[tor-bugs] #9709 [Tor]: We accept way more tap cells than we process

[Tor Bug Tracker & Wiki]

#9709: We accept way more tap cells than we process
-----------------------+------------------------------------
 Reporter:  arma       |          Owner:
     Type:  defect     |         Status:  new
 Priority:  normal     |      Milestone:  Tor: 0.2.5.x-final
Component:  Tor        |        Version:
 Keywords:  tor-relay  |  Actual Points:
Parent ID:  #9657      |         Points:
-----------------------+------------------------------------
 Our fix in #7291 was meant to have us turn away onionskins that we're
 unlikely to get to. But in practice our #9658 patch shows that we're
 accepting way more than we process.

 Linus briefly did a test where he cherry-picked the #9658 patch onto
 0.2.4.16-rc and it was still only handling about 25% of incoming requests.
 His cursory analysis was that he was dropping them with the
 {{{
     log_info(LD_CIRC,
              "Circuit create request is too old; canceling due to
 overload.");
 }}}
 line.

 Should we be refusing these earlier, so clients can know to go elsewhere?

 One possible culprit is that the main Tor thread is too busy to give
 cpuworker events out on time.

-- 
Ticket URL: <https://trac.torproject.org/projects/tor/ticket/9709>
Tor Bug Tracker & Wiki <https://trac.torproject.org/>
The Tor Project: anonymity online