Thanks, I'll give it a try. Do you remember which benchmark
specifically gave better performance with the blocking?
Adi Masputra wrote:
Brian Utterback wrote:
I am confused. I read the paper and I don't see the comparison that you
mentioned between the current and original fusion implementations. Is
the current what the graphs call "Yosemite"? If so, surely the
difference between Yosemite and the original fusion wasn't just the
implementation of the data block blocking was it?
Current == Yosemite. Nevada == original fusion code.
Also, I am confused by the explanation of the performance improvement
from blocking by reducing the amount of data required to be processed
by a single copyout operation. Surely copyout has linear performance
characteristics or am I wrong?
The paper mentions about reducing latencies due to large amount of
accumulated data at the receiver's endpoint; copyout() is mostly
associated with per-byte costs.
These experiments should be repeatable; you are welcome to do that.
Adi
--
blu
"The genius of you Americans is that you never make clear-cut stupid
moves, only complicated stupid moves which make us wonder at the
possibility that there may be something to them which we are missing."
- Gamal Abdel Nasser
----------------------------------------------------------------------
Brian Utterback - Solaris RPE, Sun Microsystems, Inc.
Ph:877-259-7345, Em:brian.utterback-at-ess-you-enn-dot-kom
_______________________________________________
networking-discuss mailing list
[email protected]
