It is in kilo _bytes_, isnt it? I think 84MB/s isnt that bad result :).<br><br>[snip]<br>The 'numbers' are in 1000s of bytes per second processed.<br>type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes<br>
aes-128 cbc 51108.77k 68049.87k 73548.62k 73809.19k 75586.27k<br>aes-192 cbc 45487.20k 57737.88k 61597.64k 62914.12k 63948.21k<br>aes-256 cbc 40880.73k 50780.57k 54186.47k 55259.88k 54481.37k<br>
[snip]<br><br>... everything is measured in bytes...<br><br>Well, results are from old laptop, but 51MB/s isnt also so bad...<br><br>Marek<br><br><div class="gmail_quote">On Sun, Feb 22, 2009 at 2:52 PM, Olaf Selke <span dir="ltr"><<a href="mailto:olaf.selke@blutmagie.de">olaf.selke@blutmagie.de</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">hello there,<br>
<br>
as I understood tor spends most of its cpu time within openssl library aes crypto.<br>
Which result of "openssl speed aes" applies to tor? Is it aes-128 cbc 16 bytes?<br>
In this case my old Prestonia P4 Netburst Xeon box's throughput is supposed to<br>
be roughly about 40 MBit/s as middleman. Correct?<br>
<br>
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes<br>
aes-128 cbc 84098.99k 119729.69k 138053.97k 142741.16k 144386.04k<br>
aes-192 cbc 75035.35k 104143.72k 115681.81k 120099.84k 120949.42k<br>
aes-256 cbc 69559.47k 92221.78k 102006.05k 105361.75k 100274.74k<br>
<br>
Strange to say that my desktop Core2 Duo E8400 @home performs only 33% better in<br>
openssl aes crypto than one of the old P4 Netburst Xeon cores from my tor node.<br>
For the sake of better performance I'm thinking about replacing my tor node's<br>
hardware.<br>
<font color="#888888"><br>
Olaf<br>
</font></blockquote></div><br>