure that allows maintaining optimal conditions for client equipment is a key feature for a modern data center. The TEL data center is a prime example of such a facility.

A detailed story about the technical component of our data center (from which you can get a general idea of ​​​​the data center) is posted on the corporate blog on Habré.

Currently, more than 80 commercial data centers operate in Moscow High competition and proximity to the channels of backbone operators make Moscow prices the most competitive on Russian market. In the regions of Russia, prices for data center services are several times higher than in Moscow.

Data Center Differences

TIA-942 standard

According to this standard, all DCs receive a certain level - from tier1 to tier4.

The TEL data center formally complies with the tier2+ standard.

Format

According to this criterion, there are:

A) standalone data centers
b) data centers renting space from larger providers
c) server rooms, usually used for the needs of a particular enterprise
d) "trash" data centers (not having the proper infrastructure).

The TEL Hosting data center is owned by the telecommunications company TEL and belongs to the facilities of the first type.

Basically, information is provided on already implemented projects of the data center, or on advanced technologies used in its creation. For some reason, the question of justifying the choice of a data center, questions of the competent preparation of technical specifications for it, as well as questions about efficient use all the possibilities inherent in the data center are lost. To the best of my ability and ability, I will try to cover these issues in more detail.

Scope of the document and list of issues under consideration

This document is intended to obtain a set of necessary information for specialists involved in the creation and operation of data centers, server and computer rooms.

The document covers:

  • Problems that appear at the stages of design, construction and operation of the data center, as well as possible solutions to these problems
  • Recommendations on the use of modern standards are given, as well as a brief description of them.
  • The main errors in the design are given, and the problems that appear during operation, their consequences are shown, as well as possible ways to eliminate errors and solve problems.
  • Separately, the rules for creating successful IT projects are given.
  • The most important requirements for the main elements of the data center are disclosed, and, if possible, the reason for these requirements and the consequences of their non-compliance are explained.
  • The main trends in the creation of data centers and some statistical data of foreign and Russian data centers are listed.

Of course, this is not an all-encompassing document, and within the framework of one document it is not possible to consider the main issues that arise at the stages of justification, design, commissioning and operation itself. Therefore, I will try, as far as possible, to highlight the key points of everything life cycle DPC, to pay special attention to issues, in my opinion, the least described in the literature and the Internet. From the fact that some issues have not received proper coverage, they do not cease to be important, especially since some of them, as will be shown below, are hushed up for very specific reasons.

First, I will try to clarify the circle of specialists for whom the document will be oriented. These will be specialists from organizations that do not have a data center, but want to build it, specialists who have decided to build a data center, but do not know what to look for when writing terms of reference(T)3 and how to choose a partner, specialists who have built a data center, but who are trying to ensure the declared characteristics and reduce costs during operation. And also, probably, the document will be of interest to equipment suppliers and data center developers, at least in terms of understanding the problems of their customers. Although the document will consider most of the issues that arise when justifying the choice of a data center, its design, construction and operation, the document will not indicate the choice of this or that equipment, and even the mandatory use of certain technologies. The fact is that new equipment, solutions and technologies appear every year, often, in fact, differing in the introduction of some minor changes, or the implementation of long-known solutions, but on a new technical level. Remember - " Knowing a few principles frees us from knowing many particulars. ". Based on this, I will try, first of all, to talk about the principles of design and operation of complex computing systems, which are the best suited for a data center.

In order to discuss the problems of building and operating a data center, it is necessary to define some terms and understand what a data center is. Therefore, at first I will try to define the term “data center” itself.

Definition of the term "data center"

Recently, it has become very fashionable to talk about the creation of a data center. Almost every self-respecting company claims that one of its specializations is the construction of data centers or data centers. Typically, companies refer to positive reviews completed projects, etc. etc.

Let's first try to figure out what a data center is, how it differs from just a good server room, and what properties of a data center allow it to be called a data center. We will also try to understand what kind of work when building a data center requires special attention and where you can save money without losing quality. The analysis of all this will not only create a better data center, but also useful when building other data storage and processing objects.

If you turn to Wikipedia then data center or center storage and data processing (data center/CHOD) is a specialized building for placing (hosting) server and communication equipment and connecting subscribers to Internet channels. Another name for DPC is Data center(from English. data center).

Comment : If the document contains the term " Data center”, then this means that a document is quoted or paraphrased where exactly such a term is used, and not the term“ data center».

In fact, such an interpretation at least does not reveal the whole essence of what a data center is. Much closer in meaning is the following interpretation “DPC is a building (or part of it) for which complex solutions for the storage, processing and dissemination of information data with an IT infrastructure that allows it to provide its functions that meet certain criteria »

In any case, in the definition of a data center, one should not emphasize the presence of hosting and the Internet, because they really can be, but their absence is not critical for the data center. In the form in which the refined wording of the DPC is given, it most fully corresponds to the concept of the DPC set out in the Standard TIA-942. Although, in my opinion, the wording " DPC is a building, part of it, or group of buildings for which... » further in the text. Because it may well turn out that when implementing a data center with duplication of subsystems, the data center will be geographically separated between several buildings. Sometimes they also remember that during the functioning of the data center it is necessary to develop a set of organizational procedures and constantly engage in staff training. But this is no longer so important, because. one has only to understand that the data center is not only a building, but also a complex of engineering solutions, and not only it, but also providing necessary services and availability of qualified personnel.

