| 1 |
On 01/22/2011 09:50 AM, Dale wrote: |
| 2 |
> Nikos Chantziaras wrote: |
| 3 |
>> On 01/22/2011 12:31 AM, Dale wrote: |
| 4 |
>>> [...] |
| 5 |
>>> And I thought there was something weird with me on this one. o_O I did |
| 6 |
>>> switch it back to AHCI after I got done booting the CD thingy. I really |
| 7 |
>>> can't tell any difference in speed between the two and neither could |
| 8 |
>>> hdparm -tT either. |
| 9 |
>> |
| 10 |
>> hdparm measures raw throughput when reading continuously from one |
| 11 |
>> position to another. AHCI improves performance when the disk needs to |
| 12 |
>> read from several different places, which is the case in every day |
| 13 |
>> use. It does this by providing a feature similar to what SCSI |
| 14 |
>> provides: native command queuing (NCQ). You can read about what this |
| 15 |
>> is and why we want it here: |
| 16 |
>> |
| 17 |
>> http://en.wikipedia.org/wiki/Native_Command_Queuing |
| 18 |
> |
| 19 |
> Other than copying a file and using time to measure how long it takes, |
| 20 |
> what is the best test of a hard drive's speed? |
| 21 |
|
| 22 |
By running a benchmark tool that does exactly this. IOzone is a nice one: |
| 23 |
|
| 24 |
http://www.iozone.org |
| 25 |
|
| 26 |
It's in portage: "app-benchmarks/iozone". |
| 27 |
|
| 28 |
|
| 29 |
> Also, does or can the kernel override the BIOS setting? I think it uses |
| 30 |
> AHCI no matter what is in the BIOS. It seems it would be at least some |
| 31 |
> difference in speed. |
| 32 |
|
| 33 |
The kernel can't change this setting and has no access to it whatsoever. |
Archives