mpthreer said:
i have been drinking a lot, but (lol) if you can overclock the fsb and get better results it seems that the fsb would be where the bottleneck (strain on dataflow) is created....
Let me put it this way, mp, suppose you had a crappy band and you replaced the drum player with a better one and the band got better, but it was still crappy.
Does that mean that you should look for an even better drummer, or should you try to find out why the band is crappy in the first place?
--
Here's the straight dope on RAID: On single-user computers RAID (of any kind) will hardly ever lead to an improvement in performance and will very often degrade performance. RAID levels 1 and up are handy for guarding against disk failure, though.
The reason you've heard differently is because RAID is one of those things that scores very high on synthetic benchmarks. Unfortunately those benchmark scores don't help real-life applications.
If you'd like to read a little more, here is a link to some detailed information about it.
RAID Controller Review
If you just want the condensed version, here it is:
Unfortunately, Business Winstone scores don't scale much at all. The performance benefit moving from a single drive to RAID 1 or RAID 0 is negligible at best.
...
We see a little more scaling action in the Multimedia Content Creation Winstone, particularly moving to RAID 0, but the small performance boost probably isn't enough to justify the cost of a second hard drive.
...
RAID doesn't offer much of a performance benefit over single-drive configurations in our DivX encoding test. Sure you can pick up a fraction of a frame per second by adding a second drive, but really, that's about it.
Okay, then, maybe RAID doesn't help with running programs, but how about with booting?
The ranking from first to fifth is the same for single drives, RAID 1 arrays, and RAID 0. RAID doesn't do much to speed up boot times.
Well, at least it will help you load your game levels faster, won't it?
Sorry. Nope. Going to RAID doesn't speed things up a whole lot. The SiS964 and nForce3 250Gb both flirt with a one second slow-down moving from a single drive to RAID 1, but level load times are otherwise pretty consistent in the Unreal Tournament 2004 demo.
And in conclusion:
I would be remiss not to point out how little performance impact different RAID levels had in our application benchmarks and stopwatch tests. Although multi-user and synthetic disk subsystem tests like IOMeter, HD Tach, and ATTO show clear differences between the performance of each RAID implementation and array configuration, the performance benefit in more real world applications is significantly less pronounced.
-- Rick