Historically, data centers (the name DPC appeared later in Russia) grew out of large server rooms available to IT companies in the 90s. This qualitative change was facilitated by the advent of client-server technology, the advent of new cabling standards, and the advent of hierarchical media management. The main features of the data center were formed by 2000, when data centers became in great demand for deploying Internet servers of organizations that do not have the ability to support them, as well as ensuring the operation of expanded databases of various organizations in their computer centers.

At present, in St. Petersburg alone, there are more than 30 DPC. In fact, there are more of them, because. some organizations have built themselves infrastructures suitable for the concept of a data center.

Concerning the Standard TIA-942 it should be noted that the document elaborates on the issues of building (mainly in the form of requirements statements) engineering subsystems, but if you try to ask yourself the question of choosing a specific project for building a data center in order to perform specific tasks, questions immediately arise. The TIA-942 Standard introduces the concept TIER levels. The standard considers four levels associated with varying degrees readiness (TIA-942 terminology ) data center equipment infrastructure. Higher levels not only correspond to higher availability, but correspondingly cause higher infrastructure costs. In fact, the TIA-942 Standard divides (classifies) data centers only by the level of reliability (sometimes they write that by the level of availability, but this term, although close, is still already the term " reliability»).

Data center classification

The very concept of a data center is rather uninformative, the fact is that all data centers are different not only in size, but also in the tasks assigned to them, if possible, provide their main functions with a certain level (quality). Yes, and the main functions of different data centers, depending on their orientation, can be considered different functions.

If you look more closely, you can identify a lot of criteria by which you can divide data centers. Basically, it is these criteria that will be decisive in the functioning of data centers, or these criteria will carry a set of some properties that make it possible to single out a certain group of data centers.

Data centers can be divided by:

  • Purpose, or more precisely, to divide them into public and non-public (the term “corporate” is more often used) data centers;
  • Reliability of data storage (to be more precise, in terms of the combination of reliability and availability).

They also exist as separate groups. disaster-proof Data Processing Centers (DPC) and « trash data centers". The name "thrash" came from (eng. trash- garbage) - usually these are small data centers, in which cooling is realized only due to natural air exchange.

Such "junk" data centers, for the most part, do not fully meet the requirements for data centers, but they are less expensive, environmentally friendly, and renting server racks from them is much cheaper.

With the division into public and non-public data centers, everything is clear, and their design approach is different. After all, making a data center for itself, the organization knows quite well which of the main properties it needs, and where it can save. This implies the possibility of selective fulfillment of requirements for the data center. In public data centers, everything is somewhat more complicated, and if they want to get certification at a data center in order to increase the number of their customers, then at least the mandatory recommendations will have to be followed.

If we talk about reliability, then you need to start by considering the term “time to failure”. In fact, it is not a fact that the system will cease to function after failure if one of its elements fails. If, upon failure (transition from a working state to a non-working state) of one of the elements of the system, the system becomes inoperative, then they say that refusal. If, nevertheless, the system remains operational, then they say that something has happened. failure. The moment and frequency of occurrence of failures and failures are described by methods of probability theory and are not considered in this document. The only thing to remember is that, only by analyzing scheme reliability of the system and having data on the time between failures in digital terms of each of its components, one can speak of the level of availability or operability of the entire system. The proportion (%) of time during the year when the system is up and/or down time (% Uptime and Down time) are directly related. The downtime is the total downtime for the year. These terms are often used when discussing different levels ( Tier) DPC. But their numerical expression for different levels is not correct, because the spread of fault tolerance indicators for data centers of the same level can be large. In the appropriate place of the document, it will be shown that all the figures characterizing the period of downtime at various levels of the data center are from the evil one and it is impossible to really rely on them. In short, the list of the most characteristic features of the various levels of the data center can be summarized in a simple table.

Data center class (level)
The most characteristic feature Baseline low fault tolerance With reservation With the possibility of parallel maintenance work High fault tolerance
It is subject to violations of the normal course of work from both planned and unplanned actions. It has power distribution and computer cooling systems, but may or may not have raised floors, a UPS, or a generator. Even if there are UPS or generators, they are single-module systems and have many single points of failure. Every year, the infrastructure has to be completely shut down to perform preventive maintenance and preventive maintenance work. An urgent need may require more frequent shutdowns. Errors during operation or spontaneous failures of the infrastructure components of the facility will cause interruptions in the normal course of the data center. There are redundant components, somewhat less prone to disruptions from planned and unplanned activities than the basic data center. In this case, there is a raised floor, UPS and generators, but the project is rated N+1 (Need plus One), which means a single-stream distribution path over the entire area. Maintenance and repair of the critical power path and other parts of the facility's infrastructure will require a shutdown of data processing. Allows you to carry out any planned activity of the infrastructure of the facility without any disruption of the normal operation of the technical means of the turbine hall. Scheduled activities include preventive and programmable maintenance, repair and replacement of components, addition or removal of components that affect performance, testing of components and systems, etc. Sufficient power and distribution capabilities must be available to simultaneously carry the load on one path and at the same time time to perform repairs or testing on a different path. Unplanned actions, such as operational errors or spontaneous failures of the infrastructure components of the facility, will still cause interruptions in the normal course of the data center. Tier III facilities are often designed with the prospect of scaling up resources to Tier IV. Has multiple active power and cooling distribution paths. Provides an increased degree of fault tolerance due to the presence of 2 paths. Provides multiple paths for supplying power to all types of computing and telecommunications equipment. Requires all computer and telecommunications equipment to have multiple power inputs. The equipment continues to function when one power input is disconnected. The ability and ability of the facility infrastructure to allow any planned activity without disrupting the normal operation of the critical load is envisaged. Fault-tolerant functionality also ensures that the data center infrastructure can withstand at least one unplanned failure (or event) of the worst kind without affecting the critical load. Has two separate UPS systems, with each system having N+1 redundancy.
Type of company-consumer of resources Medium and small business. Data center for servicing the company's internal processes Medium and small business. The data center operates in the "5x8" mode Companies serving both internal and external customers in the "7X24" mode Global companies providing their services 24x365
building type With neighbors Freestanding
Number of power inputs 1 One active, one standby Two active

