機房建置自動化需要克服的障礙

機房建置,當今的數據中心管理人員經常監督日益複雜的運營環境,其中包含各種應用程序,數據庫和競爭平臺的混合。通過腳本和平臺,以及特定於應用程序的調度工具來管理數據中心環境,這有可能效率低下,並且耗時,從而導致數據中心自動化孤島,導致工作負載出現管理難題。這些不協調的工具需要不斷更新以應對變化,否則將增加運營成本,並降低員工工作效率。

然而,工作負載自動化有一個更高效的企業範圍戰略,可以幫助數據中心管理人員承擔越來越多的責任。爲了處理預算不足和它技能差距的問題,企業正在研究這樣的策略以避免中斷。事實上,根據調查機構Gartner公司的“預測2018年:它運營”的調查報告,到2020年,75%的企業將因基礎設施和運營的技能差距而出現明顯的業務中斷。
企業用特定的自動化工具解決自動化問題是一種分散的方法,可以被描述爲一種“元素”。更高效的方法是採用一種“架構”,便於數據庫自動化和調度,以簡化複雜工作流程的管理,減少對定製腳本的需求,同時提高生產力並降低它運營成本。
這種架構方法可幫助數據中心管理人員克服六個自動化障礙,例如:
(1)跨服務器的分段計劃
特定於平臺的計劃工具通過強制在機器和操作系統級別執行數據中心任務和進程的調度會增加風險。而採用工作負載自動化解決方案將這些工具統一到一個框架中,以便更好地進行控制,從而消除了許可,部署和管理多個工具的需要,並消除了在數據庫級別調度和執行作業的麻煩,以及容易出錯的做法。
(2)重複和耗時的數據中心操作
數據中心有效運行的關鍵是維護功能,如數據庫備份,文件系統移動,FTP操作等。工作負載自動化解決方案可通過單一解決方案實現管理,提高批次成功率,同時減少運行時間,通過在多個數據庫和平臺間的動態平衡工作負載來提高資源可用性,並提供集中式監控和警報,以更快地解決問題。
(3)複雜的數據庫增長和變化
隨着企業發展,將新技術應用到數據中心是競爭和高效運營的關鍵要素。數據中心自動化的基本方法提供了一個短期的臨時解決方案。這最好體現在自動化的腳本這個主要方法中。創建,修改和測試腳本既耗時又耗費資源,可能會阻礙更新現有工作流程或整合新工作流程的能力。架構方法利用生產就緒模板和工作流程來減少對定製腳本的依賴,提供基於對象的架構,強調可重用性,簡化現有工作負載的修改,並通過簡化數據集成,ETL(數據抽取,清洗與轉換)和數據倉庫以適應數據增長和複雜性流程。
(4)安全漏洞
分散的數據中心自動化策略會對未經授權的生產過程和工作負載更改構成威脅,有可能導致敏感信息的泄露,例如,在受管制的行業中,任何未經授權的更改涉及患者數據或財務賬戶信息的生產工作流程都可能具有破壞性。此外,特定於平臺的調度工具可能導致跨不同服務器的作業和腳本不受控地擴散,從而增加了作業失敗風險。工作負載自動化解決方案建立了基於用戶的角色,提供了一個平臺來防止未經授權的更改,併爲數據中心管理人員提供了監控和審覈安全合規變更的能力。
(5)虛擬和雲計算的複雜情況
當需要管理同一網絡上的大量機器時,基於虛擬和/或雲計算的數據中心就會遇到挑戰。當數據中心由本地部署,虛擬環境和/或雲計算環境的異構組合組成時,會出現更多複雜情況。這些平臺配備了自己的本地作業調度程序,但與物理數據庫一樣,它們代表了自動化的孤島,從而阻止數據中心在其範圍內的工作負載中動態管理和配置虛擬和/或雲實例。採用架構解決方案爲虛擬和物理計算平臺提供單一控制點,通過基於工作負載執行自動配置和取消配置虛擬/雲計算資源,可以降低它運營成本,並自動執行涉及虛擬化資產的桌面虛擬化和管理流程。
(6)部門間協調困難
由於自動化經常超越數據中心,甚至超越它部門來實施,因此部門之間的轉換可能會產生不必要的額外工作,例如,當一個部門完成高級業務工作流程的一部分時,信息和數據將交由另一個部門處理,這往往需要人工處理和干預。架構方法提供了協調工具,通常可以消除涉及交付工作流檢查點的許多部門間依賴關係。
雖然自定義腳本和特定於平臺的工具可以快速修復日益增加的責任和靜態資源的繁忙數據中心管理人員,但實施體系結構方法可以解決數據中心管理人員當前面臨的一些問題,並防止將來出現問題。在架構模型之後的數據庫自動化控制的簡單的單點控制可以幫助數據中心管理人員完成重複任務,併爲員工提供更高級的項目,從而爲企業帶來更大的業務價值。

Data center migration,Influence of air pollution on equipment

Data center migration,the influence of air pollution on equipment can be divided into three main factors.

Category: chemical effect, mechanical effect and electric effect.
The two common mode of chemical failure is copper creep corrosion and silver metallization corrosion on PCB.
Surface mounting parts and mechanical effects include heat sink pollution, light signal interference, increasing friction and other electrical effects, including circuit impedance changes, arcing and so on. It is necessary to pay attention to reducing the feature size of PCB and miniaturization of components. Improving hardware performance also makes hardware more vulnerable to pollution attacks in data. Manufacturers have been working hard to maintain their hardware reliability.
With the shrinking feature size, no additional expensive measures are taken to harden all their equipment, most of which are not installed in the corrosive environment and exposed to higher risks.
Most data centers are well designed, in a relatively clean environment and most areas. Pollution is benign. Most data centers should not experience particulate or gas pollution and related hardware failures. This paper mainly aims at a few possible data centers.
Harmful environment caused by outdoor particulate matter and / or gas pollution. In some rare cases, pollution has been generated in data centers. The data center administrator is responsible for maintaining the reliability of the hardware. Monitoring and controlling dust and gas pollution in data center. Data center must be kept clean, class ISO 14644-18. This degree of cleanliness can usually be achieved by appropriate means.
Harmful environment caused by outdoor particulate matter and / or gas pollution. In some rare cases, pollution has been generated in data centers. The data center administrator is responsible for maintaining the reliability of the hardware. Monitoring and controlling dust and gas pollution in data center. Data center must be kept clean, class ISO 14644-18. This degree of cleanliness can usually be achieved by appropriate means.

Can data center migration security keep up with?

Over the years, software definition data center migration and its formation technologies (including virtualization, software definition network, software definition storage) have become the cornerstone supporters of agile and efficient IT.As software defined data center (SDDC) and a public Cloud infrastructure as a service (for example, apply to the AWS VMware Cloud), chief information officer from data center capacity, manageability, and disaster recovery Angle, taking advantage of the real integration of hybrid Cloud.

