--On Thursday, September 01, 2005 18:58:23 -0700 "Chen, Kenneth W"
<[EMAIL PROTECTED]> wrote:
>> +prio_tree_iter_init(, >i_mmap,
>> +vma->vm_start, vma->vm_end);
>
>
> I think this is a bug. The radix priority tree for address_space->
> i_mmap is
--On Thursday, September 01, 2005 18:58:23 -0700 Chen, Kenneth W
[EMAIL PROTECTED] wrote:
+prio_tree_iter_init(iter, mapping-i_mmap,
+vma-vm_start, vma-vm_end);
I think this is a bug. The radix priority tree for address_space-
i_mmap is keyed
Dave McCracken wrote on Tuesday, August 30, 2005 3:13 PM
> This patch implements page table sharing for all shared memory regions that
> span an entire page table page. It supports sharing at multiple page
> levels, depending on the architecture.
In function pt_share_pte():
> +
Dave McCracken wrote on Tuesday, August 30, 2005 3:13 PM
> This patch implements page table sharing for all shared memory regions that
> span an entire page table page. It supports sharing at multiple page
> levels, depending on the architecture.
>
>
> This version of the patch supports i386
Dave McCracken wrote on Tuesday, August 30, 2005 3:13 PM
This patch implements page table sharing for all shared memory regions that
span an entire page table page. It supports sharing at multiple page
levels, depending on the architecture.
This version of the patch supports i386 and
Dave McCracken wrote on Tuesday, August 30, 2005 3:13 PM
This patch implements page table sharing for all shared memory regions that
span an entire page table page. It supports sharing at multiple page
levels, depending on the architecture.
In function pt_share_pte():
+ while
--On Wednesday, August 31, 2005 12:44:24 +0100 Hugh Dickins
<[EMAIL PROTECTED]> wrote:
> So you don't have Nick's test at the start of copy_page_range():
> if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_RESERVED))) {
> if (!vma->anon_vma)
> return 0;
>> They're incompatible, but you could be left to choose one or the other
>> via config option.
>
> Wouldn't need config option: there's /proc/sys/kernel/randomize_va_space
> for the whole running system, compatibility check on the ELFs run, and
> the infinite stack rlimit: enough ways to
On Wed, 31 Aug 2005, Martin J. Bligh wrote:
> --Hugh Dickins <[EMAIL PROTECTED]> wrote (on Wednesday, August 31, 2005
> 14:42:38 +0100):
> >
> > Which is indeed a further disincentive against shared page tables.
>
> Or shared pagetables a disincentive to randomizing the mmap space ;-)
Fair
> > Which is indeed a further disincentive against shared page tables.
>
> Or shared pagetables a disincentive to randomizing the mmap space ;-)
> They're incompatible, but you could be left to choose one or the other
> via config option.
>
> 3% on "a certain industry-standard database
--Hugh Dickins <[EMAIL PROTECTED]> wrote (on Wednesday, August 31, 2005
14:42:38 +0100):
> On Wed, 31 Aug 2005, Arjan van de Ven wrote:
>> On Wed, 2005-08-31 at 12:44 +0100, Hugh Dickins wrote:
>> > I was going to say, doesn't randomize_va_space take away the rest of
>> > the point? But no, it
On Wed, 31 Aug 2005, Arjan van de Ven wrote:
> On Wed, 2005-08-31 at 12:44 +0100, Hugh Dickins wrote:
> > I was going to say, doesn't randomize_va_space take away the rest of
> > the point? But no, it appears "randomize_va_space", as it currently
> > appears in mainline anyway, is somewhat an
On Wed, 2005-08-31 at 12:44 +0100, Hugh Dickins wrote:
> I was going to say, doesn't randomize_va_space take away the rest of
> the point? But no, it appears "randomize_va_space", as it currently
> appears in mainline anyway, is somewhat an exaggeration: it just shifts
> the stack a little, with
On Tue, 30 Aug 2005, Dave McCracken wrote:
>
> This patch implements page table sharing for all shared memory regions that
> span an entire page table page. It supports sharing at multiple page
> levels, depending on the architecture.
>
> Performance testing has shown no degradation with this
On Tue, 30 Aug 2005, Dave McCracken wrote:
This patch implements page table sharing for all shared memory regions that
span an entire page table page. It supports sharing at multiple page
levels, depending on the architecture.
Performance testing has shown no degradation with this patch
On Wed, 2005-08-31 at 12:44 +0100, Hugh Dickins wrote:
I was going to say, doesn't randomize_va_space take away the rest of
the point? But no, it appears randomize_va_space, as it currently
appears in mainline anyway, is somewhat an exaggeration: it just shifts
the stack a little, with no
On Wed, 31 Aug 2005, Arjan van de Ven wrote:
On Wed, 2005-08-31 at 12:44 +0100, Hugh Dickins wrote:
I was going to say, doesn't randomize_va_space take away the rest of
the point? But no, it appears randomize_va_space, as it currently
appears in mainline anyway, is somewhat an
--Hugh Dickins [EMAIL PROTECTED] wrote (on Wednesday, August 31, 2005
14:42:38 +0100):
On Wed, 31 Aug 2005, Arjan van de Ven wrote:
On Wed, 2005-08-31 at 12:44 +0100, Hugh Dickins wrote:
I was going to say, doesn't randomize_va_space take away the rest of
the point? But no, it appears
Which is indeed a further disincentive against shared page tables.
Or shared pagetables a disincentive to randomizing the mmap space ;-)
They're incompatible, but you could be left to choose one or the other
via config option.
3% on a certain industry-standard database benchmark (cough)
On Wed, 31 Aug 2005, Martin J. Bligh wrote:
--Hugh Dickins [EMAIL PROTECTED] wrote (on Wednesday, August 31, 2005
14:42:38 +0100):
Which is indeed a further disincentive against shared page tables.
Or shared pagetables a disincentive to randomizing the mmap space ;-)
Fair point!
They're incompatible, but you could be left to choose one or the other
via config option.
Wouldn't need config option: there's /proc/sys/kernel/randomize_va_space
for the whole running system, compatibility check on the ELFs run, and
the infinite stack rlimit: enough ways to suppress
--On Wednesday, August 31, 2005 12:44:24 +0100 Hugh Dickins
[EMAIL PROTECTED] wrote:
So you don't have Nick's test at the start of copy_page_range():
if (!(vma-vm_flags (VM_HUGETLB|VM_NONLINEAR|VM_RESERVED))) {
if (!vma-anon_vma)
return 0;
}
22 matches
Mail list logo