Tuesday, March 30, 2010

RAID CONCEPT IN IBM SERVERS



The important general RAID Concept is physical and logical Arrays and Drives: Before, going into RAID Concepts we should be clear with the fundamental structure of RAID. The fundamental structure of RAID is like an array. An array is nothing but a collection of drives in some definite pattern. The drives are connected in the form of array and the data is split between them to determine the RAID level. The particular definition which are in use is Physical Drives: The Physical Drives are the physical, hard disks that are in the form of the array, Physical Arrays:
The Physical Arrays are physical drives which are connected together to form a physical array. Logical Arrays: The Logical arrays are formed by combining one or more physical arrays. Logical Drives: Logical Drives are formed by connecting one or more logical drivers and are formed from one logical array. The confusing thing is that the terms above, used are similar enough, and are more lightly used. The most RAID consist of one physical array which inturn is made up of one logical array. RAID controllers are like a rope which is needed to hang it comes to defining arrays. Another important RAID Concept is Mirroring: Mirroring is a procedure in which data in the system is written simultaneously to two or more hard disks. Thus it is also known as the mirror concept. The principle of mirroring is to obtain 100% data redundancy, which provides full protection against the failure of either of the disks containing the duplicated data.
The other RAID Concept is Duplexing: Duplexing is an update version of mirroring which is based on the same principle as that mirroring technique. Like in mirroring, all data is duplicated onto two distinct physical hard drives. Duplexing is much more advanced then mirroring in terms of availability because it can provide the data protection against drive failure that mirroring does, but it can also protects against the failure of either of the controllers. The interesting RAID Concept is Striping: Striping is obtained at the byte level, as well as in block level. The Byte-level striping breaks the file into byte-sized pieces. After Byte level striping, the first byte of the file is sent to the first drive, then the second to the second drive, and so on. Block-level striping means that each file is broken into different blocks of a certain size and those are distributed to the various drives.
The last and important RAID Concept is Parity: The parity is used for the system memory error detection. The parity used in RAID is very similar in concept to parity RAM. The principle of parity is simple: take N pieces of data, and compute an extra piece of data. After that take N+1 pieces of data and store it in N+1 drives. If you have lost any one of the data, you can recreate it from the N remain, regardless of which piece is lost. Parity protection is generally used with striping in order to get high performance results across the drives in the array.
The parity information can be stored on a separate, or mixed with the data of drives. The RAID affects important reliability factors such as, For example, a commonly-heard phrase is that RAID improves hard disk reliability, but that is not an true. The truth depends to on how you define reliability and what do you mean reliability of the individual drives, or the whole system.







The major RAID Concepts are Physical and Logical Arrays and Drives, Mirroring, Duplexing, Striping and Parity. First, we look at physical and logical arrays and drives: The structure of RAID is like an array. As we know, an array is a collection of drives that is configured in a particular way. The number of drives and the data is split between them to determine the RAID level, the capacity of the array, performance and data protection characteristics helps in deciding what types of arrays needed to be set up, and how to configure them. Second, we look at Mirroring:
The advantage of mirroring is to provide redundancy of data and also quick recovery from a disk failure. All the data which is on the second drive, is ready to be use if the first one fails. The disadvantage of RAID 1 is expense. Results are as not as good as other RAID levels. Third, we look at the Duplexing: Duplexing yields superior results then mirroring because of availability, it provides the protection against drive failure that mirroring does. It is expensive more than mirroring. Fourth, we look at striping: Striping is done at byte level. Byte level striping means file is divided into "byte-sized pieces".
The first byte is sent to the first drive, then the second byte is send to the second drive, and so on. Byte level striping is done at 512 bytes. Block level striping means that the file is split into blocks of a certain size and is distributed to the various drives. The size of the blocks is called the stripe size. Finally, parity: The term parity is used in connection of system memory error detection. The parity which is used in RAID is nearly similar to parity RAM.
The parity is simple: take N pieces of data, and from them, calculate the extra amount of data. Take the N+1 amount of data and store it in N+1 drives. If you lose any one of the N+1 pieces of data regardless of which piece is lost. Parity protection is used with striping, and the N pieces of data are of the blocks distributed across the drives in the array.
The major RAID Issues are RAID Performance Issue & RAID Reliability Issue. The RAID Performance Issue: RAID was developed for protection of data in order to find the fault tolerance. The performance could be increases RAID is parallelism. The ability to access multiple disks and allows for data to be written to or read from a RAID array faster than a single drive. RAID Reliability Issue: The RAID affects important reliability factors such as, For example, a commonly-heard phrase is that RAID improves hard disk reliability, but that is not an true.
The truth depends to on how you define reliability and what do you mean reliability of the individual drives, or the whole system are about the data, or the hardware itself. The performance could be improved through the use of RAID for businesses where the protection of critical data is important factor.