But can security keep up with data center transitions, such as software defining data centers and hybrid clouds?Traditional security usually by extract valuable resources from the production workload, introducing the application response latency and increase management complexity, thus affecting software defined data center (SDDC) infrastructure efficiency, performance and agility.In addition, such a solution may not be suitable for providing consistent and continuous protection for workloads migrating on a hybrid cloud.
The company's chief information officer must address security issues strategically, making it part of the data center's transformation strategy and roadmap.It is critical that companies choose solutions that protect hybrid cloud workloads while retaining the advantage of the software definition data center (SDDC) infrastructure.In this way, the chief information officer can be mixed in the cloud to maintain or improve its organizational safety state, and does not affect the operation efficiency, agility, and performance advantages, prompting decisions first invested in software defined data center (SDDC).
The data center that is defined by the hybrid software is happening.
It is an undeniable trend that enterprises are turning to software definition data centers.According to research firm IDC, global software definition spending rose 3.5 percent in 2016 from a year earlier to $4.32 billion.In 2016, the global software definition storage (SDS) market is $8.56 billion, and the compound annual growth rate (CAGR) is expected to be 13.5% over the next five years.In 2016, the market size of the software definition network (SDN) reached us $4.45 billion, with a compound annual growth rate of 25.4%.
About 90 percent of the chief information security officers said their data centers are undergoing major changes, according to a Bitdefender survey of 250 IT security policy makers in the United States.More than two-thirds of the user has stored a hybrid cloud data, and 64.8% of the users to use the software defined network, 62.8% of users rely on virtualization of the enterprise data, 57.2% of users use software defined storage, 35.6% of users use super integration infrastructure.
"Digital transformation" is driving the rise of software defined data center (SDDC), which describes the digital technology was applied to each organization's efforts, including the internal processes and profitable products.To succeed, companies are adopting software definition and hybrid cloud infrastructure, and quickly get rid of the three layers of hardware as the center of the traditional data centers, these data centres are often largely isolated, mainly composed of proprietary systems build, high cost of maintenance and management.The reality is that these systems are too slow and inflexible to provide resources at the speed the enterprise needs now.
The software definition data center (SDDC) provides greater efficiency and enables IT teams and development teams to meet the enterprise's digital transformation needs faster.When companies combine public Cloud resources with private clouds, the agility factor multiplies, which is consistent with the management of VMware Cloud on AWS or Microsoft Azure Stack.
The transformation brought great expectations.
Many experts agree that hybrid software defined data center (SDDC) will be the evolution of infrastructure of the next logical step, because it can create innovative cloud priority of products and services at the same time support the way of existing business applications.In Bitdefender's survey, the vast majority of IT executives expect their data center transformation to have a positive impact, making the business more flexible and reducing IT operating expenses.
As organizations use software defined technologies to transform their data centers, they also need to rethink how they ensure the security of IT infrastructure.Gartner, the company said security need to make their own software definition, this means that the organization needs to promote their security project, to support the increasingly dynamic and adaptive infrastructure, to ensure that the appropriate control automatically, regardless of the applications reside or the internal deployment in the cloud data center.
Stronger security is the main reason.
In this survey, 68.5 percent of respondents said that the main driver of the data center transformation was improved data protection.As dynamic workloads migrate between internal deployment data centers and the cloud, consistent security rules can be enforced while maintaining full visibility and end-to-end compliance reporting is imperative.In addition, the chief information security officer acknowledges that they need a security solution that helps to maximize value from software definition data centers, superfusion infrastructure, and hybrid cloud investments.
It is a good idea to use a security solution designed specifically for the infrastructure that runs it.For example, the security that is deployed to the physical machine on the virtual and cloud computing infrastructure causes unnecessary losses to CPU, memory, and other resources, and leads to application response latency.Instead, using a secure hybrid software definition data center (SDDC) will help maximize the utilization of infrastructure and application performance.
Security automation is realized through software definition data center, which can improve operation efficiency through automatic configuration and centralized control of all security functions.In addition, the security defense and control of the software definition data center can be adjusted when the system of its design protection changes.As the role of the virtual machine and the location of the cloud change, the security strategy will follow.As the new workload runs, appropriate security rules will automatically apply.
Solving these problems not only helps to effectively protect the modern infrastructure, but also helps to improve the operational and performance advantages of the hybrid software definition data center.

Can security keep pace with data center migration?

Data center migration, software defined data center (SDDC) and its forming technology (including the definition of virtualization, software, network, software defined storage) has become the basis of agile and efficient IT supporters.As software defined data center (SDDC) and a public Cloud infrastructure as a service (for example, apply to the AWS VMware Cloud), chief information officer from data center capacity, manageability, and disaster recovery Angle, taking advantage of the real integration of hybrid Cloud.

But can security keep up with data center transitions, such as software defining data centers and hybrid clouds?Traditional security usually by extract valuable resources from the production workload, introducing the application response latency and increase management complexity, thus affecting software defined data center (SDDC) infrastructure efficiency, performance and agility.In addition, such a solution may not be suitable for providing consistent and continuous protection for workloads migrating on a hybrid cloud.
The company's chief information officer must address security issues strategically, making it part of the data center's transformation strategy and roadmap.It is critical that companies choose solutions that protect hybrid cloud workloads while retaining the advantage of the software definition data center (SDDC) infrastructure.In this way, the chief information officer can be mixed in the cloud to maintain or improve its organizational safety state, and does not affect the operation efficiency, agility, and performance advantages, prompting decisions first invested in software defined data center (SDDC).
The data center that is defined by the hybrid software is happening.
It is an undeniable trend that enterprises are turning to software definition data centers.According to research firm IDC, global software definition spending rose 3.5 percent in 2016 from a year earlier to $4.32 billion.In 2016, the global software definition storage (SDS) market is $8.56 billion, and the compound annual growth rate (CAGR) is expected to be 13.5% over the next five years.In 2016, the market size of the software definition network (SDN) reached us $4.45 billion, with a compound annual growth rate of 25.4%.
About 90 percent of the chief information security officers said their data centers are undergoing major changes, according to a Bitdefender survey of 250 IT security policy makers in the United States.More than two-thirds of the user has stored a hybrid cloud data, and 64.8% of the users to use the software defined network, 62.8% of users rely on virtualization of the enterprise data, 57.2% of users use software defined storage, 35.6% of users use super integration infrastructure.
"Digital transformation" is driving the rise of software defined data center (SDDC), which describes the digital technology was applied to each organization's efforts, including the internal processes and profitable products.To succeed, companies are adopting software definition and hybrid cloud infrastructure, and quickly get rid of the three layers of hardware as the center of the traditional data centers, these data centres are often largely isolated, mainly composed of proprietary systems build, high cost of maintenance and management.The reality is that these systems are too slow and inflexible to provide resources at the speed the enterprise needs now.
The software definition data center (SDDC) provides greater efficiency and enables IT teams and development teams to meet the enterprise's digital transformation needs faster.When companies combine public Cloud resources with private clouds, the agility factor multiplies, which is consistent with the management of VMware Cloud on AWS or Microsoft Azure Stack.
The transformation brought great expectations.
Many experts agree that hybrid software defined data center (SDDC) will be the evolution of infrastructure of the next logical step, because it can create innovative cloud priority of products and services at the same time support the way of existing business applications.In Bitdefender's survey, the vast majority of IT executives expect their data center transformation to have a positive impact, making the business more flexible and reducing IT operating expenses.
As organizations use software defined technologies to transform their data centers, they also need to rethink how they ensure the security of IT infrastructure.Gartner, the company said security need to make their own software definition, this means that the organization needs to promote their security project, to support the increasingly dynamic and adaptive infrastructure, to ensure that the appropriate control automatically, regardless of the applications reside or the internal deployment in the cloud data center.
Stronger security is the main reason.
In this survey, 68.5 percent of respondents said that the main driver of the data center transformation was improved data protection.As dynamic workloads migrate between internal deployment data centers and the cloud, consistent security rules can be enforced while maintaining full visibility and end-to-end compliance reporting is imperative.In addition, the chief information security officer acknowledges that they need a security solution that helps to maximize value from software definition data centers, superfusion infrastructure, and hybrid cloud investments.
It is a good idea to use a security solution designed specifically for the infrastructure that runs it.For example, the security that is deployed to the physical machine on the virtual and cloud computing infrastructure causes unnecessary losses to CPU, memory, and other resources, and leads to application response latency.Instead, using a secure hybrid software definition data center (SDDC) will help maximize the utilization of infrastructure and application performance.
Security automation is realized through software definition data center, which can improve operation efficiency through automatic configuration and centralized control of all security functions.In addition, the security defense and control of the software definition data center can be adjusted when the system of its design protection changes.As the role of the virtual machine and the location of the cloud change, the security strategy will follow.As the new workload runs, appropriate security rules will automatically apply.
Solving these problems not only helps to effectively protect the modern infrastructure, but also helps to improve the operational and performance advantages of the hybrid software definition data center.

Data center migration,How to choose the construction site

Data center migration and project location are the starting points of project master plan layout. The location of the data center is determined by the company's development strategy, and the location decision should be made according to the TCO, and the short-term and long-term goals.

