[Tech] Re: The effect of slow nodes

[Jano]

Jano wrote:

> I'm about to finish simulations going up to 28 as the load parameter. I'm
> using the phase7 version, without modifications. I'll post my results late
> today.

Here are the results. Load is increased in steps of two (2,4,..28).
The 'nothing' line stops at 14 because I run out of memory, but I find
strange that until that point is the best performing one, specially since
the others seem to reach a plateau of throughput before that point. However
my understanding of these mechanisms is very superficial so I leave the
interpretation to you.

Note that this is with the version without slow nodes.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ratio.png
Type: image/png
Size: 3628 bytes
Desc: not available
Url : http://emu.freenetproject.org/pipermail/tech/attachments/20061130/359a7e35/attachment.png 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: throughput.png
Type: image/png
Size: 3387 bytes
Desc: not available
Url : http://emu.freenetproject.org/pipermail/tech/attachments/20061130/359a7e35/attachment-0001.png