Ultra ATA card doesn't seem to provide Ultra speeds.

[Ruben de Groot]

On Fri, Aug 01, 2003 at 04:33:08AM +0200, mh typed:
> Soeren Schmidt wrote:
> 
> >It seems Buckie wrote:
> > 
> >
> >>I ran a dd:
> >>dd if=/dev/ad1 of=/dev/zero ibs=8192
> >>
> >>OH, you need to output to /dev/null NOT /dev/zero :)
> >>   
> >>
> It doesn't matter as far  as  cdevsw entry  for zero-device write leads 
> to null_write() in /usr/src/sys/dev/null.c
> 
> I was testing the memory to memory copy through a driver using /dev/null 
> and /dev/zero and with
> dd if=/dev/zero of=/dev/null
> I get  till  4.2Gb/s.  Is  it  a  maximum  for memory throughout + cpu 
> work ? (2.4GHz Laptop  with SDRAM)

The following comparison is probably bogus, but can anybody explain the 
huge difference?

1) FreeBSD 4.8-STABLE, 2x 1Ghz PIII, 512MB Memory

bsdbox> dd if=/dev/zero of=/dev/null bs=1m count=10000
10000+0 records in
10000+0 records out
10485760000 bytes transferred in 23.482885 secs (446527758 bytes/sec)

2) Linux 2.4.21, 1x 2.6Ghz PIV, 512 MB Memory

linbox> dd if=/dev/zero of=/dev/null bs=1M count=10000
10000+0 records in
10000+0 records out
10485760000 bytes transferred in 0.308408 seconds (33999639291 bytes/sec)

-Ruben

> Varying the bs parameter from 512 to 65536, I get a linear progression 
> until bs=65536 (previous throughout) but  the relative throughout is 
> lower for bs=1024. Someone could explain?
> 
> 
> 
> 
> _______________________________________________
> freebsd-hackers at freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
> To unsubscribe, send any mail to "freebsd-hackers-unsubscribe at freebsd.org"