The location of data center is a geomantic omen. It pays attention to the harmonious co-existence of man and nature. Data center is not only a building inside the wall, but also a self integrated one. In order to avoid the natural geographical conditions, the natural geographical conditions should be taken into consideration, and it is necessary to take into account the local natural and geographical conditions, far from the frequent geological disasters, especially the seismic belts and debris flows, to avoid the typhoon invasion and flood, and to choose the land with relatively high altitude and flat terrain in the same area, and then through the geological exploration to understand the geological strip. A.
The data centers in the early years are generated around the network, where there are traffic, network resources, near the server, and the north is a typical business driven location.
Another kind is the Guangzhou Hangzhou Tianjin, they are around the huge city circle side of the sub center position, such as Hangzhou and Shanghai relations, more balance the business needs and resources. The above two categories are typical market drivers, and they are the most seller's market data centers.
The distance between the data center and the customer is also very critical. Some bank customers have a high demand for the network delay, so the distance of the data center has a great relationship with the customer's psychological expectation. We always want valuables - data near ourselves, and can see them easily, whether it's the data itself or the server cabinet that carries the data.
Now the size of the data center is getting bigger and bigger. We want to keep the scalability or sustainability of the data center, so electricity and water are very critical. The location of the data center is often restricted by the energy use index. Now the energy use index of Hangzhou is very tense. The Fuchun cloud is interconnected after solving the relevant indicators. The network data center has been able to settle in Fuyang.
Besides, we need to compare various power costs. That is to say, the cost of power sources per kilowatt hour is low enough to have alternative energy, such as renewable energy such as solar energy and wind energy, which will help enterprises to create a more green corporate image.
Ideally, the location of the project supports the development of big data industry, and the local government is responsible for solving the energy consumption index. To fully communicate before determining the land block, and to fully communicate with the local power bureau and the Water Service Company, whether the supply capacity is satisfied, and if the new facilities are built, the related path planning and policy handling should be considered. At the same time, we need to communicate with telecom operators (more than one) to make full use of network resources to ensure adequate and secure routing.
Local policy support is also very important. Land purchase preferences, supporting facilities, tax rebate and talent policy are all important factors for the location of enterprises.
Transportation convenience is also an important factor affecting the location of the data center, the construction and delivery of data center depends on whether the dependent suppliers can easily reach the location of the data center.
The choice of address for a data center naturally needs to be analyzed according to the specific circumstances of each enterprise.
General site selection steps:
1, scope of work and requirements: site selection requires wide consideration of stakeholder's opinions and requirements for location.
2, the first place for alternative locations is to examine and approve the alternative addresses according to the needs of all parties.
3, field investigation: invite the relevant expert team to visit the scene, talk with the government department of the location of the site, all kinds of service providers, and make a detailed summary of the meeting.
4. Further analysis of the list of alternative addresses: after a thorough investigation and analysis, a weighted scoring method is used to analyze the various factors in the first four ranking addresses.
5, further detailed investigation and analysis: discuss with the stakeholders in detail, view the actual data, research reports, and so on, fully consider all the factors mentioned in the previous article;
6, propose the alternative location for the final approval: release detailed investigation report, further analyze the relevant data, make further site selection, so as to obtain the final approval of the enterprise leadership.

The energy saving of data center migration should be taken from the root

Data center migration,"By 2040, China's demand for electricity will grow by 400%. This huge demand growth comes from the rapid urbanization process in China, so for China, and even the world, sustainable development and energy management are becoming very important."

Luo Shiguang, President of the Eaton Corp North Asia District, was described in the 13 day of the "City Forum on energy innovation and sustainable development". He said that in the world, the data center consumed 1% of the total electricity. But in China, the proportion has reached 5%, while China's data center is growing at an annual rate of 30%.
It is understood that in the global total energy consumption of IT, data center accounts for 40%. In 2011, the energy consumption of China's data center accounted for 5% of the total energy consumption in the country, which is 3 times that of the United States. The real energy consumers of data centers include infrastructure such as UPS, distribution system and refrigeration system. As the cost continues to rise, and the attention of the society to sustainable development is increasing, many enterprises are constantly seeking solutions that are economic and efficient, and can ensure the safe, reliable and normal operation of the information system.
At the same time, Eaton's new 9E series UPS (20-200kVA) also unveiled the Chinese market, providing new power management and solutions for medium data centers in communications, automation, security, radio and television and petrochemicals.
As a senior data center expert, Eaton electric energy quality business and general manager Zhang Guanghong said that the data center in the domestic development presents a very rapid trend, this rapid trend and more than 10 years ago, the conceptual, hype, different mainly based on two reasons, one is more than 40% of the data center, its operation time has already More than 5 years or more.
The most obvious change in IT is undoubtedly the emergence of virtualization and cloud computing in recent years, which means that there is a gap between the data center and the actual needs of the user, so the 40% data center will face a phase of update and transformation. Second, in order to adapt to virtualization and cloud computing, a large number of large-scale data centers will be launched in China. Together with these two factors, data center market will not fail. Zhang said the data center is a high-energy and high-density concentration industry. Under such circumstances, it is impacting on the original market resources. For example, in Beijing, it is difficult to build a data center with a scale, but the data center is not up to a certain scale, and the potential benefits are not due to the expected value.
In his view, the domestic real data center operation is more experienced in domestic big well-known operators, including China Telecom, China Unicom and so on, we know all the big ISP, network service providers, they are in fact relying on the data center outsourcing business of these big operators. According to his understanding, in terms of investment in data centers, the government is supporting on the one hand, but now it also wants to attract private capital to do data center operation. Zhang believes that for those hard to find ways to invest in private capital, it should be an opportunity now. The data center is showing a trend of polarization.
The first is that enterprises will use virtualization, modular, or extensible form, to build small data centers, which are more flexible, convenient and integrated. Another trend is the large-scale data center, often tens of thousands of flat meters, an independent building is a large data center, which is more convenient for resource planning, utilization, management, and reducing the cost of application. Zhang pointed out that small scale data centers and large scale data centers will develop in the next two to three years, and government policy guidance and broad demand from different types of customers will support the market development.

Intelligent management of data center migration

Data center migration and data is one of the most important commodities of today's enterprises. Whether enterprises are specialized in processing and selling or just using, data are all kings. A recent study by CB Richard Ellis showed that the data center market in Europe is still booming, and the data center capacity of enterprise leased to a new high.

But in order to meet the demand for data growth, the data center is having to use more servers, racks and hardware, which are increasingly difficult to monitor. The complexity of the dynamic environmental management of the people, electricity and assets of the data center is creating a huge data blind point, which means that the problem of inefficiency needs to be solved. And the problem is as big as a snowball. With the increasing application of the Internet of things in the 2018, more data is pouring in, and the traditional data center will be overwhelmed without proper planning.
Nowadays, the speed of data growth and the growth rate of business demand are undeniable facts. Intelligent monitoring and automation must meet the increasingly complex management requirements, so that we can achieve the required level in the foreseeable future.
If organizations are seeking new solutions, the first thing to do is plan. Better architecture can make network devices more flexible, programmable and flexible.
However, improper planning is a serious defect that must be avoided. Even if the organization takes appropriate solutions, it will be difficult for organizations to benefit from these solutions without appropriate strategies, which will eventually affect the organization's income.
Organizations need to develop an implementation plan that includes goals and expectations to identify the benefits of implementation and, more importantly, how solutions and frameworks can be used by site personnel.
Without that, new software and hardware will be installed, and engineers will have little knowledge of the real potential of these devices.
In addition, the direct result of more and more devices being added to the enterprise network is that the data center now deploys more frames to store these data, and the power density is higher than ever before, and also to run the required applications and services. It's a matter for the organization to ignore.
First, deploying more cabinets in the machine room will lead to a rise in the temperature of the data center environment, which may have a huge impact on the performance of IT devices. If not solved, it may lead to a breakdown of the IT device, and the IT staff can only try to save the core data.
However, if you have the ability to track the data of the whole center and understand its tiny position in the whole room, it will make the cooling more effective and make the data center work smoothly without the downtime.
Having this capability also means that data center managers do not have to search for the physical space to expand the computer room. By installing new and improved toolkits, data center managers can track data and see how to store data more effectively.
Without this vision, data center managers may need more budget, waste time and expenses to build new room space or install more rack.
Power interrupts and downtime in the data center will cause a lot of damage and impact on the profits of users and operators, such as the unexpected shutdown of Microsoft Azure's service for North European customers in 2017. If we do not learn from such an event, we will have a huge impact on the future revenue stream of data center operators. After all, if the user's trust is not available, the reputation of the operator will be very heavy.
It is time for organizations to protect themselves, using monitoring software to ensure that enterprises can not only maintain operation, meet their income needs, but also be able to combine with the latest increment in the space of the machine room, so as to prepare for the intelligent planning of the future service.
From a simple cost-benefit analysis, it is not worthwhile to rely on outdated, obsolete (usually artificial) solutions without implementing the DCIM solution. DCIM can realize intelligent real-time decision for monitoring, network and usage mode of the whole data center. In addition, the fault insurance mechanism can be introduced, which can use a custom alert creation form to obtain correct important information to the correct team or individual so that they take evasive measures to avoid future data interruptions. Taking precautions will bring some benefits.
DCIM can be a protective measure to reduce the growing burden of existing infrastructure, ensuring that the organization is as efficient as possible, and requires a single view of the data and performance issues in the data center. It is no longer an appended component, but an important part of data center of organization, saving capital and time and improving performance.

Data center migration requires a new architecture.

