RE: VI (Was: Avoiding deadlock in iSCSI)

[Michael Krause <krause@cup.hp.com>]

At 07:07 AM 9/18/00 -0700, Stephen Byan wrote:
>  My point was that in return for the
>pain, we can leverage the utility of the RDMA hardware assists, since the
>assists would be encapsulated in the VI layer, rather than intimately part
>of the iSCSI protocol. Consequently the RDMA hardware could be reused to
>accelerate other new protocols, as well as cluster message passing.

RDMA != VI though VI does use RDMA technologies.  Prefer to see discussion 
focused on what RDMA operations are required, what are the error and 
ordering requirements, etc.  Much of this has been improved upon within 
InfiniBand and would ideally just be "lifted" from that architecture with 
minimal if any modifications.  The rest of the functionality within VI or 
InfiniBand could be used / avoided as required.

>I think an enlarged market for the hardware is important in order to ensure
>the success of iSCSI.  iSCSI depends on getting RDMA hardware acceleration
>NICs into the servers. Consider two product scenarios:
>
>1) a NIC with RDMA hardware acceleration for iSCSI.
>2) a NIC with RDMA hardware acceleration for iSCSI, DAFS, MPI, Oracle
>Parallel Server, DB2 extended edition, and which is open to future
>applications.

Focus is how to consolidate the protocol and technology used to deliver 
storage, IPC, etc. across IP-based networks.  This will provide customers 
with the lowest total cost of ownership, reduce customer management / 
physical component requirements, reduce vendor development costs, and 
reduce hardware requirements (e.g. reduce the number of I/O chips / slots 
required per server / storage endnode).  As such, a general purpose RDMA 
solution which operates over TCP/IP is the optimal solution to pursue since 
it will lead to the broadest industry and customer adoption rate.

Mike