[openib-general] [ANNOUNCE] Initial trunk checkin of ISERinitiator
Christoph Hellwig
hch at lst.de
Fri Aug 19 07:26:02 PDT 2005
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.
More information about the general
mailing list