On Tue, 7 Apr 1998, Tim Pickering wrote:
> well, hdparm -tT says there isn't much difference between PIO and DMA
> modes for EIDE in terms of thruput, but in the real world DMA mode is
There isn't. Throughput is mostly bound by bus and drive speed. The
difference is that the PIO modes use extra CPU.
> grind away indefinitely and i don't know the difference other than the
> noise. i also have SCSI drives on an NCR810 PCI controller and some
> simple benchmarks i've done (cp of large files, dd to and from the
> drive) show that if anything the SCSI drives use a little more CPU
How did you perform these benchmarks? I find it hard to believe that any
form of IDE would outperform an NCR SCSI controller given drives of
comparable quality. The standard CPU-usage utilities such as ps and top
are not reliable indicators in cases such as this, because they only
measure CPU usage in the computational sense, not bus related performance
issues.
> insufficient cooling. i like IBM drives a lot, but they're harder to
> find and tend to cost a little more. i kinda worry sometimes that
I don't actually have any IBM drives, but it seems that they are about the
best quality you can get. Some of them seem to have some funny loadouts
of cache though...
--
PLEASE read the Red Hat FAQ, Tips, Errata and the MAILING LIST ARCHIVES!
http://www.redhat.com/RedHat-FAQ /RedHat-Errata /RedHat-Tips /mailing-lists
To unsubscribe: mail [EMAIL PROTECTED] with
"unsubscribe" as the Subject.
