Jan Edler <[EMAIL PROTECTED]> writes:
> > Sustained? How are you measuring? The ST317242A's are rated at a
> > fairly typical 8.5 MBytes/sec sustained. Your numbers are pretty good.
> measurements is a lack of repeatability. I see about 10% variation from
> run to run. For the ST317242A, Seagate simply claims >8.5MB/s.
http://www.seagate.com/support/disc/specs/st317242a.shtml says
internal transfer rate is up to 188 Mbits/sec, ie 23.5MB/s. This would
be on the outer tracks, and the inner tracks would be about third of
the speed, as in around 8.5MB/s. Average transfer rate would indeed
make 60MB/s over 6 drives quite a reachable goal, but not something
you can rely on in all situations.
> One thing I have observed in comparing various recent cheap Seagate ATA
> drives against fancy SCSI drives (Seagate Cheetah 9LP and IBM Ultrastar
> 18ZX), is greater variation in sustained transfer rates from the inner
> to the outer cylinders. I've measured >14MB/s sustained at the fast end
> of the ST317242A. The slow end is much closer to the claim of 8.5MB/s.
> On the fancy SCSI drives, I see much less variation, like from 12-15MB/s.
The platters have just as much variation due to purely physical
constraints. SCSI's support for IO queuing allows the drive to reorder
access, which probably reduces the effect of both ends of the platter
and brings the overall performance closer to the average. I assume
your ATA tests were done over multiple controllers so SCSI's ability
to command multiple devices in parallel was not a factor in the tests.
--
Osma Ahvenlampi
