On Sun, Oct 17, 2010 at 5:30 PM, David Dillow <[email protected]> wrote:
>
> On Sun, 2010-10-17 at 10:51 +0200, Bart Van Assche wrote:
> > Information about why part of the implementation has been reworked is
> > missing. Information about whether or not the reworked implementation
> > has been tested is missing too.
>
> Bart,
>
> This series has been tested as thoroughly as I possibly can. I've tried
> to analyze it for races for the months we've gone back and forth. I have
> run it against hardware RAIDs that don't use SRP_CRED_REQ, and against
> the SCST SRP target, which probes for it, but currently seems to only
> use it on reset. Feeling that both were insufficient, I then wrote an
> SRP test target that solely uses SRP_CRED_REQ to return credits, and ran
> against that.

(resending as plain text)

Thanks for the feedback. With regard to testing, that seems sufficient
to me. And with regard to the SCST SRP target: if you would have asked
me how to let it generate SRP_CRED_REQ information units, I could have
explained it to you.

Bart.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to