When data center migration involves high asset utilization and agility in data centers, there are several drivers: composability, extensibility, and openness.Composability means that companies can be hardware and specific types of workloads exact match, until the specific hardware components (e.g., CPU, memory, memory, FPGA, NVMe module, coprocessor, network connection, etc.).High scalability means that companies can use as much as possible according to need of components (even if scattered on the physical frame), also can run real-time collection of all sizes needed for the workload calculation ability.Openness means that companies can choose and integrate components that are best suited to their workload, without human compatibility issues.

Composite/decoupled infrastructure (CDI) is an architectural approach designed to provide refined hardware composability, high scalability, and open management application programming interfaces (apis).Composable/decoupling infrastructure definition with virtualization and software infrastructure (SDI) cooperation, through the calculation of overcome the fixed ratio, memory, storage, the limitation of accelerator servers and network resources, improve the efficiency and flexibility of data center.
Composite/decouple infrastructure (CDI) is a key part of the puzzle that meets the requirements of a large scale data center.So what are the challenges facing today's data centers that lead to the need for composite/decoupled infrastructure (CDI)?
The challenge for the data center.
Some trends that require dynamic hardware configuration include:
.Ultra-high-speed growth and large - scale edge of cloud computing and new calculation model of computing is driving rapid expansion of data center service provider, so that traditional deployment and management methods can not keep up with this development.
.High density - the demand for more computing and storage capacity means that the data center operators are trying to pass on the equipment, refrigeration, floor space, and to finish more computing power cost budget.
.New workloads - when it comes to new workloads, big data, the Internet of things, artificial intelligence, and other data centers are limited by the size of these workloads.In addition, over time, these applications often show significant changes in requirements and rapid growth.
.DevOps and microservices - in the past, most applications were static on a single machine.Compared to current applications, these applications are composed of physically dispersed, continuously upgraded, dynamically optimized, interconnected software components.Hardware must also be extensible.
New hardware technology and new applications have all kinds of support hardware - different types of processors, memory and connected devices, this makes any fixed "one size fits all" hardware has become inefficient and inflexible.
Now more and more data centers have been asked to run a bigger, more complex the workload, the workload is often different from each other, so they run hardware requirements may vary due to the workload, and even one hour in a day will change too.For example, some workloads may require more processing power or memory capacity.Some may require NVMe storage or dedicated processors.In addition, it is desirable to use high-end devices across multiple workloads at different times in order to reduce total cost of ownership.
How to determine if the data center is under pressure?
What are the substantive implications of these new challenges?How do organizations know if their data centers are affected by these challenges?Some real indicators of stress in the data center include:
O data center management is still complex and requires a great deal of technical staff.
O even if the average utilization rate of the virtualized environment is rarely more than 50%, the operating rate of the non-virtualized data center is around 20% to 30%.
O providing hardware for new applications still takes days or weeks and requires multiple experts to implement it.
The intelligent platform management interface (IPMI) has a 20-year history and is inherently limited due to its protocols and bit-level coding techniques.Data centers need a more scalable, secure, and internet-friendly management standard.
O interoperability between devices and management software from different vendors is often problematic, limiting functionality and programmability.
The oCPU upgrade usually requires the replacement of all the resources in the server box and server, as well as the replacement of storage devices, power, fans, and network adapters as soon as possible.
O application developers slow down due to current requirements, deployment, validation, and supply processes.
O response to unforeseeable changes in application capacity requirements is slow and labor intensive.
All these challenges are a common source: the distribution of data center operators cannot easily high particle size and mass of a specific hardware device, in order to meet the specific workload (either individually or as a group), because of the changing hardware requirements.
Virtualization and software definition infrastructure (SDI) limitations.
Virtual machines (VMS) allow multiple applications to run on the server, helping to better leverage the server's hardware, achieve rapid configuration and load balancing, and increase administrative automation.Container also provides many of these advantages, because it can make the application and its all depend on the option of packaged together, and dynamic deployment to the server in response to a change in the workload, which will further improve hardware utilization and flexibility.
In addition to computing server (including file servers, storage cluster and network switch), the definition of software infrastructure (SDI) has extended the concept of hardware abstraction, to cover other infrastructure elements, so that the whole data center infrastructure like software programmable, like operating environment and run applications that run on it.In addition, what the organization lacks is the ability to configure the elements in the server (that is, to assemble specific hardware resources on demand) anywhere in the data center.The composite decomposition infrastructure (CDI) provides these missing pieces.
Composite decomposition infrastructure (CDI) virtue.
In enabling combination decomposition infrastructure (CDI) in data center, each server of each calculation module, nonvolatile memory, accelerator, storage and so on all is broken into Shared resource pool, and therefore can be managed separately under software control.The decomposed components can be regrouped under software control, or as a workload optimized server, regardless of the physical presence of the components.Studies have shown that combination decomposition infrastructure (CDI) can achieve as much as 63% of TCO earnings (55% of capital expenditure, 75% of operating costs), the technical update saves 44% of capital expenditure and 77% of the workforce.
The results of these savings are:
O because of decomposition, common management apis and vendor interoperability can be expanded faster and easier,
O more flexible in application development, configuration, and lifecycle management,
O because of better resource utilization, lower overconfiguration and dynamic load adjustment,
O independent upgrade cycle (i.e., only need to replace the target resource, not the entire server)
O optimizes performance through custom configurations, including fast non-volatile memory (NVM) and accelerators.
O more automated infrastructure management and more efficient use of staff.
Facebook, Google and other major cloud computing service providers (CSP) are actively studying the breakdown structure of their data centers.Some of their implementation is the custom, and the vast majority of the use of proprietary software and API. In order to match the biggest cloud computing service provider (CSP), there is no such mass organization requires a combination of commercial off-the-shelf decomposition infrastructure (CDI) solution.The commonality of open technical standards will help the industry achieve scale and enable the composite decomposition infrastructure (CDI) to be generally available from vendor selection.
Open composite decomposition infrastructure (CDI) blueprint.
This is the goal of the Rack Scale Design, which is a blueprint for industry innovation centered around the generic component-based infrastructure (CDI) data center architecture.Intel RSD is an implementation specification for interoperability between hardware and software vendors.
Intel RSD defines the key aspects of the logical architecture to implement the composite decomposition infrastructure (CDI).The first is the design specification, which defines the hardware and software capabilities required for modules, racks, and data center levels to achieve the granularity composability of infrastructure and scalable software control.The second is a set of common open apis that expose these capabilities to higher-level programming software from multiple open source or commercial vendors.
These APIs are defined in Redfish, this is an open, extensible and safety standards, it is based on Web friendly principle (RESTful APIs, the JSON data model), modern open management framework to replace IPMI. Redfish is the distributed management task force (DMTF) extensible platform management BBS products, this BBS is Broadcom, Dell, Ericsson, hewlett-packard, Intel, Lenovo, Microsoft, Supermicro and VMWare industry plan released in September 2014.The Intel RSD extension is regularly submitted to Redfish's extensible platform to manage BBS as recommended in the official Redfish standard.

Data center migration,The path of evolution of object storage

Data center migration, the amount of data created every year is increasing exponentially. Almost every enterprise now relies on technology, and the information generated by these businesses can be said to have become their largest asset. Unstructured data is the best storage type, and its growth is the largest. So, how do we use object storage technology, and what can we expect it to bring?