For example, I cite the correspondence of availability, the time the system is in a non-working state (per year). I will not tie the levels to the numbers, because. I have already said above that the range of availability indicators per year can be quite large within the same level.

Availability, %
(%UPTIME)

Downtime per year, hour.
(DOWNTIMEper year), hour

Reliability Solutions
Without redundancy, generator, and backup input
Without redundancy, generator, but there is a backup input
With partial "cold" redundancy, without a generator, but there is a backup input
With "hot" backup of the most important parts and "cold" almost everything else, the presence of a generator and backup input
With "hot" standby of the most important parts and "cold" almost everything else, with a generator in "hot" standby and standby input in "hot" standby.
99,999 5.26 min. Full redundancy of everything, always the presence of 2 paths (connections) often with duplication.

An entry of the “No redundancy” type does not mean that in the event of a failure, an order and receipt from the supplier of the failed unit will be expected. The presence of calculated stocks of spare parts and a decrease in the value of the MTTR indicator (mean time to repair) also significantly affects downtime.

One more important note. The data center will have the maximum level of which the minimum level of one of its components. On the other hand, one must remember that not all recommendations from the standards are mandatory, and if you know exactly what and how their violation affects, then you can usually save some money when building a data center.

Example

Developers, quite often struggling to improve the energy efficiency of the data center, which,rated as the ratio of total power to the power of IT equipment have long fought for the ability to increase the operating temperature. The idea is sound, because in reality the service life of most computer equipment in a data center is 3-4 years, although it should be noted in passing that the equipment responsible for power supply is usually replaced less often, however, with proper maintenance. After this period, either the equipment is replaced or the most critical applications are transferred to other new equipment. An increase in room temperature by several degrees does not really affect the probability of equipment failure during this period, but significantly reduces cooling losses, thereby increasing energy efficiency.Now there are trends for some classes of data centers to further increase the allowable temperature.

Therefore, it is very important to know why certain requirements are given in the Standards, and what will happen if the standard deviates in one direction or another. All this can be dealt with only by analyzing the requirements for certain parts of the data center. It is also necessary to deal with the question of what standards regulate the requirements for constituent parts data center, whether they contradict each other, and whether these standards should be observed in general. Therefore, the next chapter will be devoted to standards and their requirements.

Standards requirements for the components of the data center

First, you need to decide on the requirements, what standards you need to be guided by, and most importantly, what will happen if they are somewhat “violated”, respectively, for the better or for the worse. At the very beginning of the chapter, I will express a somewhat seditious thought. You need to know the standards so that if necessary they can be violated if necessary. More precisely, it is reasonable to make some of the requirements for your specific data center higher or lower than the standard requirements for your chosen data center class. I wrote this line and realized that now I will definitely have to write the name of this “smart” standard, the requirements of which must be followed when developing a data center. But... no, it's not that simple. Documents bearing the proud name “Standard…” in their titles are in fact most often the generalized experience of the group of experts who created this Standard. To accessibility (%UPTIME) or idle time (DOWNTIME) recommendations are not relevant. Following the requirements of the standards does improve these indicators, but by how much, this is a mystery shrouded in darkness. The fact is that it is practically impossible to take into account all the factors that affect the decrease or increase in these indicators, and even more so it is impossible to obtain data on all the equipment of your data center that you specifically use. What to do? First of all, having prioritized the requirements for the data center you are creating, try to take one of the standards as a basis and continue to follow its requirements as accurately as possible.

In my opinion, you need to start searching for the Standard that suits you from the previously mentioned TIA-942 « Telecommunication infrastructureData Processing Centers». The first version of the standard was published in 2005. It details requirements for design, power supply, heat dissipation, safety control, redundancy, maintenance, and commissioning procedures.

In June 2010, Building Industry Consulting Service International Inc. (BICSI) published a new standard 002-2010 : Data Center Design and Implementation Best Practices. This standard BSCI 002-2010 reflects the growing complexity of arranging data centers and the need for companies and organizations to understand the requirements for energy, mechanical loads and telecommunications when designing the infrastructure of a computer center.

