Why is my RAID-0 not faster than RAIDless setup?

[behrangsa]

Hi

As RAID-0 is two times faster than a RAID-less setup in theory and about %60 faster in practice, I decided to buy two 80GB WD Cavier disks and setup a RAID-0 array on my system. The system is an Athlon64/1GB RAM/nForce4/nvRAID one.

I installed Windows XP on the system and performed some IO tests. Then I disabled the RAID-0 settings and installed Windows XP on the first HDD and ran the same IO tests.

It turned out that the IO performance wasn't any different.

As nvRAID is a hardware-based RAID, this result is very disappointing. Does anybody know what's possibly wrong? Should I increase the stripping block size from 32K to 128K?

Thanks in advance,
Behrang S.

 

[n7]

RAID-0 provides an almost 0% performance improvement for normal use.

I am assuming you read too many synthetic benchmarks, because 60% improvement? Ha, i wish... You normally don't even get 6% improvement, nevermind 60.
Here's AT's review on RAID-0

If you haven't gotten the hint by now, we'll spell it out for you: there is no place, and no need for a RAID-0 array on a desktop computer. The real world performance increases are negligible at best and the reduction in reliability, thanks to a halving of the mean time between failure, makes RAID-0 far from worth it on the desktop.

 

[The Pentium Guy]

The difference is negligible. If you're anal about load times on windows XP, go ahead stick with Raid 0, but worry your ass off because you have twice the chance of your data dying.

 

[l Xes l]

raid-0 :thumbsdown:

 

[bob4432]

raid 0 is useless unless you are moving large video files that are in the GB in size...

 

[SrGuapo]

RAID 0 sucks. If any, the perfomance increase is negligible. All you are accomplishing is creating twice the chance of losing your data.