RAID Concept






RAID is an acronym for Redundant Array of Independent Disks. It is an array of multiple independent hard disk drives that provide high performance and fault tolerance. The RAID subsystem controller implements several levels of the Berkeley RAID technology. An appropriate RAID level is selected when the volume sets are defined or created. This decision is based on disk capacity, data availability (fault tolerance or redundancy), and disk performance. The following is the RAID level, which support in the RAID subsystem.

The RAID subsystem controller makes the RAID implementation and the disks’ physical configuration transparent to the host operating system. This means that the host operating system drivers and software utilities are not affected, regardless of the RAID level selected. Correct installation of the disk array and the controller requires a proper understanding of RAID technology and the concepts.

Raid 0
RAID 0, also referred to as striping, writes stripping of data across multiple disk drives instead of just one disk drive. RAID 0 does not provide any data redundancy, but does offer the best high-speed data throughput. RAID 0 breaks up data into smaller blocks and then writes a block to each drive in the array. Disk striping enhances performance because multiple drives are accessed simultaneously; but the reliability of RAID Level 0 is less than any of its member disk drives due to its lack of redundancy.



Raid 1
RAID 1 also known as “disk mirroring”, data written to one disk drive is simultaneously written to another disk drive. Read performance may be enhanced if the array controller can parallel accesses both members of a mirrored pair. During writes, there will be a minor performance penalty when compared to writing to a single disk. If one drive fails, all data (and software applications) are preserved on the other drive. RAID 1 offers extremely high data reliability, but at the cost of doubling the required data storage capacity.



Raid 0+1
RAID 0+1 is a combination of RAID 0 and RAID 1, combing stripping with disk mirroring. RAID Level 0+1 combines the fast performance of Level 0 with the data redundancy of Leve1 1. In this configuration, data is distributed across several disk drives, similar to Level 0, which are then duplicated to another set of drive for data protection. RAID 0+1 provides the highest read/write performance of any of the Hybrid RAID levels, but at the cost of doubling the required data storage capacity.



Raid 3
RAID 3 provides disk striping and complete data redundancy through a dedicated parity drive. RAID 3 breaks up data into smaller blocks, calculates parity by performing an exclusive-or on the blocks, and then writes the blocks to all but one drive in the array. The parity data created during the exclusive-or is then written to the last drive in the array. If a single drive fails, data is still available by computing the exclusive-or of the contents corresponding strips of the surviving member disk. RAID-3 is best for applications that require very fast data- transfer rates or long data blocks.



Raid 5
RAID 5 is sometimes called striping with parity at block level. In RAID 5, the parity information is written to all of the drives in the subsystems rather than concentrated on a dedicated parity disk. If one drive in the system fails, the parity information can be used to reconstruct the data from that drive. All drives in the array system can be used to seek operation at the same time, greatly increasing the performance of the RAID system.



Raid 6
A RAID 6 array is essentially an extension of a RAID 5 array with a second independent distributed parity scheme. Data and parity are striped on a block level across multiple array members, just like in RAID 5, and a second set of parity is calculated and written across all the drives. As larger disk arrays are considered, it is desirable to use stronger codes that can tolerate multiple disk failure. When a disk fails in a parity protected disk array, recovering the contents of the failed disk requires successfully reading the contents of all no-failed disks. RAID 6 provides an extremely high fault tolerance, and can sustain two simultaneous drive failures without downtime or data loss.



Summary of RAID Levels
RAID subsystem supports RAID Levels 0, 1(0+1), 3, 5 and 6. The following table provides a summary of RAID levels.


No comments:

Post a Comment

HEVC Coding

High efficiency video coding