Cloud storage: Technology, platform, or service?

When it comes to cloud storage, the first thing to think about is Amazon, the Amazon that sold Books Online. COM pioneer. I don't know when Amazon has started selling storage services and has become a pioneer in cloud storage services.

Cloud storage is just around us





Amazon offers a service called the Flexible Computing Cloud (Amazon Ec2,amazon elastic Compute Cloud). With Amazon EC2, users can create machine images such as operating systems, applications, and configuration settings, and then upload them to the Amazon Simple storage service (Amazon S3,amazon Simplicity Storage Service) and register. Amazon EC2 can provide real-time increase and decrease, fewer than 1 virtual machines, more than 1000 units, in short, by Amazon to provide users with the computing power required, users according to their calculations and consumption of network resources to pay. As a result, the user's application of information is transformed into a way of buying services.





for Ec2,amazon has since launched a resilient block storage (ebs,elastic blocks Storage) product, while providing storage and computing capabilities. "We allow users to configure their capacity independently of the instance, from 1GB to 1TB," said Peter De Santis, general manager of Amazon's EC2. Initially, the EBS start price was 10 cents for connote months and 10 cents for every 1 million storage I/O request. It is understood that users can transfer EBS to Amazon's S3 storage service.





Amazon is just one of the vendors currently offering cloud storage services. IBM also launched a cloud storage service in April 2008 for business users with 2~3 Windows servers or small data centers. IBM Cloud Storage is a typical networked data storage service that stores data in numerous virtualized servers and provides third-party support and services. Through cloud storage, IBM provides remote data protection and mail management services to users.





has previously disclosed that Microsoft is also likely to release a web-based service that allows users to store, share and back up data via mobile phones, which are expected to be implemented on handsets running the Microsoft Windows Mobile 6 mobile operating system, and users will receive 200MB of free storage space, We can also see it as a service for cloud storage.





If these cloud storage services are still confined abroad, it is far from domestic consumers. In fact, there are already green shoots in cloud storage services around us. If you are interested, you can retrieve "networked storage" and you will see a lot of vendors offering services. For example, PSP players familiar with the "nano-disk", can be called the first real sense of support outside the chain of free high-capacity network hard disk.





free disk storage, users can access their own uploaded files anytime, or can share these files with friends. Many users use it to share photos with their friends because the nano-disk supports the picture's outer chain. It is reported that the nano-disk can support a single file size of 4GB. It uses a dedicated upload tool, called nano-robot. On the Internet, you can see a lot of such network hard disk services, such as 800Disk, mofile and Pig network, and so on, usually the service provider will promise free permanent storage, mass storage, and support the extension of breakpoint and other functions, some service providers also support the lack of client software requirements. These network hard disk services can be viewed as a personal-facing cloud storage service.





is not only the service provider in the cloud storage idea, in fact, computer manufacturers are also playing cloud storage idea. EMC acquired online backup service provider Mozy in 2007. In Europe, Mozy and Lenovo have a partnership to bundle Mozy software on their ThinkPad laptops, and users can automatically get online backup services provided by Mozy by buying ThinkPad laptops. EMC Greater China CEO Ye Chenghui has revealed that EMC will be the 2008 acquisition of another storage services company PI and Mozy into an independent company Decho, dedicated to providing online information management services, and is expected to continue to work with Lenovo to bring services to the Chinese market. This is also a cloud storage service.





Cloud storage Technology Architecture





Although cloud storage services are around us, as technical media, we still have to ask, how does cloud storage form? Technically, what are the differences and connections between storage virtualization, cluster storage, and San+nas? or to go to the cloud store to see its structure and composition.





so far, we have not had a chance to go to the data center of servers such as Amazon to understand its structure and composition. I believe that there will not be such a chance. It's like Wal-Mart, it's not going to tell you how its logistics is managed, because it's their trade secrets. But that doesn't prevent us from understanding the architecture of cloud storage.





to understand the architecture of cloud storage, first you need to be clear: what is cloud storage? "Cloud storage is not a device, it's a service, specifically, he's storing and accessing data as a service and delivering it to users over the network," says Zhu Bunzhi, director of the IBM Greater China Cloud Computing Center. Cloud computing is the ability to provide computing, and, correspondingly, cloud storage provides storage capabilities.