What is object storage?
The development of object storage stems from the highly elastic demand for long-term storage of large amounts of structured data. Looking back on the past 20 granny, we have block storage (traditional storage) and NAS devices (usually as file servers). NAS does not really extend to the PB level, and it does not provide the resilience of long term data retention. In general, enterprises use tape (Tape) to meet the needs, but the tape is slow and inefficient.
The developed object store has developed into a mature technology for years by providing online access content to fill in the gap. Using erasure coding (EC) and other new protection methods, it usually solves the problem of data protection in large files.
Object storage uses Web based protocol to store and retrieve data. In essence, most of them provide four basic CRUD: create (Create), read (Read), update (Update), delete (Delete). In many cases, Update is just to match with Delete and Create. This means that the use of embedded data and associated metadata for HTTP to issue REST based API calls is relatively simple to interact with object storage.
This simple operation highlights the problem of object storage: the application needs to be re written to use object store, API. vendors help to complete the process by providing SDK, but need to change the application. This problem lets us see the first object of the evolution of the object storage: multiple protocol access.
Multi protocol object storage has been using multiple protocol access for some time to use the object storage back end as a large capacity pool in the form of gateway or additional software. The problem with this move is whether they really provide concurrent access to the same data from different protocol stacks. You can use NFS to store and retrieve objects, but what about using NFS to store and use Web based protocol access?
Why do enterprises want to have the ability to store one protocol and access through another protocol? Providing NFS means that an application can use object storage without modification. By providing concurrent Web based models, the analysis tool can access data without introducing NFS related performance problems, such as locking or multithreading impacting the same object. The typical value read configuration file of the analysis software means that data can be analyzed without affecting the main application.
Many Internet of things devices can be stored only through NFS, so incorporating such content into object storage means that file based protocols are essential.
One factor that extensibility affects an object storage application is the ability to shrink, not just extension. The initial capacity of many object storage solutions is hundreds of TB, which is not practical for smaller IT organizations. Vendors are beginning to solve this problem by producing products that can shrink to tens of megabytes.
Obviously, a large capacity hard disk and flash can be a problem, but it can achieve the functional advantages of the object storage. Therefore, the solution provided by the manufacturer is pure software, which can be deployed on special hardware, and can also be deployed as an internal deployment or virtual instance in public cloud.
With the continuous development of the Internet of things, data will explode. A large number of small object storage will prove to be able to meet the continuous demand of Internet of things.
Software definitions go back to pure software solutions, and the provision of pure software solutions means that enterprises can choose the right type of hardware for their environment. When hardware supply contracts already exist, enterprises can simply pay for object storage software and deploy them on existing devices, including testing old hardware that may be processed in other ways.
Another direction for the development of open source object storage software definition is open source, and Ceph is one of the storage platforms developed as an open source model. OpenIO provides a high level of server - free functionality that provides the same experience as a premium service. Another open source solution, Minio, recently won $20 million to push its platform to a wider audience, including the Docker container.
The attention of software in trial version means that it is easy for organizations to try object storage. In addition to IBM Cloud Storage and DDN, almost all suppliers provide some trial process by downloading software or using company's laboratory environment. Providing a trial version of the software can be open to the software for long-term evaluation and adoption.
In the future, we should consider the future of object storage. It can be said that the most recent development direction is to make the solution easier to use, and pay more attention to the development and usability of software and vendors. Multiple protocols connect more applications, making it easier for data to enter object storage. In the next few years, we will see that object storage is still an important platform for persistent data storage.

What are the steps of a data center migration?

When it comes to data center migration, which kind of person are you? Is it an early jump on the "train of clouds" or a backward person who has not tried to virtualized anything? Or are you still in the mainstream, using a mixed cloud and a number of systems on the ground?

In our data center migration practice, we find that each type faces its own challenge. Early adopters were unable to support their ambitious deployment and found weaknesses in the first generation of cloud systems. The backwardness may be aware of the necessity of transformation, but it is hindered by costs, resources and time. Most companies are still the mainstream, and they tend to adopt a hybrid IT strategy, but they are stranded on the management level and forward.
Depending on the position of the cloud in the cycle, you may be recalibrating or starting and optimizing. In any case, caution is a good idea. The modernization of the data center is a complex and large-scale process, and the following is the 7 step of migration:
1. assessment of infrastructure
The key first step is to update your configuration management database (CMDB) or any other system that tracks assets. Without that information, you can't know what your infrastructure includes and the challenges you are facing at the moment. For a real transition, you need 100% clear.
2. directory and map applications
With the development of time, the amount of business application business will be expanded. You may find 4 tracking tools and 2 box HR applications. Do you have anything else? Is it possible to reduce the cost of the merger? Which applications should be migrated to the cloud, which is not? In the migration plan, you must clearly plan the location of the application and which dependencies are not destroyed.
3. design and estimation
There is a need for time to check. For example, an enterprise begins to know only 40%, and will realize that its original plan is too much. Once you decide what to abandon, what to move and when to move (for example, whether to migrate low or high level applications first), there will be strategic design for the future. Adding the design to the ROI tool can estimate the cost and financial rewards for you.
How does the cloud age data center migrate? Here are 7 steps
4. establishment and verification
At this stage, POC can help you familiarise yourself with the future and increase your confidence in the team. In view of the daily work of the IT team, most of the smart organizations know that to achieve their goals, they need experienced and dedicated partners. They can take care of projects while managing strategy and daily operation. Otherwise, it is difficult to make major changes.
5. migration infrastructure
Whether you follow the disaster recovery (DR) failover strategy or see the cloud as a platform for building a new version of the application, you are now in "building". Some projects will be on the cloud, while others will remain on the physical infrastructure. Some are on the edge, the rest are local, and all are based on your special needs. Through cloudy and correct settings, the infrastructure can enter a new state.
6. detection and verification
Next is the performance test to prove that your application and system are lifting, and there is nothing wrong with running. The detection should include a high availability part and a failover during the maintenance window. At the same time, the test should depend on the application, budget, and specific goals, such as RPOs or RTOs., which should be verified by any normal work.
7. start operation
This final stage is not an afterthought, because the operation manual should be created throughout the process, and it is easy to operate with cost efficiency and reliability. However, once the daily instructions are finalized, you can start working in a new migration state.
If you are like most businesses, you have already put one foot into the cloud. Those who migrate applications and infrastructure to the cloud, far more than those of "all in" and shilly-shally early adopters.

Data center migration operation operate prompt

Data center migration, there is no doubt that for any mission critical data center processing enterprises, the most critical component is not the capacity of the data processing server or UPS battery type;It is to safeguard data center operation operation personnel life property security related measure.Usually, in the event of a fire, the smoke in the fire, rather than the flame itself, is often the greatest threat to the safe evacuation and survival of the threat.Therefore, when a fire, data center and in the relevant fire extinguishing system, setting the safety evacuation exit, fire protection facilities and fire alarm system is so far to reduce/avoid personnel within the building in the center of the data were injured or killed one of the most important way.

