Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 30 Oct 1999 14:36:48 -0400 (EDT)
From:      Brian Fundakowski Feldman <green@FreeBSD.org>
To:        Andrew Atrens <atrens@nortelnetworks.com>
Cc:        current@freebsd.org
Subject:   Re: K6-III wrtalloc + mtrr support ?
Message-ID:  <Pine.BSF.4.10.9910301402380.94474-200000@green.myip.org>
In-Reply-To: <Pine.BSF.4.20.9910301334290.68077-100000@hcarp00g.ca.nortel.com>

next in thread | previous in thread | raw e-mail | index | archive | help
  This message is in MIME format.  The first part should be readable text,
  while the remaining parts are likely unreadable without MIME-aware tools.
  Send mail to mime@docserver.cac.washington.edu for more info.

--0-1484207744-941308498=:94474
Content-Type: TEXT/PLAIN; CHARSET=US-ASCII
Content-ID: <Pine.BSF.4.10.9910301435391.94587@green.myip.org>

On Sat, 30 Oct 1999, Andrew Atrens wrote:

> 
> On Fri, 29 Oct 1999, Brian Fundakowski Feldman wrote:
> > 
> > I disabled (or asked Peter to, actually) the K6-2+ MTRR driver a while
> > back because with XFree86 3.9.16 (an alpha which uses MTRR support) it
> > would cause memory corruption.  It's very strange, and something I
> > really haven't figured out... If you want to enable it, go ahead, but
> > be very wary; if you do find out what's wrong, let me know.
> 
> I remember this now, I was one of those that got bit by this problem. What
> I recall is that MTRR support made a dramatic speed improvement, but alas
> was _extremely_ unstable. That was when I had an ATI Expert@Work card.
> Since then I've gotten a 3dfx Voodoo3, perhaps this card might be more
> stable? So Brian, how do I switch this back on ?

If you REALLY want to do this, which I wouldn't recommend since it
caused instability on my TNT too... But if you do, please apply the
included patch and give me the output it has generated.  This is my
last resort in checking if I possibly did something wrong :(
Uncomment this line in src/sys/i386/conf/files.i386:
# i386/i386/k6_mem.c            standard
and reconfig/rebuild your kernel.

> 
> On the other topic - write allocation - should I be seeing an indication
> of its status in the boot up messages ?  Hmm, I guess I could just UTSL on
> this one :) ...

No, write allocation status is only printed on boot -v.  You could also
drop to ddb and type call print_AMD_info() to see if it's really on.

> 
> Andrew.
> 
> -- 
> +--
> | Andrew Atrens                 Nortel Networks, Ottawa, Canada. |
> | All opinions expressed are my own,  not those of any employer. |
>                                                                --+
>   Heller's Law: The first myth of management is that it exists.   
>   Johnson's Corollary: Nobody really knows what is going on
>                        anywhere within the organization.   
> 

-- 
 Brian Fundakowski Feldman           \  FreeBSD: The Power to Serve!  /
 green@FreeBSD.org                    `------------------------------'

--0-1484207744-941308498=:94474
Content-Type: TEXT/PLAIN; CHARSET=US-ASCII; NAME="k6_mem_debugging.patch"
Content-Transfer-Encoding: BASE64
Content-ID: <Pine.BSF.4.10.9910301434580.94474@green.myip.org>
Content-Description: 
Content-Disposition: ATTACHMENT; FILENAME="k6_mem_debugging.patch"

