RE: Avoiding deadlock in iSCSI

[Stephen Byan <Stephen.Byan@quantum.com>]

Jim Williams [mailto:jimw@giganet.com] wrote:

> Layering iSCSI on VI avoids the problem below.
> 
> see:
> http://search.ietf.org/internet-drafts/draft-csapuntz-ips-iscs
> ivi-00.txt
> 
> VI layer flow control will be invoked when target is unable 
> to accept more
> commands, but this will not impede flow of data in response 
> to RDMA read
> requests by the target.  Functionally this is equivalent to 
> option 1 below.

I haven't seen much discussion of iSCSI over VI here. I think it makes
sense. Using VI makes the iSCSI remote DMA hardware acceleration available
to other applications besides iSCSI. This broader market should greatly
increase the utility of iSCSI hardware, and thus speed the market
penetration of iSCSI, bringing the usual benefits of customer acceptance,
lower cost, and better implementions courtesy of darwinian competition.

And, as an added bonus, you get flow control on commands for free :-)


Regards,
-Steve

Steve Byan
<stephen.byan@quantum.com>
Design Engineer
MS 1-3/E23
333 South Street
Shrewsbury, MA 01545
(508)770-3414
fax: (508)770-2604