Zhu Bunzhi said, compared with the storage virtualization, or cluster storage, San+nas and so are a technology, there is no inevitable link between the two. But from an architectural perspective, cloud storage leverages existing storage technologies. For example, storage virtualization, cloud storage can use this technology to build a huge storage pool, shielding the underlying storage differences, so as to provide a consistent service externally.





from this perspective, cloud storage and no more technical breakthroughs, it is only better use of existing storage technology, better to play, the external provision of unified storage outsourcing services. Formally, similar to software SaaS services, the difference is the storage management and services provided by cloud storage. If this service is for individuals, such as the network hard drive mentioned earlier, the Microsoft Mobile 6 Mobile Web service, and EMC Mozy provide online backup services, they can be called personal-facing cloud storage services. Since the security requirements of individual users for storing data are not as high as enterprise-level user requirements and are less sensitive to issues such as leaks, the development of personal-oriented cloud storage services is faster.





In addition to the personal cloud storage services, there are enterprise-oriented cloud storage services, for enterprise-class cloud storage services, because the data related to the core competitiveness of enterprises, so the operators have high requirements, whether SLA (server level protocol), or data security, Operators are required to meet the requirements. At home, due to the lack of relevant legal provisions, as well as the lack of credibility of the whole society, enterprise-oriented cloud storage services there are many obstacles. However, these obstacles in the enterprise does not become a hindrance, with the development of economic globalization, the emergence of the global village, the world has become flat, then, through one or several centralized data centers for the enterprise branches to provide global unified standardization of support and services, this has become a trend. With cloud storage thinking, the cloud storage services within the enterprise will be full of business opportunities.

The idea of a

cloud storage is also being used by it vendors to market competition, such as HP's new financial Services--financial service, which promises that HP can price and buy products regardless of what brand of storage they are using now. And then provide storage services to users in the form of service leasing, and users only need to buy services on a monthly basis. This can effectively activate the user's assets. So why does HP dare to carry out such a service, according to the analysis of the industry, Hewlett-Packard is based on similar cloud storage services, through the use of existing storage technology, and make the necessary transformation, the relevant professional services staff can more effectively manage and utilize existing storage assets, to play greater benefits. The same product, the different management level, its effect is quite divergent. In the case of storage virtualization technology, although the technology has been more mature, but by various factors, many users are not able to use it well. But for specialized personnel, by storing virtualization, building a huge storage pool, you can maximize the capacity of existing storage products, and this does not require more investment.

The

Current cloud storage System Architecture model consists of 4 layers.

Storage Layer: It is the most basic part of cloud storage. Storage devices can be FC Fibre Channel storage devices, IP storage devices such as NAS and iSCSI, or DAS storage devices such as SCSI or SAS. Storage devices in cloud storage are often large and geographically diverse, connected to each other over a wide area network, the Internet, or FC Fibre Channel networks. The

storage device is a unified storage device management system that enables logical virtualization management of storage devices, Multilink redundancy management, and state monitoring and fault maintenance for hardware devices.

Base Management layer: It is the core part of cloud storage and the most difficult part of cloud storage. Through clustering, distributed file system and Grid computing, the basic management realizes the collaborative work among multiple storage devices in cloud storage, so that multiple storage devices can provide the same service externally, and provide greater and stronger data access performance. CDN Content distribution System, data encryption technology to ensure that the data in the cloud storage will not be accessed by unauthorized users, at the same time, through a variety of data backup and disaster-tolerant technology and measures to ensure that the data in the cloud storage will not be lost, to ensure the security and stability of the cloud storage.

Application Interface layer: The application interface layer is the most flexible part of cloud storage. Different cloud storage operating units can develop different application service interfaces and provide different application services according to the actual business type. such as video surveillance application platform, IPTV and video-on-demand application platform, network hard disk reference platform, remote data backup application platform.

Access layer: Any authorized user can log on to the cloud storage system through the standard public application interface and enjoy the cloud storage service. Cloud storage operates in different units, and cloud storage provides different types of access and means of access.

Although cloud storage has a four-tier structure, and some cutting-edge technologies are in the research and development phase, such as the Daoli Trusted infrastructure project announced by EMC, designed to provide a trusted cloud computing platform with virtualization and trusted computing, Enables isolation of a single host computer environment to be suitable for leasing to multiple users. To put it simply, the project is to solve the problem of cloud computing security.

