Tor client performance

[Olaf Selke]

Andrew Lewman wrote:
> On Monday May 10 2010 10:21:24 Olaf Selke wrote:
>> Was it me?
> 
> Unofficially, I think no.  I would be concerned in one relay, as fast as 
> blutmagie's are, could have this much impact on the network.

about 25% of all traffic reported by nodes flagged as exit are relayed
by blutmagie (23MB/81MB). Besides improved latency the new blutmagie3
and blutmagie4 nodes provide some 80 MBit/s additional bandwidth.

> My sneaking suspicion is that it's related to China unblocking the Tor network 
> in April, and re-blocking it on May 4th.

probably Chinese government won't does us the favor to unblock Tor again
just for educational purpose. On the other hand we can easily stop two
blutmagie nodes, overload the remaining two again and watch the latency
graphs. We should get a better understanding how Tor network behaves in
stress.

Olaf