What Is Data Store?
Data storage objects include temporary files generated by the data stream during processing or information that needs to be found during processing. Data is recorded in a format on the computer's internal or external storage media. The data store should be named, and this name should reflect the composition and meaning of the information characteristics. The data flow reflects the data flowing in the system, showing the characteristics of dynamic data; the data storage reflects the static data in the system, showing the characteristics of static data.
- Disks and tapes are common storage media. The organization of data storage varies depending on the storage medium. Data on tape only
- Sometimes a forklift-type upgrade of the system is needed, but a little scrutiny during the procurement process can avoid the price traps that may be encountered in storage procurement.
- The heterogeneity of data center data storage architectures and controllers is a major obstacle to standardizing infrastructure to support different workloads.
For all wishes and goals, the core of the data storage system is productization. However, in the battle to achieve the interoperability of data storage arrays from different vendors, there are still differences at different levels.
Distributed computing means that data center data storage must interoperate with servers from different vendors, which increases the requirements for data storage architecture standardization, and cloud computing promotes greater progress in standardization.
Data storage data storage management
- Data center storage capacity management has always relied on a relatively constant basic data storage technology: traditional mechanical hard drives. There are only a few manufacturers of mechanical hard drives-Western Digital and Seagate, and Hitachi and Toshiba-hard drives are essentially a commodity.
The problem needs to be solved by implementing different brands of arrays and controllers to work together. Some companies have purchased high-end, expensive storage, such as EMC's Symmetrix VMAX, and want to manage the entire data storage with a single toolset. However, the operation of the disk array is controlled by dedicated software and data storage in the array controller, which is problematic for creating a fully functional data storage management tool.
Data storage vendors-IBM has a SAN Volume Controller, EMC uses VPLEX, and Hitachi Data Systems, HP and NetApp of Hitachi are touting their own proprietary data storage management tools, claiming that they can implement a virtualized storage architecture. Integration. However, these tools basically only support their own data storage systems, and in most cases, they only target some products. End-users end up on the road to finding true data storage and highly functional heterogeneous data storage management tools.
Cloud computing is changing our view of data storage. Workloads are becoming more mixed, and data storage needs to manage objects, files, and block patterns based on different I / O requirements. However, to support cloud architecture, the data storage infrastructure must be viewed as a single pool of resources, and organizations need to be able to automate changes to workloads. This is possible only by providing highly standardized data storage tools. This initiative has begun, but there is still a long way to go.
Data storage flash data storage rescue
- Standardized data center data storage capacity is difficult to create solely from disk storage. Media relies on the interaction of disk platters. Read / write stabs require mediation by intelligent disk controllers to manage the needs of different workloads.
The data management method of flash data storage is different from hard disk. Flash data storage is a direct access storage architecture; there is no need to search for the correct disk area through the head to retrieve data, so there is no delay. The speed of data storage management means that flash can be applied to different workload types on the same array. It is also more unified to virtualize data storage products from different vendors.
In the end, standardized data storage can be a real commitment, not just the focus of talk-but it's far away.
Data storage vendors still have many different ways to market and deploy flash. Many established data storage vendors sell in a hybrid way: adding a separate layer of flash memory in front of the disk array. Problems can arise when workloads require data stores that are not in this flash tier because the controller needs to pull these data stores from the hard disk. This makes some data storage operations slower than pure hard disk arrays.
A necessary step to maximize the investment in data storage capacity of existing data centers is to cascade all-flash and disk array systems. Nonetheless, these existing traditional arrays can become troublemakers when building a single management layer. EMC ViPR data storage virtualization products have demonstrated their commitment to provide greater control over hybrid data storage architectures.
All-flash arrays are tied together in a fierce competition for hybrid data storage. Flash data storage such as Pure Storage, Violin Memory, and Nimble Storage provide intelligent software to minimize data storage volumes and provide an advanced data storage management system to manage the entire virtualized environment.
Data storage data storage system fusion
- When converged infrastructure (CI) systems encountered cloud data storage management, they were a little mixed up.
Nutanix-a supplier that started with data storage space, provides super CI platform services, including advanced data storage management software. IBM's PureFlex system and PureData system, Dell's PowerEdge FX2 system, HP's Converged Infrastructure, and other data storage products also provide various methods to integrate direct-attached data storage and CI systems, not only existing arrays or new arrays Both are stepping up their integration with CI.
There is another trick that can improve the speed of server-side data storage connection, such as flash data storage of PCIe interface. IBM has developed a method for internal connection of its own system that can further speed up data storage. This CAPI connector once again poses a proprietary problem-it will depend on whether IBM will enable the connector to maintain a high level of unified collaboration with other vendors' data storage systems. Converged systems must still pool resources for sharing and utilization. This will require more advanced data storage tools to support than we can see. [4]