On Thu, 24 Apr 2003, Jon LaBadie wrote:

> On Thu, Apr 24, 2003 at 11:45:02AM -0400, Mitch Collinsworth wrote:

> > Yes, I agree.  This sounds suspicious.  The slowdown described sounds
> > like exactly what happens with DLT4000 and DLT7000 when you can't feed
> > them data fast enough to keep them streaming.  Supposedly this was fixed
> > somewhat in DLT8000 but I never bought one to verify that claim.  I've
> > never heard of anyone claiming this also happens with compression.
>
>
> I mentioned earlier today attending a tape technology talk.
> This sounds like the "adaptive speed" the presenter mentioned saying
> that if the source could not keep up with the drive, rather than dropping
> out of streaming mode it would switch to writing at a slower rate.

Something like that.  If I remember correctly the DLT8000 implementation
is to continue streaming the tape at the same physical speed, but write
the data with varying density depending on data speed.  This implies that
if you don't keep the tape input queue fed you'll no longer know how much
data will fit on a tape.  But that's already somewhat true when using
h/w compression...

-Mitch