| 1 |
On Fri, Aug 30, 2013 at 9:40 PM, Duncan <1i5t5.duncan@×××.net> wrote: |
| 2 |
> Rich Freeman posted on Thu, 29 Aug 2013 15:56:10 -0400 as excerpted: |
| 3 |
>> You did mention USB3, as did others in this thread. Hopefully this is |
| 4 |
>> obvious to all, but under no circumstances should you try to run an OS |
| 5 |
>> on USB2 or less. |
| 6 |
> |
| 7 |
> People did it for years before USB3 and SATA2/3 arrived... |
| 8 |
|
| 9 |
Anybody with a motherboard supporting USB2 almost certainly had a |
| 10 |
motherboard supporting PATA at a faster transfer rate. |
| 11 |
|
| 12 |
I do agree that random access speed does lower the effective rate. My |
| 13 |
hard drives are running at 3GB/s transfer rates each on a dedicated |
| 14 |
channel, and yet they're probably not any faster than they would have |
| 15 |
been under PATA (assuming one drive per cable). |
| 16 |
|
| 17 |
Hopefully one of these days there will be a decent SSD cache option |
| 18 |
for Linux. Bcache is still fairly experimental, and I'm not sure how |
| 19 |
well it performs in practice with btrfs - plus it is a device layer |
| 20 |
and not filesystem layer implementation (ie if you have mirrored |
| 21 |
drives you end up with mirrored cache which seems a bit dumb, |
| 22 |
especially if the mirrors end up being on separate partitions on the |
| 23 |
same device). |
| 24 |
|
| 25 |
Rich |
Archives