Six SSD DC S3500 Drives And Intel's RST: Performance In RAID, Tested

[cryan]

Intel lent us six SSD DC S3500 drives with its home-brewed 6 Gb/s SATA controller inside. We match them up to the Z87/C226 chipset's six corresponding ports, a handful of software-based RAID modes, and two operating systems to test their performance.

Six SSD DC S3500 Drives And Intel's RST: Performance In RAID, Tested : Read more

 

[apache_lives]

page 2 - 8GB cache?

 

[SteelCity1981]

"we settled on Windows 7 though. As of right now, I/O performance doesn't look as good in the latest builds of Windows."

Ha. Good ol Windows 7...

 

[colinstu]

These gotta be the most difficult-to-read graphs ever.

 

[vertexx]

In your follow-up, it would really be interesting to see Linux Software RAID vs. On-Board vs. RAID controller.

 

[tripleX]

Wow, some of those graphs are unintelligible. Did anyone even read this article? Surely more would complain if they did.

 

[utomo]

There is Huge market on Tablet. to Use SSD in near future. the SSD must be cheap to catch this huge market.

 

[tripleX]

Wow, some of those graphs are unintelligible. Did anyone even read this article? Surely more would complain if they did.

 

[tripleX]

Wow, some of those graphs are unintelligible. Did anyone even read this article? Surely more would complain if they did.

 

[klimax]

"You also have more efficient I/O schedulers (and more options for configuring them)." Unproven assertion. (BTW: Comparison should have been against Server edition - different configuration for schedulers and some other parameters are different too)
As for 8.1, you should have by now full release. (Or you don't have TechNet or other access?)

 

[rwinches]

" The RAID 5 option facilitates data protection as well, but makes more efficient use of capacity by reserving one drive for parity information."

RAID 5 has distributed parity across all member drives. Doh!

 

[Guest]

Love this article. I'd like to see the same test done on the AMD 990fx. It's had 6* Sata 3 ports for a long time. I suspect it's a lot slower than Intel's, and plateau's more quickly, obviously being an older SB.

"The larger block sizes generate less bandwidth" Really? Seems to me the opposite is happening. I'd guess the high IOPS of smaller blocks also uses more, not less cpu resources. But what do I know?

 

[Taracta]

I can't believe that nobody mentioned the big write holes errors in the sequential write for RAID 5, 4 drive and 6 drive. This is because your RAID 5 array is not properly configured for your 4 drive and 6 drive configuration at least.

 

[Nazia hassan]

Hi