[Author Prev][Author Next][Thread Prev][Thread Next][Author Index][Thread Index]

Re: [tor-bugs] #30901 [Core Tor/Tor]: Add control port trace logging to tor



#30901: Add control port trace logging to tor
-----------------------------------+------------------------------------
 Reporter:  teor                   |          Owner:  (none)
     Type:  enhancement            |         Status:  new
 Priority:  Medium                 |      Milestone:  Tor: 0.4.2.x-final
Component:  Core Tor/Tor           |        Version:
 Severity:  Normal                 |     Resolution:
 Keywords:  tor-ci-fail-sometimes  |  Actual Points:
Parent ID:  #29437                 |         Points:  1
 Reviewer:                         |        Sponsor:  Sponsor31-can
-----------------------------------+------------------------------------

Comment (by catalyst):

 Replying to [comment:3 catalyst]:
 > Replying to [comment:2 teor]:
 > > Hi catalyst,
 > >
 > > I'd like to make progress on this ticket today or tomorrow:
 > >
 > > Replying to [comment:1 nickm]:
 > > > For outgoing responses and events, I'd like catalyst's POV: they are
 actively refactoring that code right now, and probably have a better idea
 of how to hook it than I do.
 > >
 > > Here's one way we could move forward:
 > >
 > > I write a patch, and then you refactor it so that it fits in the new
 control code.
 > >
 > > Let me know if you'd like me to do it another way.
 > If you're OK with hooking `control_write_reply()` and missing the set of
 control protocol writers that don't yet funnel through there, that might
 be best. I think after #30889 is merged, the remaining control protocol
 writers that don't go through that are the async control events,
 `GETINFO`, and `GETCONF`. (I'd have to check again to be more sure.)
 Looking at my notes, it seems to be `GETCONF` (not `GETINFO`, sorry for
 misremembering), `MAPADDRESS`, and the async control events that use
 `connection_add_buf()` directly. I guess you could wrap specifically the
 `connection_add_buf()` that are related to the control protocol.

 The control reply refactor work that I'm working on is #30984. I think we
 can minimize conflicts in that code if you stick to wrapping the callers
 of `connection_add_buf()` that talk to the control protocol. Or we can
 talk more about coordinating more invasive changes if you think that's
 better.

--
Ticket URL: <https://trac.torproject.org/projects/tor/ticket/30901#comment:4>
Tor Bug Tracker & Wiki <https://trac.torproject.org/>
The Tor Project: anonymity online
_______________________________________________
tor-bugs mailing list
tor-bugs@xxxxxxxxxxxxxxxxxxxx
https://lists.torproject.org/cgi-bin/mailman/listinfo/tor-bugs