Re: FastSCSI on WarpEngine
On Tue, Mar 04, 2003 at 12:32:28AM +0100, Richard Zidlicky wrote:
> > Regarding to the above text from kernel source, it might get parity errors
> > with 10 MHz, but how "dangerous" is this?
> silent data corruption, that may be very nasty. You would need a few
> days of stresstesting to figure out.
Well, right now there is no time to stresstest it. We're some packages
behind so it is better to run buildd than to do some stresstests...
> I don´t think 2 MB/s is so bad on m68k, there are probably other
> factors than won´t let it go much faster anyway.
Hmm, but 2 MB/s isn't that good as well... could be better and I think I got
better performance under AmigaOS, but that was a few years ago, so I might
be wrong. ;)
Of course, a 060-50 would give some extra boosts in piping data into the
SCSI chain - with the loss of FastSCSI, being unable to use a CybSCSI module
in an A3000 desktop... ;)
I would like to see around 4-6 MB/s coming out of the disks on that machine,
so I wonder how to achieve this. Maybe the mentioned change in the source
code from 50 to 25 would be a way. Instead of facing the frontier and risk
data corruption with 10 MHz transfer a value of 37 could mean 7.5 MHz
transfers... don't know whether this might work or not...
--
Ciao... //
Ingo \X/
Reply to: