disk structure and multiple RAID levels .ppt
- 1. Disks are potential bottlenecks for system performance and storage system reliability. Even though disk performance has been improving continuously, microprocessor performance has advanced much more rapidly. The performance of microprocessors has improved at about 50 percent or more per year, but disk access times have improved at a rate of about 10 percent per year and disk transfer rates at a rate of about 20percent per year. In addition, since disks contain mechanical elements, they have much higher failure rates than electronic parts of a computer system. If a disk fails, all the data stored on it is lost. A disk array is an arrangement of several disks, organized so as to increase performance and improve reliability of the resulting storage system. Performance is increased through data striping. Data striping distributes data over several disks to give the impression of having a single large, very fast disk. Reliability is improved through redundancy. Instead of having a single copy of the data, redundant information is maintained. The redundant information is carefully organized so that in case of a disk failure, it can be used to reconstruct the contents of the failed disk.
- 2. Disk arrays that implement a combination of data striping and redundancy are called redundant arrays of independent disks, or in short, RAID.1 Several RAID organizations, referred to as RAID levels, have been proposed. Each RAID level represents a different trade-off between reliability and performance. In the remainder of this section, we will first discuss data striping and redundancy and then introduce the RAID levels that have become industry standards. While having more disks increases storage system performance, it also lowers overall storage system reliability. Assume that the mean-time-to-failure, or MTTF, of a single disk is 50; 000 hours (about 5:7 years). Then, the MTTF of an array of 100 disks is only 50; 000=100 = 500 hours or about 21 days, assuming that failures occur independently and that the failure probability of a disk does not change overtime. (Actually, disks have a higher failure probability early and late in their lifetimes. Early failures are often due to un detected manufacturing defects; late failures occur Reliability of a disk array can be increased by storing redundant information. If a disk failure occurs, the redundant information is used to re construct the data on the failed disk.
- 3. Redundancy can immensely increase the MTTF of a disk array. When incorporating redundancy into a disk array design, we have to make two choices. First, we have to decide where to store the redundant information. We can either store the redundant information on a small number of check disks or we can distribute the redundant information uniformly over all disks. The second choice we have to make is how to compute the redundant information .Most disk arrays store parity information: In the parity scheme, an extra check disk contains information that can be used to recover from failure of any one disk in the array. Assume that we have a disk array with D disks and consider the first bit on each data disk. Suppose that i of the D data bits are one. The first bit on the check disk is set to one if i is odd, otherwise it is set to zero. This bit on the check disk is called the parity of the data bits. The check disk contains parity information for each set of corresponding D data bits.In a RAID system, the disk array is partitioned into reliability groups, where a reliability group consists of a set of data disks and a set of check disks. A common redundancy scheme (see box) is applied to each group. The number of check disks depends on the RAID level chosen. In the remainder of this section, we assume for ease of explanation that there is only one reliability group. The reader should keep in mind that actual RAID implementations consist of several reliability groups, and that the number of groups plays a role in the overall reliability of the
- 4. Most of our systems we are having one hard disk for storing the data if due to any mechanical failure or some disk failure it may be that hard disk will get corrupt and all our data get lost. So what could be the solution we could replace a single hard disk with multiple hard drives so what will be the advantage of this, our data will remain secure our data for a longer time. How will define the RAID now? RAID is nothing but redundant array of inexpensive or independent disks. What is the advantage of using of RAID? In this system, because of failure one hard disk data loss does not take place; RAID is collection of various disk organization techniques. It is used to get better disk performance, reliability or both. RAID can be structured in many ways, there many levels of RAID such as RAID 0,1,2,34,5,6,10 Before Discussing about RAIDS first we need to about Data Striping? Data striping is the technique of splitting the data for spreading the data across multiple hard drives. The division of data can be done at 3 levels. Bit Level Byte Level(1 byte=8bits) Block Level(Group of number of bytes)
- 5. A1 B1 A2 B2 A3 B3 STRIPE Stripe 1 Stripe 2 Stripe 3
- 6. RAID-0:Data Striping BLOCK 1 BLOCK 3 BLOCK 5 BLOCK 7 BLOCK 2 BLOCK 4 BLOCK 6 BLOCK 8 RAID-0 DRIVE 1 DRIVE 2 Block data Striping Fault Tolerance=None(means of our hard disk fails we lost the data) Performance: Fast Storage Space=100% (consider both hard drives have 50 GB each that could be used to 100 GB utilized to storing the data.
- 7. RAID-1:Mirroring BLOCK 1 BLOCK 2 BLOCK 3 BLOCK 4 BLOCK 1 BLOCK 2 BLOCK 3 BLOCK 4 RAID-1 DRIVE 1 DRIVE 2 It uses the concept of mirroring; what is mirroring? Means is written identically to two drives(mirror set). Required at least 2 disks Advantage: Fault Tolerance: Mirrored Set(it means if any one hard disk failed we can replace with new hard disk in place of old one, here we can’t lost the data even one hard disk failed. Disadvantage: Performance: 50%: Because if one disk is allocated for backup of the another disk so it occupies extra 50% space.
- 8. RAID-2 A1 B1 C1 D1 Use of Mirroring as well as stores error correcting codes for its data striped on different disks It is bit level striping hamming ECC Each data bit in a word is recorded on a separated disk and ECC codes of the data words are stored on a set disks Due to its complex structure and high cost RAID 2 not commercially available A2 B2 C2 D3 A3 B3 C3 D3 A0 B0 C0 D0 ECC/Ax ECC/Bx ECC/Cx ECC/Dx ECC/Ay ECC/By ECC/Cy ECC/Dy ECC/Az ECC/Bz ECC/Cz ECC/Dz
- 9. Byte level striping along the parity is used at this level. It uses an extra disk for storing all the parity information, if any drive gets failed, the parity restores the failed disk If parity drive fails fault tolerance is not possible. Data Disks Parity Disk B1 B2 B3 B4 B7 B5 B8 B6 B9 p1 p2 p3
- 10. RAID-4:Block Striping with parity A1 B1 C1 D1 A2 B2 C2 D2 Block level striping along with parity is used at this level It uses one extra disk for storing all the parity information A3 B3 C3 D3 Ap Bp Cp Dp If any drive gets failed, the parity drive restores the failed disk If parity disk fails fault tolerance is not possible
- 11. Block level striping along with parity is used at this level It requires at least 3 hard disks Fault Tolerance: Parity(You can handle one disk failure) Performance: Fast Storage Space: 75%(Loose one hard disk space) It can handle fault tolerance at two disk failures DISK 1 A B P3 DISK 2 C P2 D DISK 3 P1 E F
- 12. It is enhanced version of RAID level 5 In this Level for each block double parity are distributed among several hard disks so this particular level helps to restore failure of two hard drives also successfully restore which was not possible in RAID 5 This RAID level 6 is mostly utilized in big companies such as google, face book so on DISK 1 A C P5 DISK 2 B P3 P6 DISK 3 P1 P4 E DISK 3 P2 D F
- 13. The data blocks are spread over separate drives and mirrored (duplicated)this arrangement provides both speed and fault tolerance. This is the recommended RAID configuration for most database installations(if cost is not an issue)
- 14. If data loss is not an issue, RAID Level 0 improves overall system performance at the lowest cost. RAID Level 0+1 is superior to RAID Level 1. The main application areas for RAID Level 0+1 systems are small storage subsystems where the cost of mirroring is moderate. Sometimes RAID Level 0+1 is used for applications that have a high percentage of writes in their workload, since RAID Level 0+1 provides the best write performance. RAID levels 2 and 4 are always inferior to RAID levels 3 and 5, respectively. RAID Level 3 is appropriate for workloads consisting mainly of large transfer requests of several contiguous blocks. The performance of a RAID Level 3 system is bad for workloads