Port-vax archive
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]
Re: Performance degradation over time on VAX...
My posting is related to original work by Johnny Billquist:
> Had a bit of discussions about NetBSD on VAXen (on discord of all places), and the perceived performance degradation over time.
He demonstrated this by running "dd" on several NetBSD VAX releases illustrating disk performance had dropped significantly with newer releases.
My posting is a second follow-up to his original posting. Boot a release ISO, drop to a shell and run a "dd" command.
My comment about the boot loader is only to indicate that I did not have the patience to wait more than 15 or 20 minutes for a release ISO to boot, from the NetBSD 6.x era, so I was unable to run my tests there. I did not encounter this issue with simH.
From my testing this morning, I found that with NetBSD 7 and onward, the boot loader was dramatically faster and this remained so up to 11rc5, FWIW.
________________________________________
From: Jason Thorpe <thorpej%me.com@localhost>
Sent: Monday, June 29, 2026 3:45 PM
To: Ken Wellsch
Cc: port-vax List
Subject: Re: Performance degradation over time on VAX...
> On Jun 29, 2026, at 12:08 PM, Ken Wellsch <kcwellsch%outlook.com@localhost> wrote:
>
> ... I also wanted to try testing on some real hardware.
>
> In this case, a vaxstation 4000/60 and a zuluscsi card.
>
> The simH testing I did was MSCP disk path, while this hardware is SCSI based.
>
> The 6.x releases and to a lesser extent, the 5.x releases, I had to give
> up booting them. The boot loader was just too slow to load. (I left one
> of the 6.x run while I got lunch - it was still loading on my return)
The **bootloader** got that much slower???
-- thorpej
Home |
Main Index |
Thread Index |
Old Index