What is the best standard to use? What are their differences? How then to get certified? After all, there are standards from other organizations. For example, the main difference in Uptime Institute certification is that certified specialists of this organization must ensure that the requirements set out in their standards are implemented on the spot. In mid-2010, the Uptime Institute released another standard “ Operational Sustainability(Operational Sustainability)” Regulatory and Operational Services. It was the requirements for the operation service that were lacking in TIA-942 . And although jointly fulfilling the requirements of the Standard TIA-942 and standard Operational Sustainability it is already possible to formulate the requirements for the data center quite precisely, but in practice, builders of new data centers often refer to the TIA-942 standard. The fact is that each of the standards was compiled by a different organization and in many details differ from each other. Moreover, according to Uptime Institute experts, their order of division into availability levels is in no way functionally related to TIA-942 levels, they evaluate the ability of computer centers to maintain operability in the face of failures and accidents. To avoid confusion, Uptime Institute experts suggest designating accessibility levels in their interpretation with Roman numerals I, II, III and IV. It is quite difficult to certify a data center. If you go to the site Uptime Institute(website http://uptimeinstitute.com) then at the end of May 2012, only 1 center actually provides Level IV (that is, not only the documentation and the created building with technical means in it, but also the level of operation), certification of the constructed facility for IV Tier was held for 6 data centers. Documentation certification for the construction of IV Tier data centers was obtained for 22 objects. Russian data centers among Tier IV on this moment no. Level III data centers are also not very numerous. Provide complete meeting the requirements for Level III in "Operational Sustainability" with only 4 data centers. There are no Russians among them. Documentation and premises correspond to Tier III at 5 Russian data centers (4 Design Documents and 1 Constructed Facility).

During 2012, the TIA-942-A Standard will be published, which includes changes and additions. next versions TIA-942-1 and TIA-942-2. Unfortunately, the new version of the standard has changed a lot. The new TIA-942-A standard will only deal with cabling and will no longer be as comprehensive as the TIA-942 standard was. Those. basically he will regulate only the construction of cable systems. The section on energy efficiency will most likely deal with this topic only from the point of view of the cabling system and the use of the "green" data transmission medium - optical fiber.

The following is a list of major changes included in the current draft TIA-942-A (according to the developer's preliminary statement). This information is in italics.

TIA-942-A aligned with the TIA-568-C series of standards for topology, terminology, and media classifications provided in the 568-C.0 standard, as well as component specifications provided in TIA-568-C.2 and C .3;

  • Applications, TIA-942-1 and TIA-942-2, are included in the TIA-942-A standard;
  • Grounding information has been moved from TIA-942-A to TIA-607-B;
  • Administration information will be moved to the TIA-606-B standard;
  • Much of the information relating to telecommunications cabinets and server racks, separation of power and telecommunications cabling will be moved to the TIA-569-C standard;
  • External cabling information moved to TIA-758-B;
  • The length limit of 100 meters for horizontal fiber optic cable systems has been removed.
  • Category 3 and Category 5e cables should no longer be used in horizontal cabling. The working version of the standard allows the use of Category 6 and Category 6A balanced twisted pairs in horizontal cabling systems. Category 6 and Category 6A can also be used in backbone cabling systems;
  • The use of OM3 and OM4 multimode fiber optic cables (50/125 µm core/cladding multimode optical fiber, optimized for operation with light sources based on lasers at a wavelength of 850 nm) has been approved for use in horizontal and backbone cable systems. Cable types OM1 and OM2 are no longer allowed;
  • To connect one or two fiber cables, fiber optic connectors of the LC type must be used and for multi-fiber connectors of the MPO type;
  • The data center topology includes an intermediate distribution area (IDA);
  • A section on energy efficiency has been added to the standard;
  • Added the terms "hardware outlet" (EO - equipment outlet) and "external network interface" (ENI - external network interface), borrowed from the international standard ISO / IEC 24764.

Standard “Operational Sustainability” just complements TIA-942 especially in terms of data center operation.

The Operational Sustainability standard describes the requirements to guarantee the stability of data centers, as well as to minimize the associated risks. As you know, the previous widespread standard "Tier Standard: Topology" regulated the technical parameters of the data center necessary to achieve a certain level of reliability. The peculiarity of the new standard is that it takes into account the human factor in the sustainable operation of the data center. And it has great importance, since the percentage of errors in work associated with this factor reaches 70% , of which a little more 40% associated with the errors of the operating service managers. To minimize these errors, it is necessary to conduct purposeful work with personnel, improve their qualifications, and take measures to retain qualified personnel.

If we consider the standards from the corporation BICSI, it can be seen that their approach differs from the approaches to assessing the levels of sustainability of other organizations.

The system for assessing levels of stability and the main sections of the standard BICSI 002 2010 . According to the association, the developers of the standard set themselves the goal of ensuring the design and construction of data centers, taking into account the long-term perspective of their operation. The main sections of the document:

  • Data center layout
  • Site selection
  • Architectural solutions
  • Building construction
  • Electrical systems
  • Mechanical systems
  • Firefighting
  • Safety
  • Building automation systems
  • Telecommunications
  • Information Technology
  • Commissioning
  • Operation and maintenance
  • Design Process
  • Reliability

Therefore, regarding the standards for building a data center, it should be noted that all developers of common standards for a data center do not contradict each other in terms of requirements and references to the Standards when building the basic levels of a data center. Commercial data centers, due to their specifics, must satisfy (and preferably be certified) all the requirements of the standard that they took as a basis. Not all recommendations affect the main quality of the data center - ensuring a given level of availability. Therefore, non-commercial data centers in some cases may ignore some requirements. Especially since certification is not only expensive, but also does not directly affect the level of data center performance. After the implementation of the data center, it is still possible to make some changes not only to the support level, but also to other levels, trying to meet the requirements of one of the standards for obtaining certification.