But existing storage products and technologies are sufficient to support the enterprise's internal cloud storage service requirements. The EMC China Research and Development Center chief architect, Ningyuxiang, said in an interview that existing storage offerings, such as EMC's high-end storage offerings Symmetrix or mid-tier clariion, were built as storage tiers of cloud storage, without any technical problems. But if it is a public-facing cloud storage service, the cost is somewhat too high. To this end, he suggested, cloud storage should have several basic characteristics: first, large capacity. Cloud storageThe maximum storage capacity can be up to several PB. The second is low-cost, Google, for example, in order to reduce storage procurement and operational costs, their storage systems are often their own "save". Third, flexible expansion capabilities. He points out that cloud storage is the epitome of storage technology. Virtualization, data compression, duplicate data deletion, security, policy-based management are all the capabilities that cloud storage should have.

Several large cloud storage products

If you measure the cloud storage products with a few elements, such as high-capacity, low-cost, and flexible scalability, there are several outstanding products that should be brought to our attention. The

Atmos

Atmos is a cloud storage infrastructure solution released by EMC, which features automatic configuration, self-healing, and can scale to petabytes. It is understood that Atmos uses a policy-based management system that provides the ability to build different types of cloud storage, for example, it can create two copies of files for non-paying users and store them in different locations around the world and create 5~10 backups for paid users to store. and provides greater reliability and faster access to files throughout the world. In software systems, Atmos includes data services, such as replication, data compression, and data de-duplication, to obtain hundreds of TB of hard disk storage space through inexpensive standard x86 servers. EMC promises that it has the ability to automatically configure new storage space and adapt to hardware failures. Also allows users to manage and read using Web service protocols. Currently there are three versions of Atmos, with system capacity of 120TB, 240TB, and 360TB, all based on x86 servers and support gigabit or 10GbE Ethernet connections.

ExDS9100 (StorageWorks 9100 Extreme Data Storage) is a massive, scalable storage system for file content that combines HP PolyServe software, BladeSystem chassis and blade servers to improve performance, and also uses a storage called "block". These blocks contain 82 1TB SAS drives in the same container. The

ExDS9100 is designed to simplify PB-level data management, offering new business services to Web 2.0 and digital media companies, including picture sharing, streaming, video VOD, and social networking, bringing a lot of document-based data to fully meet immediate storage and management needs. At the same time can meet the oil and gas production, safety monitoring and genetic research and other large enterprises similar needs. The

ExDS9100 is a unified system with the following three main accessories:

Configured block: The energy-efficient HP BladeSystem chassis is equipped with blades to meet the needs of High-volume high-performance operations. The solution's basic features include four blades that can be extended to 16 blade configurations, each with up to 12.8 cores, with performance up to 3.2 GB per second.

Capacity Block: Basic configuration provides three high availability storage blocks and up to 246 TB of storage capacity. The maximum configuration supports up to 10 blocks of storage, providing 820 TB storage capacity.

Software: This system uses HP's file clustering technology to meet the stringent requirements of Web 2.0 and digital environments. To reduce the complexity and cost of the system, the application can run directly on the server module, removing unnecessary software layers. Through a single image management interface, users can easily manage more storage products and devices.

XIV

XIV is a new generation of storage products provided by IBM. It uses grid technology, which greatly improves the reliability of data, the scalability of capacity, and the manageability of the system.

XIV is an upgrade above traditional storage devices. It has a mass storage device + Large capacity file system + High throughput Internet Data access interface + Management system design features. XIV because of its unique design, so that it is born with a huge amount of storage capacity and strong scalability, to meet the needs of a variety of Web2.0 applications, is an ideal product to achieve cloud storage. The

XIV product, which has important functions such as IBM Information Management, protection, archiving, is a key component of IBM's information infrastructure and storage, and is a product of IBM's ability to redefine the concept of storage. "IBM Systems and Technology division of Greater China Product DepartmentDaniel Hou said. The

XIV structure combines the characteristics of midrange and high-end storage. When a user has a new business, or the data grows rapidly, and is able to anticipate a high rate of growth in the future and a complex data type, XIV is a reasonable choice for the user.

The virtualization technology built into the XIV storage system dramatically simplifies management and configuration tasks, and thin provisioning improves IT operations, provides almost unlimited snapshots, and instantly clones data volumes, dramatically increasing the speed of testing and accessing database operations. Its aim is to provide highly consistent performance by eliminating the full footprint of hotspots and system resources. IBM? The XIV storage System enables users to deploy reliable, multipurpose, and usable information infrastructures, while improving storage management, configuration, and improved asset utilization.