On Tue, Mar 28, 2000 at 08:22:22AM -0500, Mike Bilow wrote:
> > >From the CPU load on the raid-1 soft IDE test, I think seems likely that you
> > didn't have DMA enabled. Could that be possible ?
> >
> > It doesn't make sense to have 97% CPU load when reading with 4 MB/s unless
> > it's done with port I/O.
>
> I am not sure I agreed with that. Here is a test on a 166 MHz Pentium
> with a Triton PIIX IDE chipset:
>
> -------Sequential Output-------- ---Sequential Input-- --Random--
> -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
> Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
> 100 1835 98.2 6728 30.2 3301 34.1 1844 94.5 9390 41.8 173.3 5.7
unfortunately i don't have any hard benchmark results with me at the
moment, but i got well over 20meg/sec with 4 x IBM Deskstar 20GB 7200RPM
drives. (they're the DPTA ones or whatever - the ones with 2MB of cache).
each was running off its own IDE channel, two of them on ATA/33 and two of
them on ATA/66. (BP6+HPT366, if anybody cares.)
also, try hdparm -c3 -X66 at the very least :).
next time i put linux back on here, i'll do another test.
--
: Andre Pang <[EMAIL PROTECTED]> - Purruna Pty Ltd - ph# 0411.882299 :
: #ozone - http://www.vjolnir.org/ozone/ | trust in love to save :