Building codes and data center may need put extra life safety equipment, or data center construction of the owner or operator may increase the life safety equipment, in order to increase security.Below, we will give you a brief overview of these measures.
Fire extinguishing system
Automatic fire extinguishing systems usually have four basic types: water-based wet, water-based dry, non-water-based wet and non-water-based dry.A water-based "wet" system is an ordinary pressurized water system running through an iron conveyance system;It usually runs on its own dedicated water supply line and is separated from other water supply lines in the data center building."Dry" system based on water is usually a loft for warehouse, parking lot, and the slot of power lines, and water through space, such as the heating position of water-based wet system, main remain vacant, but iron pipes to avoid freezing.These pipes are pressurized when activated.Due to water based system (wet and dry) is more effective than other systems, and usually cost is cheaper, so they are widely used frequently, but rarely is believed to be the best choice for data center computer room, because they can damage expensive servers and data can not be replaced.
Water - based systems are usually "wet" chemicals and "dry" chemicals."Wet" chemical systems (including foams and gels) are mainly used in commercial cigarette hoods to inhibit grease, oil and electrical fires;Because "wet" foam and gels damage printed files, cables and computer files, they are rarely used in other parts of the building.However, some of the "dry" chemical systems are usually designed to deliberately leave a sticky residue (to help put out the embers), it is good in some cases, it is certainly not for a data center server.Other dry chemical systems are not designed to leave lasting residue, so they are widely used as "cleaners".The national fire protection agency (NFPA) will this kind of cleaner is defined as "not conductive, volatile, or when the evaporation will not leave a residue in the form of gas fire extinguishing agent" - so many in the industry prefers to be used for data to the server room in the center of the fire extinguishing system.
Set safe exit
The setting of safe exit is to ensure that when a fire accident occurs in the data center building, the relevant staff can escape the safe escape route of the burning building as soon as possible.It often has a fireproof enclosure (including firewalls, fire staircases and fire floors/ceiling components);At the same time, these safe escape routes often use such guidance as reflective exit signs, flashing flashes and emergency lighting to indicate the direction of the escape route.These safe escape routes usually lead people to escape from the data center building to the open public Spaces, which also comply with the relevant legal definitions of public safety.
Of course, the data center's safe exit is more complicated than other buildings.Due to the data center are usually set has a long channel (usually 500-800 feet in length) and connect to export the stairs, and built a typical data center in the design of large channel need to pay special attention to, when its near data center server (rather than in the main channel at both ends, as a typical office building or hotel), it will need to set up their own export channels.In addition, the long channel of the data center needs to be exported, because large floor boards can easily exceed the distance between "public access" and "dead Angle".
Isolate the fire
In summary, fire prevention measures are used to prevent the spread of fire and smoke in the entire data center building by adopting a fire barrier at the main site.These fire barriers include: fire doors, fire prevention floor/ceiling components, open fire protection (fire fire shutter release and overhead door) and the firewall (the walls in the vast majority of the stairs, corridor walls, and many internal tenants to dividing walls, some walls and any two of interior wall of the building's most widely used).Through fire rating to maintain the integrity of fire protection layer is also very important (for example through sealed electrical pipes, electrical tray and plumbing pipe or provide automatic release on mechanical pipe and register fire damper valve).Also, through the adoption of smoke sealing barrier (provided around the internal fire door and window frame of the gasket, the internal fire door seal, seal belt between the drywall and sealant or smoke spray/wall and ceiling joint gap filling) to form a smoke barrier is also critical.
Because the owner of the data center and management researchers usually hope phased gradually adjust the structure of its internal decoration, this makes the data center of fire control is much more complicated than other building types.Most of the data center must online online as soon as possible, so the data center buildings are often built in stages: the first stage, its data center building construction permit and construction schedule, and then handed them to the subsequent stage of the construction team.During the design process, these early stages need to be taken into account in order to provide a complete and independent security export system.In addition, due to the rating data centers typically use plasterboard is connected to the floor or roof exposed underside (e.g., concrete floor or metal roof decorating plate), so need to pay special attention to the fire protection and smoke seal seams of walls and ceilings.
Data center is different from other types of building another point is that its internal installation of related equipment (especially their server racks and cable tray) occasionally experience requires relocation requirements, has already established that could damage the firebreak.When I visited the site of a data center site, I had seen rectangular openings through several established walls (all aligned with each other).Apparently, the cable tray of its servers had once crossed the wall and was removed.But these openings are left unsealed.At the scene of the other data center operations, on the other hand, during the visit, I found that through the established wall (especially the cable bracket or single line), do not seem to accord with the requirement of any tested fire penetration system.
Alarm system
The fire alarm system usually includes an electric bell or horn (and strobe light) connected to a fire and smoke sensor, and usually must be connected to the local fire department in the data center.These alarm system (usually requires the entire data center building there a bell or horn, and almost all of the contact area of the flash will be for the use of auditory handicaps) means that you can in the event of a fire is urged officials to evacuate as soon as possible, and then guide the personnel evacuation along the safest way to export.Data center and its complicated management system to ensure its operation need special operation staff's life safety, so the alarm will never connect to other alarm system, such as security and energy management system.
Further action
But in addition to the standard method to ensure the safety of life, the relevant building codes or regional government regulators may also require the use of other tools to ensure staff safety of life, or data center building owner or operator may use these tools to increase security.Here are a few examples.
Establish an ADA fire safety (two-way communication), it is called a refuge area, the area can for people with physical disabilities and unable to leave quickly provide shelter, so they can in the event of a disaster can temporarily located in safer environment, at the same time make a phone call and wait for help.
In the data center building, a safe evacuation plan is posted along the main exit passageway (especially near the exit staircase) to clearly mark "you are here!"And allow the relevant staff to review and understand the building evacuation routes prior to normal working hours and emergencies.
Set up high-level template to help avoid because during the daily maintenance of physical devices, and later the renovation during the construction period or in building a new stage of internal oversight, caused by the fire rating.
Post warning label specific room door, indicate which room (such as server room) should be specially protected by chemical fire extinguishing system, so as to encourage the relevant personnel to evacuate from the room, and won't see these rooms as fire control safety
Final act
The final measure is periodic inspection.In data center construction during the period of construction, especially in the building will be put into use and used with permission to sign, and before the presentation, project general contractor to deal with all potential factors influencing life safety personnel for preliminary examination.The work should at least be as follows:
At any stage of temporary storage building materials will not be blocking safe passage, and the safety of the public traffic channel availability (in a data center during the field trip, I actually saw a particular external export plywood was deliberately covered on the door, but exit sign above the door is still lit).
Confirm that the relevant reflective safety exit sign in the data center building is installed and visible along all exit paths (including in the large server room).
Small and visible signs are marked on all emergency lights (I find many manufacturers ignore such instructions).
Ensure that all area lights can be turned off to test for continuous emergency lighting.
Enable the internal smoke screen door test to ensure that its automatic pull-out function is normal (its operation is usually as simple as the flip switch to release its fuse wire).
Confirm that all fire doors are covered with smoke.
Ensure that the firewall is equipped with a smoke proof wall (wall duct tape and spray or sealant smoke sealant) and fire penetration device.
Confirmation standard orange plastic cap on sprinkler and smoke sensor (in most of the data center in the process of construction, has been installed, and regular maintenance to prevent damage and dusty) have been removed, I find it difficult to see in the server room cold channels, because they tend to be pipe, cable tray and wiring.
Verify fire rating marks on the doors and door frames are not painted (if paint the shave their want to paint or even find fire rating symbol is very difficult, especially when the door is equipped with only allow its only 15 seconds at a time when the alarm display).
Confirm the installation at the specified nonflammable any timber buildings (such as temporary walls, electric or telephone service plywood and roof mechanical platform) has no combustible label on (according to my experience, the paint label and use the standard combustible plywood often appear on the wood bolt).
During the design and construction, and then, using the above to ensure life safety precautions and procedures, to reduce the spread of fire and smoke, raise survival rate of the data center to protect data center is the most valuable assets: its internal operations staff safety operation.

How many optical modules do you want to use for a data center migration?

Data center migration and high-speed optical module market has been growing rapidly since the end of 2016. Its core driving force is the upgrading and new demand of overseas large-scale / super large data centers for 40G and 100G modules.

Optical module, as the core device to realize photoelectric conversion, is widely used in the data center. At the rate of more than 10G or more than 10 meters, the optical module, or the active optical cable AOC wrapped by multi-mode optical fiber and VCSEL optical module, is the only mature wiring scheme. High definition video, live broadcast, VR and other new applications promote the rapid growth of global network traffic. Cloud computing, IaaS services, big data and other emerging applications demand higher data center data transmission. Therefore, the data center needs not only continuous expansion, new construction, but also the continuous evolution of the network architecture to achieve non blocking network performance.
In the process of data center architecture evolution, resulting in new changes of optical module needs, we calculate the traditional three layer architecture, three layer architecture improved and new two tier structure analysis can be seen, with the development of network architecture, a single cabinet need light module configuration significantly increased.
1) the number of optical modules under the traditional three layer architecture is about 8.8 times the number of cabinet (8 40G light modules, 0.8 100G optical modules).
2) the number of optical modules under the improved three layer architecture is about 9.2 times the number of cabinet (8 40G optical modules, 1.2 100G optical modules).
3) two layer architecture of emerging optical module number about 44 or 48 times the number of cabinets (where 80-90% is the 10G optical module, configuration module of 8 40G or 4 100G module); from the high-end optical module needs to see, the overseas market due to the rapid development of cloud computing and other downstream applications, rapid development of firms self third party data center data center and cloud computing, network architecture to flat continuous evolution, produced strong demand for high-speed optical module. In contrast, the domestic market is still in the early stage of development due to the downstream applications, and the network traffic pressure and the data transmission demand of the data center are relatively low. Therefore, the domestic high-speed optical module market still needs to wait for the downstream applications to mature.
Data center flat is mainly used to solve data flow in Data Center (east-west). East-West data are mainly driven by cloud computing, cloud migration, IaaS virtual configuration, distributed computing, and big data (large data volume, storage and different servers). Overseas markets, such as AWS, Google and other cloud platforms, Salesforce and other professional platforms, as well as the rapid development of distributed computing and big data applications, push data center flat and generate strong demand for high-speed optical modules. In contrast, domestic downstream applications are still in the stage of market cultivation and business mode exploration. The domestic high-speed digital optical module market is expected to enter the explosive growth stage after its downstream application reaches maturity.

Data center migration, reasons for applying virtualization of data center

Data center migration, virtualization, and cloud computing technology are changing the pattern of computing technology. In order to make use of this wave of technology, enterprises need to virtualization existing physical servers, storage, network and other devices that constitute the current infrastructure.

