> > Here's the dmesg for my Tor exit relay, which runs on a D2700. It moves > > about 2.0-4.5 MB/s in each direction. > > Hmmm.... that's nowhere near as fast as what we do, and not even as fast > as a P3.
I have an N280 1000/1666 MHz netbook which is roughly the same computation power as a P3 750 MHz (reference md5 -tt), and a D525 1800 MHz (Supermicro board) with 2 GigE ports (1 shared IPMI) which is more than twice the N280. The nice thing is that N280 works even when the fan blocks continuously for long periods without thermal shutdown on the lower CPU frequency. The D525 is quite older than the new systems suggested in the thread, and fully saturates the 100 Mbps LAN with SSH so no worries, external networks is << 100 Mbps. That's a 50 Watt system, main issue is heat in the mini-ITX case and fans are noisy for my delicate ears, had to add 2x 60 mm fans to keep it from overheating. Mainboard is picky on RAM so select a good compatible ECC module provider if the system supports it (newer Atoms). The D525 was a bit pricey for me at the time, but works since 2011 without concern. > >It seems to be running at full > > capacity doing so, > > I don't know much about tor. When you say "full capacity", do you mean > the hardware was maxed out, or that you were doing the most that the tor > network would allow you? Recommendation for a very capable router are C2750/C2758 Supermicro board and a case that can use 12 cm fans if you're going to be listening to it. Reference mainboard models: A1SAi-2750F or A1SRi-2758F, those about roughly as half as the computing power of Xeon E3-1230/1245. If I was picking now I'd go for the Xeon E3 anyway instead + dmesg is invaluable.
