RAID Level Definitions

RAID is an acronym for "Redundant Array of Independent (or Inexpensive) Disks" and describes a group of multiple small hard disk drives organized to appear as one large drive. RAID setups improve system performance through increased data availability and/or data-transfer rates; but most importantly, disk arrays add storage capacity and enhance system reliability through data redundancy.

Typically, a RAID configuration consists of a number of hard disks, a specialized controller, and one or more parity drives. In the event of a drive failure, the parity drives in the array provide single error detection, and redundant information to recover the original information stored on the failed drive.

RAID technology is integral to today's high performance systems. Customers who set up such systems should expect the following qualities from the disk array and its components (e.g. controller):

• High Performance
• High Capacity
• Fault-Tolerance
• Reliability
• Adequate Price
• Easy Setup and Maintenance

State-of-the-art products fulfill and maximize all these requirements simultaneously. The successful design and efficient development of disk array controllers not only requires know-how, but also broad knowledge of the entire range of RAID technology. The disk array controller and the connected drives are a very important part of a complete system.

Each RAID level has certain inherent advantages and disadvantages. The following definitions should help you understand the different levels of RAID offered by Aspen Systems and will help you determine the right RAID level for your particular application.

---

According to the adjusted stripe size (e.g., 16 kb) and the number of disk drives, the data blocks are split into stripes. Each stripe is stored on a separate disk drive. RAID Level 0 provides a significant improvement of data throughput, especially with sequential read and write operations. RAID 0 includes no redundancy at all, i.e., when one disk drive fails, all data is lost.

---

All data is stored twice on two identical disk drives. When one disk drive fails, all data is immediately available on the other without any impact on the performance and data integrity. We talk about "Disk Mirroring" when two disk drives are mirrored on one SCSI channel. If each disk drive is connected with a separate SCSI channel, this is called "Disk Duplexing" (additional security). RAID 1 represents an easy and highly efficient solution for data security and system availability. It is especially suitable for installations that are not too large (the capacity available is only half of the installed capacity).

---

Mirroring / Striping - This level combines the redundancy of RAID Level 1 (mirroring) with the speed of RAID Level 0 (multiple spindle/disk striping) and mirrors data across multiple disks. It is quite similar to, but not exactly the same as RAID 10. RAID Level 0+1 consists of striping data across multiple RAID-1 disks in parallel sectors. I/O transfer rate is increased compared to that of a single disk. A single disk failure does not cause a loss of data. In addition to redundant protection, read performance can be faster than a single disk due to overlapping reads. Striping provides for load balancing and improved read and write performance as compared to single disks.

---

In RAID 3, all parity information is stored on a single drive. Therefore, this RAID level has high data transfer rates which are ideal for moving large files, such as those used in graphics and imaging, and some scientific and technical applications.

In RAID-3, data is sent to and from the disc drives in parallel, one I/O request at a time. Parity data is stored on a single additional drive. The disc spindles are synchronized to transfer data to all drives simultaneously. Because of the high degree of parallelism, data transfers are very fast, although concurrent I/O is not possible. If a single drive fails, data is still available by using the data on the working drives and the parity drive to reconstruct the data. RAID-3 is typically used on supercomputers, image-manipulation processors and other applications where very high data-transfer rates are needed. It is most efficient for long block transfers and is inefficient for short transactions with high I/O request rates. For a given capacity, fewer drives are needed than for RAID-1, as only a single drive for redundancy must be added to the data drives. However, the controller may be more complex and expensive. RAID-3 is best for situations that require very fast data transfer rates or long data blocks.

---

RAID 4 works very much like RAID 0. The data is striped amongst the disk drives. Additionally, the controller calculates redundancy data (parity information) which are stored on a separate disk drive (P1, P2...). Even when one disk drive fails, all data is still fully available. The missing data is recalculated from the data still available and the parity information. Unlike RAID 1, only the capacity of one disk drive is needed for the redundancy. If we consider, for example, a RAID 4 disk array with 5 disk drives, 80% of the installed disk drive capacity is available as user capacity, only 20% is used for redundancy. In situations with many small data blocks, the parity disk drive becomes a throughput bottleneck. With large data blocks, RAID 4 shows significantly improved performance.

---

Unlike RAID 4, the parity data in a RAID 5 disk array are striped in all disk drives. The RAID 5 disk array delivers a balanced throughput. Even with small data blocks, which are very likely in a multitasking and multi-user environment, the response time is very good. RAID 5 offers the same level of security as RAID 4: when one disk drive fails, all data is still fully available, the missing data are recalculated from the data still available and the parity information. RAID 4 and RAID 5 are particularly suitable for systems with medium to large capacity requirements; both have an efficient ratio of installed to actually available capacity.

---

RAID 6 is similar to RAID 5, but with additional parity information written to recover data in case two drives fail. This configuration requires extra parity drives, and write performance is theoretically slower than for an equivalent implementation of RAID-5. Proposed by UC Berkeley in late 1989, RAID-6 is also used by some manufacturers to designate a layered array with RAID-1 and RAID-0 capabilities, but this does not conform to the Berkeley definition.

---

RAID 10 is based on the combination of RAID 0 (Performance) and RAID 1 (Data Security). Unlike RAID 4 and RAID 5, there is no need to calculate parity information. RAID 10 disk arrays offer good performance and data security. Like RAID 0, optimum performance is achieved in highly sequential load situations. Like RAID 1, 50% of the installed capacity is lost for redundancy.

---

Please fill out our price quote request if you are interested in a high-performance RAID storage system. We'll assess your requirements and recommend a configuration that meets your exact specifications.