Mailing List Archive: Anycast stability experiment results?

By the way, has there been any initial data from the near-month of
data being collected by users of
http://rip.psg.com/~randy/anycast_gatherer-1.4.tar.gz
...or where should we watch for more details, since presumably one
if not more locations of its announcement is not likely to be
re-visited by the authors?

randy had said:
> [. fyi, my personal bet is that it's usually pretty stable except
> for sites in strangely unstable routing environments. but i am
> under my quota of wrong for the week. ]

My opinion extends to presuming that networks with issues visible
in off-net anycast are generally not deterministic in steady state
and fail the third need of goodput in the classic "paths must be
short, fast and stable" troika.

Cheers,

Joe

--
RSUC / GweepNet / Spunk / FnB / Usenix / SAGE

> By the way, has there been any initial data from the near-month of
> data being collected by users of
> http://rip.psg.com/~randy/anycast_gatherer-1.4.tar.gz
> ...or where should we watch for more details, since presumably one
> if not more locations of its announcement is not likely to be
> re-visited by the authors?

i believe, but could be very wrong, that the measurement has been
stopped on all hosts except some planetlab nodes (we want to be
able to compare planetlab to the real internet). peter is a grad
student, and finals were last week. so he is just starting to
take the first looks at the data. for starters, he says he is
trying to look at geo and topo distribution of both sources and
responding servers.

randy