Subject: Re: SCSI DMA testers wanted.
To: Anders Magnusson <ragge@ludd.luth.se>
From: Jon W Grubbs <jgrubbs@megsinet.net>
List: port-vax
Date: 10/18/1999 13:50:12
Ragge,

Here are the results from a 3100M48 with an RZ23 (SCSI/SCSI)

# dd if=/dev/rsd1c of=/dev/null bs=60k count=1000
1000+0 records in
1000+0 records out
61440000 bytes transferred in 126 secs (487619 bytes/sec)

Which is much better than the PIO numbers!

Also, FWIW, this kernel properly detects the RRD-40 where the stock 1.4.1 
kernel does not in my configuration.  Also a slight surprise to me, ln0 is 
now le0 which confused my init code somewhat :)

Thanks for the effort.

--Jon

At 11:55 PM 10/17/99 +0200, you wrote:
>I have finally gotten some spare time, and have focused on getting the
>VS3100 SCSI DMA engine running. And it seems to work for me now
>on a MicroVAX 3100 anyway :-)
>
>It's quite a bit faster that PIO:
># dd if=/dev/rsd1c of=/dev/null bs=60k count=1000
>1000+0 records in
>1000+0 records out
>61440000 bytes transferred in 111 secs (553513 bytes/sec)
># dd of=/dev/rsd1c if=/dev/zero bs=60k count=1000
>1000+0 records in
>1000+0 records out
>61440000 bytes transferred in 142 secs (432676 bytes/sec)
>
>(on my slow disk)
>
>I would like people to fetch the kernel and test it:
>ftp://subzero.campus.luth.se/users/ragge/netbsd
>
>Tell me about success/strange printouts/etc...
>The driver do _not_ find the root device at bootup.
>
>I have only tried the SCSI/SCSI boards, but I believe that it would
>work on the MFM/SCSI board also.
>
>MicroVAX 2000 is not supported yet, but it is probably easy to get it
>running also.
>
>Have fun,
>
>-- Ragge