Memory for disk arrays
Thus, if even a few years ago RAID arrays used in expensive servers scale
enterprises using SCSI disks, but today they have become a kind of de facto
standard, even for entry-level servers. Moreover, the market is gradually
increasing and IDE RAID controller, it is important to the task of constructing
RAID arrays in the working-stan-conflict with the use of cheap IDE drive. Thus,
many motherboard manufacturers are already beginning to integrate on-IDE RAID
controllers on board themselves. So, RAID - a redundant array of independent
disks (Redundant Arrays of Independent Discs), which has the task of ensuring
the reliability and productivity of improving. Fault tolerance is achieved
through redundancy. That is part of capacity disk space stranstva is for
business purposes, becoming inaccessible to the user. Increased productivity
disk subsystem is the simultaneous work of several ra-ROM drive, and in that
sense, the more disks in the array (up to a certain limit), the better.
Contemporary work drives in the array can be arranged using a parallel lelnogo
or independent access. With parallel access disk space is divided into blocks (strips)
to letters-of the data. Similarly information to be recording on the disc is
divided into the same blocks. When recording individual blocks are recorded on
different disks (Fig. 1), the record number of units at various drives happening
at the same time, and that leads to an increase in productivity of write
operations. Useful information, it reads as single units simultaneously with
multiple discs (Fig. 2), which also contributes to higher productivity
proportion to the number of disks in the array.
Next part
|