3- In RHEL5 there's no need for a specific hugemem kernel anymore as
the kernel is smart enough to decide during boot what kind of
technology should it use.
That does not make sense to me. The kernel can find out whether it needs
more than 1GB for the kernel space during boot according to the
On Mon, May 14, 2007 at 09:51:15AM +0300, Noam Meltzer wrote:
This is from the release notes of RHEL5 (Kernel Notes). I tend to believe
that it applies on hugemem as well.
o X86 SMP alternatives
o optimizes a single kernel image at runtime according to
Noam Meltzer wrote:
This is from the release notes of RHEL5 (Kernel Notes). I tend to
believe that it applies on hugemem as well.
o X86 SMP alternatives
o optimizes a single kernel image at runtime
according to
the available platform
On 5/14/07, Shachar Shemesh [EMAIL PROTECTED] wrote:
While I cannot rule out that they did the same for hugemem, it still
leaves in the question of boot time detection.
I'll pose a wild guess as to what is done, and you tell me how likely it
is:
At boot time, RHEL 5 tests whether the machine
Hi Shachar!
On Monday 14 May 2007, Shachar Shemesh wrote:
Noam Meltzer wrote:
Hi,
Quick answer is no.
A bit longer answer is:
1- PAE refers to a certain technology avail. in the CPU which allows
32bit kernels to address larger address spaces.
2- Hugemem is a technology which
Noam Meltzer wrote:
So, is it possible that PAE technology, in a way, replaces the hugemem?
Seems extremely unlikely to me.
A few words about the technologies (since you brought up the
distinction, I'm surprised it is relevant).
On a 32 bit platform each process can address, at most, 4GB of
Well,
It would be really nice if some1 on this list have a RHEL(/CentOS)5 at hand
with =4GB RAM to test it. (Hetz?)
- Noam
On 5/14/07, Shachar Shemesh [EMAIL PROTECTED] wrote:
Noam Meltzer wrote:
So, is it possible that PAE technology, in a way, replaces the hugemem?
Seems extremely unlikely
On Mon, May 14, 2007 at 01:47:35PM +0300, Shachar Shemesh wrote:
PAE is but an extension to the virtual memory technique, but using
unaddressable memory instead of the disk. The machine has 64GB of
physical memory, but can only actually address 4GB at a time. Pages
of physical memory are
Muli Ben-Yehuda wrote:
Hmm? that doesn't sound correct. All PAE does it make it possible to
have 36-bits PFNs in the PTEs, so that your physical addressability is
up to 64GB. You *can* address all 64GB of physical memory at the same
time. In other words PAE lets you map 4GB of virtual - 64GB
On Mon, May 14, 2007 at 02:42:11PM +0300, Shachar Shemesh wrote:
Muli Ben-Yehuda wrote:
Hmm? that doesn't sound correct. All PAE does it make it possible to
have 36-bits PFNs in the PTEs, so that your physical addressability is
up to 64GB. You *can* address all 64GB of physical memory at
Muli Ben-Yehuda wrote:
You are confusing *virtual* memory and *physical* memory. PAE has
nothing to do with virtual memory and everything to do with physical
memory.
I don't think I am. The simple truth of the matter is that it is not
possible to access physical memory directly (at least,
On Mon, May 14, 2007 at 03:20:10PM +0300, Shachar Shemesh wrote:
Muli Ben-Yehuda wrote:
You are confusing *virtual* memory and *physical* memory. PAE has
nothing to do with virtual memory and everything to do with physical
memory.
I don't think I am. The simple truth of the matter is
Quoting Noam Meltzer, from the post of Sat, 12 May:
Actually, that what PAE means according to wikipedia
(http://en.wikipedia.org/wiki/Physical_Address_Extension):
yes I know PAE, so that was my questions - does PAE in the kernel
package name refer to the same patch as the hugemem package of
Hi,
Quick answer is no.
A bit longer answer is:
1- PAE refers to a certain technology avail. in the CPU which allows 32bit
kernels to address larger address spaces.
2- Hugemem is a technology which changes the ratio between the user space
and kernel space from 3GB/1GB to 4GB/4GB. (So the
Noam Meltzer wrote:
Hi,
Quick answer is no.
A bit longer answer is:
1- PAE refers to a certain technology avail. in the CPU which allows
32bit kernels to address larger address spaces.
2- Hugemem is a technology which changes the ratio between the user
space and kernel space from 3GB/1GB
Hi,
that's some odd bug in RHEL5 then, because it works fine for me on
RHEL4...
Umm, ok, thanks for notifying me.
Visit my blog (hebrew) for things that (sometimes) matter:
http://wp.dad-answers.com
I'm sure Hannit won't mind you borroing her title banner, but at least
edit it so it
Actually, that what PAE means according to wikipedia
(http://en.wikipedia.org/wiki/Physical_Address_Extension):
In computing, Physical Address Extension (PAE) refers to a feature of
x86 processors that allows for up to 64 gibibytes of physical memory
to be used in 32-bit systems, given
Quoting Noam Meltzer, from the post of Mon, 07 May:
They were actually wrong. Hapends even to big RedHat..
Apparently, Anaconda knows only to detect MORE THEN 4GB. If I have
4GB, then it installs the standard kernel which only recognizes 3GB
(iommu doesn't work).
that's some odd bug in
ooopss. it was sent private. all should see :)
-- Forwarded message --
From: Hetz Ben Hamo [EMAIL PROTECTED]
Date: May 6, 2007 11:30 PM
Subject: Re: 4GB Memory question
To: Noam Meltzer [EMAIL PROTECTED]
They were actually wrong. Hapends even to big RedHat..
Apparently,
19 matches
Mail list logo