On Fri 15 Aug 2003 at 16:36:26 +0200, Jochen Kunz wrote:
> On Fri, Aug 15, 2003 at 02:42:25PM +0200, Olaf Seibert wrote:
> > Would adding an IDE card help despite my DMA troubles, do you think?
> Possibly. AFAIK the more modern IDE adapters have working DMA. 

Ok, I got a Promise Ultra133 TX2 card. These are my boot messsages:

pciide1 at pci1 dev 10 function 0: Promise Ultra133/ATA Bus Master IDE Accelerator (rev. 0x02)
pciide1: bus-master DMA support present
pciide1: primary channel configured to native-PCI mode
pciide1: using dec 550 irq 20 for native-PCI interrupt
wd0 at pciide1 channel 0 drive 0: <IBM-DPTA-353750>
wd0: drive supports 16-sector PIO transfers, LBA addressing
wd0: 35772 MB, 16383 cyl, 16 head, 63 sec, 512 bytes/sect x 73261440 sectors
wd0: 32-bit data port
wd0: drive supports PIO mode 4, DMA mode 2, Ultra-DMA mode 4 (Ultra/66)
wd0(pciide1:0:0): using PIO mode 4, Ultra-DMA mode 4 (Ultra/66) (using DMA data transfers)
pciide1: secondary channel configured to native-PCI mode

On the first access of wd0 I get this (despite using the 80-wire cable
that came with the card):

wd0: transfer error, downgrading to Ultra-DMA mode 2
wd0(pciide1:0:0): using PIO mode 4, Ultra-DMA mode 2 (Ultra/33) (using DMA data transfers)
wd0c: error reading fsbn 0 (wd0 bn 0; cn 0 tn 0 sn 0), retrying
wd0: (aborted command, interface CRC error)
wd0: soft error (corrected)

Is this something to worry about?

In the mean time, performance has gone up considerably. In a simple test
(dd from a big file) I got about 3,6 M/s with 90% interrupt time, now I
get about 12 M/s with around 1% interrupt time (according to top).

-Olaf.
-- 
___ Olaf 'Rhialto' Seibert - rhialto@       -- "What good is a Ring of Power
\X/ polderland.nl            -- if you're unable...to Speak." - Agent Elrond