[Author Prev][Author Next][Thread Prev][Thread Next][Author Index][Thread Index]
Re: [tor-bugs] #1854 [Analysis]: Investigate raising the minimum bandwidth for getting the Fast flag
#1854: Investigate raising the minimum bandwidth for getting the Fast flag
---------------------------------------+------------------------------------
Reporter: arma | Owner: arma
Type: task | Status: needs_information
Priority: normal | Milestone:
Component: Analysis | Version:
Keywords: performance loadbalancing | Parent:
Points: | Actualpoints:
---------------------------------------+------------------------------------
Comment(by iang):
OK, so my eyeballing of ~500 MB/s excluded at a 1 MB/s cutoff turned out
to be pretty darned close. ;-)
So at that cutoff, about 15% of the network bandwidth disappears. But
that 15% was spread (highly unevenly) over 2100 relays. Each of those
relays, according to the linf figure, contributed a maximum of about 0.5%
of the bandwidth, and in turn, the remaining relays see at most 0.5% extra
users. (NOTE: that's 0.5% of *all* the users, not 0.5% of what it had
before.)
OK, here's the plot I'm interested in now: x-axis: bandwidth of relay (log
scale). y-axis: one line showing the probability distribution of relay
selection with a 20 KB/s cutoff, and one with a 1 MB/s cutoff. Feel free
to throw other intermediate values in there as well. We'll probably need
a version with a linear y-axis and one with a log y-axis.
Is that easy to do?
--
Ticket URL: <https://trac.torproject.org/projects/tor/ticket/1854#comment:45>
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