FreeBSD 5.3b7and poor ata performance

[Poul-Henning Kamp]

In message <417CD0CA.8010708 at ng.fadesa.es>, fandino writes:
>Poul-Henning Kamp wrote:
>> In message <417CC2F9.1050900 at ng.fadesa.es>, fandino writes:
>> 
>> 
>>>Robert, I'm trying to understand where GEOM fits in the FreeBSD I/O structure
>>>and I only had found the original McKusick figure:
>> 
>> http://phk.freebsd.dk/pubs contains a number of slidesets and papers
>> relevant to GEOM.
>
>ok, I see it. Then it's impossible bypass GEOM to test character access
>to disks.

yes.

>However I would like to know disk performance of list members using a
>VIA 82C686B chipset. Anyone in the list is using this chipset?

Just a check:  You _have_ disabled all the debugging right ?
WITNESS and all that stuff ?  (See top of src/UPDATING)

-- 
Poul-Henning Kamp       | UNIX since Zilog Zeus 3.20
phk at FreeBSD.ORG         | TCP/IP since RFC 956
FreeBSD committer       | BSD since 4.3-tahoe    
Never attribute to malice what can adequately be explained by incompetence.