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

[Tor Bug Tracker & Wiki]

#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 dgoulet):

 This surprises me. I've been running perf on my fast relay
 (https://globe.torproject.org/#/relay/A69221A7EC7498D2F88A0FB795261013FA36CAAE)
 and time call is just far from being the top CPU consumer...

 On Linux, getting the time is a vdso so unless somehow their time call
 became a syscall, I don't see how this could all of the sudden become a
 huge impact. A very quick strace of the process could tell us if they see
 syscall for time (or perf/ftrace/lttng/<insert tracer>).

 If not, I would first suspect a kernel issue here with a rate that large.

--
Ticket URL: <https://trac.torproject.org/projects/tor/ticket/14056#comment:2>
Tor Bug Tracker & Wiki <https://trac.torproject.org/>
The Tor Project: anonymity online