In part 2 of our storage subsystem discussion and how to optimize performance we’ll focus on selecting the right storage solution for your situation, taking fault tolerance and high availability into consideration.
The number of storage solutions that are available, in particular to enterprises is extensive to say the least and not always an easy choice. As administrators, some of you will choose to deploy a traditional storage array, backed by SAS or SATA hard drives and directly attached or accessed through a separately managed Fibre Channel or iSCSI fabric. The storage array typically manages the redundancy and performance characteristics internally.
In addition to traditional storage, Windows 2012 supports Commodity Storage, and introduces so-called Storage Spaces. Storage Spaces provide platform storage virtualization, enabling you to deploy a storage solution that are affordable, offer high-availability, are resilient, and offer good performance by using commodity SAS or SATA drives in BJOD enclosures.
The following are some of the options and considerations for a traditional storage array solution:
|· SAS or SATA||Improve performance, and reduce cost. SATA drives are mostly built with higher capacity and lower cost targets than SAS drives. The benefit of SAS is typically better performance than SATA|
|· Hardware RAID capabilities||Maximum performance and reliability|
|· Maximum storage capacity||Total usable storage space|
|· Storage bandwidth||Maximum peak and sustained bandwidths are determined by the number of physical disks in the array, the speed of the controllers, the type of bus protocol (such as SAS or SATA), hardware- or software-managed RAID, and the adapters that are used to connect the storage array to the system|
Most storage solutions provide a form of resiliency and performance-enhancing capabilities. A hardware-managed array is presented to the operating system as a single drive, which is called a logical unit number (LUN), virtual disk, or any other name.
The following are some typical options for storage arrays:
|· JBOD||Not a RAID level. But it can provide a baseline for measuring the performance, reliability, and availability of various fault-tolerant and performance configurations. Disks in a JBOD configuration are referenced separately, not as a combined entity.Sometimes, a JBOD configuration provides better performance than striped laytous. For example, when serving multiple sequential streams, performance is best when a single disk services each stream.Any physical disk failure will result in data loss, however, the loss is limited to the failed drive(s) only.|
|· Spanning||Not a RAID level. Spannig is the concatenation of multiple physical disks into a single logical disk. Each disk contains one continuous set of sequential logical blocks. Spanning has the same performance and reliability characteristics as a JBOD configuration.|
|· Striping (RAID 0)||Striping is a layout scheme where sequential logical blocks are distributed across multiple disks. It results in a logical disk that stripes disk accesses over a set of physical disks. The overall storage load is balanced across all physical drives.For most workloads, a striped data layout provides better performance than a JBOD. Because no disk is allocated for redundant data, striping does not provide fault tolerance as provided in other RAID schemes. Also, if you loose any disk, it results in data loss on a larger scale than a JBOD configuration because the entire file system spread across all physical disks is affected.|
|· Mirroring (RAID 1)||Mirroring is a RAId configuration in which each logical block exists on two or more physical disks.Mirroring often has worse bandwidth and latency for write operations when compared to striping or JBOD because data must be written to a pair of physical disks. It can offer faster read operations than striping because it can (depending on the controller) read from the least busy physical disk of the mirrored pair.It is the most expensive resiliency scheme in terms of physical disks because half (or more) of the disk capacity stores redundant data copies, however, a mirrored array can survive the loss of any single physical disk.Do keep in mind that mirroring has greater power requirements than a non-mirrored storage configuration. It doubles the number of disks; therefore, it doubles the required amount of power.|
|· Striped mirroring (RAID 0+1 or 10)||The combination of striping and mirroring is intended to provide the performance benefits of striping and the redundancy benefits of mirroring.Cost and power characteristics are similar to those of mirroring.|
|· RAID 5||A RAID 5 array consists of a logical disk composed of multiple physical disks that have data striped across the disks in sequential blocks (stripe units) in a manner similar to simple striping (RAID 0). However, the underlying physical disks have parity information spread throughout the disk array.RAID 5 read operations have characteristics similar to striping. However, small writes are much slower because each parity block that corresponds to the modified data block(s) must be updated.RAID 5 provides fault tolerance since data can be reconstructed from parity. RAID 5 can survive the loss of any one physical disk, as opposed to mirroring, which can survive the loss of multiple disks if the mirrored pair is not lost.RAID 5 is more cost efficient than mirroring because it requires only one additional disk per array, instead of double the total number of disks in an array.|
|· Double rotated parity, or double parity disks (RAID 6)||Traditional RAID 6 is basically RAID 5 with additional redundancy built in. Instead of a single block of parity per stripe of data, two blocks of redundancy are included. The second block uses a different redundancy code (instead of parity), which enables data to be reconstructed after the loss of any two disks. More complex implementations may take advantage of algorithmic or hardware optimizations to reduce the overhead that is associated with maintaining the extra redundant data.As far as power and performance, the same general statements can be made for RAID 6 that were made for RAID 5, but to a larger magnitude.|
RAID schemes are not new to not of you and as an administrator you know that RAID 5 and RAID 6 are the most difficult to understand and plan for. In our next article we’ll give you a detailed comparison to help you choose the right fault-tolerance scheme for your storage subsystem.