Main technical analysis of cloud storage

    Cloud storage is a new concept that extends and develops in the cloud computing concept, which means that a large number of different types of storage devices in the network can be assembled together through application software through cluster application, grid technology or Distributed File system. A system that provides data storage and business access functions together externally. When the core of cloud computing system operation and processing is large amount of data storage and management, cloud computing system needs to configure a large number of storage devices, then cloud computing system is transformed into a cloud storage system, so cloud storage is a data storage and management as the core cloud computing system.

Cloud Storage can be considered a cloud computing system configured with large storage space, compared to cloud computing systems. Cloud storage System has the following characteristics: Data security, super scalability, in accordance with the use of charges, can be used across different applications, automatic failover, easy to manage. Cloud storage is mainly used for backup, archiving, allocation and sharing collaboration in four major areas. The

Cloud storage System is a collection of multiple devices, multiple applications, and multiple services, and its implementation is premised on the development of a variety of technologies. According to the characteristics of cloud storage and its application fields, the main cloud storage technology involves storage virtualization, Distributed file system, cluster storage, storage centralized management, heterogeneous platform collaboration, automatic hierarchical storage, and of course, data deduplication and compression technology.

One, storage virtualization

Storage Virtualization (storagevirtualization) is the most popular understanding of the storage hardware resources for the abstraction of performance. Unify and provide a useful comprehensive functional service by integrating one or more target services or functions with other additional functions. Typical virtualization involves the complexity of shielding systems, adding or integrating new features, simulating, consolidating, or decomposing existing service functions. Virtualization is a function of one or more entities that are used to provide storage resources or services.

Storage Virtualization is a technology that runs through the entire IT environment and simplifies the underlying infrastructure that might otherwise be relatively complex. The idea of storage virtualization is to separate logical images of resources from physical storage, providing a simplified, seamless resource virtual view for systems and administrators.

for users, virtualized storage resources are like a huge "storage pool" where users do not see specific disks, tapes, or what path their data passes through to which particular storage device.

Two, Distributed File System

Hadoop Distributed File System (HDFS) is a distributed file system designed to be used on common hardware devices. It has much in the same place as the existing distributed file system, but it has a clearThe difference. HDFs is highly fault-tolerant and is designed to be deployed on inexpensive hardware. HDFS provides high throughput for application data and applies to large dataset applications. HDFs opens up some POSIX-required interfaces that allow streaming access to file system data. The

HDFs is a master/from structure. A cluster has a name node, which is the master control server, which manages the file System namespace and coordinates client access to the file. There is also a stack of data nodes, typically deployed on a physical node, responsible for storage management on the physical node where they reside. HDFs Open File system namespaces so that user data is stored in a file. Internally, a file is divided into one or more blocks of data that are stored in a set of data nodes. The name node performs the namespace operation of the file system, such as opening, closing, renaming a file or directory, and determining the data block's mapping from the data node. The data node is responsible for providing the customer with read and write requests. The data node also performs the creation, deletion and duplication of the data blocks according to the instruction of the name node.

Third, cluster storage

Cluster storage is the aggregation of storage space from multiple storage devices into a storage pool that provides a unified access interface and management interface to the application server, where applications can transparently access and utilize the disks on all storage devices. Can give full play to storage device performance and disk utilization. Data will be stored and read from multiple storage devices according to certain rules for higher concurrency access performance. The advantages of

Cluster storage are primarily in improving the overall performance of parallel or partitioned I/O, especially workflows, read-intensive, and large file access, reducing overall costs by adopting lower-cost servers. There are two ways to implement cluster storage: One is hardware infrastructure plus software, the other is dedicated cluster storage, built on the NAS infrastructure, but cluster storage is implemented through the operating system.

      IV, centralized storage management

Cloud storage management platform requires support for deployment and management across data centers, as well as support for user access scheduling, data migrations, and offsite data storage backups across data centers.

Support centralized management, cloud storage management platform deployed in the Cloud Computing center room, storage nodes can be deployed in the computer room, management platform for the points of the computer room storage equipment can be unified management scheduling.

through the cloud storage management platform, users can easily understand the various nodes of the cloud storage system services, including the capacity and performance of each node (read ioPS, write ioPS, read traffic, write traffic) and other information, so that users real-time understanding of resource information in the domain, running state, so you can manipulate these resources At the same time, timely understanding of the resource anomalies, if necessary, can take appropriate measures to ensure their normal operation.

Five, heterogeneous platform collaboration

The current storage scenarios and technologies are very complex and diverse, and light from a single enterprise may have a variety of different types of storage devices in the condition of one or two, not to mention the storage environment between the different storage equipment vendors have been a compatibility problem, So yelling for years of storage consolidation, still hard to be desired by enterprise requirements, is the biggest drag on storage virtualization and cloud storage.

While the storage cloud is easy to cross in one way (for example, online storage and backup), it seems not easy to achieve a comprehensive storage consolidation through private cloud storage on the other hand. In this context, the need to successfully complete the storage virtualization goals must improve the enterprise's existing IT storage environment, with improved focus on shared storage architectures, affinity environments, simple, single interface, and efficient storage solutions. Among them, whether it is a single operation interface or unified standard API, it is a key to solve the problem of coordination among different storage devices. The

Cdmi is a new standard interface for cloud storage, developed by the International Storage Network Industry Association SNIa. For cloud computing, CDMI provides a common cloud operations management infrastructure, while the focus of information management has gradually shifted from storage management to data management. The CDMI standard helps users to mark special interpretation data (Metadata) on the data, which tells the endpoint storage provider what data services provide that data (such as backup, archive, encryption, and so on). Through the implementation of the CDMI standard interface, users can move data between different cloud vendors and no longer need to endure the pain of recoding in different interfaces.

Six, automatic tiered storage

Improved storage management efficiency has become the primary problem for many enterprises, and automatic tiered storage is the most effective base technology, referring to the different disk types and RaiThe ability to migrate data blocks between D levels to meet the appropriate balance between performance and space use, quickly put data in place and avoid so-called hotspots.

is a widespread concern for this technology, and mobile data requires a fully automated migration process between different tiers of storage media, such as FC disks and SATA disks.

In a tiered data storage structure, storage devices typically have tape libraries, disks, or disk arrays, and disks can be grouped into FC disks, SCSI disks, SATA disks, and so on, while Flash storage media (NVRAM) Also because higher performance can be a higher level in the hierarchical data storage structure. In general, expensive, fast devices, such as disk or disk arrays, are used to store important information that is frequently accessed, while lower-cost storage resources such as tape libraries are used to store information that is less frequently accessed.

Seven, summary

Cloud storage, like cloud operations, must be provided with the selected allocation of storage resources over the network. Importantly, the network must have a good QoS mechanism. For the user, the flexible expansion and the use of flexible configuration of the demand for cloud storage, can save a lot of storage equipment procurement and management costs, and even the loss of storage equipment caused by the risk of losing data can be avoided. In summary, whether the endpoint user backs up data to the cloud, or the enterprise is based on regulatory compliance, or other purposes of data archiving and preservation, cloud storage can meet the different needs of all parties, all the development of cloud storage technology to ensure that this goal.