[tor-talk] (no subject)

[Roman Mamedov]

On Tue, 11 Aug 2015 15:28:01 -0700
Yuri <yuri at rawbw.com> wrote:

> On 08/11/2015 15:13, Ryan Carboni wrote:
> > Why is there no multicore support for Tor? I haven't been able to find an
> > answer to this question.
> 
> This is maybe because even with the quite high for the Tor network 
> bitrates of 5-6MBps tor process never comes close to 100% CPU usage on 
> the average hardware. So multicore capability will add no benefit.

> never comes close

> to 100% usage

> never

*Repeatedly headbangs on the desk*

Uhm so what was I talking about. Ah yes, I believe that's not the case. It
would add a great deal of benefit actually.

As to why it's not implemented, I think simply because no one has coded it yet.
Often things tend to not exist until someone creates them. For the reason why
it's not added, my guess is because it is rather difficult. And yeah, maybe
because other priorities, such as the need to work on other features and keep
the code reasonably simple still outweigh the performance benefit from proper
multi-threading.

Currently Tor can use about 130-150% of a CPU, so if you have 4 cores you
could run 2 copies of Tor on the same IP and attain a reasonable degree of
your resources' utilization.

-- 
With respect,
Roman
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 198 bytes
Desc: not available
URL: <http://lists.torproject.org/pipermail/tor-talk/attachments/20150812/8c0b7701/attachment.sig>