Read Disk Array Technology

Brief description of RAID level: RAID 0 reads and writes both disks. If one disk breaks down, all data is lost. Raid 1 is a write disk and one disk is used for backup. Raid 2, 3, 4 is not commonly used. RAID 5 and raid 6 are the most commonly used ones. RAID 5 allows a bad disk, but at least three disks are required, the size is the size of the N-1 (equivalent to a piece used to write verification information); raid 6 allows two bad disks, but at least four disks, capacity is N-2 (equivalent to two disk verification); 1. Introduction to raid Technical Specifications RAID technology mainly includes RAID 0 ~ Raid 7 and other specifications have different focuses. common specifications include:RAID 0:RAID 0 continuously splits data by bit or byte and reads/writes data on multiple disks in parallel. Therefore, RAID 0 has a high data transmission rate, but it does not have data redundancy, therefore, it cannot be regarded as a real raid structure. RAID 0 only improves performance and does not guarantee data reliability. However, failure of a disk affects all data. Therefore, RAID 0 cannot be used in scenarios with high data security requirements.Raid 1:It achieves data redundancy through disk data mirroring and generates data backed up by each other on a pair of Independent Disks. When raw data is busy, data can be directly copied from the image, so RAID 1 can improve read performance. Raid 1 is the most costly disk array, but provides high data security and availability. When a disk fails, the system can automatically switch to the image disk to read and write data without restructuring the invalid data.RAID 0 + 1:Also known as the raid 10 standard, it is actually a product that combines RAID 0 and RAID 1 standards, when data is continuously divided by bit or byte and multiple disks are read/written in parallel, the disk image is redundant for each disk. Its advantage is that it has both the extraordinary speed of RAID 0 and the high data reliability of RAID 1, but the CPU usage is also higher, and the disk utilization is relatively low. Raid 2: Data is distributed in blocks on different hard disks, measured in bytes or bits, and the average error correction code (Hamming Code) is used) "encoding technology to provide error detection and recovery. This encoding technology requires multiple disks to store inspection and recovery information, making raid 2 more complicated and therefore rarely used in commercial environments. RAID 3: similar to raid 2, RAID 3 blocks data on different hard disks. The difference is that raid 3 uses simple parity, use a single disk to store the parity information. If a disk is invalid, data can be re-generated on the parity disk and other data disks. If the parity disk is invalid, data usage will not be affected. RAID 3 provides a good transfer rate for a large amount of continuous data, but for random data, the parity disk will become the bottleneck of write operations. Raid 4: Raid 4 also blocks data and distributes the data on different disks. However, the disk unit is block or record. Raid 4 uses a disk as the parity disk. Each write operation requires access to the parity disk. In this case, the parity disk becomes the bottleneck for write operations. Therefore, raid 4 is rarely used in commercial environments. RAID 5: RAID 5 does not separately specify a parity disk. Instead, it accesses data and parity information across all disks. On RAID 5, read/write pointers can be performed on the array devices at the same time, providing higher data traffic. RAID 5 is more suitable for small data blocks and random read/write data. The main difference between RAID 3 and RAID 5 is that each data transmission of RAID 3 involves all array disks. For RAID 5, most data transmission only operates on one disk and can be performed in parallel. There is a "Write loss" in RAID 5, that is, each write operation will generate four actual read/write operations, two of which read the old data and parity information, write new data and parity information twice. Raid 6: Compared with RAID 5, raid 6 adds a second independent parity information block. Two independent parity systems use different algorithms, and the data reliability is very high. Even if the two disks are invalid at the same time, the data usage will not be affected. However, raid 6 needs to allocate more disk space to the parity check information, which has a greater "Write loss" compared with RAID 5. Therefore, the "Write Performance" is very poor. Poor performance and complex implementation methods make raid 6 rarely applied in practice. Raid 7: this is a new raid standard. It comes with an intelligent real-time operating system and a software tool for storage management. It can run completely independently of the host and does not occupy host CPU resources. Raid 7 can be viewed as a storage computer, which is significantly different from other raid standards. In addition to the above standards (such as table 1), we can combine multiple raid specifications like RAID 0 + 1 to build the required raid array, such as RAID 5 + 3 (RAID 53) it is a widely used array. Generally, you can flexibly configure disk arrays to obtain a more suitable disk storage system. At the beginning, the raid solution mainly targets the SCSI hard drive system, and the system cost is relatively high. In 1993, highpoint company launched the first IDE-RAID control chip, can use relatively cheap IDE hard disk to build a RAID system, thus greatly reducing the raid "threshold ". Since then, individual users have begun to pay attention to this technology, because hard disks are the most "slow" and least secure devices in modern personal computers, the data stored by users often far exceeds the computer's own price. When the cost is relatively small, RAID technology can enable individual users to enjoy doubled