Re: aes performance

[slush <slush@xxxxxxxx>]

Oh, also dont forget that openssl speed runs only on one core!

I tested it on my server 2x dualcore Xeon 3GHz and results:

type             16 bytes     64 bytes    256 bytes   1024 bytes   8192 bytes
aes-128 cbc      92860.55k   120028.42k   130562.36k   132490.03k   135248.26k
aes-192 cbc      82754.33k   102625.36k   110524.08k   113481.96k   114419.55k
aes-256 cbc      74095.94k    90670.80k    96039.18k    97677.96k    98717.71k

.. but you have to multiple number by 4. So teoretical limit (in my case) is 371 MB/s and it is absolutely enough to run fast Tor node :-). I dont know how much cores you have, but dont forget on that...

Marek

On Sun, Feb 22, 2009 at 2:52 PM, Olaf Selke <olaf.selke@xxxxxxxxxxxx> wrote:

hello there,

as I understood tor spends most of its cpu time within openssl library aes crypto.
Which result of "openssl speed aes" applies to tor? Is it aes-128 cbc 16 bytes?
In this case my old Prestonia P4 Netburst Xeon box's throughput is supposed to
be roughly about 40 MBit/s as middleman. Correct?

type             16 bytes     64 bytes    256 bytes   1024 bytes   8192 bytes
aes-128 cbc      84098.99k   119729.69k   138053.97k   142741.16k   144386.04k
aes-192 cbc      75035.35k   104143.72k   115681.81k   120099.84k   120949.42k
aes-256 cbc      69559.47k    92221.78k   102006.05k   105361.75k   100274.74k

Strange to say that my desktop Core2 Duo E8400 @home performs only 33% better in
openssl aes crypto than one of the old P4 Netburst Xeon cores from my tor node.
For the sake of better performance I'm thinking about replacing my tor node's
hardware.

Olaf