Re: TCP limitations (was Re: ISCSI: Urgent Flag requirement violates TCP.)

["Jim Williams" <jimw@giganet.com>]

This is a different draft (not VI) with a different framing proposal.
It does NOT propose using the CRC to discover alignment.  Segment
alignment is recommended, not required.  Connection ID is used
to confirm (or not) alignment.

This draft was for discussion purposes only and might be of interest
regarding the alignment issue.  I would be interested if anyone
besides Doug thinks this is non-conformant with TCP or breaks TCP
in any way.

 - Jim

----- Original Message -----
From: Douglas Otis <dotis@sanlight.net>
To: Jim Williams <jimw@giganet.com>; <ips@ece.cmu.edu>
Sent: Monday, November 27, 2000 5:32 PM
Subject: RE: TCP limitations (was Re: ISCSI: Urgent Flag requirement
violates TCP.)


> Jim,
>
> Dropped the urgent pointer method and retain the VI TCP segment alignment
> with now a required CRC-32.  Segment alignment is not TCP just as is exact
> repeated segments upon retry.  I can't see use of a CRC to discover
> alignment.
>
> Doug
>
>
> > > csapuntz@cisco.com wrote:
> > >
> > > > Given that shim protocol requires no changes to the TCP in the
sender,
> > > > it is currently my favorite way of doing RDMA.
> > > >
> > > > -Costa
> > >
> > > Please see Jeff's message on 10/26.  If you don't have framing, when
you
> > lose
> > > a segment, you need to buffer generic TCP segments on the NIC before
you
> > can
> > > "RDMA" them somewhere, because you don't know where the "RDMA"
> > information
> > is
> > > in the "byte stream".
> > >
> > > -Matt
> > >
> >
> > http://www.ietf.org/internet-drafts/draft-williams-rdmatcp-00.txt
> >
> > is an example of a shim layer that provides a mechanism
> > to recover framing upon loss of TCP segments.
> >
> >
>
>