disk speed and higher data security, the IDE-RAID control chips on the PC market are mainly from highpoint and promise, and some are from AMI companies (such as table 2 ). IDE-RAID chips for individual users generally only support RAID 0, RAID 1 and RAID 0 + 1 (RAID 10) raid specifications, although they are technically incomparable with commercial systems, the speed improvement and security assurance provided by ordinary users are sufficient. With the continuous improvement of hard disk interface transmission rate, IDE-RAID chip is constantly updated, mainstream chip on the chip market has all supported the ATA 100 standard, highpoint's new HPT 372 chip and promise's latest pdc20276 chip can even support the ATA 133 standard IDE hard drive. In today's increasingly competitive motherboard manufacturers and increasingly demanding personal computer users, there are no fewer vendors that carry raid chips on the motherboard. users do not need to purchase raid cards, directly build your own disk array and feel the speed of the disk. the hardware control chip is used to implement ide raid. RAID 0 and RAID 1 are the most widely used in the raid family, after all, there are few individual users who are willing to use four or more hard disks to build RAID 0 + 1 or other hard disk arrays, therefore, we will only explain the two raid methods here. We choose to support the upgrade IDE-RAID motherboard KT7A-RAID function, step by step to introduce you to the installation of IDE-RAID. The upgraded KT7A-RAID integrates a highpoint 370 chip that supports RAID 0, 1, 0 + 1. Hard Disks are indispensable for raid. RAID 0 and RAID 1 have different requirements on disks. Raid 1 (mirror) Disk Images generally require the same capacity of two or more hard disks, RAID 0 (striping) disks generally do not have this requirement. Of course, it is ideal to choose hard disks with similar capacity and performance or even completely the same. To facilitate the test, we have selected two 60 GB hard drives (barracuda ata IV and st360021a ). The system selects duron MHz CPU, 2 x mb of gold cord SDRAM, and upgrades geforce2 pro graphics card. It should be said that it is a common configuration. We also hope to learn about the system requirements for raid construction. 1. To create RAID 0, first back up the data in the hard disk. Many users do not pay attention to backup, especially some careless individual users. Creating raid is a dangerous operation for data, and data on the entire hard disk may be destroyed without any worries. We first introduce RAID 0. This is especially true when creating RAID 0, all data on the disk in the array will be erased, including the hard disk partition table. Therefore, you must first prepare a Windows 98 boot disk with the fdisk and format commands. This step is also important. Step 2: Set the jumper of the two hard disks as the master, connect the ide3 and ide4 ports of the upgrade KT7A-RAID respectively (they are controlled by the highpoint370 chip on the motherboard ). Since RAID 0 will recreate the partition tables of two hard disks, we do not need to consider the order of Hard Disk connections (we will see below that this order is important when creating RAID 1 ). Step 3 configure the bios and enable the ata raid Controller. We enter the integrated peripherals option in the BIOS of the upgrade KT7A-RAID board and enable the ata100 raid ide controller. We recommend that you change the boot sequence to ATA 100 raid. Actually, we find that this is not feasible during system installation. Can a hard disk with no partitions be started? Therefore, we still set the soft drive as the preference. Step 4: The next step is to create the core content of RAID 0. We will introduce it in illustration: 1. after the system BIOS settings are complete, restart the computer and no hard disk will be reported during boot detection. 2. disk management will be taken over by the Highpoint 370 chip. 3. The following are critical highpoint 370 BIOS settings. On the Highpoint 370 disk scan page, press Ctrl and h at the same time ". 4. Go to the Highpoint 370 BIOS settings page and select "create raid" to create a raid. 5. select the raid mode in "array mode". Here we can see the options for RAID 0, RAID 1, RAID 0 + 1, and span, select RAID 0 here. 6. After the raid mode is selected, the system automatically exits from the top menu and selects "disk drivers". Generally, press enter directly. 7. The next setting is the unit size of the band. The default value is 64 KB. You can ignore this setting without special requirements. 8. next is the "Start create (start to create)" option. Before you press "Y", please think about whether there is any important data on the hard disk. This is your last chance! Once raid is created, all data on the hard disk is cleared. 9. After the boot disk is created, specify one. Press ESC to exit. Of course, Press Y to confirm. Highpoint 370 BIOS does not provide a function similar to "exit without save". After the modification is irreversible, step 5 restarts the computer again, we can see "striping (RAID 0)" on the screen) for array #0. Insert a previously created boot disk to start dos. Open the fdisk program. Why? Why is it visible on a hard disk? Yes, the raid array has been regarded as a hard disk. For the operating system, raid is completely transparent, so we don't have to worry about raid disk management. These are all done by the control chip. Next, partition by using the common single hard disk method. You will find that the "capacity" of this "hard disk is increased. Calculate carefully. Right, the total capacity is the total capacity of the two hard disks! We can compare RAID 0 reading and writing to a zipper, which separates data on two hard disks, reading data faster, and does not waste disk space. Do not forget to activate the primary partition After partitioning