| 1 |
Dan Farrell wrote: |
| 2 |
|
| 3 |
> in reality, though, I think the best performance would probaby involve |
| 4 |
> just using the fast drive. RAID introduces too much overhead to make |
| 5 |
> up for itself in this situation I think. |
| 6 |
|
| 7 |
I'm betting the act of seeking across the platters on the fast drive for |
| 8 |
two separate partitions on the disk makes performance truly awful. The |
| 9 |
idea of separate stripe sizes in the original post makes sense for |
| 10 |
shifting more I/O to drive A, the fast one, without causing weird things |
| 11 |
to happen on the physical disc that the software can't optimize for. |
| 12 |
|
| 13 |
However I think messing with stripe sizes is not something Linux |
| 14 |
software raid (or any hardware raid I've dealt with) supports. |
| 15 |
|
| 16 |
kashani |
| 17 |
-- |
| 18 |
gentoo-user@g.o mailing list |
Archives