SW5kZXg6IGs2X21lbS5jDQo9PT09PT09PT09PT09PT09PT09PT09PT09PT09
PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09DQpSQ1Mg
ZmlsZTogL3VzcjIvbmN2cy9zcmMvc3lzL2kzODYvaTM4Ni9rNl9tZW0uYyx2
DQpyZXRyaWV2aW5nIHJldmlzaW9uIDEuNA0KZGlmZiAtdSAtcjEuNCBrNl9t
ZW0uYw0KLS0tIGs2X21lbS5jCTE5OTkvMDkvMDUgMTU6NDU6NTcJMS40DQor
KysgazZfbWVtLmMJMTk5OS8xMC8zMCAxODozMTo0NQ0KQEAgLTY2LDcgKzY2
LDggQEANCiAjZGVmaW5lIGs2X3JlZ19tYWtlKGFkZHIsIG1hc2ssIHdjLCB1
YykgCQkJCVwNCiAJCSgoYWRkcikgfCAoKG1hc2spIDw8IDIpIHwgKCh3Yykg
PDwgMSkgfCB1YykNCiANCi1zdGF0aWMgdm9pZCBrNl9tcmluaXQoc3RydWN0
IG1lbV9yYW5nZV9zb2Z0YyAqc2MpOw0KK3N0YXRpYyBjaGFyICpiaXRwcmlu
dF80KHVfaW50MzJfdCwgY2hhciBbMzNdKTsNCitzdGF0aWMgdm9pZCBrNl9t
cmluaXQoc3RydWN0IG1lbV9yYW5nZV9zb2Z0YyAqKTsNCiBzdGF0aWMgaW50
IGs2X21yc2V0KHN0cnVjdCBtZW1fcmFuZ2Vfc29mdGMgKiwgc3RydWN0IG1l
bV9yYW5nZV9kZXNjICosIGludCAqKTsNCiBzdGF0aWMgX19pbmxpbmUgaW50
IGs2X21ybWFrZShzdHJ1Y3QgbWVtX3JhbmdlX2Rlc2MgKiwgdV9pbnQzMl90
ICopOw0KIHN0YXRpYyB2b2lkIGs2X21lbV9kcnZpbml0KHZvaWQgKik7DQpA
QCAtNzcsOSArNzgsMjIgQEANCiAJTlVMTA0KIH07DQogDQorc3RhdGljIGNo
YXIgKg0KK2JpdHByaW50XzQodV9pbnQzMl90IGksIGNoYXIgcmVzWzMzXSkg
ew0KKyAgICAgICAgcmVnaXN0ZXIgaW50IGNvdW50Ow0KKw0KKyAgICAgICAg
Zm9yIChjb3VudCA9IDA7IGNvdW50IDwgMzI7IGNvdW50KyspDQorICAgICAg
ICAgICAgICAgIHJlc1szMSAtIGNvdW50XSA9IChpICYgKDEgPDwgY291bnQp
KSA/ICcxJyA6ICcwJzsNCisgICAgICAgIHJlc1szMl0gPSAnXDAnOw0KKyAg
ICAgICAgcmV0dXJuIHJlczsNCit9DQorDQogc3RhdGljIF9faW5saW5lIGlu
dA0KIGs2X21ybWFrZShzdHJ1Y3QgbWVtX3JhbmdlX2Rlc2MgKmRlc2MsIHVf
aW50MzJfdCAqbXRycikgew0KIAl1X2ludDMyX3QgbGVuID0gMCwgd2MsIHVj
Ow0KKyNpZm5kZWYgSzZfTVRSUl9TSUxFTlQNCisJY2hhciBidWZbMzNdOw0K
KyNlbmRpZg0KIAlyZWdpc3RlciBpbnQgYml0Ow0KIA0KIAlpZiAoZGVzYy0+
bXJfYmFzZSAmfiAweGZmZmUwMDAwKQ0KQEAgLTk1LDYgKzEwOSwxMSBAQA0K
IAl1YyA9IChkZXNjLT5tcl9mbGFncyAmIE1ERl9VTkNBQ0hFQUJMRSkgPyAx
IDogMDsNCiANCiAJKm10cnIgPSBrNl9yZWdfbWFrZShkZXNjLT5tcl9iYXNl
LCBsZW4sIHdjLCB1Yyk7DQorI2lmbmRlZiBLNl9NVFJSX1NJTEVOVA0KKwlw
cmludGYoIms2X21ybWFrZTogYmFzZSA9ICVwLCBsZW4gPSAlI3gsIGZsYWdz
ID0gJSN4XG5rNl9tcm1ha2U6ICVzXG4iLA0KKwkgICAgZGVzYy0+bXJfYmFz
ZSwgZGVzYy0+bXJfbGVuLCBkZXNjLT5tcl9mbGFncywNCisJICAgIGJpdHBy
aW50XzQoKm10cnIsIGJ1ZikpOw0KKyNlbmRpZg0KIAlyZXR1cm4gMDsNCiB9
DQogDQo=
--0-1484207744-941308498=:94474--


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.10.9910301402380.94474-200000>