Archive Home arrow Reviews: arrow Storage arrow SandForce SF1500 Enterprise SSD Processor
SandForce SF1500 Enterprise SSD Processor E-mail
Reviews - Featured Reviews: Storage
Written by Olin Coles   
Wednesday, 20 January 2010
Table of Contents: Page Index
SandForce SF1500 Enterprise SSD Processor
OCZ Vertex-2 Pro Enterprise SSD
SandForce SF-1500 Performance

SandForce SF-1500 Performance

The ATTO Disk Benchmark 2.34 program measures interface transfer rates at various intervals for a user-specified length and then reports read and write speeds for these spot-tests. ATTO Disk Benchmark requires that an active partition be set on the drive being tested, and for testing purposes we format using NTFS after SSD partition alignment. The charted results illustrate bandwidth speed using various file size chunks, and can be used as a general performance indicator.

ATTO-Benchmark_Vertex-2-Pro_SandForce_SSD.png

HD Tune is a low-level test that will not operate on a drive which contains a partition, so Benchmark Reviews uses DISKPART to prepare hardware and remove any partitions before conducting these tests. Random Access tests are divided into 512b, 4KB, 64KB, 1MB and random size test files sizes. The Random Access test measures the performance of random read or write operations. The amount of data which will be read varies from 512 bytes to 1 MB. Performance is reported in operations per second (IOPS), average access time, and average speed. Because it is our intent to compare one product against another, Benchmark Reviews has focused on random transfer size IOPS performance.

OCZ-Vertex-2-Pro-SSD-SandForce-219461-Firmware-231A11F0-Read.png

Using the OCZ Toolbox utility to format a +1 alignment to the drive, ATTO reported a maximum read-speed of 250 MBps and a respectable 263 MBps write performance. For operational input/output, HD Tune reports 16,355 IOPS for 4KB reads and 13,429 IOPS for write-to operations. Because of the impressive I/O performance, the SandForce SF1500 SSD processor is best suited for high-transaction enterprise environments.

OCZ-Vertex-2-Pro-SSD-SandForce-219461-Firmware-231A11F0-Write.png

In the coming months, Benchmark Reviews will test several new Solid State Drive products based on SandForce SSD processors. Our entire collection of SSD articles is available in the Benchmark Reviews Featured Reviews: Storage section.

Questions? Comments? Benchmark Reviews really wants your feedback. We invite you to leave your remarks in our Discussion Forum.


Related Articles:


 

Comments 

 
# This tests say nothing!stas 2010-03-05 01:50
Hi,

Have to say that standard SSD/HDD tests can not correctly test SandForce-based SSDs.

The main reason is in the nature of the SandForce chip - it is not only RAID 5 - like controller, it is also a data compression engine.

So, any testing data stream (ually a small repeated data pattern) dous not test a drive, but only a compression engine productivity.
This results in very high throughput and IOPS.

To test the drive itself, the data stream should be virtually uncompressible - think this will give quite another results.

Also, database read pattern (reading random parts af a huge file) will not be that fast even on highly compessible data.

So, the good test of this drive should provide benchmarks on both - highly comressible and virtually uncomressible data, giving the possible productivity range in the real live.
Report Comment
 
 
# RE: This tests say nothing!Jeff 2010-03-10 21:46
Hey,

You are just wrong lol,

mabye the benchmarks are misleading however you need to consider the way these controllers work, indilinx has a huge write amplification (x10) where as SANDFORCE have a write amplification of x1.1 meaning the MLC NAND on a SANFORCE controller will last much longer than any indilinx controlled SSD. I own both indilinx and sandforce based SSD's and sandforce performance is much better. Have a read on the sandforce website, they have a fact and fiction section, its very interesting!
Report Comment
 
 
# RE: RE: This tests say nothing!stas 2010-03-10 22:38
Once again - I do not say SandForce is worse or better than other controllers - it's just a bird of another flock and should be treated (tested) accordingly.

On highly compressible data it will by definition outperform any other drive, but in other applications it might lag way behind, and the tests show nothing on this side. We may only guess what is a compression impact on the internal drive productivity.
Report Comment
 

Comments have been disabled by the administrator.

Search Benchmark Reviews
QNAP Network Storage Servers

Follow Benchmark Reviews on FacebookReceive Tweets from Benchmark Reviews on Twitter