On Thu, Jun 17, 2004 at 12:45:07AM +0300, Micha Feigin wrote:
> What would be the drawback of the 2:2 split patch in this case? It
> would give you only 2GB of memory instead of 4
2 GB of virtual address space. That's the drawback ;-)
> but saves on the context switches.
Like everything else
On Wed, Jun 16, 2004 at 11:10:17PM +0300, Muli Ben-Yehuda wrote:
> On Wed, Jun 16, 2004 at 11:58:36PM +0300, guy keren wrote:
>
> > to sum it all up - we're back to the days of himem.sys and emm386.sys on
> > good old MSDOS, except that 896MB replaces the old 640KB on msdos (which
> > himem.sys li
On Wed, Jun 16, 2004 at 11:58:36PM +0300, guy keren wrote:
>
> to sum it all up - we're back to the days of himem.sys and emm386.sys on
> good old MSDOS, except that 896MB replaces the old 640KB on msdos (which
> himem.sys lifted to a 1MB limit), and 'ZONE_HIGHMEM' comes instead of the
> memory sw
On Wed, Jun 16, 2004 at 11:58:36PM +0300, guy keren wrote:
> to sum it all up - we're back to the days of himem.sys and emm386.sys on
> good old MSDOS, except that 896MB replaces the old 640KB on msdos (which
> himem.sys lifted to a 1MB limit), and 'ZONE_HIGHMEM' comes instead of the
> memory swap
to sum it all up - we're back to the days of himem.sys and emm386.sys on
good old MSDOS, except that 896MB replaces the old 640KB on msdos (which
himem.sys lifted to a 1MB limit), and 'ZONE_HIGHMEM' comes instead of the
memory swapping performed by EMM386.sys .
now, who was the linux geek that sa
On Wed, Jun 16, 2004 at 08:52:18AM +0300, Micha Feigin wrote:
> There was just a thread about this in kernel newbies, but I don't
> remember the exact details. IIRC the kernel address the first 896M of
> memory directly, not as virtual memory
No, the kernel maps the first 896M into its virtual a
On Wed, Jun 16, 2004 at 06:48:48AM +0300, Shachar Shemesh wrote:
> Is it one of the options in himem support? I have there "off", "4GB",
> and "64GB".
No, it's an external patch, by mingo of redhat. The RH kernels
probably have it as an option, and so do -mm.
> Let's see what I understand. I g
On Wed, Jun 16, 2004 at 06:48:48AM +0300, Shachar Shemesh wrote:
> Muli Ben-Yehuda wrote:
>
> >On Tue, Jun 15, 2004 at 11:19:42PM +0300, Shachar Shemesh wrote:
> >
> >
> >>If choosing "off" gives each process a 3GB usable address space, why
> >>should I want to turn it on if my machine only has
Muli Ben-Yehuda wrote:
On Tue, Jun 15, 2004 at 11:19:42PM +0300, Shachar Shemesh wrote:
If choosing "off" gives each process a 3GB usable address space, why
should I want to turn it on if my machine only has 2GB?
Because Linux only direclty maps the first 896mb of physical
memory. If your
On Tue, Jun 15, 2004 at 11:19:42PM +0300, Shachar Shemesh wrote:
> From the kernel build system help:
>
> >Linux can use up to 64 Gigabytes of physical memory on x86 systems.
> >However, the address space of 32-bit x86 processors is only 4
> >Gigabytes large. That means that, if you have a large a
On Tue, Jun 15, 2004 at 11:19:42PM +0300, Shachar Shemesh wrote:
> If choosing "off" gives each process a 3GB usable address space, why
> should I want to turn it on if my machine only has 2GB?
Because Linux only direclty maps the first 896mb of physical
memory. If your machine has 2GB of phys.
From the kernel build system help:
Linux can use up to 64 Gigabytes of physical memory on x86 systems.
However, the address space of 32-bit x86 processors is only 4
Gigabytes large. That means that, if you have a large amount of
physical memory, not all of it can be "permanently mapped" by the
kern
12 matches
Mail list logo
