Subject: Re: The SCSI DMA kernel.
To: Thor Lancelot Simon <tls@rek.tjls.com>
From: David Brownlee <abs@mono.org>
List: port-vax
Date: 10/27/1999 12:50:58
	Is is reasonable to tweak the default of newfs/tunefs to do
	this automatically on __vax__?

		David/absolute

On Wed, 27 Oct 1999, Thor Lancelot Simon wrote:

> On Wed, Oct 27, 1999 at 10:43:31AM +0200, Anders Magnusson wrote:
> > > 
> > > It also depends a lot on the drive you're using and the blocksize you're
> > > using to access the drive.  For instance, if you're hitting the raw device
> > > /dev/rsd0c using `dd' with a block size of 64k vs 4k or 1k, you'll see
> > >
> > Note here that you probably get better performance with 60k than 64k.
> > This is because max transfer size is set to 63k on VAX. 64k will
> > force a request to be split into one big and one small, while a smaller
> > transfer (56k for example) will result only in big transfers.
> 
> This implies BTW that if you're using FFS on your VAX you should set
> "maxcontig" (with tunefs or at filesystem creation time) to 7.
> 
> Incidentally, has anyone tried LFS on NetBSD/vax?
> 
> -- 
> Thor Lancelot Simon	                                      tls@rek.tjls.com
> 	"And where do all these highways go, now that we are free?"
>