Uptime Institute at one time identified four levels associated with varying degrees of readiness of the data center equipment infrastructure (DPC). In fact, although they are related to the level of accessibility, it is probably more correct to talk about TIER levels, although the term “TIER” itself is translated as “Level”. Above, I, not in vain, revealing the concept of "Level", did not give digital characteristics of the level of availability of the data center. Numerical expressions were obtained only from the analysis of implemented projects. Here is some data from a document developed by The Uptime Institute in their Bulletin, Industry Standard Tier Classifications Define Site Infrastructure Performance.

Parameter / Class
Data Center (level)

1
Low fault tolerance

4
High fault tolerance
building type With neighbors With neighbors Freestanding Freestanding
Number of power inputs 1 1 one active,
second backup		 Two active
Initial power W per m 2 215 - 323 430 - 537 430 — 645 537 - 860
Maximum power W per m 2 215 - 323 430 - 537 1075- 1615 1615+
Uninterrupted air conditioning Not Not maybe There is
Raised floor height in meters 0.3 0.45 0.75 - 0.9 0.75 - 0.9
415 488 732 732+
(according to the standard 2005 1000+)
Total duration of failures per year 28.8 h 22 h 1.6 h 0.4 h
Data center availability 99,671 % 99,749 % 99,982 % 99,995%
Commissioning period (months) 3 3 - 6 15 - 20 15 - 20
A typical project was first implemented in 1965 1970 1985 1995

General conclusion on the use of standards:

  • The use of the TIA - 942 standard with the latest additions (for example, with the “Operational Sustainability” standard) should be considered fundamental;
  • The new TIA-942-A (approved April 24, 2012) is only about cabling and will no longer be as comprehensive as TIA-942 was;
  • When building a data center, one should use not only standards, but also common sense, which allows significant savings without worsening its most demanded qualities;
  • Certification is more necessary for a commercial data center, while an organization's data center may not. Of course, if the data center was still created on the basis of standards, then all deviations from the recommendations should be justified;
  • To read, and, most importantly, to understand which Standard to take as a basis and what requirements it will need to focus on in future development, you cannot assume that you have finished working with the standards. Before proceeding to the next stage, it is imperative to re-read the old, good, however, currently mostly forgotten GOSTs - series 34. And nothing that they have not been updated for many years, but there is a detailed consideration of the pre-design stages. They do not contain the well-known words “business processes”, “processor approach”, but there is the concept of “ information model” quite correctly replacing them. Therefore, especially at the TK stage, these documents will help you. Of course, you need to be creative and not follow literally all the recommendations, but you need to read them carefully.

The order of building a data center

Strangely enough, the initial stages make the greatest contribution to the success or failure of the future project. Actually, according to world statistics in the IT industry only one project out of 3 becomes successful. If we take a tougher approach, and evaluate the success of the project as:

  • the ability to perform the declared functions with the required quality
  • complete the job within the scheduled time
  • not exceeding the original project budget
  • lack of emergency work at various stages of the project
  • no need to immediately start work on the modernization of the project.

Everything will get worse. Probably no more than 20% of projects will fall under the definition of “successful”.

There are many reasons for the failure of the project. Here is the wrong policy (precisely politics, because resolving contentious issues is most often finding compromises) of the project management, lack of proper support from the head of the organization, poor study of the technical specifications and, as a result, a large number of unplanned works, poor participation of specialists from the organization for which the project and any force majeure circumstances.

If virtually every project is dominated by the possibility of failure, then what about peppy statements about dozens of successful projects in many firms? First you need to immediately put everything in its place, defining the term " Project».

Project(If you refer to Wikipedia) - this is a unique (unlike operations) activity that has a beginning and an end in time, aimed at achieving a predetermined result / goal, creating a specific, unique product or service, with given resource and time constraints, as well as quality requirements and an acceptable level risk. Perhaps this definition can be simplified for greater specificity. Project— is a set of tasks, activities or work performed related to the achievement of the planned goal, which usually has a unique and non-recurring character . The main thing is that the project is always unique (at least for the people who carry it out). Therefore, everything that the performers talk about as a successful project is actually successful. implementation, those. implementation of a ready-made solution. The percentage of successful implementations is significantly higher than that of successful projects. And if for programmers writing any complex program is always a project, then in the field of building infrastructure, implementations are also possible. It is quite difficult to draw the line when the implementation develops into a project. For example, if a small software and hardware complex is being created to automate some remote site and this is not the first time the developer has done this, and the number of differences from previously created ones both in hardware and in the set of installed programs is minimal, then this is implementation. And it has a fairly high chance of success. If there are differences in terms of a significant amount of new hardware, the installation of new complex software, or the emergence of new requirements that cannot be met as part of the implementation of previous solutions, then the creation of such a hardware and software complex will be a project. Those. the executor of the project is always at the beginning of his work in a state where goals are defined, solutions are uncertain, successful solution of the problem is questionable. I explain why I dwelled in detail on a seemingly terminological issue.

The fact is that there are 2 approaches to the performance of work and their evaluation. This is the approach of the Developer and the approach of the Customer.

