Shulou(Shulou.com)06/02 Report--

Disk array technology can be divided into several levels of 0-5 RAID technology in detail, and a new level called RAID Level 10, 30, 50 has been developed. RAID is short for cheap redundant Array of disks (Redundant Array of Inexpensive Disk). To put it simply, the advantages of using RAID are: high security, high speed, and large data capacity.

Some levels of RAID technology can increase speed to 400% of the speed of a single hard drive. The disk array connects multiple hard drives to work together, which greatly improves the speed and improves the reliability of the hard disk system to a near error-free level. These "fault-tolerant" systems are extremely fast and reliable.

.

From the disk array point of view

The most important specification of the disk array is speed, that is, the type of CPU. We know that the evolution of SCSI is from SCSI 2 (Narrow, 8 bits, 10MB/s), SCSI 3 (Wide, 16bits, 20MB/s), Ultra Wide (16bits, 40MB/s), Ultra 2 (Ultra Ultra Wide, 80MB/s), Ultra 3 (Ultra Ultra Ultra Wide, 160MB/s), from SCSI to Serial I and O That is, the so-called Fibre Channel (FC-AL, Fibre Channel-Arbitration Loop, 100-200MB/s), SSA (Serial Storage Architecture, 80,160 MB/s), in the past, when using the disk array of Ultra Wide SCSI and 40MB/s, the requirement of CPU is not too fast, because SCSI itself is not very fast, but when SCSI evolves to Ultra 2, 80MB/s, the requirement of CPU is very critical. General CPU, such as 586, must be changed to high-speed RISC CPU, such as Intel RISC CPU, i960RD 32bits, i960RN 64 bits), not only RISC CPU, but even 32bits, 64 bits RISC CPU differences. The difference between 586 and RISC CPU can be imagined! This is seen from the point of view of disk arrays.

.

From the server's point of view

The structure of _ server has changed from the traditional Intelligent O structure to the I2O (I2O) structure. The purpose is to reduce the CPU burden of the server and separate the CPU load of the system from that of the server. Therefore, Intel proposes the framework of I2O, and I2O is also managed by a RISC CPU (i960RD or I960RN). Just imagine if RISC i960 CPU is in charge of Imax O in the server, but 586 CPU is still used on the disk array, will it be faster?

.

From the operating system's point of view

SCO OpenServer 5.0 32 bits

MicroSoft Windows NT 32 bits

SCO Unixware 7.x 64 bits

MicroSoft Windows NT 2000 32 bit 64 bits

SUN Solaris 64 bits. .. Other operating systems

When the operating system has been transferred from 32 bits to 64 bits, the CPU on the disk array must be Intel i960 RISC CPU to meet the speed requirements. 586 CPU is insatiable!

.

Function of disk array

-- is the connection of the hard disk in the disk array connected by the overall backplane of SCA-II or just by SCSI cable? Whether there is an isolation chip on the overall backplane of the SCA-II to prevent the high / low voltage generated by the hard disk during hot plug, causing the system voltage to flow back, resulting in system instability and data loss. We must pay attention to this problem, because many hard drives in the disk array share the same SCSI bus.

One hard drive is hot-swappable, but it can't affect other hard drives! Is it either hot-swappable or live plug-in? Hard disk has hot-swappable hard disk, 80-pin hard disk is hot-swappable hard disk, 68-pin hard disk is not hot-swappable hard disk, the difference in circuit design lies in whether there is a protective circuit design, the same hard disk trailer is also the difference between real hot-swappable and fake hot-swappable.

Is there a sequential requirement for the hard drives in the disk array? In other words, can the hard disk be inserted back into the array out of order, and the data can still be accessed normally? Many people think that it is not very important and unlikely to happen, but if it may happen, we have to prevent it from happening. If you use six hard drives as an array, at the end of initialization, the six hard drives are placed sequentially in the disk array, divided into the first and second … To the sixth hard drive, there is an order.

-- if the disk array you buy is ordered, you should be careful: one day you take out the hard disk and insert it back into the disk array in the original order when you clean it. Otherwise, your data may be lost because the order of the hard disk is different from the original, and the controller on the disk array does not recognize it. Because the SCSI ID number of your hard drive is out of order. Today's disk array products already have this function that does not require the order of the hard disk. In order to prevent the occurrence of the above events, the order of the hard disk is not required.

We will discuss these new technologies, as well as the advantages and disadvantages of different levels of RAID. We don't want to get into the key technical details, but instead introduce disk arrays and RAID technologies to people who are not yet familiar with them. I believe this will help you choose the right RAID technology.

.

Hard disk data cross-disk (Spanning)

Data cross-disk technology makes multiple hard disks work like one hard disk, which enables users to break through the existing hard disk space restrictions cheaply by combining existing resources or adding some resources.

Four 300 megabyte hard drives are linked together to form a SCSI system. Users only see a C disk with 1200 megabytes, not C, D, E, F, four 300 megabyte hard drives. In such an environment, the system administrator does not have to worry about the lack of hard disk security check space on a hard disk. Because now 1200 megabytes of capacity is all on one volume (Volume) (for example, on hard disk C). The system administrator can safely build any level of file system needed without having to plan his file system under the limitations of multiple separate hard disk environments.

Hard disk data cross-disk itself is not a RAID, it can not improve the hard disk * and speed. But it has the advantage that multiple small, inexpensive hard drives can be added to the hard subsystem as needed.

.

Disk array classification

-- hard disk segmentation (Disk Striping, RAID 0)

The method of hard disk segmentation writes data to multiple hard disks instead of just one disk, which is also called RAID O. In disk array subsystems, data is written to multiple hard disks in turn according to the "Segment" specified by the system, for example, segment 1 is written to hard disk 0, segment 2 is written to hard disk 1, segment 3 is written to hard disk 2, and so on. When the data is written to the last hard disk, it starts writing again from the next available segment of disk 0, and the whole process of writing data is repeated here until the data is finished.

Segments are made up of blocks, which in turn are made up of bytes. Therefore, when the size of the segment is 4 blocks and the block consists of 256bytes, the size of the segment is equal to 1024 bytes in terms of byte size. 1 ~ 1024 bytes are written to disk 0, 1025 ~ 2048 bytes to disk 1, etc. If our hard subsystem has five hard drives, we have to write 20000 bytes

In short, because the method of hard disk segmentation is to write (read) data to multiple hard disks immediately, it is relatively fast. In fact, the transmission of data is sequential, but multiple read (or write) operations can overlap each other. That is to say, when segment 1 is written to drive 0, the operation for segment 2 to write to drive 1 also begins; while segment 2 is still writing disk drive 1, segment 3 data has been sent to drive 2; and so on, there are several disks (if not all disks) writing data at the same time. Because the data is fed into the disk drive much faster than it is written to the physical disk. Therefore, as long as the control software is compiled according to this characteristic, the operation of writing the above data at the same time can be realized.

Unfortunately, RAID 0 does not provide redundant data, which is very dangerous. Because the calculator must ensure that the entire hard disk subsystem works properly, for example, if a file segment 1 (in drive 0), segment 2 (in drive 1), segment 3 (in drive 2), then as long as there is a failure in drive 0,1,2, it will cause a problem; if drive 1 fails, we can only physically obtain segment 1 and segment 3 data from the drive. Fortunately, a solution can be found, which is hard disk segmentation and data redundancy.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.