Hi On a technical note, RAMBO maintains multiple active replica configurations and hence i would think r/w is costly. Etna (http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.4911) is a protocol that works over Chord DHT to provide atomic read writes and is inspired from RAMBO as mentioned in the paper. This might give some ideas w.r.t Freenet and also claims to work well with high churns.
Kryptos On Wed, Dec 15, 2010 at 4:43 PM, Matthew Toseland <toad at amphibian.dyndns.org> wrote: > On Tuesday 14 December 2010 08:01:48 Colten Jackson wrote: >> Has anyone seen/read this? >> >> http://groups.csail.mit.edu/tds/papers/Gilbert/rambo-journal3.pdf >> >> "In this paper, we present RAMBO, an algorithm for emulating a read/write >> distributed shared memory in a dynamic, rapidly changing environment. RAMBO >> provides a highly reliable, highly available service, even as participants >> join, leave, and fail. In fact, the entire set of participants may change >> during an execution, as the initial devices depart and are replaced >> by a new set of devices. Even so, RAMBO ensures that data stored in the >> distributed shared memory remains available and consistent." >> >> Hopefully some of the ideas in the paper can be helpful to freenet's goals. >> > And by reading them we expose ourselves to triple damages when we implement > something similar and they sue us for patent infringement (versus > implementing the same thing having thought of it ourselves). Great idea. What > is our attitude to published literature and patents? IMHO anything MIT > publishes that is useful there is a good chance it's patented... > > _______________________________________________ > Devl mailing list > Devl at freenetproject.org > http://freenetproject.org/cgi-bin/mailman/listinfo/devl >
