mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Justin Piszcz <jpiszcz@lucidpixels.com>
To: Robert Hancock <hancockr@shaw.ca>
Cc: Parag Warudkar <parag.warudkar@gmail.com>, linux-kernel@vger.kernel.org
Subject: Re: Case: 7454422: Re: Kernel 2.6.21.3 does not work with 8GB of RAM on Intel 965WH motherboards. (FULL DMESG)
Date: Fri, 1 Jun 2007 14:10:09 -0400 (EDT)	[thread overview]
Message-ID: <Pine.LNX.4.64.0706011409590.3716@p34.internal.lan> (raw)
In-Reply-To: <Pine.LNX.4.64.0706011355520.3716@p34.internal.lan>



On Fri, 1 Jun 2007, Justin Piszcz wrote:

>
>
> On Fri, 1 Jun 2007, Justin Piszcz wrote:
>
>> 
>> 
>> On Wed, 30 May 2007, Robert Hancock wrote:
>> 
>>> Parag Warudkar wrote:
>>>> Robert Hancock wrote:
>>>> 
>>>> 
>>>>> 0-3319MB
>>>>> 4096-8832MB
>>>>> 
>>>>> leaving 64MB of memory at the top of RAM uncached. What do you want to
>>>>> bet that something important (kernel code?) is getting loaded there..
>>>>> 
>>>>> So essentially it's a BIOS problem, it's not setting up the MTRRs
>>>>> properly in order to map all of RAM as cacheable. As Andi says, complain
>>>>> to Intel.
>>>>> 
>>>> 
>>>> Could the BADRAM patch be useful for him?
>>>> http://rick.vanrein.org/linux/badram/download.html has 2.6.21 version.
>>>> It says it supports x86_64. May be using this patch he can exclude
>>>> that RAM from being used/accessed?
>>> 
>>> I think that mem=8832M would work as well, to make the kernel use only the 
>>> memory that is marked cacheable. (It looks like this parameter takes the 
>>> highest memory address we want the kernel to use, not the highest memory 
>>> amount.)
>>> 
>>> -- 
>>> Robert Hancock      Saskatoon, SK, Canada
>>> To email, remove "nospam" from hancockr@nospamshaw.ca
>>> Home Page: http://www.roberthancock.com/
>>> 
>> 
>> Is 8832MB a typo?  8GB of memory is ~8192MB right?  Did you mean 8132MB or? 
>> Intel wants me to flash my bios and reset everything to the defaults to see 
>> if it is still an issue, I'd prefer to try the mem= option first.
>> 
>> Justin.
>> 
>
> mem=8064M" [top: Mem:   7264144k total]
> mem=8832M" [top: Mem:   8039820k total]
>
> I am using 8832MB and it does not have the bug/slowness!  How did you 
> calculate that from the MTRR output?
>
> $ cat /proc/mtrr
> reg00: base=0x00000000 (   0MB), size=2048MB: write-back, count=1
> reg01: base=0x80000000 (2048MB), size=1024MB: write-back, count=1
> reg02: base=0xc0000000 (3072MB), size= 256MB: write-back, count=1
> reg03: base=0xcf800000 (3320MB), size=   8MB: uncachable, count=1
> reg04: base=0xcf700000 (3319MB), size=   1MB: uncachable, count=1
> reg05: base=0x100000000 (4096MB), size=4096MB: write-back, count=1
> reg06: base=0x200000000 (8192MB), size= 512MB: write-back, count=1
> reg07: base=0x220000000 (8704MB), size= 128MB: write-back, count=1
>
> It sees 7.66GB now!
>
> 8039820 / 1024 / 1024
> 7.66GB
>
> top - 13:56:48 up 3 min,  5 users,  load average: 0.12, 0.14, 0.06
> Tasks: 163 total,   1 running, 162 sleeping,   0 stopped,   0 zombie
> Cpu0  :  4.4%us,  1.4%sy,  0.2%ni, 89.7%id,  4.1%wa,  0.0%hi,  0.1%si, 
> 0.0%st
> Cpu1  :  0.1%us,  0.5%sy,  0.6%ni, 98.4%id,  0.3%wa,  0.0%hi,  0.0%si, 
> 0.0%st
> Cpu2  :  1.2%us,  0.3%sy,  0.1%ni, 97.9%id,  0.5%wa,  0.0%hi,  0.0%si, 
> 0.0%st
> Cpu3  :  0.2%us,  1.9%sy,  0.7%ni, 96.0%id,  1.1%wa,  0.0%hi,  0.0%si, 
> 0.0%st
> Mem:   8039820k total,  1039588k used,  7000232k free,     3552k buffers
> Swap: 16787768k total,        0k used, 16787768k free,   141480k cached
>
>
>
>

Ahh here we go:

Justin Piszcz wrote:
> That output looked nasty, attaching entries from syslog.
>
> Justin.

