[tor-bugs] #4086 [Analysis]: Compare performance of TokenBucketRefillInterval params in simulated network

[Tor Bug Tracker & Wiki]

#4086: Compare performance of TokenBucketRefillInterval params in simulated
network
-------------------------------------+--------------------------------------
 Reporter:  arma                     |          Owner:       
     Type:  task                     |         Status:  new  
 Priority:  normal                   |      Milestone:       
Component:  Analysis                 |        Version:       
 Keywords:  performance flowcontrol  |         Parent:  #4465
   Points:                           |   Actualpoints:       
-------------------------------------+--------------------------------------

Comment(by arma):

 Replying to [comment:22 robgjansen]:
 > I just attached
 [https://trac.torproject.org/projects/tor/attachment/ticket/4086/refill_20120313.pdf
 another set of experimental results]. The differences from the original
 setup are:
 >
 >  * relay capacity is based on observed bandwidth rather than consensus
 weights
 >  * run on my 2.2 GHz server instead of EC2
 >  * added a "refill every 50 ms" experiment
 >
 > The results are a bit different than before. This is expected given the
 changes in relay capacity.

 Exciting! For your "no ewma, bulk download, refill 1/s" case, it looks
 like 60% of them finish in a reasonable time, and the other 40%...what?
 That's a high fraction of cases that look basically broken.

 It looks like in the ewma case, refilling more than 1/s is the best option
 for bulk downloaders? Why would refilling more often slow them down so
 much? Are we just seeing network breakdown because we kept the load the
 same while reducing the capacity too much? Hm.

 >Perhaps we want to pick a couple of refill settings in which we are most
 interested, do 5-10 runs each, and show the cumulative performance to
 reduce variances?

 Do you think there's a lot of variance from one run to the next? Is the
 variance from the choice of topology? You're already averaging lots of
 individual fetches from clients I believe. What else might be big
 contributing factors to variance?

-- 
Ticket URL: <https://trac.torproject.org/projects/tor/ticket/4086#comment:24>
Tor Bug Tracker & Wiki <https://trac.torproject.org/>
The Tor Project: anonymity online