and formatting. Step 6: Selecting the operating system will bring us a lot of trouble. The highpoint370 chip provides drivers for windows98, NT, 2000, and XP. Considering that the raid function is intended for relatively advanced users, therefore, we chose the English version of Windows XP Professional, which provides better support for new hardware (the English version is used to facilitate the subsequent winmtr testing, and you can use the Chinese version of the operating system for raid ), windows 2000 is also a good choice, but the hardware support is obviously not as good as Windows XP Professional. Step 7 for a computer using raid, the operating system is installed differently from the normal situation. Let's take a look at the figure below, which is displayed after Windows XP completes the first step of "file copy" restart, the installer prompts "Press F6 to install a SCSI device or raid disk" in English. This process is very short, and users often ignore the prompts at the bottom of the screen. Press f6 and select "S". The raid control chip driver will be installed, and "enter" will not be installed. Press the "S" key to insert the raid chip drive disk. Press enter. The installer will automatically search for the program on the drive disk, select "WINXP", and press Enter. If the provided version is different from the built-in driver version of Windows XP Profesional, the installer will prompt you to choose. Press "S" to install the driver provided by the floppy disk and press "enter" to install the driver that comes with Windows XP Professional. Press "S" and then confirm. This time, press "enter" (this ...... Too much confirmation, huh, huh ). The next step is normal system installation, which is no different from normal installation. Here we will introduce the installation settings of RAID 0. Next we will talk about the installation of RAID 1. Compared with RAID 0, the installation process of RAID 1 is much simpler, and the installation process is non-destructive in the case of proper operations. 2. Although RAID 1 is completely different in principle from RAID 0, the installation and configuration process of RAID 1 is similar to RAID 0. The main difference lies in the settings in the Highpoint 370 BIOS. To avoid duplication, we will only focus on this part of settings: Go to highpoint 370 bios and select "create raid" to create: 1. click "array mode" and press Enter. In raid mode selection, select "Mirror (RAID 1) for data security (create an image for the data source disk )". 2. The next step is the selection of the source disk. We remind the user again: Be careful not to choose the wrong one. 3. Select the target disk, that is, the image disk or backup disk. 4. Start creating. 5. After the image is created, the BIOS will prompt you to create the image. This process is quite long. 6. It takes about 45 minutes to create a 60 GB image. Now RAID 1 is created. Raid 1 copies data from the primary disk to the image disk. Therefore, you must be careful when creating RAID 1. Do not mix the primary disk with the image disk. Otherwise, the results will be tragic. Raid 1 can be created on two non-data hard disks or a hard disk with an operating system installed, it is much more convenient than RAID 0 (except for the long image production process ). After the creation is complete, we try to unplug one of the hard disks. The highpoint370 BIOS gave a warning and pressed "ESC". The other hard disk took on the important task of the source disk, and all the data was intact. To add RAID 1 to a hard disk with an operating system installed, we recommend that you follow these steps: enable the control chip in the BIOS → start the operating system and install the Highpoint 370 driver → shut down and connect the source and image disks to ide3 and 4 → go to highpoint 370 BIOS to set RAID 1 (for the steps described above) → restart the system to complete the creation. We conducted a simple test on the two raid types. Although the test result of RAID 0 is confusing, it still feels much faster than a single hard disk in actual use, especially for Windows XP Professional, the startup is abnormal and the progress bar is flashing. As for the unstable transmission rate curve, we estimate there is some relationship with the Platform selection. After all, the integrated chip is very easy to interfere with such high data throughput. Even so, we can see that the data transmission rate of the RAID 0 system has reached a very high level, which was close to 60 Mb/s at a time. Compared with RAID 0, although the performance of RAID 1 is not significantly improved compared with a single disk system, we found that the operating curve of RAID 1 is very stable, rarely fluctuating. Check the disk test results in winbench99 2.0 at a glance. For users and operating systems, RAID 0 and 1 are transparent and do not affect any operations, just like using a hard disk. 3. Implementing raid using software methods apart from using raid cards or chips on the motherboard to implement disk arrays, we can directly use software to implement raid functions in some operating systems, for example, the raid function is built in Windows 2000/XP. Before learning about raid in Windows 2000/XP, let's take a look at Dynamic Disk management, a feature in Windows 2000. Compared with a basic disk, a dynamic disk no longer uses the previous partitioning method, but is called a volume set. Its role is actually the same as that of a partition, but it has the following differences: 1. you can change the disk capacity. Dynamic disks can change the disk capacity without restarting the computer without losing data, the basic disk will lose all the data if it needs to change the partition capacity (of course, some special disk tool software can change the partition without damaging the data, such as pqmagic ). 