mismatch results with disk performance

Dmitry Mityugov dmitry.mityugov at gmail.com
Fri Jun 10 06:49:50 GMT 2005


On 6/9/05, scuba at centroin.com.br <scuba at centroin.com.br> wrote:
> Dmitry,
> 
>         Both situations have the same result, an Slave IDE HDD on primary
> controller, or a master HDD on the 2nd IDE controler, works much more
> slow, testing with 'dd'.
>         I couldn't see that with diskinfo.

I can't reproduce this. On a dual Xeon server with 2 PATA Seagate
disks attached as masters to both IDE channels and a PATA CD-ROM as a
slave on the 1st channel, reading them with dd procuces this:

%dd if=/dev/ad0 of=/dev/null bs=1m count=20
20+0 records in
20+0 records out
20971520 bytes transferred in 0.378772 secs (55367171 bytes/secs)
%dd if=/dev/ad2 of=/dev/null bs=1m count=20
20+0 records in
20+0 records out
20971520 bytes transferred in 0.364243 secs (57575625 bytes/secs)

Please let me know if there is anything else I shall try to reproduce
the problem.

-- 
Dmitry

"We live less by imagination than despite it" - Rockwell Kent, "N by E"


More information about the freebsd-questions mailing list