[openib-general] [ANNOUNCE] Initial trunk checkin of ISERinitiator

[Christoph Hellwig]

On Fri, Aug 19, 2005 at 08:22:23AM +0300, Yaron Haviv wrote:
> Not sure how you do your LOC counting or what's included in it
> In any case a protocol that is generalized to multiple transports, has
> built in discovery, error-recovery, global routing/naming,
> authentication, built-in multi-pathing, multi-connection per session,
> optimizations for small messages, comprehensive management and
> configuration with industry standard APIs, etc'

 .... is a total mess and nothing you'd want to run in a production
 enviroment.  Point taken ;-)

> The important things is how many LOC are on the command path and how
> optimized it the protocol, this code runs SCSI at 850-900MB/s and on the
> same time provides the most comprehensive set of features, and is
> managed out of the box with industry standard tools  

Which is slower than plain iscsi over 10Gige..

> A variation of that code runs today on PPC, so I assume it's not an
> issue to make sure it runs over PPC 

Maybe on toy ppc processors like the 4xx.  The code won't run on any
non-toy platform with proper iommus without a major rework.  That beeing
said any driver that makes plattform assumptions at all has no business
in the openib.org or mainline kernel tree.