RAID technology
The development of computer technology has entered the speed of the CPU into the GHz era. The computer's memory is also developed from 66MHz to 100 MHz or even 133MHz. The speed of the graphics is also a new month. Computer manufacturers have fully played a speedy war. As the most important external storage device of the computer, the hard disk is of course not glow, and the ATA66 and ATA100 hard drives have also been launched. Even so, the hard disk storage still can't get the role of the system performance bottleneck, even because other computer components are much more performance improvement, the hard disk speed is improved, but still falls into a more embarrassing situation. And because the hard disk speed is largely dependent on the mechanical part, based on the current hard disk technology, it is very difficult to speed up. Not only that, but the hard disk is stored in data security. Nowadays, people are now unable to get rid of the computer. This aspect makes people's work efficiency improvement, but potential dangers are also clear: Once the hard disk is damaged, people can be destroyed once. So, is there a technology based on the current hard drive to improve storage performance and data security? Yes, it is RAID technology. What is RAID? RAID is an abbreviation of English Redundant Array Of Independent Disks, translated into Chinese, is a separate disk redundant array, or an abbreviated disk array. Simply put, RAID is a hard disk group (physical hard disk) to form a hard disk group (logical hard disk) in different ways, providing higher storage performance and providing data redundancy than a single hard disk. The different ways of constituting the disk array become a RAID level (RAID Levels). The function of data redundancy is to use redundant information to restore the damaged data after the user data is damaged, and the damage data can be restored, thereby ensuring the security of the user data. In the user, the composed disk group is like a hard disk, and the user can partition, format it, and so on. In summary, the operation of the disk array is exactly the same as a single hard drive. Different, the storage performance of the disk array is much higher than a single hard drive, and data redundancy can be provided. Independent or INEXPENSIVE? Careful readers can notice that a part of the article explains RAID as Redundant Array of INEXPENSIVE Disks, ie inexpensive disk redundant array. So, is it independent or INEXPENSIVE? Speaking here, let's take a look at the history of RAID. In 1988, the David A. Patterson et al. In the University of California, David A. Patterson et al. Expanded on the original technology, proposing several new disk-test ways, with a number of cheap disks used in personal computers to replace data at the time The central system is widely used in the price of SINGLE LARGE EXPENSVE. Based on this purpose, David A. Patterson et al. First used the name of Redundant Array of INEXPENSIVE Disks. RAID has been proposed, causing great interest in people and successful. But with the development of storage technology, SLEDS disks have become the past. The magnetic disk that is generally widely used is similar to the price and performance, so if it is not suitable to consist of RAIDs if it is inexpensive. In order to adapt to the development of technology, the Commission began to interpret RAID as Redundant Array Of Independent Disks. RAID level: RAID technology has been developing, and now has a basic RAID level from RAID 0 to 6.
In addition, there are some combinations of basic RAID levels, such as RAID 10 (combination of RAID 0 and RAID 1), RAID 50 (combination of RAID 0 and RAID 5), and the like. Different RAID levels represent different storage performance, data security and storage costs. The following is a brief introduction to some of the most commonly used RAID levels. RAID 0: RAID 0 is also known as Stripe or Striping, which represents the highest storage performance in all RAID levels. The principle of RAID 0 improves storage performance is to disperse continuous data to access on multiple disks, so that the system has data requests to be executed in parallel with multiple disks, each disk performs the part of its own data request. The parallel operation on this data can take advantage of the bandwidth of the bus, significantly improve the overall access performance of the disk. Figure one
As shown in Figure 1: The I / O data request emitted by the system to three disk components (RADI 0 disk group) is converted to 3 operations, each of which corresponds to a physical hard disk. We can clearly see the data requests that are scattered by establishing RAID 0, the original order data request is transmitted simultaneously in all three hard drives. In theory, the parallel operation of the three hard drives has increased by three times the disk read and write speed in the same time. However, due to the influence of various factors such as bus bandwidth, the actual lifting rate will definitely be lower than the theoretical value, but a large amount of data parallel transmission and serial transmission are significantly unquestionable. The disadvantage of RAID 0 is that the data redundancy is not provided, so once the user data is corrupted, the damaged data will not be recovered. RAID 0 features features, particularly applicable to fields with high performance requirements, such as graphics workstations, etc. For individual users, RAID 0 is also an excellent choice for improving hard disk storage performance. RAID 1: RAID 1 is also known as mirror or mirroring, which is the purpose of maximizing the availability and removability of user data. The way RAID 1 is moderately copied to another hard disk with hundreds per percent of the user writes the user. as shown in picture 2:
Figure II
When reading data, the system reads data from the source disk of RAID 0. If the data is successfully read, the system does not depends on the backup disk; if the source disk data fails, the system is automatically turned to read. The data on the backup disk will not cause interruption of user work tasks. Of course, we should replace the damaged hard drive in time and re-establish the mirror with backup data, avoiding the backup discs cause irreparable data loss. Because of the hundred percent backup of the stored data, RAID 1 provides the highest data security in all RAID levels. Similarly, due to 100% of the data, the backup data accounts for half of the total storage space, so that the disk space utilization rate of mirror is low and the storage cost is high. Although Mirror cannot improve storage performance, due to its high data security, it is especially suitable for storage important data such as servers and database stores. RAID 0 1: As its name, RAID 0 1 is the combination of RAID 0 and RAID 1, also known as RAID 10. RAID 0 1 consisting of four disks as an example, its data storage method is shown in Figure 3:
Figure three
RAID 0 1 is a scheme that stores performance and data security. It also provides a storage performance similar to RAID 0 while providing data security as RAID 1. Since RAID 0 1 also provides data security by 100% backup of data, the disk space utilization rate of RAID 0 1 is the same as RAID 1, and the storage cost is high. The characteristics of RAID 0 1 make it particularly applicable to both large amounts of data require access, and also require strict data security requirements, such as banks, finance, commercial supermarkets, warehouses, and various archives management. RAID 5: RAID 5 is a storage solution for storage performance, data security, and storage costs. RAID 5 composed of four hard drives as an example, its data storage is shown in Figure 4: Figure 4
In the figure, P0 is the parity information of D0, D1, and D2, which is pushed in this class. As can be seen from the figure, the RAID 5 does not back up the stored data, but stores the data and the corresponding parity information to each disk constituting the RAID5, and the parity information and corresponding data are stored separately. Different disks. When a disk data of RAID5 occurs, the damaged data is restored by the remaining data and the corresponding parity information. RAID 5 can be understood as a compromise between RAID 0 and RAID 1. RAID 5 can provide data security for the system, but the degree of protection is lower than that of mirror and the disk space utilization rate is higher than Mirror. The RAID 5 has a data read speed similar to the RAID 0, just a parity information, and the speed of writing data is slightly slower than the single disk. At the same time, since multiple data corresponds to a parity check information, the disk space utilization rate of RAID 5 is higher than RAID 1, and the storage cost is relatively low. JBOD: JBOD (Just Bundle of Disks) can be "simple disk bundle", usually also known as SPAN. JBOD is not a standard RAID level. It is only proposed by some manufacturers in recent years and is widely used. SPAN consisting of three hard drives as an example, and its data storage is shown in Figure 5:
Figure 5
