This message is from the T13 list server.
Mark Overby wrote:
As far as backwards compatbility goes, I was arguing against changing the way freeze lock works as Thomas Jensen had suggested: "Some thing like the BIOS must issue a command before the first read command for the drive not to be frozen perhaps". You'll break a lot of platforms (embedded or non-embedded).
Agreed.
SFL is neither recommended or not recommended by T13. (It's not the job of a standards body to recommend the use or non-use of an optional feature in the standards). Ultimately this is a customer (end-user and OEM / MB) decision.
That's a very politically correct answer :)
In the context of this thread, and my message, "T13" was referring to the collective wisdom of T13 reflector regarding SFL usage on one of the highest-volume platforms on the planet.
> I question the 66% number, but that's mainly because
I don't know how they generated their sample set to know if it is
statistically valid or not.
Agreed; I am interested in hearing details on the number as well.
Speaking purely on my interactions with my customers, SFL is a requirement for many of them (and has been for some time), but ultimately they get to make the decision. It's not up to T13 (since we don't do compliance testing), me (as a chipset / HBA vendor), or the drive manufacturers to enforce an optional feature to a customer who is building a system.
Enforce, no.
But there has got to be _some_ method of making cross-vendor platform recommendations, some way of collecting "wisdom" of the T13 reflector?
Anecdotal evidence seems to suggest that, at a minimum, a large number of system vendors are probably unaware of SFL's existence, and haven't even evaluated it enough to come to any sort of conclusion.
Jeff
