RAID 0 - Real-world peformance on the home desktop?

ByteJuggler said:
Surely we should be talking *median* filesize, as opposed to *average* filesize... that's what the size interval tables effectively give you... :confused:

OK, specillay for you:

Stripe Size = Median File Size / n

Where n is the Stripe Width.

Do you want me to incorporate some measure of interquartile range in there too? :D
 
omg lol this sounds like something from discreet computer mathematics 101 :P.

i'm surprised though. i would have thought that mirroring a drive would effectivly mean files are accessed twice as fast. if you have a 2 gig file and you are reading it from start to finish, would it not be noticable? if there isnt a great leap in performance is this because the data is accessed in a linear method, i.e the start of the file is accessed first before the middle and end.

would there be a greater amount of performance gotten from bi-linear file usage, as in , if you have this same 2 gig file, and 1 drive reads it from the start, while the other reads it from the end, and reverses to the center. it would mean the file has been completely loaded in half the time would it not?
*hmmmmm*
 
Last edited:
Back
Top Bottom