If the enterprise is looking for ways to improve the physical data center, virtualization may provide the enterprise with the answer. People can get more information about the virtualization of the data center and understand the eight benefits of the virtualized data center.
1. speed up redeployment when one of the physical servers in the data center fails, redeployment time depends on a variety of factors. The enterprise needs the standby machine available and has the current effective image for restoring the server. Virtualization reduces these problems by using a virtual machine snapshot to redeploy the server, and does not require a downtime, which does not affect the user (ydotpub).
2. better backup, in addition to the traditional virtual server backup, can also create snapshots and backups of all virtual machines. A snapshot can be regularly implemented in a day so that the current image is deployed on other servers. The snapshot starts the machine faster than the backup, thereby minimizing the downtime.
3. a better test virtual environment provides a good test platform for new servers and applications. When the test is wrong, the snapshot can be quickly and simply restored to the older version. An enterprise can also easily create a test environment that is isolated from end-user access.
4. improving the disaster recovery of the current server and virtual machine snapshots can simplify the disaster recovery process. By including the backup (if it is a network addressing scheme of enterprise), enterprises can re create a data center in any virtual environment, even if the virtual machine hosting data center itself will failure and disaster, so companies need to obtain a more powerful disaster recovery capabilities, and ensure that business continues to run.
5. eliminating vendor locking with the emergence of new technologies brings possibilities for the abstraction of the inherent hardware and software in virtualization. The virtual environment of an enterprise can make full use of the flexibility of using new hardware or software platforms.
6. single - purpose server virtualization will not require multiple applications on a single physical server to reduce costs. Today, the e-mail, Web, and database servers of an enterprise can run on their own virtual servers. This will lead to more reliable function of the organization as a whole.
7. more easily migrated to cloud enterprises to use virtual machines instead of physical servers, making it a big step towards creating a complete cloud computing environment. Virtual machines can be used to create cloud based infrastructure and eventually be transferred to the cloud infrastructure. By using this virtualization technology, the enterprise can access all connected devices (ydotpub) at the cloud end.
8. environmental and economic benefits are virtualized, and enterprises can take advantage of the economies of scale provided by the data center and use fewer servers. This will greatly reduce the cost related to the use of cooling and electricity, reduce the carbon footprint, and make companies more attractive to environmental consumers. It can also reduce the cost of hardware. Together, these factors make virtualization a real cost saving measure and means for the enterprise.
Through all the advantages provided by virtualization, enterprises need to start migrating their data center business into virtual space. The first step in a good start is to use port virtualization technology. Enterprises may first want to virtualization several servers, but after recognizing these advantages, enterprises may be on the way of data center comprehensive virtualization.

What is the essence of a data center migration hyper fusion architecture?

Data center migration, we do not judge right and wrong, nor is to explore the real super fusion, but again check, think about why are now focused on super fusion, what kind of IT infrastructure more "suitable" in today's business.

First of all, the reason for choosing the superfusion architecture is that traditional storage cannot solve the problem of enterprise data center.
According to the McKinsey study, global IT data are increasing at a rate of 40% a year.Data is gradually affecting business, and enterprises make decisions and management through data analysis.
Alone, however, more and more faster and faster, auditing of the CPU is not enough, the bottleneck is that traditional storage disk is too slow, most computing capacity idle CPU or waiting to store data transmission to come over.Traditional storage capacity and performance do not have the scalability to match the "computing power", which can not meet the requirement of enterprise data access.
The problem is not new.Google has had this problem early.So how does GuGe do it?
As an enterprise that provides data retrieval to Internet users around the world, GuGe has considered EMC, IBM, and SUN storage products of that year, but it can't solve its problems.Neither the capacity nor the performance, the products of these companies can satisfy the scale demand of Google.So Google can only build a storage structure for its own data search.
Google excellent computer scientists, has broken the traditional thinking of storage using the server's local hard disk and software built a capacity and performance is scalable distributed file system, and built its search and analysis on the calculation of engine: don't have to remove the data from the store, and then through the network transmission to the computing side, but the operation on the distributed computing directly into the store, to transmit "computing" as a unit for transmission, such large amounts of data storage is local access, no longer need to across the network transmission, natural visit soon.As a result, naturally, "computing" and "storage" run (" fusion ") on a server, here we can see one of the strengths of the super fusion architecture is that local access to data, do not have to across a network.
The amount of data that modern enterprises bigger and bigger, more and more applications, they began to face problems when Google, cios must consider how to more efficient to build their own computing and storage infrastructure, to meet the demand of the application data access.
Virtual into easier management applications, it solves the problem of CPU, memory resources idle.But with the large-scale application of virtualization, virtual machines are becoming more and more, and virtual machines are running slower and slower on traditional storage."Slow" causes "poor experience" and "poor experience" becomes the biggest bottleneck restricting the application of virtualization.Here the nature is the most important reasons, the storage I/O performance is not enough, a large number of virtual machine and container running at the same time, the I/O hybrid, the random read/write a sharp increase in the structure of traditional storage can't afford a lot of random I/o. super fusion is precisely in order to solve this problem, was taken to the field of virtualization and container.At the same time, the industry also has different ways to solve the problem of I/O, we try to analyze the other solution: to solve method: do the Cache in a storage device adopts the SSD, accelerated I/o. this under certain scale may be effective, but the storage devices SSD Cache ratio is small, usually less than 5% of the capacity than the case, it is difficult to meet the user's thermal data Cache requirements.In addition, it is still impossible to expand on demand, and all data still flows out of the centralized storage controller, which is bound to block the "highway".
Solution 2: using the server side SSD Cache, accelerated I/o. a similar solution, usually lack the support of high reliability software on the server side Cache if used to write Cache, a single point of failure problem, need to be in more than one server Cache devices, do transcripts to provide reliability, can say this is a super gimped fusion architecture, the Cache on the server side, still use traditional storage, when the Cache is full, need to be written back to the traditional storage, is still the "controller" of traditional storage limit the overall performance.
We see, the above two solutions are limited by the structure of traditional storage, storage is not super fusion, through the completely get rid of traditional storage, distributed file system is used to provide the "limit" performance and capacity, on this basis, through the Cache to accelerate again, even all use flash memory (full flash memory products) to build is a natural, not be restricted.
Super fusion architecture, therefore, not for a single server storage quickly, but in order for each additional servers, storage performance is linear, so don't limit the storage structure of the operation of the enterprise business, and ensure the reliability of the business.
Because of this extensive sharing of storage, the whole Google business is running smoothly.What SMARTX is doing is a better, more stable base service.
In addition, the reason for the rapid development of superfusion in recent years is due to the hardware equipment.More and more number of CPU cores, the server's memory capacity is more and more big, the SSD equipment and Internet network equipment is more and more fast, which means: a. the server resources in addition to run the business, you can still set aside enough CPU and memory resources to run the storage software.Running the storage software and business together reduces the amount of equipment, reduces the power usage, and the local reading improves the access efficiency of I/O.This was not possible a few years ago, because CPU and memory were too limited.
B. interconnection network is more and more quickly, whether Wan Zhao, 40 gb Ethernet, or Infiniband (unlimited broadband technology), which makes the software we will separate storage devices for interconnection, the distributed file system the formation of a Shared storage pool, for the use of the upper application.
C. if the SSD to hardware manufacturers such as a single storage device to run faster, the meaning of our software is that more than a lot of these storage devices, work together to provide endless overall performance and capacity.

Data center migration, how to build a hyper fusion data center

Data center migration, superfusion system as the latest integrated data center product is successfully implementing the integration of infrastructure products.For many companies, superfusion represents the modernization of their data centers in a way that is accessible and affordable.

