| 1 |
Sean Cook wrote: |
| 2 |
> Redhat In their manual: |
| 3 |
> "With today's fast CPUs, Software RAID performance can excel against |
| 4 |
> Hardware RAID." |
| 5 |
> |
| 6 |
> As I stated before, it depends on where your bottleneck is... if you |
| 7 |
> are not cpu bound, software raid is great! and will boost IO through |
| 8 |
> put on comparable hardware. If you are already CPU bound, forget |
| 9 |
> software raid, it will degrade your system to a crawl... |
| 10 |
|
| 11 |
Badly done tests circa 1998 without any sort of methodology, mention of |
| 12 |
cluster sizes, etc is proof than any idiot can make a computer slower. |
| 13 |
|
| 14 |
I'll argue that a fully supported hard raid card is always superior to |
| 15 |
a software raid by it's very nature, having local I/O cache and a |
| 16 |
dedicated chip. However there are definitely workloads where a software |
| 17 |
raid is good enough that spending money on a hardware raid card is |
| 18 |
pointless. I can not imagine a case where all things being equal that |
| 19 |
software raid would be measurably faster. |
| 20 |
|
| 21 |
In the event that removing your RAID card makes your disk 5x faster I'd |
| 22 |
also recommend removing the admin who setup the original system as well. :-) |
| 23 |
|
| 24 |
kashani |
| 25 |
-- |
| 26 |
gentoo-server@g.o mailing list |
Archives