[tor-bugs] #14056 [Tor]: IPredator complains that we call time() too much when running over 500Mbps

Tor Bug Tracker & Wiki blackhole at torproject.org
Fri Jan 2 13:22:29 UTC 2015


#14056: IPredator complains that we call time() too much when running over 500Mbps
------------------------+-----------------------------------------
     Reporter:  teor    |      Owner:
         Type:  defect  |     Status:  new
     Priority:  normal  |  Milestone:  Tor: 0.2.6.x-final
    Component:  Tor     |    Version:  Tor: 0.2.5.10
   Resolution:          |   Keywords:  performance tor-relay lorax
Actual Points:          |  Parent ID:
       Points:          |
------------------------+-----------------------------------------

Comment (by teor):

 I just reviewed my profiling of an exit relay running chutney verify with
 200MB of random data (standard chutney verify uses 10KB of random data).
 This is on OS X 10.9.5 with tor 0.2.6.2-alpha-dev running the chutney
 basic-min network.

 In an optimised build of tor, I see around 4% of the CPU usage devoted to
 `time()`.

 Which means that the maximum performance impact of eliminating all calls
 to `time()` on OS X is 4%. (This is not much at all.)

 But OS X doesn't seem to achieve a very high data transfer rate - perhaps
 the issue could become more apparent at higher data transfer rates?
 (Or maybe I need to put more effort into performance tuning tor on OS X
 before I come to any firm conclusions.)

--
Ticket URL: <https://trac.torproject.org/projects/tor/ticket/14056#comment:12>
Tor Bug Tracker & Wiki <https://trac.torproject.org/>
The Tor Project: anonymity online


More information about the tor-bugs mailing list