In this article, we will help you understand the relevant knowledge of building hyperfusion data center through the introduction of the main building trend of the virtual data center.It also gives you a clear idea of what companies are currently using a hyperfusion system and how to avoid being locked up by vendors.
The superfusion trend of building virtual data centers.
The trend of data center consolidation continues, and the pre-integrated fusion infrastructure is giving way to more tightly integrated superfusion products.The superfusion system brings simplicity to management and task integration, but they actually define the term "vendor lock-in".Therefore, enterprise data center managers need to understand the relevant basic knowledge of the superfusion system and how to work in a virtual environment.
What is superfusion?
Superfusion takes a modular approach to centralizing key IT system components into a box or system and managing the box or system through the software layer.The superfusion market is growing fast, with established suppliers and emerging start-ups competing aggressively to win customers.
Are superfusion and fusion infrastructure the same concept?
The main difference is that the components of grid software management constitute the superfusion infrastructure products.The fusion infrastructure is a bundle of components, and the superfusion iteration is not just a simple integration package, but a management console for all the included systems.Fusion systems are usually only includes storage and servers together, or increase the computation, but the initial fusion products are growing, now includes data deduplication, compression and other functions such as backup.
How does superfusion fit into the virtual data center?
A hyperfusion system usually inserts existing infrastructure to make integration easier.The virtual machine can be migrated to the fusion system and managed through the interface.The product either integrates with the enterprise's virtual platform or provides its own virtual platform.Many of the fusion products come from existing storage vendors and typically use flash storage to improve speed and performance.While this may sound expensive, superfusion eliminates the need for expensive storage area networks (SAN).
The superfusion system does not allow you to use existing storage and computing.However, VMware Inc. 's storage product: VSAN will be the key to solving the problem of integration in VMware environments.VSAN is actually a feature of the vSphere that converts existing hardware from an enterprise user into a hyperfusion setting.Other providers typically use storage functions as virtual storage devices or virtual machines running on the host.
About vendor lock-in.
Superfusion vendors are selling simple and hands-free data center management methods.But these systems are absolutely proprietary;When your enterprise purchases such a solution, this means that your enterprise will purchase a large number of infrastructure from the same vendor.Its supporters say the superfusion system is the future of IT, but opponents point out that IT makes no sense to buy more hardware in the traditional hardware IT environment.
While the trend towards convergence is simplistic, the boxes are not necessarily simple.Lack of control may apply to some IT teams, but not to systems engineers who enjoy hands-on hands-on work.
Which companies are using superfusion systems?
The superfusion system has come a long way in the IT companies seeking to simplify operational management.These are likely to be small companies that don't have the resources to manage multiple systems or to think that managing a virtual infrastructure is too complex.For example, a hyperfusion system can take on backup and DR tasks, while also providing high-end storage area networks (SAN) and network hardware.
In general, deploying VDI is ideal for superfusion systems;They can reduce the complexity and performance of storage technologies.
The superfusion system addresses storage and server issues.
The simplicity of the integrated data center product makes the superfusion system popular among small businesses.IT infrastructure vendors in spent more than a decade after sales to the IT enterprises independent servers and storage environment, are now beginning to take different strategies, the server and storage (in some cases, including network) to similar to lego modules.Its greatest benefit is that it can extend capacity and performance, and can be managed as a single system.
The superfusion infrastructure is the logical successor to the integration infrastructure, which is a data center component that has been pre-integrated and tested, such as VCE's Vblock or the FlexPod of NetApp.
"On a technical level, the fusion infrastructure can assemble the best components.If your business follows this approach, your business will find it works."Said Mike Matchett, an IT analyst at Taneja Group."Value is still important, it's more like a vendor's device, and you don't have to worry about patching and upgrading individual components."
These systems have their advantages, but many IT companies see this converged infrastructure as a packaged solution that does not actually address the challenges of the data center infrastructure.
Matchett says that through the integration of grid software, superfusion is further developed.It can automatically discover and add new nodes to the cluster and provide additional computing and storage resources by adding each new module.Many superfusion products also offer a level of storage service (in some cases, with flash memory and custom chip acceleration), as well as a single management interface.
Thus, "you can take advantage of the tight integration efficiency that traditional fusion infrastructure does not have."Matchett said.
Some new suppliers in the data center infrastructure market offer a range of superfusion products.Superfusion products such as Nutanix, SimpliVity and Scale Computing are rooted in storage and reconstitute their products as a comprehensive data center platform.
These systems are one of the only bright spots in the data center infrastructure market.Industry research firm IDC is bullish on the market for any type of so-called "integrated systems" (servers, storage, networks, and common management interfaces).
One-stop shopping
For small companies, the superfusion infrastructure represents a way to modernize their data centers in an accessible and affordable way.
A business services and consulting firm, Project Resources Group (PRG), based in La, Colorado, has launched a Project to replace independent tower servers for the first time and implement virtualization.Joshua Bailey, the IT manager in charge of procurement, was shocked by the prospect of moving from a physical server with a direct attached storage to a virtual server and a storage area network (SAN)."My company is the only one I'm an IT manager. SAN is not something I can manage."In particular, there is no time for proper VMware and SAN training.
This leads to the company considering super integration system, and finally decided to use the Scale Computing HC3. "HC3 fulfil all our points: rebuild their hot-swappable drives, automatically discover and gather your own node."Bailey said.In addition, he says, the system's management interface is so easy to use that he makes it possible to forgo formal training.The company purchased three HC3 nodes and a new switch platform for about $30,000.The HP server, storage and VMware virtualization offers that Bailey received were half as low.Part of the savings is because Scale is built on the open source KVM hypervisor.
Superfusion also applies to companies that have taken the virtualization path but still struggle with the cost and complexity of storage and data protection.
Dairylea Cooperative Inc., an agricultural marketing and services organization based in Syracuse, n.y., has implemented high virtualization, hosting about 120 server virtual machines and nearly 300 virtual desktops on nine VMware hosts.Last year, its IT team resolved a project to upgrade an unreliable backup process and add nonexistent disaster recovery capabilities.'Dairylea is in the middle of buying EMC Avamar and DataDomain to solve its backup problem,' explained Jeremy Wheeler, an innovation designer at Dairylea, adding that there is an iSCSI array that supports copying to a secondary site.
Then they demonstrated Simplivity's OmniCube.Wheeler found that the company could end backup and disaster recovery, and upgrade its servers and SAN infrastructure.The price of the SimpliVity product is the same as the price of the EMC backup solution.
After about six months of procurement cycle, the company decided to withdraw from EMC procurement.Wheeler started the Simplivity installation in mid-january and moved the company's entire virtual server field to a new cluster within three weeks by using VMware's storage migration feature.It took several weeks, but eventually the infrastructure of Dairylea was copied to the disaster recovery site. "suddenly, we had a consistent, off-site backup," Wheeler said.A 1.5 TB of file servers need to replicate the whole weekend in the past, you can now in a less than 60 seconds of time through the snapshot backup, and then use the OmniCube custom storage hardware acceleration at the scene to reproduce, and delete.
The last thing Wheeler plans to do is to move the VDI environment to the OmniCube cluster;He suspended the project until he could verify 40 daily backups and two years of repeated data deletion rates.At present, the repeated data deletion rate is close to 40:1.
'VDI is a popular use case for a hyperfusion platform,' says Mark Bowker, a senior analyst at corporate strategy group in milford, mass.
Not for all businesses.
But for all those who are not satisfied in the fusion system of enterprise customers, there is a lot of IT companies tend to build on existing infrastructure components, rather than buy proprietary hardware system.Emerging software definition storage products (such as Microsoft Windows Server 2012 storage space capabilities and VMware VSAN) have captured their interest.
VMware VSAN is a function of VMware vSphere, which "can transform your enterprise's x86 server platform into a storage platform.""Said Alberto Farronato, director of storage and usability products marketing at VMware.
Unlike products such as SimpliVity and Nutanix (or VMware's early virtual storage devices), VSAN itself runs within the vSphere kernel.The storage feature of Scale Computing HC3 also USES the custom block storage driver in the KVM hypervisor to pass through the kernel.Most other providers use their storage capabilities as virtual storage devices or virtual machines running on the host.
VMware says the kernel-based approach offers some performance advantages."VSAN provides highly optimized data paths."Farronato said."I/O is transmitted through the kernel and is no longer stored in storage devices."More importantly, the VSAN design allows it to be used on any hardware running the vSphere.
VSAN enterprise users are located in Massachusetts Cohasset software development and hosting providers Itrica company, over the years, the company has accumulated a large number of high-performance server equipment, but "still encounters the bottleneck of centralized storage architecture".Dave Sampson, executive vice President and chief technology officer at Itrica, said.The company considers fusion and superfusion products because they want better redundancy and higher scalability without too much CPU and RAM overhead, Sampson says.At the same time, "we want to make better use of our data center's existing footprint and maintain our existing HP server hardware."
So when the VSAN released the beta, Sampson knew, "that's what we want."It provides high I/O and availability and is displayed as another VMware storage volume.Its performance meets the needs of most Itrica customers, and the management interface is fully integrated with the rest of the VMware stack.The company is experimenting with most of the traditional storage hardware and will use the VSAN as the main storage platform for all of its workloads.
In fact, the arrival of VSAN has brought a big shock to the superfusion market, says ESG's Bowker, who expects to see more superfusion ideas starting to appear in existing suppliers.
"Why isn't VMware just using a VSAN on a VSAN to match some hardware?"A further put forward.In fact, there are rumours in the media that Project Mystic, a joint venture between VMware and EMC, the parent company, can do just that.
Similarly, Bowker won't be surprised to see a superfusion product from Microsoft, cisco or NetApp."It's hard to say we're not going in that direction.
When the server and network crash.
At present, most hyperfusion products solve the problem of data center storage, namely IOPS and continuous growth.But there are some emerging platforms that focus on combining computing with the web.Pluribus network company, for example, provides a platform, the platform will stand at the top of the computing and exchange fusion somewhere closer to the backbone network, for those who need than the existing architecture provides higher network performance and the application of visibility, the company's chief marketing officer, Dave Ginsburg said.The company's existing customers include TIBCO, which renamed the white box its next-generation messaging bus architecture and Lucera's financial infrastructure as the basis for its high-frequency trading services.Other use cases may include cloud business process scheduling and management, tier 4 to tier 7 devices or monitoring and analysis.