The developer, when implementing the task from the Customer, tries to:

  1. Try to apply the solution already implemented by the Developer;
  2. If this is not possible, it tries to apply a solution tested by other companies (most often a solution recommended by the hardware or software manufacturer);
  3. Try to reduce the requirements of the Customer and, if possible, reduce them to the same standard solutions;
  4. In case of failure of the previous paragraph, the Developer tries to increase the time for completing the work or make the requirements for acceptance of his work more lenient;
  5. Try to focus on the acceptance phase strengths completed project and hide your mistakes and unfinished business;
  6. Try to quickly hand over the project and start a new one, or, in extreme cases, secure outsourcing for yourself.

The Customer's approach is primarily characterized by:

  1. An attempt to get as much as possible from the Developer and for less money;
  2. Attempts during the development of the project to change or clarify the points of the original TOR;
  3. During acceptance, try to get as much documentation as possible, and look for developer errors;
  4. To try at the expense of the Customer not only to correct the errors identified during the acceptance process, but also to make further changes to the project.

Therefore, the use of implementation, instead of developing a project that has a much less chance of success, is always desirable for the Contractor. The above option is of course the most relevant if the development of the project is carried out by a third-party organization. In fact, when ordering a really complex project (and the construction of a data center belongs to such projects) from a third-party company, the participation of the Customer's specialists is absolutely necessary, at least at the initial stages of the project. Indeed, no one knows the requirements for the created data center as much as the Customer's specialists. Of course the customer at a minimum, it should be able to control the implementation of the project, more precisely, have information about the timing of each of the stages, the progress of its implementation, and also not only participate in the acceptance of the project, but also participate in writing the test program. Only in this case is it possible to formulate Tech. tasks, prompt resolution of emerging issues, a comprehensive check of the result.

There are two options for implementing a project to build a data center. The first involves the implementation of the project on its own, and the second assigns these responsibilities to a third-party contractor. In its pure form, such schemes are rare. Almost always, the construction of such systems is a joint work of the Contractor (or several Contractors) and the Customer. But it all comes down to the question of who will lead the project. It would seem, to whom, if not the Contractor, to give such rights, but ... Participation in the writing of the TOR at the same time by the Customer (since he knows all the requirements for his data center) and the Contractor (because if the Contractor is not involved, then the Customer may well write such a TOR that no one can implement at all) allows you to develop a fairly accurate idea of ​​the system that will be created and the software that should be used during the discussion. Those. specialists involved in the writing of the TOR become at the time of completion of its writing the most competent in terms of specific requirements for a project carried out for a particular customer. I immediately answer possible questions about the joint writing of technical specifications. Customer in the development of large projects can alone write only the Preliminary TOR, which is only suitable for the competition when looking for an executor. And the jointly written TOR with disputes settled between the Contractor and the Customer will serve as the main document for the acceptance of the data center, since the "Test Program and Methodology" will be written on the basis of the TOR.

Therefore, one of the main mistakes of the Customer is removal from work of specialists involved in writing technical specifications and episodic participation in the draft and working design of only narrow specialists when solving particular issues. Specialists involved in the implementation of large projects must be at the Customer's in the department of complex works. And it is they who should involve, if necessary, all specialists in certain areas. In this case, the specialists of the complex department will be aware of all the "thin" places of the project and the project itself will have a great chance of successful completion. Also, specialists of the complex department should participate in the acceptance of the work of the Customer, because constantly monitoring the progress of work, they will be aware of all its problems.

Note on the work related to the competence of the complex department.

It is wrong to think that the workload of the integrated department will be limited only to participation in large projects, of which the Customer usually does not have very many. Big projects do not exist by themselves. Usually, each project requires its expansion, docking with various subsystems, making changes in connection with newly emerging tasks. It is in addressing these issues that specialists-complexists will come in handy. The previous was not only about big projects, because it is necessary to understand that only implementations of individual products not affecting a large number of employees of the Customer, it is possible to implement, bypassing the complex department.

If we turn to the experience of implementing large projects, we will notice that large organizations (for example, banks), or those whose specialization is related to IT, manage projects to create their own data centers themselves.

Summing up the stages of substantiation and preparation of TOR

From the above, we can conclude:

  1. Speaking about the creation of a data center, it is necessary first of all to prioritize the requirements that it will have to satisfy.
  2. After prioritizing, you need to take as a basis one of the standards, the requirements of which you will follow. (I would suggest using TIA-942, but we must not forget that he does not consider questions of exploitation.)
  3. All deviations from the standard for better or worse must be justified.
  4. To draw up the TOR, it is necessary to involve your own department of complex works (or create it), because. on your part, you need people who are personally interested in the successful implementation of the project and who will supervise all work with the Contractor.

If you notice that in this part I considered the issues before writing the TOR, I emphasized that it is necessary to write the TOR with the Contractor, but I did not write anything about the choice of the contractor. The fact is that the choice of the Contractor is a separate and responsible task. And if we mention this very briefly, then usually the choice is divided into 2 stages:

  1. Determination of the circle of applicants for solving the problem of building your specific data center.
  2. Analysis of the material presented by firms and clarification of issues during personal meetings.

It is usually easier to select several firms implementing successful projects in this area and provide them with a preliminary TOR (such TOR can be drawn up by the Contractor's specialists). Next, data center candidates are asked to write a short document that briefly describes all the subsystems of the data center and the process of its operation. Usually, by the completeness of the issues under consideration, the validity of decisions and the results of personal communication, the choice of the Contractor becomes obvious. And I’ll add on my own: if you are promised everything at a personal meeting and for cheap (in any case, much cheaper than others), this is a reason not to believe and once again check the reality and quality of the projects completed by the company. In addition, often in really complex data center construction projects, the execution of some of its subsystems requires the involvement of other companies. In this case, you must immediately agree that one of the companies is a system integrator for this project and you will solve all technical and other issues with it. There is nothing worse than a “piecewise” implementation of a project. Otherwise, in case of any trouble, everything will be like Raikin’s immortal monologue “Do you have any complaints about buttons?”.