Here's your E820 memory map, from dmesg:

BIOS-e820: 0000000000000000 - 000000000008f000 (usable)
BIOS-e820: 000000000008f000 - 00000000000a0000 (reserved)
BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved)
BIOS-e820: 0000000000100000 - 00000000cf58f000 (usable)
BIOS-e820: 00000000cf58f000 - 00000000cf59c000 (reserved)
BIOS-e820: 00000000cf59c000 - 00000000cf653000 (usable)
BIOS-e820: 00000000cf653000 - 00000000cf6a5000 (ACPI NVS)
BIOS-e820: 00000000cf6a5000 - 00000000cf6a8000 (ACPI data)
BIOS-e820: 00000000cf6a8000 - 00000000cf6ef000 (ACPI NVS)
BIOS-e820: 00000000cf6ef000 - 00000000cf6f1000 (ACPI data)
BIOS-e820: 00000000cf6f1000 - 00000000cf6f2000 (usable)
BIOS-e820: 00000000cf6f2000 - 00000000cf6ff000 (ACPI data)
BIOS-e820: 00000000cf6ff000 - 00000000cf700000 (usable)
BIOS-e820: 00000000cf700000 - 00000000d0000000 (reserved)
BIOS-e820: 00000000fff00000 - 0000000100000000 (reserved)
BIOS-e820: 0000000100000000 - 000000022c000000 (usable)

so the usable memory ranges are:

0-572K
1MB-3317.55MB
3317.60MB-3317.75MB
3318.94MB-3318.945MB
3318.996MB-3319MB
4096MB-8896MB

and the MTRRs (from /proc/mtrr, from private email):

reg00: base=0x00000000 (   0MB), size=2048MB: write-back, count=1
reg01: base=0x80000000 (2048MB), size=1024MB: write-back, count=1
reg02: base=0xc0000000 (3072MB), size= 256MB: write-back, count=1
reg03: base=0xcf800000 (3320MB), size=   8MB: uncachable, count=1
reg04: base=0xcf700000 (3319MB), size=   1MB: uncachable, count=1
reg05: base=0x100000000 (4096MB), size=4096MB: write-back, count=1
reg06: base=0x200000000 (8192MB), size= 512MB: write-back, count=1
reg07: base=0x220000000 (8704MB), size= 128MB: write-back, count=1

so the ranges mapped as cacheable are:

0-3319MB
4096-8832MB

leaving 64MB of memory at the top of RAM uncached. What do you want to
bet that something important (kernel code?) is getting loaded there..

So essentially it's a BIOS problem, it's not setting up the MTRRs
properly in order to map all of RAM as cacheable. As Andi says, complain
to Intel.

-- 
Robert Hancock      Saskatoon, SK, Canada
To email, remove "nospam" from hancockr@nospamshaw.ca
Home Page: http://www.roberthancock.com/


  reply	other threads:[~2007-06-01 18:10 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-05-31  0:57 Parag Warudkar
2007-05-31  4:38 ` Robert Hancock
2007-05-31 12:33   ` Justin Piszcz
2007-05-31 12:49   ` Parag Warudkar
2007-05-31 13:08     ` Justin Piszcz
2007-05-31 14:27       ` Robert Hancock
2007-05-31 18:44         ` Justin Piszcz
2007-06-01 16:33   ` Justin Piszcz
2007-06-01 17:57     ` Justin Piszcz
2007-06-01 18:10       ` Justin Piszcz [this message]
2007-06-01 20:56     ` Robert Hancock
     [not found] <fa.t8TZNHj4vrYcIs37jScT0oZl02s@ifi.uio.no>
     [not found] ` <fa.nsJ3dX+uNBCD7bTYffkYm0DLnR4@ifi.uio.no>
     [not found]   ` <fa.lfTXDj3RBbaCLDUJJFzLVowMlxc@ifi.uio.no>
     [not found]     ` <fa.lrZMTvBB9xwYW1mcA0nyYFjB9qY@ifi.uio.no>
     [not found]       ` <fa.AIUKY82rbgpQ/AiIxhRL0fahxaQ@ifi.uio.no>
     [not found]         ` <fa.yz+v/A2zkJKIswF0Y4Mo4FxwnCI@ifi.uio.no>
2007-05-30 23:29           ` Robert Hancock
2007-05-31  4:56             ` Yinghai Lu
     [not found] <fa.4kEpre7NAj1mG6fooUMp/WVc8tg@ifi.uio.no>
2007-05-30  4:08 ` Kernel 2.6.21.3 does not work with 8GB of RAM on Intel 965WH motherboards Robert Hancock
2007-05-30  8:43   ` Justin Piszcz
2007-05-30 14:27     ` Robert Hancock
2007-05-30 14:33       ` Case: 7454422: Re: Kernel 2.6.21.3 does not work with 8GB of RAM on Intel 965WH motherboards. (FULL DMESG) Justin Piszcz
2007-05-30 14:36         ` Justin Piszcz

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=Pine.LNX.4.64.0706011409590.3716@p34.internal.lan \
    --to=jpiszcz@lucidpixels.com \
    --cc=hancockr@shaw.ca \
    --cc=linux-kernel@vger.kernel.org \
    --cc=parag.warudkar@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®