On Wed, Nov 01, 2006 at 07:58:28AM +0000, Michael Rogers wrote: > toad wrote: > >And there are proposals to deal with this, such as putting in searches > >first unless searches make up more than X% of the total. Or putting one > >transfer block in, then filling the rest up with searches, unless there > >are no transfer blocks or the searches are urgent, in which case we send > >a packet full of searches. > > OK, I'll look into implementing one of these. > > >In both cases these messages are supposed to be before the data blocks. > >And having to wait behind many very large messages will increase latency > >significantly. > > I still don't see how it affects latency - we can't finish processing > the CHK until all the parts have arrived, regardless of what order they > arrive in.
Because 90%+ of traffic is data blocks, and small messages take precedence; therefore any message stuck behind a large number of data blocks will take some time to arrive. > > Cheers, > Michael -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 189 bytes Desc: Digital signature URL: <https://emu.freenetproject.org/pipermail/devl/attachments/20061101/40c1fe6b/attachment.pgp>
