Lennart Augustsson wrote:

>> Note that you're testing a 100MB file on a box that can effectively have
>> (a little bit less than) 493MB of buffers.| | Look| at| the| seeks-per-second
>> column of your bonnie results - no (non-solid-state) disk can do 10,000
>> seeks a second!
>
> If the disk is not involved I think the question about the slowdown
> is even more interesting. Something bad has happened in the kernel.

Precisely. Sorry that I didn't explain well enough the first time. 
I'm not attempting to determine *drive* speed. I intentionally used
the small testfile size so the test would likely run in fs buffer.

I'm asking why does the *filesystem* on #1) behave so poorly as
compared to the other systems with very similar hardware and drives
overall but slightly *slower* cpu and memory subsystems? This is
what I do not understand.