»

Data processing center (DPC)- a single multi-component system, which is designed to ensure uninterrupted automated operation of business processes. Data processing centers are created primarily to increase the productivity of companies that actively use information technology in their activities, as well as to improve the quality of services provided.

To store and process a large amount of information, specialized technical solutions, powerful servers, disk storage. It is quite difficult and expensive to create and maintain such technical systems on your own: the maintenance of servers requires special technical conditions, separate premises and qualified personnel. One of the main purposes of data centers is to create suitable conditions to accommodate such technical solutions.

Business Benefits

Creating multi-component systems that solve most business problems significantly reduces the costs of enterprises. In particular, for companies with a geographically distributed infrastructure, this is an indispensable solution, since 1-2 employees serving the data center successfully replace many people working in offices in the regions. Subsequently, many entrepreneurs thought about acquiring data centers due to the fact that it was necessary to integrate a large amount of information together. The risk of losing certain information irrevocably has become very high and has led to certain costs for information recovery. In addition, there were risks of deprivation of part of the income due to downtime for various reasons. That is, thanks to their unique features The data center ensures the efficient and uninterrupted operation of any organization.

The advantage of a data center is that a person or company can, from anywhere in the world, using any network access device, work with the necessary and sufficient computing power, the required amount of memory, all the necessary software that will work and be stored on servers in the data center.

Traditional services in data centers: rack rental, server placement, Internet connection, communication channel rental, installation, software configuration, administration. Currently, they have been added to the provision of rental computing power, virtual servers, disk space for Reserve copy data, application rental.

  • Reliability of information storage. Moreover, this reliability is confirmed both by the architecture laid down at the design stage and by subsequent operation. Interesting fact that a detailed comparison of the cost of ownership of an information system located on the territory of the customer (as a rule, this is a business center) and in the data center results in quite comparable figures, which cannot be said about comparing the reliability of these methods.
  • Reduction of time spent on the implementation of new IT projects. When working in a data center, companies choose the services they want to receive on their own. The most popular are renting a rack, a unit, a ready-made server, virtual server and data backup. But besides this, there are a number of other services that tenant companies can use if necessary, which will significantly save time on launching a new IT project. For example, this is the rental of applications, which allows you to avoid large-scale investments at the initial stage of work. An example is the rental of 1C accounting - to deploy a ready-made system suitable for work, it is enough to order and pay for such a service in the data center. At the same time, often, at the customer's office, you do not need to buy, install or configure anything, except for Internet access.
  • Reducing the cost of renting a room. These include the cost of electricity, office space used for "server rooms", and maintenance of their own cooling systems and uninterruptible power supplies. By the way, equipment purchased for the office becomes the main assets of the enterprise, they are subject to property tax.
  • Organization of continuous work of the head office with the branches of the company throughout the country. access to work information regardless of the location of the employee. For example, the head of the company, while on vacation, can check work mail, contact his employees via IP-telephony.
  • The ability to create a backup office of the organization, if for some reason work in the main office is impossible, but you need to get important information, complete the project

reducing the cost of purchasing applications. To strengthen their competitive position, data center owners are developing a new range of services that can be offered to tenants.

The first to use data processing centers in their work were large foreign companies. They were followed by Russian entrepreneurs. In the Russian Federation in 2000-2001, the first owners of the data center appeared. The pioneer was Sberbank of Russia. It is he who is the most geographically distributed organization. That is, the need to create an integration of multiple data was high. In the future, large oil companies also acquired their own data centers.

Types of data centers

Depending on the purpose, there are three different types of data centers, each of which is designed for a specific enterprise model and has its own operational tasks and problems:

  • corporate data centers;
  • hosted data centers providing computer infrastructure as a service (IaaS);
  • data centers using Web 2.0 technology.

Below are the parameters that can vary significantly in different types of data centers:

  • type of traffic (internal, external or mixed);
  • use of Layer 2 (L2) and/or Layer 3 (L3) for traffic management in the center or at the periphery (Top of Rack);
  • data storage technology;
  • server virtualization level;
  • the total size of the data center (by number of servers).

Creation and modernization of the data center

Data Center Components

Traditional data center

The mandatory components that make up the data center can be divided into three main groups:

1. Technical Components. They create conditions for effective work of the center. These include:

  • server complex, includes servers for information resources, applications, information presentation, as well as service servers
  • the data storage and backup system is the core of the data center. It consists of consolidating disk arrays, a storage network, a backup and disaster recovery system
  • the network infrastructure provides interaction between servers, combines logical levels and organizes communication channels. It includes trunks for communication with operators public access, telecommunications providing communication of users with the data center
  • the engineering system of data center operation supports the conditions for normal functioning center. It includes subsystems for energy supply, climate control, fire alarm and fire extinguishing, data transmission, as well as automated dispatching systems, information resource management
  • the security system prevents unauthorized intrusion into the zones of confidential information. It consists of protective equipment, a warning system and an access control system.