2. Restrictions on disk space dynamic disks can be expanded to non-sequential disk space in the disk. You can also create cross-disk volume sets to combine several disks into a large volume set. The basic disk partition must be the continuous space on the same disk. The maximum partition capacity is of course the disk capacity. 3. there is no limit on the number of volumes or partitions that a dynamic disk can create on a single disk. The relative basic disk can be divided into up to four partitions on a single disk, in addition, DOS or Windows 9x can only be divided into one primary partition and one extended partition. * Note that dynamic disks can only be used in Windows NT/2000/XP systems. Dynamic disks cannot be identified by other operating systems. Most users' disks are basic disk types. To use the software raid function, we must convert them to dynamic disks: Control Panel> Management Tools> Computer Management> disk management, in the View menu, switch one of the windows to the disk list. In this case, you can right-click the menu to convert the selected disk to a dynamic disk. When dividing dynamic volumes, you can see these types of dynamic volumes. 1. Simple volume: contains the disk space on a single disk, which is the same as the partition function. (When there are two or more dynamic disks in the system and there is no allocated space on both disks, we can choose the following two volume separation methods) 2. cross-zone volume: A Cross-zone volume combines unallocated space from multiple disks into one logical volume. 3. Strip volume: Combine multiple (2 to 32) disks with no allocated space to one volume. (If the two dynamic disks in the system share the same capacity, we will see another partitioning method.) 4. Image volume: two copies of a single volume are the same, and each copy is on one hard disk. Raid 1. When we have three or more dynamic disks, we can use RAID 5, a more complex raid method. In this case, a new form of volume splitting appears on the volume splitting interface. 5. RAID 5 volume: equivalent to a zone volume with parity, that is, RAID 5. For most PC users, building RAID 0 is the most economical and practical array form. Therefore, we will only explain the construction of software RAID 0 here: to use software RAID 0 in Windows 2000/XP, you must first convert the disk to be included in the array to the Dynamic Disk described above (note that, basic disks and dynamic disks cannot be converted in the default disk management interface of Windows 2000/XP. For details, refer to the description above). Here we try to use partitioning strip, this is exactly the difference between software raid and raid chips used to build disk arrays. We have selected a 29 GB partition to partition the with-area volume. When dividing the with-area volume area, the system will require a corresponding partition, that is to say, other dynamic disks must have the same 29gb or larger unallocated space. After the partition volume is allocated, the two volumes of the same size will be merged by the system, at this time, our formatting and other operations are also performed on both disks. After building RAID 0, we decided to test its hard disk transfer rate to determine the degree of Performance Improvement for this software raid. The platform for building software raid is different from the hardware raid platform in the previous article, to ensure CPU performance to ensure the implementation of our software raid, we adopt a high-end system: athlon XP 1700 +, Samsung 256 mb ddr memory, Asus A7V266-E motherboard, because software raid has low requirements on hard disk specifications, we have selected hard disks of different specifications for the hard disk system. We have two hard disks: Seagate fish IV 60 GB and Western data 1200bb 120gb. In the second half of the transmission curve, we can clearly see that the hard disk transfer rate of the software RAID 0 has reached 60 Mb/s, completely surpassing the transmission rate of any hard disk in the array, the advantage of RAID 0 began to be reflected. For users pursuing high performance, this should be what they dream. In Linux, we can also use raidtools to implement software raid. This tool can create a variety of disk arrays, such as soft RAID 0, RAID 1, raid 4, and RAID 5. Before using raidtools, you must first determine whether the Linux core currently in use supports Md. If you are using 2.0.x and are not compiled by yourself, soft RAID is supported in most cases. If you are not sure, You need to compile the core. Although raid can bring us a better speed experience and data security, it should be noted that most of the current market's cheap IDE-RAID solutions are essentially "semi-soft" raid, only raid control information is integrated into the raid chip, so the CPU usage is relatively high and the performance is not very stable. This is also the reason why the performance of software RAID 0 in high-end systems can sometimes exceed the "hardware" RAID 0 solution. For users, high-performance IDE-RAID storage systems, or the need for strong CPU computing capabilities, or more expensive RAID card, so disk arrays should still be considered relatively high-end applications. However, for novice users, it is also a good choice to use simple and inexpensive disk arrays to improve the availability of computer data or increase the storage speed. Of course, its performance is far from comparable to that of high-end systems. In short, we see more and more raid architecture in the market, especially in the low-end market, more and more popular cheap IDE-RAID solutions and hard disk prices continue to decline to take care of each other, it seems that the future trend of personal data storage is also predicted. Let's wait and see that highpoint 370 BIOS does not provide a function similar to "exit without save". After modification, it is irreversible.