欢迎访问ic37.com |
会员登录 免费注册
发布采购

STK12C68-P35I 参数 Datasheet PDF下载

STK12C68-P35I图片预览
型号: STK12C68-P35I
PDF下载: 下载PDF文件 查看货源
内容描述: [Non-Volatile SRAM, 8KX8, 35ns, CMOS, PDIP28, 0.300 INCH, PLASTIC, DIP-28]
分类和应用: 可编程只读存储器电动程控只读存储器电可擦编程只读存储器静态存储器光电二极管内存集成电路
文件页数/大小: 4 页 / 36 K
品牌: SIMTEK [ SIMTEK CORPORATION ]
 浏览型号STK12C68-P35I的Datasheet PDF文件第1页浏览型号STK12C68-P35I的Datasheet PDF文件第2页浏览型号STK12C68-P35I的Datasheet PDF文件第4页  
Using nvSRAM in RAID Controller Applications  
as airline reservation systems, financial and banking  
applications, etc.  
RAID Level 6  
RAID 6 is a non-Berkeley level controller that is  
designed for extremely high data reliability. RAID 6  
is an independent access array concept that  
requires two parity blocks be updated for each block  
written. This requires an extra parity disk but gives  
nvSRAM Applications & System Archi-  
tecture  
In modern RAID systems the Array Management  
Software can run in the host or in a dedicated  
embedded controller. Most modern systems are  
using embedded controllers, including many manu-  
facturers using the Intel i960 chip as the engine.  
the added data safety of requiring 3 disks to fail  
before data will be lost. RAID 6 data transfer and I/O  
capability is lower than RAID 5 for writes, but data  
reliability is highest of all RAID architectures. Pres-  
ently RAID level 6 is not widely used because of the  
higher costs associated with the added complexity,  
and the high penalty paid in system I/O performance  
due to long write times.  
In the past RAID systems were designed to use a  
distributed block of disk to maintain system configu-  
ration and to store system recovery address vec-  
tors. The primary problem with this type of  
architecture is that if a power failure occurs, and the  
controllers volatile system memory is lost, the entire  
disk array must be scanned upon power up to rees-  
tablish configuration and to redefine data locations.  
On a large array this is very time consuming, requir-  
ing many minutes to accomplish. Service-oriented  
industries cannot afford this length of down time and  
must come up and be operating very quickly once  
power is restored. In the latest generation of RAID  
systems the restart vectors are stored in nonvolatile  
semiconductor memory on the controller board  
itself. Due to the fact that the Array Management  
System is constantly moving data among the indi-  
vidual array members to optimize I/O balance, maxi-  
mize I/O rates, and assure redundancy, the RAID  
controller is constantly tweaking the address vector  
tables. Also, the system configuration data is being  
Additional RAID Implementations  
RAID 10 is a combination of RAID 0 & 1. This archi-  
tecture gives high I/O performance and good data  
reliability. It is accomplished by using RAID 0 (data  
striping) to enhance I/O rates and by using RAID 1  
(disk mirroring) for high data reliability. RAID 10  
requires costly hardware (disk and port) to imple-  
ment, and is primarily used in applications where the  
data has high value and can justify a mirrored stor-  
age system.  
RAID 53 is a combination of RAID levels 0 & 3 and  
provides RAID 3-like data transfer performance, and  
striping-like I/O request rates at RAID 3 or 5 costs.  
RAID 53 is used where both high data request rates  
and high data transfer performance is required such  
Physical  
Disk 0  
Physical  
Disk 1  
Virtual  
Disk  
Chunk 0  
Chunk 4  
Chunk 8  
Chunk 12  
Chunk 1  
Chunk 5  
Chunk 9  
P (12-15)  
Physical  
Disk 2  
Chunk 0  
Chunk 1  
Chunk 2  
Chunk 3  
Chunk 4  
Chunk 2  
Chunk 6  
P (8-11)  
Chunk 13  
Chunk 5  
Array  
Management  
Software  
Chunk 6  
Physical  
Disk 3  
Chunk 7  
Chunk 8  
Chunk 9  
Chunk 10  
Chunk 11  
Physical  
Disk 4  
Chunk 3  
P (4-7)  
P (0-3)  
Chunk 7  
Chunk 11  
Chunk 10  
Chunk 14  
Chunk 15  
Figure 2  
Example of a Typical RAID Level 5 Controller  
From The RAID Book Edition 1-1  
8-27