toad wrote: > A few months ago we concluded that mandatory backoff wasn't worthwhile > because we have a separate mechanism (client-side load limiting) to limit > load, and also that it wasn't fair on users with few connections, and so > made backoff advisory rather than mandatory. I.e. a node will consider > nodes which are not backed off first, but will route to backed off nodes > if it has no other alternative.
Ah, I didn't realise that, I'll update my code. > Obviously the truth will be best known if a minority of the simulation > are very slow / overloaded by external causes, as I said before. Yup, heterogeneous capacity is the next thing I intend to look at. Cheers, Michael
