Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 29 Jan 1998 05:20:25 +0100 (MET)
From:      Luigi Rizzo <luigi@labinfo.iet.unipi.it>
To:        bac@sympatico.ca (Brian Campbell)
Cc:        freebsd-hackers@FreeBSD.ORG
Subject:   Re: Busmastering code for IDE drives in 2.2.6?
Message-ID:  <199801290420.FAA05338@labinfo.iet.unipi.it>
In-Reply-To: <19980128185953.56562@pobox.com> from "Brian Campbell" at Jan 28, 98 06:59:34 pm

next in thread | previous in thread | raw e-mail | index | archive | help
> > > with the big code merges into 2.2.5-STABLE over the last weeks, I wonder
...
> That's the easy answer.
> 
> It requires two files (/sys/pci/ide_pci.c and /sys/ide_pcireg.h) to be added,
> two files (/sys/i386/isa/wd.c /sys/i386/isa/wdreg.h) to be replaced, and
> a line to be changed in /sys/i386/conf/files.i386.
> 
> I've been running with it in 2.2-x since it was announced and it
> works just fine.  Hardly a dramatic change.  However, I've asked
> the same question before and met with the same disapproving glare.

perhaps you can put together a small .tgz which goes into some
"experimental" or "unsupported" directory so that people can try
it even if it's not into the source tree.

I did the same with PnP and snd driver and I think it was useful
to several people.
Talk to Jordan about this.

NOTES:

1) I don't believe that there is any risk of the "unsupported" dir
   becoming a kitchen sink, especially if we restrict to
   features/kernel modules which are considered of some interest
   or already are in -current and have little impact on the rest of the
   system (i.e. I would not expect a smp.tgz package, but I _would
   like_ to see there the various splashkits or the cbq package which
   was posted some time ago, or possibly an IPV6 implementation...)

2) about the IDE busmastering code, I still would like to see some
   good benchmark result showing when/how it improves performance.
   The only comment I have seen (from the author ?) is that it
   improves throughput by a few percent under moderate load, but no
   data on how it behaves say with concurrent activity on the IDE bus,
   or with heavily loaded systems.

	Cheers
	Luigi
-----------------------------+--------------------------------------
Luigi Rizzo                  |  Dip. di Ingegneria dell'Informazione
email: luigi@iet.unipi.it    |  Universita' di Pisa
tel: +39-50-568533           |  via Diotisalvi 2, 56126 PISA (Italy)
fax: +39-50-568522           |  http://www.iet.unipi.it/~luigi/
_____________________________|______________________________________



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199801290420.FAA05338>