|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] Re: Status summary on multiple connections> David: > > If a TCP stack were to allow delivery out of order... and I don't > see how it could since by definition it is a stream of bytes > sent in order... it would have to keep track of the segments > it has received and prevent duplicates from being propagated up > to the application above. As you state, SACK helps, but it can NOT > eliminate the duplicates that MAY show up. I think the TCP stack > itself would HAVE to track all of this not the application... > > I really do NOT see how one can allow a TCP to deliver out of order > though, oh > I know technically how to do it, but it is a fundamental violation > of what TCP is supposed to be delivering.... i.e. the bytes being > transfered from 0 to N... David, I think the discussion is about command reordering issues in the Symmetric model case, with multiple connections. Since commands within a single iSCSI session are distributed on multiple TCP connections, it is quite likely that one TCP connection delivers ahead of another even if each TCP connection delivers an ordered byte stream. Regards, Venkat Rangan venkat@rhapsodynetworks.com www.rhapsodynetworks.com 510-249-0197
Home Last updated: Tue Sep 04 01:06:51 2001 6315 messages in chronological order |