Slave IDE HDD not working in UDMA5
Bruce Evans
bde at zeta.org.au
Mon Jun 20 12:49:17 GMT 2005
On Thu, 16 Jun 2005 scuba at centroin.com.br wrote:
> This was first posted on freebsd-question, but I could not find
> the solution yet.
> Maybe you could help me.
Maybe a little. I don't use 5.4...
> I´ve installed FreeBSD 5.4 on a new machine with the following
> hardware:
>
> Asus P4P800 SE (BIOS v. 1008)
> 2GB RAM ( 4x 512 DDR400 )
> 2 HDD Samsung SP0802N (80GB 7200rpm ata-100) 80 pins cable.
>
> The HD were formated with newfs defaults, and the following
> results were the same using both as master (primary e secondary) or with a
> master / slave (same interface).
>
> With diskinfo both performance are the same, but with "dd", the
> second disc (the slave or the secondary master), is always worst as if it
> were working in DMA2.
I remember a commit to the ata driver to fix misprogramming of DMA timing
on an Intel chipset for devices and/or channels other than the first. I'm
not sure if 5.4 has the bug or the fix.
diskinfo only tests reading, and you only showed a dd test using writing
(to a file), so the problem is apparently only that writing to the second
drive is slow.
> what should be the right results?
Swap the devices to see if it is a drive problem (unlikely with the
same model of drive but... I have one system that apparently has
worse timing on the secondary channel. This showed up as writes
causing subsequent reads to be slow -- apparently the writes caused
some errors and error correction as perfect except for slowing things
down).
Bruce
More information about the freebsd-performance
mailing list