| 1 |
On 01/22/2011 12:31 AM, Dale wrote: |
| 2 |
> Alan McKinnon wrote: |
| 3 |
>> My notebook works like that too. |
| 4 |
>> |
| 5 |
>> Hard disk works fine when everything is set to AHCI, but then the |
| 6 |
>> system won't |
| 7 |
>> boot from CD. So I enabled the IDE driver and the IDE driver for CD-ROMs. |
| 8 |
>> |
| 9 |
>> My take on this is that Dell had a vast stock of cheap-skate CD-ROM |
| 10 |
>> hardware |
| 11 |
>> and used them up. The engineering logic would have been "it doesn't |
| 12 |
>> matter |
| 13 |
>> that we use the slow interface for that device, it's still faster than |
| 14 |
>> we can |
| 15 |
>> get the data off the media." |
| 16 |
>> |
| 17 |
> |
| 18 |
> And I thought there was something weird with me on this one. o_O I did |
| 19 |
> switch it back to AHCI after I got done booting the CD thingy. I really |
| 20 |
> can't tell any difference in speed between the two and neither could |
| 21 |
> hdparm -tT either. |
| 22 |
|
| 23 |
hdparm measures raw throughput when reading continuously from one |
| 24 |
position to another. AHCI improves performance when the disk needs to |
| 25 |
read from several different places, which is the case in every day use. |
| 26 |
It does this by providing a feature similar to what SCSI provides: |
| 27 |
native command queuing (NCQ). You can read about what this is and why |
| 28 |
we want it here: |
| 29 |
|
| 30 |
http://en.wikipedia.org/wiki/Native_Command_Queuing |
Archives