| 1 |
Neil Bothwick wrote: |
| 2 |
> Hello Daniel Iliev, |
| 3 |
> |
| 4 |
> |
| 5 |
>> Actually I'd be glad to read some results from a "Fake RAID-0 vs LVM" |
| 6 |
>> tests. My bet would be that RAID-0 w/o LVM would give the best speeds |
| 7 |
>> |
| 8 |
> |
| 9 |
> Omitting LVM isn't an option, I'd lose all the flexibility that LVM |
| 10 |
> offers. I don't see why RAID-0 should be necessarily more efficient than |
| 11 |
> LVM, unless there's something superior about RAID-0's striping |
| 12 |
> algorithms. I could do some before and after tests, but I'd first have the |
| 13 |
> reformat the filesystems to remove any effects of fragmentation. |
| 14 |
> |
| 15 |
> If no one comes up with a good reason for keeping the RAID, I'll get rid |
| 16 |
> of it, running bonnie++ before and after. |
| 17 |
> |
| 18 |
> |
| 19 |
> |
| 20 |
|
| 21 |
Hi, Neil! |
| 22 |
|
| 23 |
Out of curiosity I made some tests which confirmed my expectations. What |
| 24 |
about you - did you have time (and wish) to take some performance |
| 25 |
benchmarks? I would be glad to see some additional results. |
| 26 |
|
| 27 |
I'm attaching my tests in file called "bench.txt". |
| 28 |
|
| 29 |
|
| 30 |
-- |
| 31 |
Best regards, |
| 32 |
Daniel |
Archives