2. Software . These are actually data center infrastructure services and software for the correct operation of business processes that are necessary for a particular organization. Infrastructure components include:

  • server operating systems;
  • database software;
  • operating systems of workstations;
  • clustering tools;
  • backup tools;
  • storage device programs;
  • administration tools for servers and workstations;
  • means of inventory;
  • office software;
  • Email;
  • Internet browsers.

The programs responsible for the functioning of business processes include:

  • business applications;
  • basic corporate information services;
  • applications for teamwork;
  • industry components;
  • software for solving problems of the design and technological plan of the electronic archive system and project management;
  • programs that provide file, print, directory services, and other application services.

3. Organizational environment resolves issues related to the provision of IT services. It must comply with the requirements for the provision of IT services, such as ISO / IEC 20000. Here are:

  • service delivery processes, i.e. the quality and availability of services;
  • relationship processes between the supplier and the client, as well as with contractors;
  • processes for solving problems that arise during the operation of any of the components of the system;
  • configuration management processes, monitoring and control of the IT infrastructure status, inventory, verification and registration of configuration items, collection and management of documentation, provision of information about the IT infrastructure for all other processes;
  • change management processes, that is, determining the necessary changes and how to implement them with the least risk to IT services, as well as consulting and coordinating actions with the organization as a whole;
  • release processes, that is, joint testing and introduction of a number of configuration items into the active work of the organization.

Software Data Center

In the software data center, we implement the entire environment in the form software modules in virtual machines– virtual appliances. The idea is that only servers and switches are physically used. Everything else is implemented in the form of virtual machines - virtual appliance.

In the world of service providers, this technology is known and even standardized under the name NFV - Network Function Virtualization - virtualization network functions. Only there it is used to provide services and, accordingly, a lot of attention is paid to orchestration and management tools, integration with OSS systems, which allows you to automate the process of creating services for each of the subscribers. In a corporate data center, it is not necessary to change the composition of services so often, the level of automation can be significantly lower, but the transfer of all network functions to virtual machines still provides significant benefits.

Data center is still a rare concept for Ukrainian companies. And if among IT people his role does not raise questions, then from managers to owners of companies in other areas, a lot of questions arise. The questions are very diverse - from what a Data Center is, how the process of its work works, and why it is needed.

So what is a data center? Of course, you can refer to Wikipedia and read that: A data center (from the English data center), or a (storage and) data processing center (DPC / DPC) is a specialized building for hosting (hosting) server and network equipment ... This is clear for the same it-shniks mentioned above. But what about those people who are not included in the caste of "aliens", how to explain to them?

So, let's start in order. The data center is a high-tech protected area where the servers of various companies are located. Simply put, a data center is a kind of “server house”. First of all, it is worth mentioning that the service itself will be useful to companies whose activities directly depend on the uninterrupted provision of fast and efficient processing of large, and sometimes colossal information flows. In the age of information technology, often with the aim of stealing, information is subjected to all sorts of attacks. It is the introduction of special disaster-proof solutions, the organization of data backup in data centers that will protect data from the risks of loss as much as possible. It is generally accepted that the services of the Data Center are in demand only by large companies, but in fact, there is a tendency to use the services and developing companies, especially when it comes to start-ups with foreign investment.

In fact, the purpose of a commercial data center is to provide customers with services related to ensuring the reliability and fault tolerance of storing and processing information (text, graphics, digital and other data), to ensure the performance of large Internet portals, for volumetric computing.

The data center provides special secure channels for international communications. Guaranteed security, reliability of the data center, as well as maximum speed are now commercially in demand on the world market.

Basic data center services

The main services are:

  • Server rental
  • Shared hosting

Additional services

There are also a number of additional services:

  • Backup (backup)
  • Cloud Solutions
  • Administered Server
  • Remote Desktop

Technologies used in data centers

High-tech infrastructure that ensures uninterrupted operation of equipment in the data center is the main characteristic of a modern data center. To do this, the Data Center site is equipped with climate control systems, uninterruptible power supply, security and other life support systems.

So, the main technical specifications reliable data center are:

  • The presence of a special building designed to accommodate the data center
  • Guaranteed power supply and air conditioning system.
  • Industrial ventilation system.
  • Automatic fire extinguishing system.
  • Availability of security and access control.
  • The presence of a diesel generator.
  • 24/7 access to server hardware for both staff and clients.

Often, data centers are located in close proximity to the point of presence of several telecom operators or a telecom node in order to provide instantaneous exchange of huge amounts of data and fast data download from anywhere in the world. The key criterion for assessing the reliability of a data center is uptime, i.e. server availability time.
Everything is simple, isn't it? Now let's move on to the second part of our article.

Why do you need a data center?

At first glance, the question seems simple, because servers and other equipment need to be placed somewhere, but why build entire buildings for this, if you can get by with a server room. First of all, the answer lies in the economic benefit. Consolidation of computing resources and data storage facilities in the data center can reduce the overall cost of operating IT resources.

Experts identify the following ways to optimize financial costs, provided that the equipment is placed in a commercial data center:

  • no need to create your own infrastructure;
  • Internet connection discounts, since the data center has its own connections to the main Internet nodes;
  • reduction of administration costs due to maintenance of servers by data center employees;
  • reduction of rent due to lack of space occupied by servers;
  • redistribution of loads in order to more quickly solve business problems.

In other words, placing servers in reliable data centers not only ensures the safety, integrity and protection of data, but also optimizes the financial costs of each individual company.