Subject: Re: MAXBSIZE should be MAXPHYS; a yes vote!
To: None <firstname.lastname@example.org, rhealey@MR.NET>
From: Missing - presumed fed. <greywolf@defender.VAS.viewlogic.com>
Date: 11/10/1995 10:00:27
If this is disk transfers we're talking here, I thought MAXPHYS maxed out at
63K (126 blocks) per transfer.
If not, wolf is blowing smoke again and you can go about your business :-)
#define AUTHOR "email@example.com (Martin Cracauer)"
* I found 32K to be sufficient for maximum performance on my
* system. Whatever the reason to set it 16K was, maybe saving memory, it
* should be reconsidered before setting this value to something
* 64KB, whihc is MAXPHYS on i386, BTW, break the current i386 port
* (tested with sup 19951106).
* Here are some numbers, this is sup19950927:
* Setting MAXBSIZE to more that 16 K and up to 57K works and gives
* the following bonnie results. The machine is P90, triton, NCR 810,
* older barracouda 2 GB.
[ figures deleted ]
#undef AUTHOR /* "firstname.lastname@example.org (Martin Cracauer)" */
Are you being infected by a UNIX virus? If you're receiving OS shipments
from your vendor, you may be subjecting your computer to the worst virus
in history: SVR4. There is a cure for this virus: upgrade to NetBSD
(now running on a platform near you).