[geeks] The new IPC/LX, from Dell?

[Lionel Peterson]

On Nov 19, 2009, at 2:19 PM, Joshua Boyd <jdboyd at jdboyd.net> wrote:

> On Thu, Nov 19, 2009 at 01:02:54PM -0500, Lionel Peterson wrote:
>
>> eSATA is the unfiltered, unaltered native connection between drive  
>> and
>> controller. FW and USB add overhead and impose limits on performance.
>> Informal 'ghost' tests have 30 Gig system images taking 10-12  
>> minutes on
>> eSATA, and twice as long on USB 2.0. I'd put FW between those two,
>> closer to eSATA, but not the same.
>
> So, a 30 gig ghost image in 10 minutes is 50 MB/s on write.  I would  
> say
> that it is clear that eSATA isn't the limiting factor, and so FW800
> could be just as fast (maybe faster but probably not), and FW400 is
> probably only slightly slower at maybe 38 MB/s if the same drive was
> taken from the eSATA case and placed in a good FW400 case.
>
> At 12 minutes, that datarate would suggest that the eSATA drive could
> run neck to neck with what a FW400 drive, since the eSATA is not doing
> the best it could probably do.
>
> USB 2.0 may be about half the speed, but if it were me doing this, I'd
> want to know why the eSATA wasn't past 3x and closer to 4x the speed  
> of
> USB 2.0

When an eSATA drive is hooked up to mainboard controller port (in this  
case an intel notebook chipset) it is as fast as the on-board  
controller can go, up to the speed of the drive.

On a USB 2.0 or FW port, there is an additional limiting factor, the  
bridge chipset. A well-designed chipset could get out of the way, but  
I don't think ultimately be able to be as fast as the native drive  
interface. The processing overhead will approach, but never equal zero.

Also, remember, I'm talking about an actual 'ghosting' of the laptop,  
booting off a ghost CD-ROM, I am at the mercy of Ghost's drivers...

Lionel